+
+
+
+
+
+
+D1_data_assembly_20190130
+Murray Scown
+30 January 2019
+ +setwd("C:/Users/mu5106sc/Dropbox/STAGS/D1_Database/")
+library(rgdal)## Loading required package: sp## rgdal: version: 1.3-4, (SVN revision 766)
+## Geospatial Data Abstraction Library extensions to R successfully loaded
+## Loaded GDAL runtime: GDAL 2.2.3, released 2017/11/20
+## Path to GDAL shared files: C:/Program Files/R/R-3.5.1/library/rgdal/gdal
+## GDAL binary built with GEOS: TRUE
+## Loaded PROJ.4 runtime: Rel. 4.9.3, 15 August 2016, [PJ_VERSION: 493]
+## Path to PROJ.4 shared files: C:/Program Files/R/R-3.5.1/library/rgdal/proj
+## Linking to sp version: 1.3-1library(sp)
+library(dplyr)##
+## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
+##
+## filter, lag## The following objects are masked from 'package:base':
+##
+## intersect, setdiff, setequal, unionlibrary(sf)## Linking to GEOS 3.6.1, GDAL 2.2.3, proj.4 4.9.3library(ggplot2)
+library(viridis)## Loading required package: viridisLitelibrary(eurostat)geodata <- get_eurostat_geospatial(output_class = "spdf", year = "2016", resolution = "60") ###NOTE: NUTS 2016 ONLY FOR CROP, LIVESTOCK, AND ACCOUNTS PROCESSING##
+## COPYRIGHT NOTICE
+##
+## When data downloaded from this page
+## <http://ec.europa.eu/eurostat/web/gisco/geodata/reference-data/administrative-units-statistical-units>
+## is used in any printed or electronic publication,
+## in addition to any other provisions
+## applicable to the whole Eurostat website,
+## data source will have to be acknowledged
+## in the legend of the map and
+## in the introductory page of the publication
+## with the following copyright notice:
+##
+## - EN: (C) EuroGeographics for the administrative boundaries
+## - FR: (C) EuroGeographics pour les limites administratives
+## - DE: (C) EuroGeographics bezuglich der Verwaltungsgrenzen
+##
+## For publications in languages other than
+## English, French or German,
+## the translation of the copyright notice
+## in the language of the publication shall be used.
+##
+## If you intend to use the data commercially,
+## please contact EuroGeographics for
+## information regarding their licence agreements.
+## ## SpatialPolygonDataFrame at resolution 1:60 read from local file##
+## # --------------------------
+## HEADS UP!!
+##
+## Function now returns the data in 'sf'-class (simple features)
+## by default which is different
+## from previous behaviour's 'SpatialPolygonDataFrame'.
+##
+## If you prefer either 'SpatialPolygonDataFrame' or
+## fortified 'data_frame' (for ggplot2::geom_polygon),
+## please specify it explicitly to 'output_class'-argument!
+##
+## # --------------------------
+## nuts <- readOGR(dsn='C:/Users/mu5106sc/Dropbox/STAGS/D1_Database/EU_Farming_Systems_20181015.gdb', layer='NUTS_RG_01M_2013_3035_LEVL_2')## OGR data source with driver: OpenFileGDB
+## Source: "C:\Users\mu5106sc\Dropbox\STAGS\D1_Database\EU_Farming_Systems_20181015.gdb", layer: "NUTS_RG_01M_2013_3035_LEVL_2"
+## with 320 features
+## It has 7 fieldshead(nuts@data)## CNTR_CODE FID_1 LEVL_CODE NUTS_ID NUTS_NAME Shape_Length
+## 1 AT AT11 2 AT11 Burgenland (AT) 628921.6
+## 2 AT AT22 2 AT22 Steiermark 814700.6
+## 3 AT AT12 2 AT12 Niederösterreich 1044711.5
+## 4 AT AT13 2 AT13 Wien 116902.7
+## 5 AT AT21 2 AT21 Kärnten 625727.5
+## 6 AT AT31 2 AT31 Oberösterreich 790984.0
+## Shape_Area
+## 1 3963509482
+## 2 16414303341
+## 3 19201725666
+## 4 411979159
+## 5 9541848203
+## 6 11984617500str(nuts@data)## 'data.frame': 320 obs. of 7 variables:
+## $ CNTR_CODE : Factor w/ 35 levels "AT","BE","BG",..: 1 1 1 1 1 1 1 2 2 1 ...
+## $ FID_1 : Factor w/ 320 levels "AT11","AT12",..: 1 5 2 3 4 6 7 11 12 8 ...
+## $ LEVL_CODE : int 2 2 2 2 2 2 2 2 2 2 ...
+## $ NUTS_ID : Factor w/ 320 levels "AT11","AT12",..: 1 5 2 3 4 6 7 11 12 8 ...
+## $ NUTS_NAME : Factor w/ 320 levels "Ãstra Mellansverige",..: 40 271 192 312 137 209 255 231 235 289 ...
+## $ Shape_Length: num 628922 814701 1044711 116903 625728 ...
+## $ Shape_Area : num 3.96e+09 1.64e+10 1.92e+10 4.12e+08 9.54e+09 ...#SDG variables
+sdg_data <- readOGR(dsn='C:/Users/mu5106sc/Dropbox/STAGS/SDG_data_eurostat/Final_database', layer='SDGs_database')## OGR data source with driver: ESRI Shapefile
+## Source: "C:\Users\mu5106sc\Dropbox\STAGS\SDG_data_eurostat\Final_database", layer: "SDGs_database"
+## with 471 features
+## It has 28 fieldshead(sdg_data@data)## geo STAT_LEVL_ SHAPE_AREA SHAPE_LEN risk_pov factor_in org_farm
+## 0 AT 0 10.14648271 20.7854134 18.43333 2315.97000 13.56732
+## 1 AT1 1 2.94056324 9.5340600 NA 1070.85000 NA
+## 2 AT11 2 0.53145726 4.7954485 13.73333 173.70857 16.89976
+## 3 AT12 2 2.37700914 8.3963979 13.83333 884.43857 12.43632
+## 4 AT13 2 0.03209684 0.9114204 27.23333 12.70143 14.46384
+## 5 AT2 1 3.09701419 9.7616839 NA 505.33857 NA
+## train35bas train35ful train_bas train_ful nitr_high nitr_mod nitr_poor
+## 0 NA NA NA NA 64.58924 20.20774 15.20302
+## 1 NA NA NA NA NA NA NA
+## 2 0.1375661 0.3333333 0.1243050 0.1779190 NA NA NA
+## 3 0.2084775 0.4809689 0.2534787 0.3449437 NA NA NA
+## 4 0.3750000 0.7500000 0.1753247 0.4740260 NA NA NA
+## 5 NA NA NA NA NA NA NA
+## irrigated irrig_vol energy ren_energy gdp_rural unemp_yout
+## 0 1.350 2.16 113.4390710 169.3286 0.7992295 61.35624
+## 1 NA NA NA NA NA NA
+## 2 5.850 NA 7.5699818 NA NA NA
+## 3 2.650 NA 37.8083090 NA NA NA
+## 4 10.525 NA 0.3336333 NA NA NA
+## 5 NA NA NA NA NA NA
+## unemp_rate unemp_long pesticides forest artific soil_loss
+## 0 104.716 56.66667 1915425.167 NA NA 7.324
+## 1 NA NA NA NA NA 2.164
+## 2 NA NA 127819.574 0.3161203 0.04355635 1.842
+## 3 NA NA 638395.448 0.4286079 0.04875064 2.236
+## 4 NA NA 5633.417 0.1469534 0.73118280 1.014
+## 5 NA NA NA NA NA 7.927
+## com_birds farm_birds
+## 0 NA 65.98
+## 1 NA NA
+## 2 NA NA
+## 3 NA NA
+## 4 NA NA
+## 5 NA NAstr(sdg_data@data)## 'data.frame': 471 obs. of 28 variables:
+## $ geo : Factor w/ 471 levels "AT","AT1","AT11",..: 1 2 3 4 5 6 7 8 9 10 ...
+## $ STAT_LEVL_: int 0 1 2 2 2 1 2 2 1 2 ...
+## $ SHAPE_AREA: num 10.1465 2.9406 0.5315 2.377 0.0321 ...
+## $ SHAPE_LEN : num 20.785 9.534 4.795 8.396 0.911 ...
+## $ risk_pov : num 18.4 NA 13.7 13.8 27.2 ...
+## $ factor_in : num 2316 1070.8 173.7 884.4 12.7 ...
+## $ org_farm : num 13.6 NA 16.9 12.4 14.5 ...
+## $ train35bas: num NA NA 0.138 0.208 0.375 ...
+## $ train35ful: num NA NA 0.333 0.481 0.75 ...
+## $ train_bas : num NA NA 0.124 0.253 0.175 ...
+## $ train_ful : num NA NA 0.178 0.345 0.474 ...
+## $ nitr_high : num 64.6 NA NA NA NA ...
+## $ nitr_mod : num 20.2 NA NA NA NA ...
+## $ nitr_poor : num 15.2 NA NA NA NA ...
+## $ irrigated : num 1.35 NA 5.85 2.65 10.53 ...
+## $ irrig_vol : num 2.16 NA NA NA NA NA NA NA NA NA ...
+## $ energy : num 113.439 NA 7.57 37.808 0.334 ...
+## $ ren_energy: num 169 NA NA NA NA ...
+## $ gdp_rural : num 0.799 NA NA NA NA ...
+## $ unemp_yout: num 61.4 NA NA NA NA ...
+## $ unemp_rate: num 105 NA NA NA NA ...
+## $ unemp_long: num 56.7 NA NA NA NA ...
+## $ pesticides: num 1915425 NA 127820 638395 5633 ...
+## $ forest : num NA NA 0.316 0.429 0.147 ...
+## $ artific : num NA NA 0.0436 0.0488 0.7312 ...
+## $ soil_loss : num 7.32 2.16 1.84 2.24 1.01 ...
+## $ com_birds : num NA NA NA NA NA NA NA NA NA NA ...
+## $ farm_birds: num 66 NA NA NA NA ...names(sdg_data@data)## [1] "geo" "STAT_LEVL_" "SHAPE_AREA" "SHAPE_LEN" "risk_pov"
+## [6] "factor_in" "org_farm" "train35bas" "train35ful" "train_bas"
+## [11] "train_ful" "nitr_high" "nitr_mod" "nitr_poor" "irrigated"
+## [16] "irrig_vol" "energy" "ren_energy" "gdp_rural" "unemp_yout"
+## [21] "unemp_rate" "unemp_long" "pesticides" "forest" "artific"
+## [26] "soil_loss" "com_birds" "farm_birds"sdg.dat <- sdg_data@data[,c(1:6,8:15,24:28)] #we will add organic farming, energies, employment, GDP later
+
+#here we replace SDG variables that were corrected after initial processing of database
+#Organic farming
+org.farm <- read.csv("C:/Users/mu5106sc/Dropbox/STAGS/SDG_data_eurostat/Final_database/SDGs/Goal2/Percentage_organic_farming/org_farm.csv", head=T)
+head(org.farm)## geo STAT_LEVL_ organic_farms_mean ag_area_mean org_farm
+## 1 AT 0 396606.0 3063526.0 12.946063
+## 2 AT1 1 119970.0 1138110.0 10.541160
+## 3 AT11 2 36312.5 186847.5 19.434298
+## 4 AT12 2 123420.0 919957.5 13.415837
+## 5 AT13 2 1307.5 7952.5 16.441371
+## 6 AT2 1 75990.0 790560.0 9.612174sdg.dat <- left_join(sdg.dat, org.farm[,c(1,5)])## Joining, by = "geo"#Energy consumption in agriculture
+energy.rt <- read.csv("C:/Users/mu5106sc/Dropbox/STAGS/SDG_data_eurostat/Final_database/SDGs/Goal7/Energy_use/energy_rate_in_ag_20190104.csv", head=T)
+ren.energy <- read.csv("C:/Users/mu5106sc/Dropbox/STAGS/SDG_data_eurostat/Final_database/SDGs/Goal7/Renewable_energy/ren_energy_pct_in_ag_20190104.csv", head=T)
+
+head(energy.rt)## geo energy_use_mean ag_energy energy_rt
+## 1 AT 518.52857 226.87693 0.08319988
+## 2 BE 736.84286 489.26256 0.37408254
+## 3 BG 191.40000 98.50132 0.02117880
+## 4 CY 39.25714 13.82370 0.12644017
+## 5 CZ 590.04286 322.88530 0.09247833
+## 6 DE 0.00000 0.00000 0.00000000head(ren.energy)## geo ag_energy ag_ren_energy ren_nrg_pct
+## 1 AT 226.87693 74.088003 32.655591
+## 2 BE 489.26256 28.276851 5.779484
+## 3 BG 98.50132 4.300886 4.366323
+## 4 CY 13.82370 1.307920 9.461426
+## 5 CZ 322.88530 53.706075 16.633174
+## 6 DE 0.00000 0.000000 NAsdg.dat <- left_join(sdg.dat, energy.rt[,c(1,4)])## Joining, by = "geo"## Warning: Column `geo` joining factors with different levels, coercing to
+## character vectorsdg.dat <- left_join(sdg.dat, ren.energy[,c(1,4)])## Joining, by = "geo"## Warning: Column `geo` joining character vector and factor, coercing into
+## character vectornames(sdg.dat)[22] <- "renew_pct"
+
+sdg.dat[!is.na(sdg.dat$energy_rt), c("geo", "energy_rt", "renew_pct")]## geo energy_rt renew_pct
+## 1 AT 0.08319988 32.6555914
+## 18 BG 0.02117880 4.3663233
+## 27 CY 0.12644017 9.4614265
+## 30 CZ 0.09247833 16.6331743
+## 48 BE 0.37408254 5.7794839
+## 75 DE 0.00000000 NA
+## 105 DK 0.20918463 8.2563274
+## 112 EE 0.03396048 3.2504309
+## 116 EL 0.04639303 7.5043321
+## 133 ES 0.06894380 3.0152604
+## 174 HR 0.05016945 0.8461058
+## 178 HU 0.07918869 6.4675409
+## 194 FI 0.02956624 22.5146831
+## 202 FR 0.09725156 3.3937818
+## 230 IE 0.04240159 0.0000000
+## 260 LT 0.02018419 11.0719610
+## 263 LU 0.11485572 14.0080046
+## 266 LV 0.02838868 8.9837713
+## 275 MT 0.42373931 0.0000000
+## 278 NL 1.75149448 3.6927288
+## 290 IT 0.12395977 1.1361492
+## 301 PT 0.05362489 1.0188356
+## 312 RO 0.02160031 2.4277124
+## 342 PL 0.14355187 14.3339623
+## 358 SE 0.01350281 41.0113526
+## 365 SK 0.03502762 13.0074813
+## 410 UK 0.04487651 23.7198977
+## 419 SI 0.04163011 3.9145197#Renewable energy production in agriculture
+ren.nrg.prod <- read.csv("C:/Users/mu5106sc/Dropbox/STAGS/SDG_data_eurostat/Final_database/SDGs/Goal7/Renewable_energy/c43_en_clean.csv", head=T)
+head(ren.nrg.prod)## geo ktoe pct_ren_prod
+## 1 BE 833.1227 28.159356
+## 2 BG 31.0925 1.529691
+## 3 CZ 773.6845 18.079698
+## 4 DK 128.6000 3.644711
+## 5 DE 10329.3300 26.563039
+## 6 EE NA NAnames(ren.nrg.prod)[3] <- "renew_prod"
+sdg.dat <- left_join(sdg.dat, ren.nrg.prod[,c(1,3)])## Joining, by = "geo"## Warning: Column `geo` joining character vector and factor, coercing into
+## character vector#Gross Nutrient Balances
+gnb <- read.csv("C:/Users/mu5106sc/Dropbox/STAGS/SDG_data_eurostat/Final_database/SDGs/Goal2/Gross_nutrient_balance/gross_nutrient_balance_mean_allnuts.csv")
+head(gnb)## geo gross_N gross_P
+## 1 AT 32.57143 1.833333
+## 2 BE 138.33333 5.333333
+## 3 BG 20.33333 -6.000000
+## 4 CH 58.83333 1.833333
+## 5 CY 190.16667 31.000000
+## 6 CZ 80.28571 -2.428571sdg.dat <- left_join(sdg.dat, gnb)## Joining, by = "geo"## Warning: Column `geo` joining character vector and factor, coercing into
+## character vector#Factor income from Eurostat table agr_r_accts has gaps that can be filled with NUTS0 data from table aact_eaa01
+afi.nuts0 <- read.csv("C:/Users/mu5106sc/Dropbox/STAGS/SDG_data_eurostat/Final_database/SDGs/Goal2/Agricultural_factor_income/factor_income_NUTS0_mean_allnuts.csv")
+head(afi.nuts0)## geo factor_income_mean
+## 1 BG 2032.4813
+## 2 CH 3937.8550
+## 3 CY 320.0075
+## 4 AL NA
+## 5 CZ 1904.5900
+## 6 BE 2179.0687(afi.na <- sdg.dat[which(is.na(sdg.dat$factor_in) & sdg.dat$STAT_LEVL_ == 0), 'geo'])## [1] "CY" "BE" "HR" "LI" "LT" "LU" "LV" "ME" "MK" "MT" "NO" "PL" "TR" "SI"(afi.nuts0.geo <- afi.nuts0[!is.na(afi.nuts0$factor_income_mean),'geo'])## [1] BG CH CY CZ BE AT DE DK EE EL ES FI HR FR HU IE IS IT LT LU LV MK MT
+## [24] NL NO PL PT RO SE SI SK UK
+## 2017 Levels: AL AL0 AL01 AL011 AL012 AL013 AL014 AL015 AL02 AL021 ... UKN16sdg.dat[which(is.na(sdg.dat$factor_in) & sdg.dat$geo %in% afi.nuts0.geo),c('geo', 'factor_in')]## geo factor_in
+## 27 CY NA
+## 48 BE NA
+## 174 HR NA
+## 260 LT NA
+## 263 LU NA
+## 266 LV NA
+## 272 MK NA
+## 275 MT NA
+## 333 NO NA
+## 342 PL NA
+## 419 SI NAfor(e in afi.nuts0.geo) {
+ sdg.dat[which(is.na(sdg.dat$factor_in) & sdg.dat$geo == e), 'factor_in'] <- afi.nuts0[which(afi.nuts0$geo == e), 'factor_income_mean']
+}
+sdg.dat[which(sdg.dat$geo %in% afi.na), c('geo', 'factor_in')]## geo factor_in
+## 27 CY 320.00750
+## 48 BE 2179.06875
+## 174 HR 937.82375
+## 257 LI NA
+## 260 LT 931.65125
+## 263 LU 79.65875
+## 266 LV 471.46500
+## 269 ME NA
+## 272 MK 614.92000
+## 275 MT 68.66250
+## 333 NO 1832.13000
+## 342 PL 10472.04500
+## 371 TR NA
+## 419 SI 439.74250#additional consensus variables
+con_data <- readOGR(dsn='C:/Users/mu5106sc/Dropbox/STAGS/SDG_data_eurostat/Final_database', layer='Add_con_vars_database')## OGR data source with driver: ESRI Shapefile
+## Source: "C:\Users\mu5106sc\Dropbox\STAGS\SDG_data_eurostat\Final_database", layer: "Add_con_vars_database"
+## with 471 features
+## It has 42 fieldshead(con_data@data)## geo STAT_LEVL_ SHAPE_AREA SHAPE_LEN total wintercrop cover_crop
+## 0 AT 0 10.14648271 20.7854134 0.747063 0.3504656 0.2685136
+## 1 AT1 1 2.94056324 9.5340600 NA NA NA
+## 2 AT11 2 0.53145726 4.7954485 NA NA NA
+## 3 AT12 2 2.37700914 8.3963979 NA NA NA
+## 4 AT13 2 0.03209684 0.9114204 NA NA NA
+## 5 AT2 1 3.09701419 9.7616839 NA NA NA
+## plant_res bare_soil conv_till cons_till zero_till nfert arable
+## 0 0.01832581 0.109758 NA NA NA NA 50.01522
+## 1 NA NA NA NA NA NA 76.90925
+## 2 NA NA 0.6182190 0.3199207 0.025012794 7.6840 83.64566
+## 3 NA NA 0.6226791 0.3280354 0.019896256 7.4528 76.22380
+## 4 NA NA 0.5109890 0.4047619 0.007326007 7.4970 79.80050
+## 5 NA NA NA NA NA NA 30.51920
+## grassland permanent wheat_a rye_a barley_a oats_A crnmaize_a
+## 0 47.536571 2.389535 304.4137 47.565000 149.032500 27.995 206.2050000
+## 1 18.041880 4.257529 NA 38.207143 93.364286 NA 88.0371429
+## 2 8.715722 7.545200 NA 5.232857 9.365714 NA 22.7585714
+## 3 20.140837 3.585850 NA 32.715714 83.720000 NA 65.1400000
+## 4 10.099751 10.099751 NA 0.260000 0.280000 NA 0.1357143
+## 5 57.091839 2.448436 NA 2.724286 14.268571 NA 67.6742857
+## fruits_a grmaize_a olives_a citrus_a vegetab_a wine_a bovine
+## 0 8.9075 87.270000000 0 0 17.2775 44.77875 NA
+## 1 NA 33.821428571 0 0 NA NA NA
+## 2 NA 3.625714286 0 0 NA NA 20.9925
+## 3 NA 30.187142857 0 0 NA NA 444.7362
+## 4 NA 0.007142857 0 0 NA NA 0.1000
+## 5 NA 20.728571429 0 0 NA NA NA
+## milk_cows pigs sheep goats org_carbon labour_for soil_prod
+## 0 NA NA NA NA 262.1 77677.5 NA
+## 1 NA NA NA NA NA NA NA
+## 2 4.21875 48.02125 5.56375 241.68000 NA 3632.5 6
+## 3 103.90000 798.19571 72.91375 15.29125 NA 22395.0 6
+## 4 0.02625 0.18750 95.23125 65.09875 NA 347.5 6
+## 5 NA NA NA NA NA NA NA
+## wheat_y rye_y barley_y oat_y maize_y grmaize_y lab_prod
+## 0 5.3825 4.31125 5.3575 3.96125 10.0475 45.49125 23.00056
+## 1 NA NA NA NA NA NA NA
+## 2 NA NA NA NA NA NA NA
+## 3 NA NA NA NA NA NA NA
+## 4 NA NA NA NA NA NA NA
+## 5 NA NA NA NA NA NA NAstr(con_data@data)## 'data.frame': 471 obs. of 42 variables:
+## $ geo : Factor w/ 471 levels "AT","AT1","AT11",..: 1 2 3 4 5 6 7 8 9 10 ...
+## $ STAT_LEVL_: int 0 1 2 2 2 1 2 2 1 2 ...
+## $ SHAPE_AREA: num 10.1465 2.9406 0.5315 2.377 0.0321 ...
+## $ SHAPE_LEN : num 20.785 9.534 4.795 8.396 0.911 ...
+## $ total : num 0.747 NA NA NA NA ...
+## $ wintercrop: num 0.35 NA NA NA NA ...
+## $ cover_crop: num 0.269 NA NA NA NA ...
+## $ plant_res : num 0.0183 NA NA NA NA ...
+## $ bare_soil : num 0.11 NA NA NA NA ...
+## $ conv_till : num NA NA 0.618 0.623 0.511 ...
+## $ cons_till : num NA NA 0.32 0.328 0.405 ...
+## $ zero_till : num NA NA 0.02501 0.0199 0.00733 ...
+## $ nfert : num NA NA 7.68 7.45 7.5 ...
+## $ arable : num 50 76.9 83.6 76.2 79.8 ...
+## $ grassland : num 47.54 18.04 8.72 20.14 10.1 ...
+## $ permanent : num 2.39 4.26 7.55 3.59 10.1 ...
+## $ wheat_a : num 304 NA NA NA NA ...
+## $ rye_a : num 47.56 38.21 5.23 32.72 0.26 ...
+## $ barley_a : num 149.03 93.36 9.37 83.72 0.28 ...
+## $ oats_A : num 28 NA NA NA NA ...
+## $ crnmaize_a: num 206.205 88.037 22.759 65.14 0.136 ...
+## $ fruits_a : num 8.91 NA NA NA NA ...
+## $ grmaize_a : num 87.27 33.82143 3.62571 30.18714 0.00714 ...
+## $ olives_a : num 0 0 0 0 0 0 0 0 0 0 ...
+## $ citrus_a : num 0 0 0 0 0 0 0 0 0 0 ...
+## $ vegetab_a : num 17.3 NA NA NA NA ...
+## $ wine_a : num 44.8 NA NA NA NA ...
+## $ bovine : num NA NA 21 444.7 0.1 ...
+## $ milk_cows : num NA NA 4.2188 103.9 0.0262 ...
+## $ pigs : num NA NA 48.021 798.196 0.188 ...
+## $ sheep : num NA NA 5.56 72.91 95.23 ...
+## $ goats : num NA NA 241.7 15.3 65.1 ...
+## $ org_carbon: num 262 NA NA NA NA ...
+## $ labour_for: num 77678 NA 3632 22395 348 ...
+## $ soil_prod : int NA NA 6 6 6 NA 6 6 NA 6 ...
+## $ wheat_y : num 5.38 NA NA NA NA ...
+## $ rye_y : num 4.31 NA NA NA NA ...
+## $ barley_y : num 5.36 NA NA NA NA ...
+## $ oat_y : num 3.96 NA NA NA NA ...
+## $ maize_y : num 10 NA NA NA NA ...
+## $ grmaize_y : num 45.5 NA NA NA NA ...
+## $ lab_prod : num 23 NA NA NA NA ...names(con_data@data)## [1] "geo" "STAT_LEVL_" "SHAPE_AREA" "SHAPE_LEN" "total"
+## [6] "wintercrop" "cover_crop" "plant_res" "bare_soil" "conv_till"
+## [11] "cons_till" "zero_till" "nfert" "arable" "grassland"
+## [16] "permanent" "wheat_a" "rye_a" "barley_a" "oats_A"
+## [21] "crnmaize_a" "fruits_a" "grmaize_a" "olives_a" "citrus_a"
+## [26] "vegetab_a" "wine_a" "bovine" "milk_cows" "pigs"
+## [31] "sheep" "goats" "org_carbon" "labour_for" "soil_prod"
+## [36] "wheat_y" "rye_y" "barley_y" "oat_y" "maize_y"
+## [41] "grmaize_y" "lab_prod"con.dat <- con_data@data[,c(1:4,10:16,35)] #we will add labour productivity, soil cover, SOC, crop and livestock data later
+
+#here we add new eurostat variables to con.dat that were processed after the Add_con_vars_database was created
+awu_tot <- read.csv("C:/Users/mu5106sc/Dropbox/STAGS/SDG_data_eurostat/Final_database/Additional_consensus_variables/C22_labour_force_awu_total_mean_allnuts_20190104.csv", head=T)
+head(awu_tot)## geo c22_labour_force
+## 1 AT 138800.0
+## 2 AT1 NA
+## 3 AT11 7007.5
+## 4 AT12 38360.0
+## 5 AT13 1975.0
+## 6 AT2 NAtot_uaa <- read.csv("C:/Users/mu5106sc/Dropbox/STAGS/SDG_data_eurostat/Final_database/Additional_consensus_variables/uaa_mean_allnuts.csv", head=T)
+head(tot_uaa)## geo uaa_mean
+## 1 BG 4559720
+## 2 CH NA
+## 3 CY 110630
+## 4 AL NA
+## 5 CZ 3473440
+## 6 BE 1331075gva <- read.csv("C:/Users/mu5106sc/Dropbox/STAGS/SDG_data_eurostat/Final_database/Additional_consensus_variables/gross_value_added_mean_20190104.csv", head=T)
+head(gva)## geo gva_mean
+## 1 AT 2769.36857
+## 2 AT1 1172.67143
+## 3 AT11 177.76429
+## 4 AT12 975.25143
+## 5 AT13 19.65571
+## 6 AT2 641.63571#There are some holes in this from Eurostat table agr_r_accts that can be filled with NUTS0 data from table aact_eaa01
+gva.2 <- read.csv("C:/Users/mu5106sc/Dropbox/STAGS/SDG_data_eurostat/Final_database/Additional_consensus_variables/gross_value_added_NUTS0_mean_allnuts_20190108.csv", head=T)
+head(gva.2)## geo c14_eea_gva
+## 1 BG 1671.6575
+## 2 CH 3323.7038
+## 3 CY 310.0225
+## 4 AL NA
+## 5 CZ 1432.8025
+## 6 BE 2332.7675(gva.na <- gva[is.na(gva$gva), 'geo'])## [1] BE3 BE31 BE32 BE33 BE34 BE35 CY CY0 CY00 CZ01 BE BE1 BE10 BE2
+## [15] BE21 BE22 BE23 BE24 BE25 FRA5 HR FI1B FI1C FI1D LI LI0 LI00 LT
+## [29] LT0 LT00 LU LU0 LU00 LV LV0 LV00 ME ME0 ME00 MK MK0 MK00
+## [43] MT MT0 MT00 NO NO0 NO01 NO02 NO03 NO04 NO05 NO06 NO07 SI04 TR
+## [57] TR1 TR10 TR2 TR21 TR22 TR3 TR31 TR32 TR33 TR4 TR41 TR42 TR5 TR51
+## [71] TR52 TR6 TR61 TR62 TR63 TR7 TR71 TR72 TR8 TR81 TR82 TR83 TR9 TR90
+## [85] TRA TRA1 TRA2 TRB TRB1 TRB2 TRC TRC1 TRC2 TRC3 SI SI0 SI03
+## 471 Levels: AT AT1 AT11 AT12 AT13 AT2 AT21 AT22 AT3 AT31 AT32 AT33 ... UKN0(gva.2.geo <- gva.2[!is.na(gva.2$c14_eea_gva),'geo'])## [1] BG CH CY CZ BE AT DE DK EE EL ES FI HR FR HU IE IS IT LT LU LV MK MT
+## [24] NL NO PL PT RO SE SI SK UK
+## 2017 Levels: AL AL0 AL01 AL011 AL012 AL013 AL014 AL015 AL02 AL021 ... UKN16gva[which(is.na(gva$gva) & gva$geo %in% gva.2.geo),]## geo gva_mean
+## 27 CY NA
+## 48 BE NA
+## 174 HR NA
+## 260 LT NA
+## 263 LU NA
+## 266 LV NA
+## 272 MK NA
+## 275 MT NA
+## 333 NO NA
+## 419 SI NAfor(e in gva.2.geo) {
+ gva[which(is.na(gva$gva) & gva$geo == e), 'gva_mean'] <- gva.2[which(gva.2$geo == e), 'c14_eea_gva']
+}
+gva[which(gva$geo %in% gva.na),]## geo gva_mean
+## 12 BE3 NA
+## 13 BE31 NA
+## 14 BE32 NA
+## 15 BE33 NA
+## 16 BE34 NA
+## 17 BE35 NA
+## 27 CY 310.02250
+## 28 CY0 NA
+## 29 CY00 NA
+## 32 CZ01 NA
+## 48 BE 2332.76750
+## 49 BE1 NA
+## 50 BE10 NA
+## 51 BE2 NA
+## 52 BE21 NA
+## 53 BE22 NA
+## 54 BE23 NA
+## 55 BE24 NA
+## 56 BE25 NA
+## 173 FRA5 NA
+## 174 HR 1057.60250
+## 197 FI1B NA
+## 198 FI1C NA
+## 199 FI1D NA
+## 257 LI NA
+## 258 LI0 NA
+## 259 LI00 NA
+## 260 LT 1019.96250
+## 261 LT0 NA
+## 262 LT00 NA
+## 263 LU 106.55875
+## 264 LU0 NA
+## 265 LU00 NA
+## 266 LV 311.59125
+## 267 LV0 NA
+## 268 LV00 NA
+## 269 ME NA
+## 270 ME0 NA
+## 271 ME00 NA
+## 272 MK 671.34000
+## 273 MK0 NA
+## 274 MK00 NA
+## 275 MT 58.47625
+## 276 MT0 NA
+## 277 MT00 NA
+## 333 NO 2086.08375
+## 334 NO0 NA
+## 335 NO01 NA
+## 336 NO02 NA
+## 337 NO03 NA
+## 338 NO04 NA
+## 339 NO05 NA
+## 340 NO06 NA
+## 341 NO07 NA
+## 364 SI04 NA
+## 371 TR NA
+## 372 TR1 NA
+## 373 TR10 NA
+## 374 TR2 NA
+## 375 TR21 NA
+## 376 TR22 NA
+## 377 TR3 NA
+## 378 TR31 NA
+## 379 TR32 NA
+## 380 TR33 NA
+## 381 TR4 NA
+## 382 TR41 NA
+## 383 TR42 NA
+## 384 TR5 NA
+## 385 TR51 NA
+## 386 TR52 NA
+## 387 TR6 NA
+## 388 TR61 NA
+## 389 TR62 NA
+## 390 TR63 NA
+## 391 TR7 NA
+## 392 TR71 NA
+## 393 TR72 NA
+## 394 TR8 NA
+## 395 TR81 NA
+## 396 TR82 NA
+## 397 TR83 NA
+## 398 TR9 NA
+## 399 TR90 NA
+## 400 TRA NA
+## 401 TRA1 NA
+## 402 TRA2 NA
+## 403 TRB NA
+## 404 TRB1 NA
+## 405 TRB2 NA
+## 406 TRC NA
+## 407 TRC1 NA
+## 408 TRC2 NA
+## 409 TRC3 NA
+## 419 SI 450.92125
+## 420 SI0 NA
+## 421 SI03 NA#add to con.dat
+con.dat2 <- left_join(awu_tot, gva)## Joining, by = "geo"con.dat2 <- left_join(con.dat2, tot_uaa)## Joining, by = "geo"## Warning: Column `geo` joining factors with different levels, coercing to
+## character vectornames(con.dat2)## [1] "geo" "c22_labour_force" "gva_mean"
+## [4] "uaa_mean"names(con.dat2)[2:4] <- c("tot_awu", "gva", "tot_uaa")
+head(con.dat2)## geo tot_awu gva tot_uaa
+## 1 AT 138800.0 2769.36857 2698320
+## 2 AT1 NA 1172.67143 NA
+## 3 AT11 7007.5 177.76429 181150
+## 4 AT12 38360.0 975.25143 895805
+## 5 AT13 1975.0 19.65571 7190
+## 6 AT2 NA 641.63571 NAcon.dat <- left_join(con.dat, con.dat2)## Joining, by = "geo"## Warning: Column `geo` joining factor and character vector, coercing into
+## character vectorhead(con.dat)## geo STAT_LEVL_ SHAPE_AREA SHAPE_LEN conv_till cons_till zero_till
+## 1 AT 0 10.14648271 20.7854134 NA NA NA
+## 2 AT1 1 2.94056324 9.5340600 NA NA NA
+## 3 AT11 2 0.53145726 4.7954485 0.6182190 0.3199207 0.025012794
+## 4 AT12 2 2.37700914 8.3963979 0.6226791 0.3280354 0.019896256
+## 5 AT13 2 0.03209684 0.9114204 0.5109890 0.4047619 0.007326007
+## 6 AT2 1 3.09701419 9.7616839 NA NA NA
+## nfert arable grassland permanent soil_prod tot_awu gva
+## 1 NA 50.01522 47.536571 2.389535 NA 138800.0 2769.36857
+## 2 NA 76.90925 18.041880 4.257529 NA NA 1172.67143
+## 3 7.6840 83.64566 8.715722 7.545200 6 7007.5 177.76429
+## 4 7.4528 76.22380 20.140837 3.585850 6 38360.0 975.25143
+## 5 7.4970 79.80050 10.099751 10.099751 6 1975.0 19.65571
+## 6 NA 30.51920 57.091839 2.448436 NA NA 641.63571
+## tot_uaa
+## 1 2698320
+## 2 NA
+## 3 181150
+## 4 895805
+## 5 7190
+## 6 NA#whole database for processing
+dbase <- as.data.frame(matrix(nrow=nrow(nuts@data), ncol=(ncol(sdg.dat[,-c(1:4)]) + ncol(con.dat[,-c(1:4)]) + 1)))
+dbase[,1] <- nuts@data$NUTS_ID
+names(dbase) <- c("NUTS_ID", names(sdg.dat)[-c(1:4)], names(con.dat)[-c(1:4)])
+head(dbase)## NUTS_ID risk_pov factor_in train35bas train35ful train_bas train_ful
+## 1 AT11 NA NA NA NA NA NA
+## 2 AT22 NA NA NA NA NA NA
+## 3 AT12 NA NA NA NA NA NA
+## 4 AT13 NA NA NA NA NA NA
+## 5 AT21 NA NA NA NA NA NA
+## 6 AT31 NA NA NA NA NA NA
+## nitr_high nitr_mod nitr_poor irrigated forest artific soil_loss
+## 1 NA NA NA NA NA NA NA
+## 2 NA NA NA NA NA NA NA
+## 3 NA NA NA NA NA NA NA
+## 4 NA NA NA NA NA NA NA
+## 5 NA NA NA NA NA NA NA
+## 6 NA NA NA NA NA NA NA
+## com_birds farm_birds org_farm energy_rt renew_pct renew_prod gross_N
+## 1 NA NA NA NA NA NA NA
+## 2 NA NA NA NA NA NA NA
+## 3 NA NA NA NA NA NA NA
+## 4 NA NA NA NA NA NA NA
+## 5 NA NA NA NA NA NA NA
+## 6 NA NA NA NA NA NA NA
+## gross_P conv_till cons_till zero_till nfert arable grassland permanent
+## 1 NA NA NA NA NA NA NA NA
+## 2 NA NA NA NA NA NA NA NA
+## 3 NA NA NA NA NA NA NA NA
+## 4 NA NA NA NA NA NA NA NA
+## 5 NA NA NA NA NA NA NA NA
+## 6 NA NA NA NA NA NA NA NA
+## soil_prod tot_awu gva tot_uaa
+## 1 NA NA NA NA
+## 2 NA NA NA NA
+## 3 NA NA NA NA
+## 4 NA NA NA NA
+## 5 NA NA NA NA
+## 6 NA NA NA NAnrow(dbase)## [1] 320#In this chunk, we will determine which NUTS2 have data for each variable, then apply NUTS1 or NUTS0 data to those NUTS2 without, wherever possible. We will do this in a function for all variables; however, directly translating NUTS1 or NUTS0 data to NUTS2 is only valid where the variable is a ratio (e.g., proportion, percentage, rate). In a later chunk, we will edit those variables that are absolute.
+
+#list to summarise where data are NUTS2, 1, 0 for each variable
+data.level <- vector("list", 4*length(names(dbase)[-1]))
+names(data.level) <- c(paste(names(dbase)[-1], 'n2.dat', sep='.'),
+ paste(names(dbase)[-1], 'n1.dat', sep='.'),
+ paste(names(dbase)[-1], 'n0.dat', sep='.'),
+ paste(names(dbase)[-1], 'nuts0.na', sep='.')
+ )
+labels(data.level)## [1] "risk_pov.n2.dat" "factor_in.n2.dat" "train35bas.n2.dat"
+## [4] "train35ful.n2.dat" "train_bas.n2.dat" "train_ful.n2.dat"
+## [7] "nitr_high.n2.dat" "nitr_mod.n2.dat" "nitr_poor.n2.dat"
+## [10] "irrigated.n2.dat" "forest.n2.dat" "artific.n2.dat"
+## [13] "soil_loss.n2.dat" "com_birds.n2.dat" "farm_birds.n2.dat"
+## [16] "org_farm.n2.dat" "energy_rt.n2.dat" "renew_pct.n2.dat"
+## [19] "renew_prod.n2.dat" "gross_N.n2.dat" "gross_P.n2.dat"
+## [22] "conv_till.n2.dat" "cons_till.n2.dat" "zero_till.n2.dat"
+## [25] "nfert.n2.dat" "arable.n2.dat" "grassland.n2.dat"
+## [28] "permanent.n2.dat" "soil_prod.n2.dat" "tot_awu.n2.dat"
+## [31] "gva.n2.dat" "tot_uaa.n2.dat" "risk_pov.n1.dat"
+## [34] "factor_in.n1.dat" "train35bas.n1.dat" "train35ful.n1.dat"
+## [37] "train_bas.n1.dat" "train_ful.n1.dat" "nitr_high.n1.dat"
+## [40] "nitr_mod.n1.dat" "nitr_poor.n1.dat" "irrigated.n1.dat"
+## [43] "forest.n1.dat" "artific.n1.dat" "soil_loss.n1.dat"
+## [46] "com_birds.n1.dat" "farm_birds.n1.dat" "org_farm.n1.dat"
+## [49] "energy_rt.n1.dat" "renew_pct.n1.dat" "renew_prod.n1.dat"
+## [52] "gross_N.n1.dat" "gross_P.n1.dat" "conv_till.n1.dat"
+## [55] "cons_till.n1.dat" "zero_till.n1.dat" "nfert.n1.dat"
+## [58] "arable.n1.dat" "grassland.n1.dat" "permanent.n1.dat"
+## [61] "soil_prod.n1.dat" "tot_awu.n1.dat" "gva.n1.dat"
+## [64] "tot_uaa.n1.dat" "risk_pov.n0.dat" "factor_in.n0.dat"
+## [67] "train35bas.n0.dat" "train35ful.n0.dat" "train_bas.n0.dat"
+## [70] "train_ful.n0.dat" "nitr_high.n0.dat" "nitr_mod.n0.dat"
+## [73] "nitr_poor.n0.dat" "irrigated.n0.dat" "forest.n0.dat"
+## [76] "artific.n0.dat" "soil_loss.n0.dat" "com_birds.n0.dat"
+## [79] "farm_birds.n0.dat" "org_farm.n0.dat" "energy_rt.n0.dat"
+## [82] "renew_pct.n0.dat" "renew_prod.n0.dat" "gross_N.n0.dat"
+## [85] "gross_P.n0.dat" "conv_till.n0.dat" "cons_till.n0.dat"
+## [88] "zero_till.n0.dat" "nfert.n0.dat" "arable.n0.dat"
+## [91] "grassland.n0.dat" "permanent.n0.dat" "soil_prod.n0.dat"
+## [94] "tot_awu.n0.dat" "gva.n0.dat" "tot_uaa.n0.dat"
+## [97] "risk_pov.nuts0.na" "factor_in.nuts0.na" "train35bas.nuts0.na"
+## [100] "train35ful.nuts0.na" "train_bas.nuts0.na" "train_ful.nuts0.na"
+## [103] "nitr_high.nuts0.na" "nitr_mod.nuts0.na" "nitr_poor.nuts0.na"
+## [106] "irrigated.nuts0.na" "forest.nuts0.na" "artific.nuts0.na"
+## [109] "soil_loss.nuts0.na" "com_birds.nuts0.na" "farm_birds.nuts0.na"
+## [112] "org_farm.nuts0.na" "energy_rt.nuts0.na" "renew_pct.nuts0.na"
+## [115] "renew_prod.nuts0.na" "gross_N.nuts0.na" "gross_P.nuts0.na"
+## [118] "conv_till.nuts0.na" "cons_till.nuts0.na" "zero_till.nuts0.na"
+## [121] "nfert.nuts0.na" "arable.nuts0.na" "grassland.nuts0.na"
+## [124] "permanent.nuts0.na" "soil_prod.nuts0.na" "tot_awu.nuts0.na"
+## [127] "gva.nuts0.na" "tot_uaa.nuts0.na"attach(sdg.dat)
+for(i in names(sdg.dat)[-c(1:4)]) {
+ (nuts2.na <- sdg.dat[STAT_LEVL_ == 2 & is.na(sdg.dat[,i]), 'geo'])
+ (nuts1 <- sdg.dat[STAT_LEVL_ == 1 & geo %in% gsub(".{1}$", "", nuts2.na), 'geo'])
+ (nuts1.na <- sdg.dat[geo %in% nuts1 & is.na(sdg.dat[,i]), 'geo'])
+ (nuts0 <- sdg.dat[STAT_LEVL_ == 0 & geo %in% gsub(".{1}$", "", nuts1.na), 'geo'])
+ (nuts0.na <- sdg.dat[geo %in% nuts0 & is.na(sdg.dat[,i]), 'geo'])
+
+#NUTS2 data
+(n2.dat <- sdg.dat[!(geo %in% nuts2.na) & STAT_LEVL_ == 2, 'geo'])
+#NUTS1 data
+(n1.dat <- nuts1[!nuts1 %in% nuts1.na])
+#NUTS0 data
+(n0.dat <- nuts0[!nuts0 %in% nuts0.na])
+#NO DATA
+nuts0.na
+
+data.level[[paste(i, 'n2.dat', sep='.')]] <- n2.dat
+data.level[[paste(i, 'n1.dat', sep='.')]] <- n1.dat
+data.level[[paste(i, 'n0.dat', sep='.')]] <- n0.dat
+data.level[[paste(i, 'nuts0.na', sep='.')]] <- nuts0.na
+
+ for(e in n0.dat) {
+ dbase[dbase$NUTS_ID %in% dbase$NUTS_ID[grep(paste(e, '..', sep=''), dbase$NUTS_ID)], i] <- sdg.dat[sdg.dat$geo == e, i]
+ }
+
+ for(e in n1.dat) {
+ dbase[dbase$NUTS_ID %in% dbase$NUTS_ID[grep(paste(e, '.', sep=''), dbase$NUTS_ID)], i] <- sdg.dat[sdg.dat$geo == e, i]
+ }
+
+
+ for(e in n2.dat) {
+ dbase[dbase$NUTS_ID == e, i] <- sdg.dat[sdg.dat$geo == e, i]
+ }
+}
+detach(sdg.dat)
+
+summary(dbase)## NUTS_ID risk_pov factor_in train35bas
+## AT11 : 1 Min. : 9.971 Min. : -0.73 Min. :0.00000
+## AT12 : 1 1st Qu.:18.586 1st Qu.: 144.97 1st Qu.:0.09613
+## AT13 : 1 Median :23.514 Median : 366.48 Median :0.22800
+## AT21 : 1 Mean :25.960 Mean : 1141.61 Mean :0.26424
+## AT22 : 1 3rd Qu.:29.680 3rd Qu.: 932.31 3rd Qu.:0.35996
+## AT31 : 1 Max. :54.150 Max. :10472.05 Max. :0.88217
+## (Other):314 NA's :2 NA's :28 NA's :52
+## train35ful train_bas train_ful nitr_high
+## Min. :0.0000 Min. :0.01171 Min. :0.00188 Min. : 4.082
+## 1st Qu.:0.1264 1st Qu.:0.10627 1st Qu.:0.04939 1st Qu.: 66.302
+## Median :0.2600 Median :0.19961 Median :0.12807 Median : 70.505
+## Mean :0.2738 Mean :0.26250 Mean :0.15796 Mean : 75.328
+## 3rd Qu.:0.3825 3rd Qu.:0.36488 3rd Qu.:0.25108 3rd Qu.: 87.591
+## Max. :0.8550 Max. :0.94840 Max. :0.50303 Max. :100.000
+## NA's :52 NA's :50 NA's :50 NA's :44
+## nitr_mod nitr_poor irrigated forest
+## Min. : 0.000 Min. : 0.000 Min. : 0.0000 Min. :0.00000
+## 1st Qu.: 6.533 1st Qu.: 4.106 1st Qu.: 0.3312 1st Qu.:0.08957
+## Median :15.896 Median : 8.883 Median : 1.2250 Median :0.24904
+## Mean :13.773 Mean :10.898 Mean : 5.7571 Mean :0.25141
+## 3rd Qu.:18.416 3rd Qu.:15.385 3rd Qu.: 6.5000 3rd Qu.:0.37365
+## Max. :60.000 Max. :68.367 Max. :74.5500 Max. :0.75860
+## NA's :44 NA's :44 NA's :28
+## artific soil_loss com_birds farm_birds
+## Min. :0.00000 Min. : 0.0300 Min. :54.92 Min. : 63.78
+## 1st Qu.:0.02056 1st Qu.: 0.7047 1st Qu.:62.14 1st Qu.: 81.34
+## Median :0.04020 Median : 1.5005 Median :69.50 Median : 83.82
+## Mean :0.09023 Mean : 2.5482 Mean :69.70 Mean : 81.90
+## 3rd Qu.:0.08193 3rd Qu.: 2.9420 3rd Qu.:81.30 3rd Qu.: 85.30
+## Max. :1.00000 Max. :17.6050 Max. :97.22 Max. :116.60
+## NA's :44 NA's :158 NA's :94
+## org_farm energy_rt renew_pct renew_prod
+## Min. : 0.000 Min. :0.00000 Min. : 0.000 Min. : 0.8855
+## 1st Qu.: 1.200 1st Qu.:0.03503 1st Qu.: 3.074 1st Qu.: 6.2422
+## Median : 2.687 Median :0.06128 Median : 6.124 Median : 8.3156
+## Mean : 4.056 Mean :0.15052 Mean :11.225 Mean :12.4318
+## 3rd Qu.: 5.204 3rd Qu.:0.09725 3rd Qu.:22.515 3rd Qu.:18.0797
+## Max. :27.487 Max. :1.75149 Max. :41.011 Max. :37.7797
+## NA's :28 NA's :44 NA's :82 NA's :45
+## gross_N gross_P conv_till cons_till
+## Min. : 2.857 Min. :-6.500 Mode:logical Mode:logical
+## 1st Qu.: 41.821 1st Qu.:-1.667 NA's:320 NA's:320
+## Median : 67.333 Median : 1.833
+## Mean : 67.553 Mean : 1.941
+## 3rd Qu.: 85.988 3rd Qu.: 4.714
+## Max. :190.167 Max. :31.000
+## NA's :30 NA's :30
+## zero_till nfert arable grassland
+## Mode:logical Mode:logical Mode:logical Mode:logical
+## NA's:320 NA's:320 NA's:320 NA's:320
+##
+##
+##
+##
+##
+## permanent soil_prod tot_awu gva
+## Mode:logical Mode:logical Mode:logical Mode:logical
+## NA's:320 NA's:320 NA's:320 NA's:320
+##
+##
+##
+##
+##
+## tot_uaa
+## Mode:logical
+## NA's:320
+##
+##
+##
+##
+## head(dbase)## NUTS_ID risk_pov factor_in train35bas train35ful train_bas train_ful
+## 1 AT11 13.73333 173.70857 0.1375661 0.3333333 0.1243050 0.1779190
+## 2 AT22 17.26667 393.97429 0.2160980 0.3648294 0.2017089 0.2413594
+## 3 AT12 13.83333 884.43857 0.2084775 0.4809689 0.2534787 0.3449437
+## 4 AT13 27.23333 12.70143 0.3750000 0.7500000 0.1753247 0.4740260
+## 5 AT21 17.20000 111.36714 0.2306238 0.3648393 0.2076173 0.2250348
+## 6 AT31 15.00000 452.67857 0.2508418 0.4284512 0.2014381 0.2857610
+## nitr_high nitr_mod nitr_poor irrigated forest artific soil_loss
+## 1 64.58924 20.20774 15.20302 5.850 0.3161203 0.04355635 1.842
+## 2 64.58924 20.20774 15.20302 0.325 0.6127954 0.03306278 5.804
+## 3 64.58924 20.20774 15.20302 2.650 0.4286079 0.04875064 2.236
+## 4 64.58924 20.20774 15.20302 10.525 0.1469534 0.73118280 1.014
+## 5 64.58924 20.20774 15.20302 0.100 0.5998934 0.03047416 11.671
+## 6 64.58924 20.20774 15.20302 0.125 0.4027358 0.04900973 3.791
+## com_birds farm_birds org_farm energy_rt renew_pct renew_prod gross_N
+## 1 NA 65.98 19.43430 0.08319988 32.65559 7.068917 32.57143
+## 2 NA 65.98 12.80858 0.08319988 32.65559 7.068917 32.57143
+## 3 NA 65.98 13.41584 0.08319988 32.65559 7.068917 32.57143
+## 4 NA 65.98 16.44137 0.08319988 32.65559 7.068917 32.57143
+## 5 NA 65.98 10.68078 0.08319988 32.65559 7.068917 32.57143
+## 6 NA 65.98 12.31071 0.08319988 32.65559 7.068917 32.57143
+## gross_P conv_till cons_till zero_till nfert arable grassland permanent
+## 1 1.833333 NA NA NA NA NA NA NA
+## 2 1.833333 NA NA NA NA NA NA NA
+## 3 1.833333 NA NA NA NA NA NA NA
+## 4 1.833333 NA NA NA NA NA NA NA
+## 5 1.833333 NA NA NA NA NA NA NA
+## 6 1.833333 NA NA NA NA NA NA NA
+## soil_prod tot_awu gva tot_uaa
+## 1 NA NA NA NA
+## 2 NA NA NA NA
+## 3 NA NA NA NA
+## 4 NA NA NA NA
+## 5 NA NA NA NA
+## 6 NA NA NA NAtail(dbase)## NUTS_ID risk_pov factor_in train35bas train35ful train_bas train_ful
+## 315 UKD3 23.51429 145.0767 0.00000000 0.2000000 0.07100592 0.05621302
+## 316 TRC1 54.15000 NA NA NA NA NA
+## 317 TRC2 54.15000 NA NA NA NA NA
+## 318 UKD4 23.51429 84.5800 0.15625000 0.3125000 0.07031828 0.07846040
+## 319 TRC3 54.15000 NA NA NA NA NA
+## 320 UKM6 23.51429 103.3933 0.05925926 0.1555556 0.03854333 0.06990962
+## nitr_high nitr_mod nitr_poor irrigated forest artific
+## 315 97.15694 2.388173 0.4548901 0.500 0.010517799 0.550161812
+## 316 NA NA NA NA 0.022020475 0.013843281
+## 317 NA NA NA NA 0.006621164 0.007146191
+## 318 97.15694 2.388173 0.4548901 0.625 0.014225182 0.109261501
+## 319 NA NA NA NA 0.037659533 0.005497742
+## 320 97.15694 2.388173 0.4548901 0.000 0.126063524 0.003747982
+## soil_loss com_birds farm_birds org_farm energy_rt renew_pct
+## 315 2.071 69.5 83.82 0.0000000 0.04487651 23.7199
+## 316 NA NA NA NA NA NA
+## 317 NA NA NA NA NA NA
+## 318 1.905 69.5 83.82 0.8233184 0.04487651 23.7199
+## 319 NA NA NA NA NA NA
+## 320 6.174 69.5 83.82 0.9873238 0.04487651 23.7199
+## renew_prod gross_N gross_P conv_till cons_till zero_till nfert
+## 315 7.183683 86.42857 5.857143 NA NA NA NA
+## 316 NA NA NA NA NA NA NA
+## 317 NA NA NA NA NA NA NA
+## 318 7.183683 86.42857 5.857143 NA NA NA NA
+## 319 NA NA NA NA NA NA NA
+## 320 7.183683 86.42857 5.857143 NA NA NA NA
+## arable grassland permanent soil_prod tot_awu gva tot_uaa
+## 315 NA NA NA NA NA NA NA
+## 316 NA NA NA NA NA NA NA
+## 317 NA NA NA NA NA NA NA
+## 318 NA NA NA NA NA NA NA
+## 319 NA NA NA NA NA NA NA
+## 320 NA NA NA NA NA NA NAsummary(data.level)## Length Class Mode
+## risk_pov.n2.dat 144 -none- character
+## factor_in.n2.dat 245 -none- character
+## train35bas.n2.dat 231 -none- character
+## train35ful.n2.dat 231 -none- character
+## train_bas.n2.dat 232 -none- character
+## train_ful.n2.dat 232 -none- character
+## nitr_high.n2.dat 0 -none- character
+## nitr_mod.n2.dat 0 -none- character
+## nitr_poor.n2.dat 0 -none- character
+## irrigated.n2.dat 232 -none- character
+## forest.n2.dat 320 -none- character
+## artific.n2.dat 320 -none- character
+## soil_loss.n2.dat 265 -none- character
+## com_birds.n2.dat 0 -none- character
+## farm_birds.n2.dat 0 -none- character
+## org_farm.n2.dat 231 -none- character
+## energy_rt.n2.dat 0 -none- character
+## renew_pct.n2.dat 0 -none- character
+## renew_prod.n2.dat 0 -none- character
+## gross_N.n2.dat 0 -none- character
+## gross_P.n2.dat 0 -none- character
+## conv_till.n2.dat 0 -none- NULL
+## cons_till.n2.dat 0 -none- NULL
+## zero_till.n2.dat 0 -none- NULL
+## nfert.n2.dat 0 -none- NULL
+## arable.n2.dat 0 -none- NULL
+## grassland.n2.dat 0 -none- NULL
+## permanent.n2.dat 0 -none- NULL
+## soil_prod.n2.dat 0 -none- NULL
+## tot_awu.n2.dat 0 -none- NULL
+## gva.n2.dat 0 -none- NULL
+## tot_uaa.n2.dat 0 -none- NULL
+## risk_pov.n1.dat 22 -none- character
+## factor_in.n1.dat 3 -none- character
+## train35bas.n1.dat 15 -none- character
+## train35ful.n1.dat 15 -none- character
+## train_bas.n1.dat 16 -none- character
+## train_ful.n1.dat 16 -none- character
+## nitr_high.n1.dat 0 -none- character
+## nitr_mod.n1.dat 0 -none- character
+## nitr_poor.n1.dat 0 -none- character
+## irrigated.n1.dat 15 -none- character
+## forest.n1.dat 0 -none- character
+## artific.n1.dat 0 -none- character
+## soil_loss.n1.dat 2 -none- character
+## com_birds.n1.dat 0 -none- character
+## farm_birds.n1.dat 0 -none- character
+## org_farm.n1.dat 16 -none- character
+## energy_rt.n1.dat 0 -none- character
+## renew_pct.n1.dat 0 -none- character
+## renew_prod.n1.dat 0 -none- character
+## gross_N.n1.dat 0 -none- character
+## gross_P.n1.dat 0 -none- character
+## conv_till.n1.dat 0 -none- NULL
+## cons_till.n1.dat 0 -none- NULL
+## zero_till.n1.dat 0 -none- NULL
+## nfert.n1.dat 0 -none- NULL
+## arable.n1.dat 0 -none- NULL
+## grassland.n1.dat 0 -none- NULL
+## permanent.n1.dat 0 -none- NULL
+## soil_prod.n1.dat 0 -none- NULL
+## tot_awu.n1.dat 0 -none- NULL
+## gva.n1.dat 0 -none- NULL
+## tot_uaa.n1.dat 0 -none- NULL
+## risk_pov.n0.dat 15 -none- character
+## factor_in.n0.dat 10 -none- character
+## train35bas.n0.dat 0 -none- character
+## train35ful.n0.dat 0 -none- character
+## train_bas.n0.dat 0 -none- character
+## train_ful.n0.dat 0 -none- character
+## nitr_high.n0.dat 28 -none- character
+## nitr_mod.n0.dat 28 -none- character
+## nitr_poor.n0.dat 28 -none- character
+## irrigated.n0.dat 6 -none- character
+## forest.n0.dat 0 -none- character
+## artific.n0.dat 0 -none- character
+## soil_loss.n0.dat 3 -none- character
+## com_birds.n0.dat 11 -none- character
+## farm_birds.n0.dat 19 -none- character
+## org_farm.n0.dat 5 -none- character
+## energy_rt.n0.dat 28 -none- character
+## renew_pct.n0.dat 27 -none- character
+## renew_prod.n0.dat 27 -none- character
+## gross_N.n0.dat 30 -none- character
+## gross_P.n0.dat 30 -none- character
+## conv_till.n0.dat 0 -none- NULL
+## cons_till.n0.dat 0 -none- NULL
+## zero_till.n0.dat 0 -none- NULL
+## nfert.n0.dat 0 -none- NULL
+## arable.n0.dat 0 -none- NULL
+## grassland.n0.dat 0 -none- NULL
+## permanent.n0.dat 0 -none- NULL
+## soil_prod.n0.dat 0 -none- NULL
+## tot_awu.n0.dat 0 -none- NULL
+## gva.n0.dat 0 -none- NULL
+## tot_uaa.n0.dat 0 -none- NULL
+## risk_pov.nuts0.na 2 -none- character
+## factor_in.nuts0.na 3 -none- character
+## train35bas.nuts0.na 9 -none- character
+## train35ful.nuts0.na 9 -none- character
+## train_bas.nuts0.na 7 -none- character
+## train_ful.nuts0.na 7 -none- character
+## nitr_high.nuts0.na 7 -none- character
+## nitr_mod.nuts0.na 7 -none- character
+## nitr_poor.nuts0.na 7 -none- character
+## irrigated.nuts0.na 3 -none- character
+## forest.nuts0.na 0 -none- character
+## artific.nuts0.na 0 -none- character
+## soil_loss.nuts0.na 7 -none- character
+## com_birds.nuts0.na 24 -none- character
+## farm_birds.nuts0.na 16 -none- character
+## org_farm.nuts0.na 3 -none- character
+## energy_rt.nuts0.na 7 -none- character
+## renew_pct.nuts0.na 8 -none- character
+## renew_prod.nuts0.na 8 -none- character
+## gross_N.nuts0.na 5 -none- character
+## gross_P.nuts0.na 5 -none- character
+## conv_till.nuts0.na 0 -none- NULL
+## cons_till.nuts0.na 0 -none- NULL
+## zero_till.nuts0.na 0 -none- NULL
+## nfert.nuts0.na 0 -none- NULL
+## arable.nuts0.na 0 -none- NULL
+## grassland.nuts0.na 0 -none- NULL
+## permanent.nuts0.na 0 -none- NULL
+## soil_prod.nuts0.na 0 -none- NULL
+## tot_awu.nuts0.na 0 -none- NULL
+## gva.nuts0.na 0 -none- NULL
+## tot_uaa.nuts0.na 0 -none- NULL#check data level for risk_pov as an example
+data.level$risk_pov.n2.dat## [1] "AT11" "AT12" "AT13" "AT21" "AT22" "AT31" "AT32" "BG31" "BG32" "BG33"
+## [11] "BG34" "BG41" "BG42" "CZ01" "CZ02" "CZ03" "CZ04" "CZ05" "CZ06" "CZ07"
+## [21] "CZ08" "CH01" "CH02" "CH03" "CH04" "AT33" "AT34" "DE72" "DE73" "DE80"
+## [31] "DE91" "DE92" "DE93" "DE94" "DEA1" "DEA2" "DEA3" "DEA4" "DEA5" "CH05"
+## [41] "CH06" "CH07" "DE11" "DE12" "DE13" "DE14" "DE21" "DE22" "DE23" "DE25"
+## [51] "DE26" "DE27" "DE30" "DE40" "DE50" "DE60" "DE71" "DEB1" "DEB2" "DEB3"
+## [61] "DEG0" "DK01" "DK02" "DK03" "DK04" "DK05" "ES11" "ES12" "ES13" "ES21"
+## [71] "ES22" "ES23" "ES24" "ES30" "DEC0" "DED2" "DED4" "DED5" "DEE0" "DEF0"
+## [81] "ES41" "ES42" "ES43" "ES51" "ES52" "ES53" "ES61" "ES62" "ES63" "ES64"
+## [91] "ES70" "FI1B" "FI1C" "FI1D" "IE01" "ITC2" "ITC3" "ITC4" "ITF1" "ITF2"
+## [101] "ITF3" "ITF4" "ITF5" "ITF6" "ITG1" "ITG2" "ITH1" "ITH2" "ITH3" "ITH4"
+## [111] "ITH5" "ITI1" "ITI2" "ITI3" "ITI4" "IE02" "ITC1" "RO11" "RO12" "RO21"
+## [121] "RO22" "RO31" "RO32" "RO41" "NO01" "NO02" "NO03" "NO04" "NO05" "NO06"
+## [131] "NO07" "RO42" "SE11" "SE12" "SE21" "SK01" "SK02" "SK03" "SK04" "SE22"
+## [141] "SE23" "SE31" "SE32" "SE33"data.level$risk_pov.n1.dat## [1] "BE3" "BE1" "BE2" "EL3" "EL4" "EL5" "EL6" "FI1" "FI2" "HU1" "HU2"
+## [12] "HU3" "NL1" "NL2" "PL5" "PL6" "NL3" "NL4" "PL1" "PL2" "PL3" "PL4"data.level$risk_pov.n0.dat## [1] "CY" "DE" "EE" "HR" "FR" "LT" "LU" "LV" "MK" "MT" "IS" "PT" "TR" "UK"
+## [15] "SI"data.level$risk_pov.nuts0.na## [1] "LI" "ME"#Now we repeat the above SDGs chunk for the additional consensus variables
+attach(con.dat)## The following objects are masked _by_ .GlobalEnv:
+##
+## gva, tot_uaafor(i in names(con.dat)[-c(1:4)]) {
+ (nuts2.na <- con.dat[STAT_LEVL_ == 2 & is.na(con.dat[,i]), 'geo'])
+ (nuts1 <- con.dat[STAT_LEVL_ == 1 & geo %in% gsub(".{1}$", "", nuts2.na), 'geo'])
+ (nuts1.na <- con.dat[geo %in% nuts1 & is.na(con.dat[,i]), 'geo'])
+ (nuts0 <- con.dat[STAT_LEVL_ == 0 & geo %in% gsub(".{1}$", "", nuts1.na), 'geo'])
+ (nuts0.na <- con.dat[geo %in% nuts0 & is.na(con.dat[,i]), 'geo'])
+
+#NUTS2 data
+(n2.dat <- con.dat[!(geo %in% nuts2.na) & STAT_LEVL_ == 2, 'geo'])
+#NUTS1 data
+(n1.dat <- nuts1[!nuts1 %in% nuts1.na])
+#NUTS0 data
+(n0.dat <- nuts0[!nuts0 %in% nuts0.na])
+#NO DATA
+nuts0.na
+
+data.level[[paste(i, 'n2.dat', sep='.')]] <- n2.dat
+data.level[[paste(i, 'n1.dat', sep='.')]] <- n1.dat
+data.level[[paste(i, 'n0.dat', sep='.')]] <- n0.dat
+data.level[[paste(i, 'nuts0.na', sep='.')]] <- nuts0.na
+
+ for(e in n0.dat) {
+ dbase[dbase$NUTS_ID %in% dbase$NUTS_ID[grep(paste(e, '..', sep=''), dbase$NUTS_ID)], i] <- con.dat[con.dat$geo == e, i]
+ }
+
+ for(e in n1.dat) {
+ dbase[dbase$NUTS_ID %in% dbase$NUTS_ID[grep(paste(e, '.', sep=''), dbase$NUTS_ID)], i] <- con.dat[con.dat$geo == e, i]
+ }
+
+ for(e in n2.dat) {
+ dbase[dbase$NUTS_ID == e, i] <- con.dat[con.dat$geo == e, i]
+ }
+}
+detach(con.dat)
+
+summary(dbase)## NUTS_ID risk_pov factor_in train35bas
+## AT11 : 1 Min. : 9.971 Min. : -0.73 Min. :0.00000
+## AT12 : 1 1st Qu.:18.586 1st Qu.: 144.97 1st Qu.:0.09613
+## AT13 : 1 Median :23.514 Median : 366.48 Median :0.22800
+## AT21 : 1 Mean :25.960 Mean : 1141.61 Mean :0.26424
+## AT22 : 1 3rd Qu.:29.680 3rd Qu.: 932.31 3rd Qu.:0.35996
+## AT31 : 1 Max. :54.150 Max. :10472.05 Max. :0.88217
+## (Other):314 NA's :2 NA's :28 NA's :52
+## train35ful train_bas train_ful nitr_high
+## Min. :0.0000 Min. :0.01171 Min. :0.00188 Min. : 4.082
+## 1st Qu.:0.1264 1st Qu.:0.10627 1st Qu.:0.04939 1st Qu.: 66.302
+## Median :0.2600 Median :0.19961 Median :0.12807 Median : 70.505
+## Mean :0.2738 Mean :0.26250 Mean :0.15796 Mean : 75.328
+## 3rd Qu.:0.3825 3rd Qu.:0.36488 3rd Qu.:0.25108 3rd Qu.: 87.591
+## Max. :0.8550 Max. :0.94840 Max. :0.50303 Max. :100.000
+## NA's :52 NA's :50 NA's :50 NA's :44
+## nitr_mod nitr_poor irrigated forest
+## Min. : 0.000 Min. : 0.000 Min. : 0.0000 Min. :0.00000
+## 1st Qu.: 6.533 1st Qu.: 4.106 1st Qu.: 0.3312 1st Qu.:0.08957
+## Median :15.896 Median : 8.883 Median : 1.2250 Median :0.24904
+## Mean :13.773 Mean :10.898 Mean : 5.7571 Mean :0.25141
+## 3rd Qu.:18.416 3rd Qu.:15.385 3rd Qu.: 6.5000 3rd Qu.:0.37365
+## Max. :60.000 Max. :68.367 Max. :74.5500 Max. :0.75860
+## NA's :44 NA's :44 NA's :28
+## artific soil_loss com_birds farm_birds
+## Min. :0.00000 Min. : 0.0300 Min. :54.92 Min. : 63.78
+## 1st Qu.:0.02056 1st Qu.: 0.7047 1st Qu.:62.14 1st Qu.: 81.34
+## Median :0.04020 Median : 1.5005 Median :69.50 Median : 83.82
+## Mean :0.09023 Mean : 2.5482 Mean :69.70 Mean : 81.90
+## 3rd Qu.:0.08193 3rd Qu.: 2.9420 3rd Qu.:81.30 3rd Qu.: 85.30
+## Max. :1.00000 Max. :17.6050 Max. :97.22 Max. :116.60
+## NA's :44 NA's :158 NA's :94
+## org_farm energy_rt renew_pct renew_prod
+## Min. : 0.000 Min. :0.00000 Min. : 0.000 Min. : 0.8855
+## 1st Qu.: 1.200 1st Qu.:0.03503 1st Qu.: 3.074 1st Qu.: 6.2422
+## Median : 2.687 Median :0.06128 Median : 6.124 Median : 8.3156
+## Mean : 4.056 Mean :0.15052 Mean :11.225 Mean :12.4318
+## 3rd Qu.: 5.204 3rd Qu.:0.09725 3rd Qu.:22.515 3rd Qu.:18.0797
+## Max. :27.487 Max. :1.75149 Max. :41.011 Max. :37.7797
+## NA's :28 NA's :44 NA's :82 NA's :45
+## gross_N gross_P conv_till cons_till
+## Min. : 2.857 Min. :-6.500 Min. :0.08646 Min. :0.00000
+## 1st Qu.: 41.821 1st Qu.:-1.667 1st Qu.:0.46182 1st Qu.:0.05077
+## Median : 67.333 Median : 1.833 Median :0.61740 Median :0.12499
+## Mean : 67.553 Mean : 1.941 Mean :0.60410 Mean :0.18031
+## 3rd Qu.: 85.988 3rd Qu.: 4.714 3rd Qu.:0.73832 3rd Qu.:0.28382
+## Max. :190.167 Max. :31.000 Max. :0.99752 Max. :0.65066
+## NA's :30 NA's :30 NA's :53 NA's :53
+## zero_till nfert arable grassland
+## Min. :0.00000 Min. : 0.000 Min. : 0.00 Min. : 0.00
+## 1st Qu.:0.00920 1st Qu.: 6.448 1st Qu.:39.68 1st Qu.:17.20
+## Median :0.01843 Median : 9.917 Median :62.28 Median :32.97
+## Mean :0.03000 Mean :10.975 Mean :57.72 Mean :35.74
+## 3rd Qu.:0.04003 3rd Qu.:14.254 3rd Qu.:78.19 3rd Qu.:48.62
+## Max. :0.19303 Max. :29.456 Max. :99.28 Max. :98.84
+## NA's :53 NA's :11 NA's :44 NA's :44
+## permanent soil_prod tot_awu gva
+## Min. : 0.0000 Min. :3.00 Min. : 0 Min. : 0.0
+## 1st Qu.: 0.3546 1st Qu.:6.00 1st Qu.: 9510 1st Qu.: 204.0
+## Median : 1.1324 Median :6.00 Median : 24760 Median : 431.2
+## Mean : 5.7197 Mean :6.45 Mean : 78177 Mean : 729.0
+## 3rd Qu.: 5.6520 3rd Qu.:7.00 3rd Qu.: 74294 3rd Qu.: 895.7
+## Max. :64.6743 Max. :8.00 Max. :791115 Max. :7125.2
+## NA's :44 NA's :51 NA's :28 NA's :28
+## tot_uaa
+## Min. : 0
+## 1st Qu.: 195140
+## Median : 459335
+## Mean : 3607738
+## 3rd Qu.: 1000862
+## Max. :27776795
+## NA's :36head(dbase)## NUTS_ID risk_pov factor_in train35bas train35ful train_bas train_ful
+## 1 AT11 13.73333 173.70857 0.1375661 0.3333333 0.1243050 0.1779190
+## 2 AT22 17.26667 393.97429 0.2160980 0.3648294 0.2017089 0.2413594
+## 3 AT12 13.83333 884.43857 0.2084775 0.4809689 0.2534787 0.3449437
+## 4 AT13 27.23333 12.70143 0.3750000 0.7500000 0.1753247 0.4740260
+## 5 AT21 17.20000 111.36714 0.2306238 0.3648393 0.2076173 0.2250348
+## 6 AT31 15.00000 452.67857 0.2508418 0.4284512 0.2014381 0.2857610
+## nitr_high nitr_mod nitr_poor irrigated forest artific soil_loss
+## 1 64.58924 20.20774 15.20302 5.850 0.3161203 0.04355635 1.842
+## 2 64.58924 20.20774 15.20302 0.325 0.6127954 0.03306278 5.804
+## 3 64.58924 20.20774 15.20302 2.650 0.4286079 0.04875064 2.236
+## 4 64.58924 20.20774 15.20302 10.525 0.1469534 0.73118280 1.014
+## 5 64.58924 20.20774 15.20302 0.100 0.5998934 0.03047416 11.671
+## 6 64.58924 20.20774 15.20302 0.125 0.4027358 0.04900973 3.791
+## com_birds farm_birds org_farm energy_rt renew_pct renew_prod gross_N
+## 1 NA 65.98 19.43430 0.08319988 32.65559 7.068917 32.57143
+## 2 NA 65.98 12.80858 0.08319988 32.65559 7.068917 32.57143
+## 3 NA 65.98 13.41584 0.08319988 32.65559 7.068917 32.57143
+## 4 NA 65.98 16.44137 0.08319988 32.65559 7.068917 32.57143
+## 5 NA 65.98 10.68078 0.08319988 32.65559 7.068917 32.57143
+## 6 NA 65.98 12.31071 0.08319988 32.65559 7.068917 32.57143
+## gross_P conv_till cons_till zero_till nfert arable grassland
+## 1 1.833333 0.6182190 0.31992068 0.025012794 7.684000 83.64566 8.715722
+## 2 1.833333 0.8887161 0.05005656 0.024109163 7.551429 37.02489 58.694493
+## 3 1.833333 0.6226791 0.32803537 0.019896256 7.452800 76.22380 20.140837
+## 4 1.833333 0.5109890 0.40476190 0.007326007 7.497000 79.80050 10.099751
+## 5 1.833333 0.8592546 0.05928605 0.032552288 8.131500 28.48779 71.285286
+## 6 1.833333 0.8442576 0.12043311 0.014198645 9.138333 56.49367 43.164202
+## permanent soil_prod tot_awu gva tot_uaa
+## 1 7.5451998 6 7007.5 177.76429 181150
+## 2 4.2139773 6 28225.0 519.01286 374895
+## 3 3.5858503 6 38360.0 975.25143 895805
+## 4 10.0997506 6 1975.0 19.65571 7190
+## 5 0.1679223 6 10367.5 122.62143 215230
+## 6 0.2648111 6 29657.5 653.30143 513830tail(dbase)## NUTS_ID risk_pov factor_in train35bas train35ful train_bas train_ful
+## 315 UKD3 23.51429 145.0767 0.00000000 0.2000000 0.07100592 0.05621302
+## 316 TRC1 54.15000 NA NA NA NA NA
+## 317 TRC2 54.15000 NA NA NA NA NA
+## 318 UKD4 23.51429 84.5800 0.15625000 0.3125000 0.07031828 0.07846040
+## 319 TRC3 54.15000 NA NA NA NA NA
+## 320 UKM6 23.51429 103.3933 0.05925926 0.1555556 0.03854333 0.06990962
+## nitr_high nitr_mod nitr_poor irrigated forest artific
+## 315 97.15694 2.388173 0.4548901 0.500 0.010517799 0.550161812
+## 316 NA NA NA NA 0.022020475 0.013843281
+## 317 NA NA NA NA 0.006621164 0.007146191
+## 318 97.15694 2.388173 0.4548901 0.625 0.014225182 0.109261501
+## 319 NA NA NA NA 0.037659533 0.005497742
+## 320 97.15694 2.388173 0.4548901 0.000 0.126063524 0.003747982
+## soil_loss com_birds farm_birds org_farm energy_rt renew_pct
+## 315 2.071 69.5 83.82 0.0000000 0.04487651 23.7199
+## 316 NA NA NA NA NA NA
+## 317 NA NA NA NA NA NA
+## 318 1.905 69.5 83.82 0.8233184 0.04487651 23.7199
+## 319 NA NA NA NA NA NA
+## 320 6.174 69.5 83.82 0.9873238 0.04487651 23.7199
+## renew_prod gross_N gross_P conv_till cons_till zero_till
+## 315 7.183683 86.42857 5.857143 0.5116279 0.26976744 0.083720930
+## 316 NA NA NA NA NA NA
+## 317 NA NA NA NA NA NA
+## 318 7.183683 86.42857 5.857143 0.5070682 0.07652120 0.000921942
+## 319 NA NA NA NA NA NA
+## 320 7.183683 86.42857 5.857143 0.3571254 0.01623576 0.064146551
+## nfert arable grassland permanent soil_prod tot_awu gva
+## 315 17.954800 21.626717 78.21169 0.134661998 6 1352.5 166.29333
+## 316 5.709333 NA NA NA NA NA NA
+## 317 5.508154 NA NA NA NA NA NA
+## 318 17.686000 20.185625 79.77323 0.041148500 6 7645.0 100.34333
+## 319 5.452800 NA NA NA NA NA NA
+## 320 13.097444 6.222771 93.77578 0.001447408 6 10525.0 51.39333
+## tot_uaa
+## 315 36325
+## 316 NA
+## 317 NA
+## 318 213575
+## 319 NA
+## 320 2516980#check data level for conv_till as an example
+data.level$conv_till.n2.dat## [1] "AT11" "AT12" "AT13" "AT21" "AT22" "AT31" "AT32" "BE31" "BE32" "BE33"
+## [11] "BE34" "BE35" "BG31" "BG32" "BG33" "BG34" "BG41" "BG42" "CY00" "CZ01"
+## [21] "CZ02" "CZ03" "CZ04" "CZ05" "CZ06" "CZ07" "CZ08" "CH01" "CH02" "CH03"
+## [31] "CH04" "AT33" "AT34" "BE21" "BE22" "BE23" "BE24" "BE25" "CH05" "CH06"
+## [41] "CH07" "DK01" "DK02" "DK03" "DK04" "DK05" "EE00" "EL30" "EL41" "EL42"
+## [51] "EL43" "ES11" "ES12" "ES13" "ES21" "ES22" "ES23" "ES24" "ES30" "FR52"
+## [61] "FR53" "FR61" "FR62" "FR63" "FR71" "FR72" "FR81" "FR82" "FR83" "HR03"
+## [71] "HR04" "ES41" "ES42" "ES43" "ES51" "ES52" "ES53" "ES61" "ES62" "ES70"
+## [81] "FI19" "FI1B" "FI1C" "FI1D" "FI20" "FR10" "FR21" "FR22" "FR23" "FR24"
+## [91] "FR25" "FR26" "FR30" "FR41" "FR42" "FR43" "FR51" "HU10" "HU21" "HU22"
+## [101] "HU23" "HU31" "HU32" "HU33" "IE01" "ITC2" "ITC3" "ITC4" "ITF1" "ITF2"
+## [111] "ITF3" "ITF4" "ITF5" "ITF6" "ITG1" "ITG2" "ITH1" "ITH2" "ITH3" "ITH4"
+## [121] "ITH5" "ITI1" "ITI2" "ITI3" "ITI4" "LT00" "LU00" "LV00" "ME00" "MT00"
+## [131] "NL11" "NL12" "NL13" "NL21" "NL22" "IE02" "IS00" "ITC1" "PL43" "PL51"
+## [141] "PL52" "PL61" "PL62" "PL63" "PT11" "PT15" "PT16" "PT17" "PT18" "PT20"
+## [151] "PT30" "RO11" "RO12" "RO21" "RO22" "RO31" "RO32" "RO41" "NL23" "NL31"
+## [161] "NL32" "NL33" "NL34" "NL41" "NL42" "NO01" "NO02" "NO03" "NO04" "NO05"
+## [171] "NO06" "NO07" "PL11" "PL12" "PL21" "PL31" "PL32" "PL33" "PL34" "PL41"
+## [181] "PL42" "RO42" "SE11" "SE12" "SE21" "SK01" "SK02" "SK03" "SK04" "UKC1"
+## [191] "SE22" "SE23" "SE31" "SE32" "SE33" "UKM2" "UKM3" "UKM5" "UKM6" "UKC2"
+## [201] "UKD1" "UKD3" "UKD4" "UKD6" "UKD7" "UKE1" "UKE2" "UKE3" "UKE4" "UKF1"
+## [211] "UKF2" "UKF3" "UKG1" "UKG2" "UKG3" "UKH1" "UKH2" "UKH3" "UKJ1" "UKJ2"
+## [221] "UKJ3" "UKJ4" "UKK1" "UKK2" "UKK3" "UKK4" "UKL1" "UKL2" "UKN0"data.level$conv_till.n1.dat## [1] "DE8" "DE9" "DEA" "DE1" "DE2" "DE3" "DE4" "DE5" "DE6" "DE7" "DEB"
+## [12] "DEG" "DEC" "DED" "DEE" "DEF"data.level$conv_till.n0.dat## character(0)data.level$conv_till.nuts0.na## [1] "BE" "EL" "ES" "FR" "LI" "MK" "PL" "TR" "UK" "SI"#Utilisted agricultural area (UAA) is an important variable for weighting the allocation of other variables through NUTS2 regions and for calculating proportions, etc.
+#The Eurostat UAA data is missing NUTS2 data in many areas. To fill these gaps, we will use the CORINE land cover dataset for an estimate of agricultural area (all CORINE categories in the 200s)
+
+corine.aa <- st_read(dsn='C:/Users/mu5106sc/Dropbox/STAGS/D1_Database/EU_Farming_Systems_20181015.gdb', layer='nuts2_corine_ag_area_ha')## Reading layer `nuts2_corine_ag_area_ha' from data source `C:\Users\mu5106sc\Dropbox\STAGS\D1_Database\EU_Farming_Systems_20181015.gdb' using driver `OpenFileGDB'## Warning: no simple feature geometries present: returning a data.frame or
+## tbl_dfcorine.aa$geo <- corine.aa$NUTS_ID
+head(corine.aa)## NUTS_ID ZONE_CODE COUNT AREA SUM geo
+## 1 AT11 1 35088 2193000000 219300.0 AT11
+## 2 AT22 2 65849 4115562500 411556.2 AT22
+## 3 AT12 3 160793 10049562500 1004956.2 AT12
+## 4 AT13 4 972 60750000 6075.0 AT13
+## 5 AT21 5 30610 1913125000 191312.5 AT21
+## 6 AT31 6 93214 5825875000 582587.5 AT31head(con.dat[,c("geo", "tot_uaa")])## geo tot_uaa
+## 1 AT 2698320
+## 2 AT1 NA
+## 3 AT11 181150
+## 4 AT12 895805
+## 5 AT13 7190
+## 6 AT2 NAuaa.compare <- left_join(corine.aa[,c("geo", "SUM")], con.dat[,c("geo", "tot_uaa")])## Joining, by = "geo"## Warning: Column `geo` joining factor and character vector, coercing into
+## character vectorhead(uaa.compare)## geo SUM tot_uaa
+## 1 AT11 219300.0 181150
+## 2 AT22 411556.2 374895
+## 3 AT12 1004956.2 895805
+## 4 AT13 6075.0 7190
+## 5 AT21 191312.5 215230
+## 6 AT31 582587.5 513830plot(uaa.compare$tot_uaa ~ uaa.compare$SUM)
cor(uaa.compare[,2:3])## SUM tot_uaa
+## SUM 1 NA
+## tot_uaa NA 1#Although the CORINE agricultural area slightly overestimates the Eurostat UAA data, the correlation is 1, so we will use CORINE agricultural area for its completeness
+
+#Next, we need to aggregate to NUTS1 and NUTS0 levels for calculations below
+nuts2.geos <- sdg.dat$geo[sdg.dat$STAT_LEVL_ == 2]
+nuts1.geos <- sdg.dat$geo[sdg.dat$STAT_LEVL_ == 1]
+nuts0.geos <- sdg.dat$geo[sdg.dat$STAT_LEVL_ == 0]
+
+uaa.nuts1 <- as.data.frame(nuts1.geos)
+names(uaa.nuts1) <- 'geo'
+uaa.nuts1$sum_uaa <- NA
+
+for(e in nuts1.geos) {
+ uaa.nuts1$sum_uaa[uaa.nuts1$geo == e] <- sum(uaa.compare$SUM[uaa.compare$geo %in% uaa.compare$geo[grep(paste(e, '.', sep=''), uaa.compare$geo)]])
+}
+
+head(uaa.nuts1)## geo sum_uaa
+## 1 AT1 1230331.2
+## 2 AT2 602868.8
+## 3 AT3 844343.8
+## 4 BE3 906737.5
+## 5 BG3 4221656.2
+## 6 BG4 1532893.8uaa.nuts0 <- as.data.frame(nuts0.geos)
+names(uaa.nuts0) <- 'geo'
+uaa.nuts0$sum_uaa <- NA
+
+for(e in nuts0.geos) {
+ uaa.nuts0$sum_uaa[uaa.nuts0$geo == e] <- sum(uaa.compare$SUM[uaa.compare$geo %in% uaa.compare$geo[grep(paste(e, '..', sep=''), uaa.compare$geo)]])
+}
+
+head(uaa.nuts0)## geo sum_uaa
+## 1 AT 2677543.8
+## 2 BG 5754550.0
+## 3 CY 443356.2
+## 4 CZ 4508200.0
+## 5 CH 1185400.0
+## 6 BE 1760275.0#bind all dataframes together
+uaa.compare$sum_uaa <- uaa.compare$SUM
+corine.aa.all.nuts <- rbind(uaa.compare[,c(1,4)], uaa.nuts1, uaa.nuts0)
+head(corine.aa.all.nuts)## geo sum_uaa
+## 1 AT11 219300.0
+## 2 AT22 411556.2
+## 3 AT12 1004956.2
+## 4 AT13 6075.0
+## 5 AT21 191312.5
+## 6 AT31 582587.5tail(corine.aa.all.nuts)## geo sum_uaa
+## 464 PL 18689137.5
+## 465 SE 3914437.5
+## 466 SK 2327718.8
+## 467 TR 33916137.5
+## 468 UK 13837168.8
+## 469 SI 701168.8#Here we use CAP Context Indicators to get better coverage of NUTS2 data for SDG variables currently at NUTS0
+
+#Volumes of water abstraction for irrigation are patchy and at the NUTS0 level from Eurostat. CAP Context Indicator C.39 contains NUTS1 and NUTS2 data in many areas from 2010, which we will use instead.
+#All zeros in this table were converted to no data due to uncertainty as to their accuracy
+cap.irrig <- read.csv("C:/Users/mu5106sc/Dropbox/STAGS/SDG_data_eurostat/Final_database/SDGs/Goal6/Irrigation_volume/C39_en_clean.csv", head=T)
+head(cap.irrig)## geo irrig_vol
+## 1 BE NA
+## 2 BE1 NA
+## 3 BE10 NA
+## 4 BE2 NA
+## 5 BE21 NA
+## 6 BE22 NAsummary(cap.irrig)## geo irrig_vol
+## AT : 1 Min. : 4
+## AT1 : 1 1st Qu.: 1266
+## AT11 : 1 Median : 11926
+## AT12 : 1 Mean : 367069
+## AT13 : 1 3rd Qu.: 111053
+## AT2 : 1 Max. :16658538
+## (Other):392 NA's :73#GDP from CAP Context Indicator C.08
+cap.gdp <- read.csv("C:/Users/mu5106sc/Dropbox/STAGS/SDG_data_eurostat/Final_database/Alternative_variables/c8_en_clean.csv", head=T)
+head(cap.gdp)## geo tot_mil_eur tot_eur_cap tot_mil_pps tot_pps_cap rur_mil_eur
+## 1 BE 400805 35900 368652 33000 21277
+## 2 BE1 73399 62900 67511 57900 NA
+## 3 BE10 73399 62900 67511 57900 NA
+## 4 BE2 233920 36500 215155 33500 NA
+## 5 BE21 76359 42300 70234 38900 NA
+## 6 BE22 25559 29800 23509 27400 NA
+## rur_eur_cap rur_mil_pps rur_pps_cap int_mil_eur int_eur_cap int_mil_pps
+## 1 22420.44 19571 20622.76 138660 32503.52 127538
+## 2 NA NA NA NA NA NA
+## 3 NA NA NA NA NA NA
+## 4 NA NA NA 103471 34284.63 95172
+## 5 NA NA NA 17909 39975.45 16473
+## 6 NA NA NA 10197 23334.10 9379
+## int_pps_cap urb_mil_eur urb_eur_cap urb_mil_pps urb_pps_cap
+## 1 29896.39 240598 40491.08 221297 37242.85
+## 2 NA 73399 62895.46 67511 57850.04
+## 3 NA 73399 62895.46 67511 57850.04
+## 4 31534.79 130449 38401.24 119985 35320.87
+## 5 36770.09 58450 43072.96 53761 39617.54
+## 6 21462.24 15362 36663.48 14130 33723.15#Employment rate from CAP Context Indicator C.05
+cap.emp <- read.csv("C:/Users/mu5106sc/Dropbox/STAGS/SDG_data_eurostat/Final_database/Alternative_variables/c5_en_clean.csv", head=T)
+head(cap.emp)## NUTS_ID emp_rate_15_64
+## 1 BE 62.28959
+## 2 BE1 55.27341
+## 3 BE10 55.27341
+## 4 BE2 66.52326
+## 5 BE21 63.91419
+## 6 BE22 64.76931cap.emp$geo <- cap.emp$NUTS_ID
+#EL51 is duplicated in this table, so deleted here
+cap.emp[cap.emp$geo == "EL51",]## NUTS_ID emp_rate_15_64 geo
+## 111 EL51 51.93326 EL51
+## 112 EL51 51.93326 EL51cap.emp <- cap.emp[-112,]
+
+#Youth and total unemployment from CAP Context Indicator C.07
+cap.unemp <- read.csv("C:/Users/mu5106sc/Dropbox/STAGS/SDG_data_eurostat/Final_database/Alternative_variables/c7_en_clean.csv", head=T)
+head(cap.unemp)## geo tot_unemp yth_unemp
+## 1 BE 7.8 20.1
+## 2 BE1 16.8 35.9
+## 3 BE10 16.8 35.9
+## 4 BE2 4.8 14.1
+## 5 BE21 6.1 18.5
+## 6 BE22 4.8 9.8#Merge tables
+add.cap.dat <- sdg_data@data[,1:2]
+add.cap.dat <- left_join(add.cap.dat, cap.irrig)## Joining, by = "geo"## Warning: Column `geo` joining factors with different levels, coercing to
+## character vectoradd.cap.dat <- left_join(add.cap.dat, cap.gdp[,c(1,3,5)]) #Dont include regional data because of important differences between urban-rural typologies## Joining, by = "geo"## Warning: Column `geo` joining character vector and factor, coercing into
+## character vectoradd.cap.dat <- left_join(add.cap.dat, cap.emp[,-1])## Joining, by = "geo"## Warning: Column `geo` joining character vector and factor, coercing into
+## character vectoradd.cap.dat <- left_join(add.cap.dat, cap.unemp)## Joining, by = "geo"## Warning: Column `geo` joining character vector and factor, coercing into
+## character vectorhead(add.cap.dat)## geo STAT_LEVL_ irrig_vol tot_eur_cap tot_pps_cap emp_rate_15_64
+## 1 AT 0 18316.2 38700 35700 71.54552
+## 2 AT1 1 15755.7 38900 35900 68.75891
+## 3 AT11 2 3660.6 26700 24600 69.81530
+## 4 AT12 2 10828.8 31800 29300 73.06232
+## 5 AT13 2 1266.4 47300 43700 64.90683
+## 6 AT2 1 1019.4 34100 31500 70.91171
+## tot_unemp yth_unemp
+## 1 6.0 11.2
+## 2 8.2 15.0
+## 3 5.7 NA
+## 4 5.2 9.3
+## 5 11.3 20.3
+## 6 5.2 10.8names(add.cap.dat)## [1] "geo" "STAT_LEVL_" "irrig_vol" "tot_eur_cap"
+## [5] "tot_pps_cap" "emp_rate_15_64" "tot_unemp" "yth_unemp"nrow(add.cap.dat)## [1] 471summary(add.cap.dat)## geo STAT_LEVL_ irrig_vol tot_eur_cap
+## Length:471 Min. :0.000 Min. : 4 Min. : 3800
+## Class :character 1st Qu.:1.000 1st Qu.: 1215 1st Qu.: 15675
+## Mode :character Median :2.000 Median : 10829 Median : 26400
+## Mean :1.605 Mean : 365169 Mean : 26844
+## 3rd Qu.:2.000 3rd Qu.: 91510 3rd Qu.: 34100
+## Max. :2.000 Max. :16658538 Max. :191400
+## NA's :164 NA's :69
+## tot_pps_cap emp_rate_15_64 tot_unemp yth_unemp
+## Min. : 8200 Min. :37.87 Min. : 2.100 Min. : 4.20
+## 1st Qu.: 20025 1st Qu.:62.39 1st Qu.: 4.800 1st Qu.:11.00
+## Median : 24750 Median :67.64 Median : 7.000 Median :17.20
+## Mean : 26698 Mean :66.84 Mean : 8.802 Mean :21.50
+## 3rd Qu.: 31325 3rd Qu.:73.61 3rd Qu.:10.500 3rd Qu.:28.35
+## Max. :163500 Max. :81.42 Max. :31.300 Max. :69.10
+## NA's :69 NA's :70 NA's :71 NA's :80#create whole database for processing alternative CAP indicators
+dbase.cap <- as.data.frame(matrix(nrow=nrow(nuts@data), ncol=(ncol(add.cap.dat[,-2]))))
+dbase.cap[,1] <- nuts@data$NUTS_ID
+names(dbase.cap) <- c("NUTS_ID", names(add.cap.dat[,-c(1:2)]))
+head(dbase.cap)## NUTS_ID irrig_vol tot_eur_cap tot_pps_cap emp_rate_15_64 tot_unemp
+## 1 AT11 NA NA NA NA NA
+## 2 AT22 NA NA NA NA NA
+## 3 AT12 NA NA NA NA NA
+## 4 AT13 NA NA NA NA NA
+## 5 AT21 NA NA NA NA NA
+## 6 AT31 NA NA NA NA NA
+## yth_unemp
+## 1 NA
+## 2 NA
+## 3 NA
+## 4 NA
+## 5 NA
+## 6 NAnrow(dbase.cap)## [1] 320#Repeat function above to allocate NUTS1 and NUTS0 to NUTS2 units. Again, this is appropriate for ratio variables but not absolute variables. This will be cleaned and corrected below.
+data.level.cap <- vector("list", 4*length(names(dbase.cap)[-1]))
+names(data.level.cap) <- c(paste(names(dbase.cap)[-1], 'n2.dat', sep='.'),
+ paste(names(dbase.cap)[-1], 'n1.dat', sep='.'),
+ paste(names(dbase.cap)[-1], 'n0.dat', sep='.'),
+ paste(names(dbase.cap)[-1], 'nuts0.na', sep='.')
+ )
+labels(data.level.cap)## [1] "irrig_vol.n2.dat" "tot_eur_cap.n2.dat"
+## [3] "tot_pps_cap.n2.dat" "emp_rate_15_64.n2.dat"
+## [5] "tot_unemp.n2.dat" "yth_unemp.n2.dat"
+## [7] "irrig_vol.n1.dat" "tot_eur_cap.n1.dat"
+## [9] "tot_pps_cap.n1.dat" "emp_rate_15_64.n1.dat"
+## [11] "tot_unemp.n1.dat" "yth_unemp.n1.dat"
+## [13] "irrig_vol.n0.dat" "tot_eur_cap.n0.dat"
+## [15] "tot_pps_cap.n0.dat" "emp_rate_15_64.n0.dat"
+## [17] "tot_unemp.n0.dat" "yth_unemp.n0.dat"
+## [19] "irrig_vol.nuts0.na" "tot_eur_cap.nuts0.na"
+## [21] "tot_pps_cap.nuts0.na" "emp_rate_15_64.nuts0.na"
+## [23] "tot_unemp.nuts0.na" "yth_unemp.nuts0.na"attach(add.cap.dat)
+for(i in names(add.cap.dat[,-c(1:2)])) {
+ (nuts2.na <- add.cap.dat[STAT_LEVL_ == 2 & is.na(add.cap.dat[,i]), 'geo'])
+ (nuts1 <- add.cap.dat[STAT_LEVL_ == 1 & geo %in% gsub(".{1}$", "", nuts2.na), 'geo'])
+ (nuts1.na <- add.cap.dat[geo %in% nuts1 & is.na(add.cap.dat[,i]), 'geo'])
+ (nuts0 <- add.cap.dat[STAT_LEVL_ == 0 & geo %in% gsub(".{1}$", "", nuts1.na), 'geo'])
+ (nuts0.na <- add.cap.dat[geo %in% nuts0 & is.na(add.cap.dat[,i]), 'geo'])
+
+#NUTS2 data
+(n2.dat <- add.cap.dat[!(geo %in% nuts2.na) & STAT_LEVL_ == 2, 'geo'])
+#NUTS1 data
+(n1.dat <- nuts1[!nuts1 %in% nuts1.na])
+#NUTS0 data
+(n0.dat <- nuts0[!nuts0 %in% nuts0.na])
+#NO DATA
+nuts0.na
+
+data.level.cap[[paste(i, 'n2.dat', sep='.')]] <- n2.dat
+data.level.cap[[paste(i, 'n1.dat', sep='.')]] <- n1.dat
+data.level.cap[[paste(i, 'n0.dat', sep='.')]] <- n0.dat
+data.level.cap[[paste(i, 'nuts0.na', sep='.')]] <- nuts0.na
+
+ for(e in n0.dat) {
+ dbase.cap[dbase.cap$NUTS_ID %in% dbase.cap$NUTS_ID[grep(paste(e, '..', sep=''), dbase.cap$NUTS_ID)], i] <- add.cap.dat[add.cap.dat$geo == e, i]
+ }
+
+ for(e in n1.dat) {
+ dbase.cap[dbase.cap$NUTS_ID %in% dbase.cap$NUTS_ID[grep(paste(e, '.', sep=''), dbase.cap$NUTS_ID)], i] <- add.cap.dat[add.cap.dat$geo == e, i]
+ }
+
+ for(e in n2.dat) {
+ dbase.cap[dbase.cap$NUTS_ID == e, i] <- add.cap.dat[add.cap.dat$geo == e, i]
+ }
+}
+detach(add.cap.dat)
+
+summary(dbase.cap)## NUTS_ID irrig_vol tot_eur_cap tot_pps_cap
+## AT11 : 1 Min. : 4 Min. : 3800 Min. : 8200
+## AT12 : 1 1st Qu.: 1228 1st Qu.: 16350 1st Qu.: 19750
+## AT13 : 1 Median : 10445 Median : 26500 Median : 24750
+## AT21 : 1 Mean : 361058 Mean : 26832 Mean : 26526
+## AT22 : 1 3rd Qu.: 89134 3rd Qu.: 33750 3rd Qu.: 31025
+## AT31 : 1 Max. :4720091 Max. :191400 Max. :163500
+## (Other):314 NA's :58 NA's :44 NA's :44
+## emp_rate_15_64 tot_unemp yth_unemp
+## Min. :37.87 Min. : 2.100 Min. : 4.20
+## 1st Qu.:62.16 1st Qu.: 4.700 1st Qu.:10.60
+## Median :67.91 Median : 6.850 Median :17.00
+## Mean :66.82 Mean : 8.767 Mean :21.39
+## 3rd Qu.:73.84 3rd Qu.:10.600 3rd Qu.:29.10
+## Max. :81.42 Max. :31.300 Max. :69.10
+## NA's :44 NA's :44 NA's :44head(dbase.cap)## NUTS_ID irrig_vol tot_eur_cap tot_pps_cap emp_rate_15_64 tot_unemp
+## 1 AT11 3660.6 26700 24600 69.81530 5.7
+## 2 AT22 909.0 34800 32100 71.37077 5.1
+## 3 AT12 10828.8 31800 29300 73.06232 5.2
+## 4 AT13 1266.4 47300 43700 64.90683 11.3
+## 5 AT21 110.4 32700 30200 69.88481 5.4
+## 6 AT31 319.9 39600 36500 75.46507 4.5
+## yth_unemp
+## 1 15.0
+## 2 10.2
+## 3 9.3
+## 4 20.3
+## 5 12.2
+## 6 7.6tail(dbase.cap)## NUTS_ID irrig_vol tot_eur_cap tot_pps_cap emp_rate_15_64 tot_unemp
+## 315 UKD3 582.8 29200 25000 70.77519 6.1
+## 316 TRC1 NA NA NA NA NA
+## 317 TRC2 NA NA NA NA NA
+## 318 UKD4 277.5 26400 22600 72.71144 4.4
+## 319 TRC3 NA NA NA NA NA
+## 320 UKM6 340.9 29600 25300 72.98066 4.7
+## yth_unemp
+## 315 16.1
+## 316 NA
+## 317 NA
+## 318 13.0
+## 319 NA
+## 320 14.5#check data level for irrig_vol as an example
+data.level.cap$irrig_vol.n2.dat## [1] "AT11" "AT12" "AT13" "AT21" "AT22" "AT31" "AT32" "BG31" "BG32" "BG33"
+## [11] "BG34" "BG41" "BG42" "CY00" "CZ02" "CZ03" "CZ04" "CZ05" "CZ06" "CZ07"
+## [21] "CZ08" "AT33" "AT34" "DK01" "DK02" "DK03" "DK04" "DK05" "EE00" "EL30"
+## [31] "EL41" "EL42" "EL43" "ES11" "ES12" "ES13" "ES21" "ES22" "ES23" "ES24"
+## [41] "ES30" "FR52" "FR53" "FR61" "FR62" "FR63" "FR71" "FR72" "FR81" "FR82"
+## [51] "FR83" "HR03" "HR04" "ES41" "ES42" "ES43" "ES51" "ES52" "ES53" "ES61"
+## [61] "ES62" "ES70" "FI19" "FI1B" "FI1C" "FI1D" "FI20" "FR10" "FR21" "FR22"
+## [71] "FR23" "FR24" "FR25" "FR26" "FR30" "FR41" "FR42" "FR43" "FR51" "HU10"
+## [81] "HU21" "HU22" "HU23" "HU31" "HU32" "HU33" "ITC2" "ITC3" "ITC4" "ITF1"
+## [91] "ITF2" "ITF3" "ITF4" "ITF5" "ITF6" "ITG1" "ITG2" "ITH1" "ITH2" "ITH3"
+## [101] "ITH4" "ITH5" "ITI1" "ITI2" "ITI3" "ITI4" "LT00" "LV00" "MT00" "NL11"
+## [111] "NL12" "NL13" "NL21" "NL22" "ITC1" "PL43" "PL51" "PL52" "PL61" "PL62"
+## [121] "PL63" "PT11" "PT15" "PT16" "PT17" "PT18" "PT20" "PT30" "RO11" "RO12"
+## [131] "RO21" "RO22" "RO31" "RO32" "RO41" "NL23" "NL31" "NL32" "NL33" "NL34"
+## [141] "NL41" "NL42" "PL11" "PL12" "PL21" "PL22" "PL31" "PL32" "PL33" "PL34"
+## [151] "PL41" "PL42" "RO42" "SE11" "SE12" "SE21" "SK01" "SK02" "SK03" "SK04"
+## [161] "UKC1" "SE22" "SE23" "SE31" "SE32" "SE33" "UKM2" "UKM3" "UKM5" "UKM6"
+## [171] "UKC2" "UKD4" "UKD6" "UKE1" "UKE2" "UKE3" "UKE4" "UKF1" "UKF2" "UKF3"
+## [181] "UKG1" "UKG2" "UKH1" "UKH2" "UKH3" "UKJ1" "UKJ2" "UKJ3" "UKJ4" "UKK1"
+## [191] "UKK2" "UKK3" "UKK4" "UKL1" "UKL2"data.level.cap$irrig_vol.n1.dat## [1] "CZ0" "DE8" "DE9" "DEA" "DE1" "DE2" "DE3" "DE4" "DE6" "DE7" "DEB"
+## [12] "DEG" "DEC" "DED" "DEE" "DEF" "ES6" "SI0" "UKD" "UKG"data.level.cap$irrig_vol.n0.dat## [1] "DE" "EL" "FR" "UK"data.level.cap$irrig_vol.nuts0.na## [1] "CH" "BE" "IE" "LI" "LU" "ME" "MK" "IS" "NO" "TR"#add GDP and PPS data for regional typologies
+names(dbase.cap)## [1] "NUTS_ID" "irrig_vol" "tot_eur_cap" "tot_pps_cap"
+## [5] "emp_rate_15_64" "tot_unemp" "yth_unemp"names(cap.gdp)## [1] "geo" "tot_mil_eur" "tot_eur_cap" "tot_mil_pps" "tot_pps_cap"
+## [6] "rur_mil_eur" "rur_eur_cap" "rur_mil_pps" "rur_pps_cap" "int_mil_eur"
+## [11] "int_eur_cap" "int_mil_pps" "int_pps_cap" "urb_mil_eur" "urb_eur_cap"
+## [16] "urb_mil_pps" "urb_pps_cap"cap.gdp$NUTS_ID <- cap.gdp$geo
+dbase.cap <- left_join(dbase.cap, cap.gdp[,c(7,9,11,13,15,17,18)])## Joining, by = "NUTS_ID"## Warning: Column `NUTS_ID` joining factors with different levels, coercing
+## to character vectorhead(dbase.cap)## NUTS_ID irrig_vol tot_eur_cap tot_pps_cap emp_rate_15_64 tot_unemp
+## 1 AT11 3660.6 26700 24600 69.81530 5.7
+## 2 AT22 909.0 34800 32100 71.37077 5.1
+## 3 AT12 10828.8 31800 29300 73.06232 5.2
+## 4 AT13 1266.4 47300 43700 64.90683 11.3
+## 5 AT21 110.4 32700 30200 69.88481 5.4
+## 6 AT31 319.9 39600 36500 75.46507 4.5
+## yth_unemp rur_eur_cap rur_pps_cap int_eur_cap int_pps_cap urb_eur_cap
+## 1 15.0 26690.97 24628.47 NA NA NA
+## 2 10.2 28015.67 25851.10 42289.66 39020.69 NA
+## 3 9.3 29392.91 27122.78 37037.74 34176.67 27574.60
+## 4 20.3 NA NA NA NA 47307.69
+## 5 12.2 27340.58 25228.26 38025.00 35085.71 NA
+## 6 7.6 33453.92 30867.51 48936.17 45154.26 NA
+## urb_pps_cap
+## 1 NA
+## 2 NA
+## 3 25441.27
+## 4 43651.88
+## 5 NA
+## 6 NAnames(dbase.cap)[c(3,8,10,12)] <- sub("eur", "gdp", names(dbase.cap)[c(3,8,10,12)])#In the chunks above, we allocate NUTS1 and NUTS0 data to NUTS2 regions. This works for variables that are ratios (e.g., percent, proportion, rates) but not for variables that are absolute. We need to edit these here. We also merge all the additional variables.
+
+names(dbase)## [1] "NUTS_ID" "risk_pov" "factor_in" "train35bas" "train35ful"
+## [6] "train_bas" "train_ful" "nitr_high" "nitr_mod" "nitr_poor"
+## [11] "irrigated" "forest" "artific" "soil_loss" "com_birds"
+## [16] "farm_birds" "org_farm" "energy_rt" "renew_pct" "renew_prod"
+## [21] "gross_N" "gross_P" "conv_till" "cons_till" "zero_till"
+## [26] "nfert" "arable" "grassland" "permanent" "soil_prod"
+## [31] "tot_awu" "gva" "tot_uaa"names(corine.aa.all.nuts)## [1] "geo" "sum_uaa"names(dbase.cap)## [1] "NUTS_ID" "irrig_vol" "tot_gdp_cap" "tot_pps_cap"
+## [5] "emp_rate_15_64" "tot_unemp" "yth_unemp" "rur_gdp_cap"
+## [9] "rur_pps_cap" "int_gdp_cap" "int_pps_cap" "urb_gdp_cap"
+## [13] "urb_pps_cap"#The variables that have absolute values in dbase are:
+#factor_in (million euros)
+#tot_awu
+#gva
+#tot_uaa (ha)
+
+names(dbase)## [1] "NUTS_ID" "risk_pov" "factor_in" "train35bas" "train35ful"
+## [6] "train_bas" "train_ful" "nitr_high" "nitr_mod" "nitr_poor"
+## [11] "irrigated" "forest" "artific" "soil_loss" "com_birds"
+## [16] "farm_birds" "org_farm" "energy_rt" "renew_pct" "renew_prod"
+## [21] "gross_N" "gross_P" "conv_till" "cons_till" "zero_till"
+## [26] "nfert" "arable" "grassland" "permanent" "soil_prod"
+## [31] "tot_awu" "gva" "tot_uaa"names(dbase)[c(3,31:33)]## [1] "factor_in" "tot_awu" "gva" "tot_uaa"dbase.clean <- dbase[,-c(3,31:33)]
+dbase.clean$geo <- dbase.clean$NUTS_ID
+names(dbase.clean)## [1] "NUTS_ID" "risk_pov" "train35bas" "train35ful" "train_bas"
+## [6] "train_ful" "nitr_high" "nitr_mod" "nitr_poor" "irrigated"
+## [11] "forest" "artific" "soil_loss" "com_birds" "farm_birds"
+## [16] "org_farm" "energy_rt" "renew_pct" "renew_prod" "gross_N"
+## [21] "gross_P" "conv_till" "cons_till" "zero_till" "nfert"
+## [26] "arable" "grassland" "permanent" "soil_prod" "geo"#First, convert from absolute to ratios for those variables possible, then translate to NUTS2 regions as a ratio
+
+###factor_in
+names(sdg.dat)## [1] "geo" "STAT_LEVL_" "SHAPE_AREA" "SHAPE_LEN" "risk_pov"
+## [6] "factor_in" "train35bas" "train35ful" "train_bas" "train_ful"
+## [11] "nitr_high" "nitr_mod" "nitr_poor" "irrigated" "forest"
+## [16] "artific" "soil_loss" "com_birds" "farm_birds" "org_farm"
+## [21] "energy_rt" "renew_pct" "renew_prod" "gross_N" "gross_P"names(con.dat)## [1] "geo" "STAT_LEVL_" "SHAPE_AREA" "SHAPE_LEN" "conv_till"
+## [6] "cons_till" "zero_till" "nfert" "arable" "grassland"
+## [11] "permanent" "soil_prod" "tot_awu" "gva" "tot_uaa"afi.awu <- left_join(sdg.dat[,c("geo", "factor_in")], con.dat[,c("geo", "tot_awu")])## Joining, by = "geo"afi.awu$afi_awu <- afi.awu$factor_in / afi.awu$tot_awu * 1e+06 #to convert to euros per awu
+head(afi.awu)## geo factor_in tot_awu afi_awu
+## 1 AT 2315.97000 138800.0 16685.663
+## 2 AT1 1070.85000 NA NA
+## 3 AT11 173.70857 7007.5 24788.951
+## 4 AT12 884.43857 38360.0 23056.271
+## 5 AT13 12.70143 1975.0 6431.103
+## 6 AT2 505.33857 NA NA#All Italy has zeros for factor income in the Eurostat table agr_r_accts but Italy has NUTS0 data from table aact_eaa01. We will correct here.
+afi.awu[which(afi.awu$afi_awu == 0), c('geo', 'afi_awu')]## geo afi_awu
+## 233 ITC2 0
+## 234 ITC3 0
+## 235 ITC4 0
+## 237 ITF1 0
+## 238 ITF2 0
+## 239 ITF3 0
+## 240 ITF4 0
+## 241 ITF5 0
+## 242 ITF6 0
+## 244 ITG1 0
+## 245 ITG2 0
+## 247 ITH1 0
+## 248 ITH2 0
+## 249 ITH3 0
+## 250 ITH4 0
+## 251 ITH5 0
+## 253 ITI1 0
+## 254 ITI2 0
+## 255 ITI3 0
+## 256 ITI4 0
+## 290 IT 0
+## 292 ITC1 0afi.nuts0[afi.nuts0$geo == "IT",]## geo factor_income_mean
+## 19 IT 22183.11afi.awu[afi.awu$geo == "IT",]## geo factor_in tot_awu afi_awu
+## 290 IT 0 1111788 0afi.awu[which(afi.awu$afi_awu == 0), 'afi_awu'] <- afi.nuts0[afi.nuts0$geo == "IT", 'factor_income_mean'] / afi.awu[afi.awu$geo == "IT", 'tot_awu'] * 1e+06
+
+afi.awu[afi.awu$geo == "IT",]## geo factor_in tot_awu afi_awu
+## 290 IT 0 1111788 19952.65###pesticides
+pesticides <- read.csv("C:/Users/mu5106sc/Dropbox/STAGS/SDG_data_eurostat/Final_database/SDGs/Goal12/Pesticide_sales/all_pesticide_sales_mean_allnuts.csv", head=T)
+head(pesticides)## geo pesticides_sum
+## 1 AT 3602507
+## 2 BE 6545569
+## 3 BG 1766558
+## 4 CH 2191825
+## 5 CY 819175
+## 6 CZ 6298810pest.rate <- left_join(con.dat[,c("geo", "tot_uaa")], pesticides)## Joining, by = "geo"## Warning: Column `geo` joining character vector and factor, coercing into
+## character vectorhead(pest.rate)## geo tot_uaa pesticides_sum
+## 1 AT 2698320 3602507
+## 2 AT1 NA NA
+## 3 AT11 181150 NA
+## 4 AT12 895805 NA
+## 5 AT13 7190 NA
+## 6 AT2 NA NApest.rate$pest_rate <- pest.rate$pesticides_sum / pest.rate$tot_uaa
+summary(pest.rate)## geo tot_uaa pesticides_sum
+## Length:471 Min. : 0 Min. : 144951
+## Class :character 1st Qu.: 179331 1st Qu.: 1914345
+## Mode :character Median : 403672 Median : 3624443
+## Mean : 1118138 Mean :13990649
+## 3rd Qu.: 809116 3rd Qu.:11259235
+## Max. :27776795 Max. :73505445
+## NA's :197 NA's :440
+## pest_rate
+## Min. : 0.3874
+## 1st Qu.: 0.9085
+## Median : 1.4665
+## Mean : 2.4684
+## 3rd Qu.: 2.7402
+## Max. :13.1415
+## NA's :442###irrig_tot
+irrig_tot <- read.csv("C:/Users/mu5106sc/Dropbox/STAGS/SDG_data_eurostat/SDGs/Goal6/Irrigation_volume/irrigation_volume_total_mean.csv", head=T)
+head(irrig_tot)## NUTS_ID irrigation_volume_median irrigation_volume_mean
+## 1 BG 714.535 674.93500
+## 2 CH 135.600 135.60000
+## 3 CY 163.900 160.01667
+## 4 AL NA NA
+## 5 CZ 20.650 21.51667
+## 6 BE NA NAnames(irrig_tot)[c(1,3)] <- c("geo", "irrig_tot")
+irrig.rate <- left_join(sdg.dat[,c('geo', 'irrigated')], irrig_tot[,c('geo', 'irrig_tot')])## Joining, by = "geo"## Warning: Column `geo` joining character vector and factor, coercing into
+## character vectorirrig.rate <- left_join(irrig.rate, cap.irrig)## Joining, by = "geo"## Warning: Column `geo` joining character vector and factor, coercing into
+## character vectorirrig.rate <- left_join(irrig.rate, corine.aa.all.nuts)## Joining, by = "geo"head(irrig.rate)## geo irrigated irrig_tot irrig_vol sum_uaa
+## 1 AT 1.350 18 18316.2 2677543.8
+## 2 AT1 NA NA 15755.7 1230331.2
+## 3 AT11 5.850 NA 3660.6 219300.0
+## 4 AT12 2.650 NA 10828.8 1004956.2
+## 5 AT13 10.525 NA 1266.4 6075.0
+## 6 AT2 NA NA 1019.4 602868.8irrig.rate[is.na(irrig.rate$irrig_vol),'irrig_vol'] <- irrig.rate[is.na(irrig.rate$irrig_vol), 'irrig_tot'] #use Eurostat data where CAP data is NA
+irrig.rate$irrig_rate <- irrig.rate$irrig_vol / irrig.rate$sum_uaa * 1e+03 #to convert to cubic metres per ha note this is total irrigation volume over all agricultural area, not just irrigated area, which is captured by the percentage of UAA irrigated
+
+###GVA per AWU
+gva.awu <- left_join(con.dat[,c("geo", "gva")], con.dat[,c("geo", "tot_awu")])## Joining, by = "geo"gva.awu$gva_awu <- gva.awu$gva / gva.awu$tot_awu * 1e+06 #to convert to euros per awu
+head(gva.awu)## geo gva tot_awu gva_awu
+## 1 AT 2769.36857 138800.0 19952.22
+## 2 AT1 1172.67143 NA NA
+## 3 AT11 177.76429 7007.5 25367.72
+## 4 AT12 975.25143 38360.0 25423.66
+## 5 AT13 19.65571 1975.0 9952.26
+## 6 AT2 641.63571 NA NA###AWU relative to population aged 15-64
+pop_15_64 <- read.csv("C:/Users/mu5106sc/Dropbox/STAGS/SDG_data_eurostat/Final_database/SDGs/Goal8/Employment_rate/c5_en_population_15_64.csv", head=T)
+awu.pop <- left_join(con.dat[,c("geo", "tot_awu")], pop_15_64)## Joining, by = "geo"## Warning: Column `geo` joining character vector and factor, coercing into
+## character vectorawu.pop$labour_use <- awu.pop$tot_awu / (1000 * awu.pop$pop_15_64) #Pop in 1000s of persons, AWU in persons
+head(awu.pop)## geo tot_awu pop_15_64 labour_use
+## 1 AT 138800.0 5790.3 0.023971124
+## 2 AT1 NA 2525.2 NA
+## 3 AT11 7007.5 189.5 0.036978892
+## 4 AT12 38360.0 1079.9 0.035521808
+## 5 AT13 1975.0 1255.8 0.001572703
+## 6 AT2 NA 1180.2 NA#add these variables to clean database using function from above
+add.edit.dat <- left_join(sdg.dat[,1:2], afi.awu[,c(1,4)])## Joining, by = "geo"add.edit.dat <- left_join(add.edit.dat, gva.awu[,c(1,4)])## Joining, by = "geo"add.edit.dat <- left_join(add.edit.dat, awu.pop[,c(1,4)])## Joining, by = "geo"add.edit.dat <- left_join(add.edit.dat, pest.rate[,c(1,4)])## Joining, by = "geo"add.edit.dat <- left_join(add.edit.dat, irrig.rate[,c(1,6)])## Joining, by = "geo"head(add.edit.dat)## geo STAT_LEVL_ afi_awu gva_awu labour_use pest_rate irrig_rate
+## 1 AT 0 16685.663 19952.22 0.023971124 1.335093 6.840673
+## 2 AT1 1 NA NA NA NA 12.806063
+## 3 AT11 2 24788.951 25367.72 0.036978892 NA 16.692202
+## 4 AT12 2 23056.271 25423.66 0.035521808 NA 10.775394
+## 5 AT13 2 6431.103 9952.26 0.001572703 NA 208.460905
+## 6 AT2 1 NA NA NA NA 1.690915dbase.clean$irrig_rate <- NA
+dbase.clean$afi_awu <- NA
+dbase.clean$gva_awu <- NA
+dbase.clean$labour_use <- NA
+dbase.clean$pest_rate <- NA
+
+edit.var.names <- c("irrig_rate",
+ "afi_awu",
+ "gva_awu",
+ "labour_use",
+ "pest_rate")
+
+#Repeat function above to allocate NUTS1 and NUTS0 to NUTS2 units. Again, this is appropriate for ratio variables but not absolute variables. This will be cleaned and corrected below.
+data.level.edit <- vector("list", 4*length(names(dbase.clean)[31:35]))
+names(data.level.edit) <- c(paste(names(dbase.clean)[31:35], 'n2.dat', sep='.'),
+ paste(names(dbase.clean)[31:35], 'n1.dat', sep='.'),
+ paste(names(dbase.clean)[31:35], 'n0.dat', sep='.'),
+ paste(names(dbase.clean)[31:35], 'nuts0.na', sep='.')
+ )
+labels(data.level.edit)## [1] "irrig_rate.n2.dat" "afi_awu.n2.dat" "gva_awu.n2.dat"
+## [4] "labour_use.n2.dat" "pest_rate.n2.dat" "irrig_rate.n1.dat"
+## [7] "afi_awu.n1.dat" "gva_awu.n1.dat" "labour_use.n1.dat"
+## [10] "pest_rate.n1.dat" "irrig_rate.n0.dat" "afi_awu.n0.dat"
+## [13] "gva_awu.n0.dat" "labour_use.n0.dat" "pest_rate.n0.dat"
+## [16] "irrig_rate.nuts0.na" "afi_awu.nuts0.na" "gva_awu.nuts0.na"
+## [19] "labour_use.nuts0.na" "pest_rate.nuts0.na"attach(add.edit.dat)
+for(i in names(add.edit.dat[,-c(1:2)])) {
+ (nuts2.na <- add.edit.dat[STAT_LEVL_ == 2 & is.na(add.edit.dat[,i]), 'geo'])
+ (nuts1 <- add.edit.dat[STAT_LEVL_ == 1 & geo %in% gsub(".{1}$", "", nuts2.na), 'geo'])
+ (nuts1.na <- add.edit.dat[geo %in% nuts1 & is.na(add.edit.dat[,i]), 'geo'])
+ (nuts0 <- add.edit.dat[STAT_LEVL_ == 0 & geo %in% gsub(".{1}$", "", nuts1.na), 'geo'])
+ (nuts0.na <- add.edit.dat[geo %in% nuts0 & is.na(add.edit.dat[,i]), 'geo'])
+
+#NUTS2 data
+(n2.dat <- add.edit.dat[!(geo %in% nuts2.na) & STAT_LEVL_ == 2, 'geo'])
+#NUTS1 data
+(n1.dat <- nuts1[!nuts1 %in% nuts1.na])
+#NUTS0 data
+(n0.dat <- nuts0[!nuts0 %in% nuts0.na])
+#NO DATA
+nuts0.na
+
+data.level.edit[[paste(i, 'n2.dat', sep='.')]] <- n2.dat
+data.level.edit[[paste(i, 'n1.dat', sep='.')]] <- n1.dat
+data.level.edit[[paste(i, 'n0.dat', sep='.')]] <- n0.dat
+data.level.edit[[paste(i, 'nuts0.na', sep='.')]] <- nuts0.na
+
+ for(e in n0.dat) {
+ dbase.clean[dbase.clean$NUTS_ID %in% dbase.clean$NUTS_ID[grep(paste(e, '..', sep=''), dbase.clean$NUTS_ID)], i] <- add.edit.dat[add.edit.dat$geo == e, i]
+ }
+
+ for(e in n1.dat) {
+ dbase.clean[dbase.clean$NUTS_ID %in% dbase.clean$NUTS_ID[grep(paste(e, '.', sep=''), dbase.clean$NUTS_ID)], i] <- add.edit.dat[add.edit.dat$geo == e, i]
+ }
+
+ for(e in n2.dat) {
+ dbase.clean[dbase.clean$NUTS_ID == e, i] <- add.edit.dat[add.edit.dat$geo == e, i]
+ }
+}
+detach(add.edit.dat)
+
+summary(dbase.clean)## NUTS_ID risk_pov train35bas train35ful
+## AT11 : 1 Min. : 9.971 Min. :0.00000 Min. :0.0000
+## AT12 : 1 1st Qu.:18.586 1st Qu.:0.09613 1st Qu.:0.1264
+## AT13 : 1 Median :23.514 Median :0.22800 Median :0.2600
+## AT21 : 1 Mean :25.960 Mean :0.26424 Mean :0.2738
+## AT22 : 1 3rd Qu.:29.680 3rd Qu.:0.35996 3rd Qu.:0.3825
+## AT31 : 1 Max. :54.150 Max. :0.88217 Max. :0.8550
+## (Other):314 NA's :2 NA's :52 NA's :52
+## train_bas train_ful nitr_high nitr_mod
+## Min. :0.01171 Min. :0.00188 Min. : 4.082 Min. : 0.000
+## 1st Qu.:0.10627 1st Qu.:0.04939 1st Qu.: 66.302 1st Qu.: 6.533
+## Median :0.19961 Median :0.12807 Median : 70.505 Median :15.896
+## Mean :0.26250 Mean :0.15796 Mean : 75.328 Mean :13.773
+## 3rd Qu.:0.36488 3rd Qu.:0.25108 3rd Qu.: 87.591 3rd Qu.:18.416
+## Max. :0.94840 Max. :0.50303 Max. :100.000 Max. :60.000
+## NA's :50 NA's :50 NA's :44 NA's :44
+## nitr_poor irrigated forest artific
+## Min. : 0.000 Min. : 0.0000 Min. :0.00000 Min. :0.00000
+## 1st Qu.: 4.106 1st Qu.: 0.3312 1st Qu.:0.08957 1st Qu.:0.02056
+## Median : 8.883 Median : 1.2250 Median :0.24904 Median :0.04020
+## Mean :10.898 Mean : 5.7571 Mean :0.25141 Mean :0.09023
+## 3rd Qu.:15.385 3rd Qu.: 6.5000 3rd Qu.:0.37365 3rd Qu.:0.08193
+## Max. :68.367 Max. :74.5500 Max. :0.75860 Max. :1.00000
+## NA's :44 NA's :28
+## soil_loss com_birds farm_birds org_farm
+## Min. : 0.0300 Min. :54.92 Min. : 63.78 Min. : 0.000
+## 1st Qu.: 0.7047 1st Qu.:62.14 1st Qu.: 81.34 1st Qu.: 1.200
+## Median : 1.5005 Median :69.50 Median : 83.82 Median : 2.687
+## Mean : 2.5482 Mean :69.70 Mean : 81.90 Mean : 4.056
+## 3rd Qu.: 2.9420 3rd Qu.:81.30 3rd Qu.: 85.30 3rd Qu.: 5.204
+## Max. :17.6050 Max. :97.22 Max. :116.60 Max. :27.487
+## NA's :44 NA's :158 NA's :94 NA's :28
+## energy_rt renew_pct renew_prod gross_N
+## Min. :0.00000 Min. : 0.000 Min. : 0.8855 Min. : 2.857
+## 1st Qu.:0.03503 1st Qu.: 3.074 1st Qu.: 6.2422 1st Qu.: 41.821
+## Median :0.06128 Median : 6.124 Median : 8.3156 Median : 67.333
+## Mean :0.15052 Mean :11.225 Mean :12.4318 Mean : 67.553
+## 3rd Qu.:0.09725 3rd Qu.:22.515 3rd Qu.:18.0797 3rd Qu.: 85.988
+## Max. :1.75149 Max. :41.011 Max. :37.7797 Max. :190.167
+## NA's :44 NA's :82 NA's :45 NA's :30
+## gross_P conv_till cons_till zero_till
+## Min. :-6.500 Min. :0.08646 Min. :0.00000 Min. :0.00000
+## 1st Qu.:-1.667 1st Qu.:0.46182 1st Qu.:0.05077 1st Qu.:0.00920
+## Median : 1.833 Median :0.61740 Median :0.12499 Median :0.01843
+## Mean : 1.941 Mean :0.60410 Mean :0.18031 Mean :0.03000
+## 3rd Qu.: 4.714 3rd Qu.:0.73832 3rd Qu.:0.28382 3rd Qu.:0.04003
+## Max. :31.000 Max. :0.99752 Max. :0.65066 Max. :0.19303
+## NA's :30 NA's :53 NA's :53 NA's :53
+## nfert arable grassland permanent
+## Min. : 0.000 Min. : 0.00 Min. : 0.00 Min. : 0.0000
+## 1st Qu.: 6.448 1st Qu.:39.68 1st Qu.:17.20 1st Qu.: 0.3546
+## Median : 9.917 Median :62.28 Median :32.97 Median : 1.1324
+## Mean :10.975 Mean :57.72 Mean :35.74 Mean : 5.7197
+## 3rd Qu.:14.254 3rd Qu.:78.19 3rd Qu.:48.62 3rd Qu.: 5.6520
+## Max. :29.456 Max. :99.28 Max. :98.84 Max. :64.6743
+## NA's :11 NA's :44 NA's :44 NA's :44
+## soil_prod geo irrig_rate afi_awu
+## Min. :3.00 AT11 : 1 Min. : 0.000 Min. : -3221
+## 1st Qu.:6.00 AT12 : 1 1st Qu.: 1.181 1st Qu.: 11878
+## Median :6.00 AT13 : 1 Median : 7.396 Median : 20559
+## Mean :6.45 AT21 : 1 Mean : 157.441 Mean : 24680
+## 3rd Qu.:7.00 AT22 : 1 3rd Qu.: 82.321 3rd Qu.: 34388
+## Max. :8.00 AT31 : 1 Max. :4156.725 Max. :107266
+## NA's :51 (Other):314 NA's :22 NA's :29
+## gva_awu labour_use pest_rate
+## Min. : 697.4 Min. :0.00000 Min. : 0.3874
+## 1st Qu.: 10428.3 1st Qu.:0.01049 1st Qu.: 1.2195
+## Median : 24639.3 Median :0.01976 Median : 1.8836
+## Mean : 26611.6 Mean :0.03594 Mean : 2.4120
+## 3rd Qu.: 38162.3 3rd Qu.:0.04539 3rd Qu.: 3.1595
+## Max. :122952.6 Max. :0.22557 Max. :13.1415
+## NA's :29 NA's :44 NA's :37head(dbase.clean)## NUTS_ID risk_pov train35bas train35ful train_bas train_ful nitr_high
+## 1 AT11 13.73333 0.1375661 0.3333333 0.1243050 0.1779190 64.58924
+## 2 AT22 17.26667 0.2160980 0.3648294 0.2017089 0.2413594 64.58924
+## 3 AT12 13.83333 0.2084775 0.4809689 0.2534787 0.3449437 64.58924
+## 4 AT13 27.23333 0.3750000 0.7500000 0.1753247 0.4740260 64.58924
+## 5 AT21 17.20000 0.2306238 0.3648393 0.2076173 0.2250348 64.58924
+## 6 AT31 15.00000 0.2508418 0.4284512 0.2014381 0.2857610 64.58924
+## nitr_mod nitr_poor irrigated forest artific soil_loss com_birds
+## 1 20.20774 15.20302 5.850 0.3161203 0.04355635 1.842 NA
+## 2 20.20774 15.20302 0.325 0.6127954 0.03306278 5.804 NA
+## 3 20.20774 15.20302 2.650 0.4286079 0.04875064 2.236 NA
+## 4 20.20774 15.20302 10.525 0.1469534 0.73118280 1.014 NA
+## 5 20.20774 15.20302 0.100 0.5998934 0.03047416 11.671 NA
+## 6 20.20774 15.20302 0.125 0.4027358 0.04900973 3.791 NA
+## farm_birds org_farm energy_rt renew_pct renew_prod gross_N gross_P
+## 1 65.98 19.43430 0.08319988 32.65559 7.068917 32.57143 1.833333
+## 2 65.98 12.80858 0.08319988 32.65559 7.068917 32.57143 1.833333
+## 3 65.98 13.41584 0.08319988 32.65559 7.068917 32.57143 1.833333
+## 4 65.98 16.44137 0.08319988 32.65559 7.068917 32.57143 1.833333
+## 5 65.98 10.68078 0.08319988 32.65559 7.068917 32.57143 1.833333
+## 6 65.98 12.31071 0.08319988 32.65559 7.068917 32.57143 1.833333
+## conv_till cons_till zero_till nfert arable grassland permanent
+## 1 0.6182190 0.31992068 0.025012794 7.684000 83.64566 8.715722 7.5451998
+## 2 0.8887161 0.05005656 0.024109163 7.551429 37.02489 58.694493 4.2139773
+## 3 0.6226791 0.32803537 0.019896256 7.452800 76.22380 20.140837 3.5858503
+## 4 0.5109890 0.40476190 0.007326007 7.497000 79.80050 10.099751 10.0997506
+## 5 0.8592546 0.05928605 0.032552288 8.131500 28.48779 71.285286 0.1679223
+## 6 0.8442576 0.12043311 0.014198645 9.138333 56.49367 43.164202 0.2648111
+## soil_prod geo irrig_rate afi_awu gva_awu labour_use pest_rate
+## 1 6 AT11 16.6922025 24788.951 25367.72 0.036978892 1.335093
+## 2 6 AT22 2.2086896 13958.345 18388.41 0.034606425 1.335093
+## 3 6 AT12 10.7753945 23056.271 25423.66 0.035521808 1.335093
+## 4 6 AT13 208.4609053 6431.103 9952.26 0.001572703 1.335093
+## 5 6 AT21 0.5770663 10741.948 11827.48 0.028435272 1.335093
+## 6 6 AT31 0.5491021 15263.545 22028.20 0.030650579 1.335093tail(dbase.clean)## NUTS_ID risk_pov train35bas train35ful train_bas train_ful nitr_high
+## 315 UKD3 23.51429 0.00000000 0.2000000 0.07100592 0.05621302 97.15694
+## 316 TRC1 54.15000 NA NA NA NA NA
+## 317 TRC2 54.15000 NA NA NA NA NA
+## 318 UKD4 23.51429 0.15625000 0.3125000 0.07031828 0.07846040 97.15694
+## 319 TRC3 54.15000 NA NA NA NA NA
+## 320 UKM6 23.51429 0.05925926 0.1555556 0.03854333 0.06990962 97.15694
+## nitr_mod nitr_poor irrigated forest artific soil_loss
+## 315 2.388173 0.4548901 0.500 0.010517799 0.550161812 2.071
+## 316 NA NA NA 0.022020475 0.013843281 NA
+## 317 NA NA NA 0.006621164 0.007146191 NA
+## 318 2.388173 0.4548901 0.625 0.014225182 0.109261501 1.905
+## 319 NA NA NA 0.037659533 0.005497742 NA
+## 320 2.388173 0.4548901 0.000 0.126063524 0.003747982 6.174
+## com_birds farm_birds org_farm energy_rt renew_pct renew_prod
+## 315 69.5 83.82 0.0000000 0.04487651 23.7199 7.183683
+## 316 NA NA NA NA NA NA
+## 317 NA NA NA NA NA NA
+## 318 69.5 83.82 0.8233184 0.04487651 23.7199 7.183683
+## 319 NA NA NA NA NA NA
+## 320 69.5 83.82 0.9873238 0.04487651 23.7199 7.183683
+## gross_N gross_P conv_till cons_till zero_till nfert arable
+## 315 86.42857 5.857143 0.5116279 0.26976744 0.083720930 17.954800 21.626717
+## 316 NA NA NA NA NA 5.709333 NA
+## 317 NA NA NA NA NA 5.508154 NA
+## 318 86.42857 5.857143 0.5070682 0.07652120 0.000921942 17.686000 20.185625
+## 319 NA NA NA NA NA 5.452800 NA
+## 320 86.42857 5.857143 0.3571254 0.01623576 0.064146551 13.097444 6.222771
+## grassland permanent soil_prod geo irrig_rate afi_awu gva_awu
+## 315 78.21169 0.134661998 6 UKD3 0.7351276 107265.558 122952.557
+## 316 NA NA NA TRC1 1.1807506 NA NA
+## 317 NA NA NA TRC2 1.1807506 NA NA
+## 318 79.77323 0.041148500 6 UKD4 1.4023562 11063.440 13125.354
+## 319 NA NA NA TRC3 1.1807506 NA NA
+## 320 93.77578 0.001447408 6 UKM6 0.7098479 9823.595 4882.977
+## labour_use pest_rate
+## 315 0.0007488926 1.219472
+## 316 NA NA
+## 317 NA NA
+## 318 0.0083215413 1.219472
+## 319 NA NA
+## 320 0.0299345848 1.219472names(dbase.clean)## [1] "NUTS_ID" "risk_pov" "train35bas" "train35ful" "train_bas"
+## [6] "train_ful" "nitr_high" "nitr_mod" "nitr_poor" "irrigated"
+## [11] "forest" "artific" "soil_loss" "com_birds" "farm_birds"
+## [16] "org_farm" "energy_rt" "renew_pct" "renew_prod" "gross_N"
+## [21] "gross_P" "conv_till" "cons_till" "zero_till" "nfert"
+## [26] "arable" "grassland" "permanent" "soil_prod" "geo"
+## [31] "irrig_rate" "afi_awu" "gva_awu" "labour_use" "pest_rate"#check data level for irrig_vol as an example
+data.level.edit$irrig_rate.n2.dat## [1] "AT11" "AT12" "AT13" "AT21" "AT22" "AT31" "AT32" "BG31" "BG32" "BG33"
+## [11] "BG34" "BG41" "BG42" "CY00" "CZ02" "CZ03" "CZ04" "CZ05" "CZ06" "CZ07"
+## [21] "CZ08" "AT33" "AT34" "DK01" "DK02" "DK03" "DK04" "DK05" "EE00" "EL30"
+## [31] "EL41" "EL42" "EL43" "ES11" "ES12" "ES13" "ES21" "ES22" "ES23" "ES24"
+## [41] "ES30" "FR52" "FR53" "FR61" "FR62" "FR63" "FR71" "FR72" "FR81" "FR82"
+## [51] "FR83" "HR03" "HR04" "ES41" "ES42" "ES43" "ES51" "ES52" "ES53" "ES61"
+## [61] "ES62" "ES70" "FI19" "FI1B" "FI1C" "FI1D" "FI20" "FR10" "FR21" "FR22"
+## [71] "FR23" "FR24" "FR25" "FR26" "FR30" "FR41" "FR42" "FR43" "FR51" "HU10"
+## [81] "HU21" "HU22" "HU23" "HU31" "HU32" "HU33" "ITC2" "ITC3" "ITC4" "ITF1"
+## [91] "ITF2" "ITF3" "ITF4" "ITF5" "ITF6" "ITG1" "ITG2" "ITH1" "ITH2" "ITH3"
+## [101] "ITH4" "ITH5" "ITI1" "ITI2" "ITI3" "ITI4" "LT00" "LV00" "MT00" "NL11"
+## [111] "NL12" "NL13" "NL21" "NL22" "ITC1" "PL43" "PL51" "PL52" "PL61" "PL62"
+## [121] "PL63" "PT11" "PT15" "PT16" "PT17" "PT18" "PT20" "PT30" "RO11" "RO12"
+## [131] "RO21" "RO22" "RO31" "RO32" "RO41" "NL23" "NL31" "NL32" "NL33" "NL34"
+## [141] "NL41" "NL42" "PL11" "PL12" "PL21" "PL22" "PL31" "PL32" "PL33" "PL34"
+## [151] "PL41" "PL42" "RO42" "SE11" "SE12" "SE21" "SK01" "SK02" "SK03" "SK04"
+## [161] "UKC1" "SE22" "SE23" "SE31" "SE32" "SE33" "UKM2" "UKM3" "UKM5" "UKM6"
+## [171] "UKC2" "UKD4" "UKD6" "UKE1" "UKE2" "UKE3" "UKE4" "UKF1" "UKF2" "UKF3"
+## [181] "UKG1" "UKG2" "UKH1" "UKH2" "UKH3" "UKJ1" "UKJ2" "UKJ3" "UKJ4" "UKK1"
+## [191] "UKK2" "UKK3" "UKK4" "UKL1" "UKL2"data.level.edit$irrig_rate.n1.dat## [1] "CZ0" "DE8" "DE9" "DEA" "DE1" "DE2" "DE3" "DE4" "DE6" "DE7" "DEB"
+## [12] "DEG" "DEC" "DED" "DEE" "DEF" "ES6" "SI0" "UKD" "UKG"data.level.edit$irrig_rate.n0.dat## [1] "CH" "DE" "EL" "FR" "LU" "MK" "IS" "TR" "UK"data.level.edit$irrig_rate.nuts0.na## [1] "BE" "IE" "LI" "ME" "NO"#Add CAP data to clean database
+dbase.cap$geo <- dbase.cap$NUTS_ID
+names(dbase.cap)## [1] "NUTS_ID" "irrig_vol" "tot_gdp_cap" "tot_pps_cap"
+## [5] "emp_rate_15_64" "tot_unemp" "yth_unemp" "rur_gdp_cap"
+## [9] "rur_pps_cap" "int_gdp_cap" "int_pps_cap" "urb_gdp_cap"
+## [13] "urb_pps_cap" "geo"dbase.clean <- left_join(dbase.clean, dbase.cap[,c(3:14)])## Joining, by = "geo"## Warning: Column `geo` joining factor and character vector, coercing into
+## character vector###Emissions data
+emi_co2eq <- st_read(dsn='C:/Users/mu5106sc/Dropbox/STAGS/D1_Database/EU_Farming_Systems_20181015.gdb', layer='mean_rate_co2_eqv')## Reading layer `mean_rate_co2_eqv' from data source `C:\Users\mu5106sc\Dropbox\STAGS\D1_Database\EU_Farming_Systems_20181015.gdb' using driver `OpenFileGDB'## Warning: no simple feature geometries present: returning a data.frame or
+## tbl_dfemi_co2eq$geo <- emi_co2eq$NUTS_ID
+head(emi_co2eq)## NUTS_ID ZONE_CODE COUNT AREA MEAN geo
+## 1 AT11 1 77114 4819625000 653096.3 AT11
+## 2 AT22 2 142371 8898187500 954802.7 AT22
+## 3 AT12 3 363790 22736875000 1136117.0 AT12
+## 4 AT13 4 2207 137937500 457098.6 AT13
+## 5 AT21 5 65190 4074375000 888623.1 AT21
+## 6 AT31 6 209774 13110875000 1943324.3 AT31emi_nh3 <- st_read(dsn='C:/Users/mu5106sc/Dropbox/STAGS/D1_Database/EU_Farming_Systems_20181015.gdb', layer='mean_rate_nh3')## Reading layer `mean_rate_nh3' from data source `C:\Users\mu5106sc\Dropbox\STAGS\D1_Database\EU_Farming_Systems_20181015.gdb' using driver `OpenFileGDB'## Warning: no simple feature geometries present: returning a data.frame or
+## tbl_dfemi_nh3$geo <- emi_nh3$NUTS_ID
+head(emi_nh3)## NUTS_ID ZONE_CODE COUNT AREA MEAN geo
+## 1 AT11 1 77114 4819625000 8690.371 AT11
+## 2 AT22 2 142371 8898187500 13155.494 AT22
+## 3 AT12 3 363790 22736875000 14253.957 AT12
+## 4 AT13 4 2207 137937500 6375.132 AT13
+## 5 AT21 5 65190 4074375000 11187.491 AT21
+## 6 AT31 6 209774 13110875000 22472.061 AT31emi_pm10 <- st_read(dsn='C:/Users/mu5106sc/Dropbox/STAGS/D1_Database/EU_Farming_Systems_20181015.gdb', layer='mean_rate_pm10')## Reading layer `mean_rate_pm10' from data source `C:\Users\mu5106sc\Dropbox\STAGS\D1_Database\EU_Farming_Systems_20181015.gdb' using driver `OpenFileGDB'## Warning: no simple feature geometries present: returning a data.frame or
+## tbl_dfemi_pm10$geo <- emi_pm10$NUTS_ID
+head(emi_pm10)## NUTS_ID ZONE_CODE COUNT AREA MEAN geo
+## 1 AT11 1 77114 4819625000 1025.7531 AT11
+## 2 AT22 2 142371 8898187500 850.9032 AT22
+## 3 AT12 3 363790 22736875000 1285.1966 AT12
+## 4 AT13 4 2207 137937500 609.2881 AT13
+## 5 AT21 5 65190 4074375000 471.5642 AT21
+## 6 AT31 6 209774 13110875000 1298.3660 AT31emi_pm25 <- st_read(dsn='C:/Users/mu5106sc/Dropbox/STAGS/D1_Database/EU_Farming_Systems_20181015.gdb', layer='mean_rate_pm25')## Reading layer `mean_rate_pm25' from data source `C:\Users\mu5106sc\Dropbox\STAGS\D1_Database\EU_Farming_Systems_20181015.gdb' using driver `OpenFileGDB'## Warning: no simple feature geometries present: returning a data.frame or
+## tbl_dfemi_pm25$geo <- emi_pm25$NUTS_ID
+head(emi_pm25)## NUTS_ID ZONE_CODE COUNT AREA MEAN geo
+## 1 AT11 1 77114 4819625000 818.8200 AT11
+## 2 AT22 2 142371 8898187500 331.4128 AT22
+## 3 AT12 3 363790 22736875000 856.1814 AT12
+## 4 AT13 4 2207 137937500 426.0527 AT13
+## 5 AT21 5 65190 4074375000 220.7500 AT21
+## 6 AT31 6 209774 13110875000 629.6217 AT31###Soils data
+soc <- st_read(dsn='C:/Users/mu5106sc/Dropbox/STAGS/D1_Database/EU_Farming_Systems_20181015.gdb', layer='nuts2_SOC_2010_stats')## Reading layer `nuts2_SOC_2010_stats' from data source `C:\Users\mu5106sc\Dropbox\STAGS\D1_Database\EU_Farming_Systems_20181015.gdb' using driver `OpenFileGDB'## Warning: no simple feature geometries present: returning a data.frame or
+## tbl_dfsoc$geo <- soc$NUTS_ID
+head(soc)## NUTS_ID ZONE_CODE COUNT AREA MIN MAX RANGE
+## 1 AT11 1 35064 2191500000 30.83195 155.75535 124.92340
+## 2 AT22 2 65757 4109812500 34.05482 498.82918 464.77436
+## 3 AT12 3 160776 10048500000 18.63442 372.08350 353.44907
+## 4 AT13 4 955 59687500 40.83359 67.69893 26.86534
+## 5 AT21 5 30546 1909125000 41.81581 323.11070 281.29489
+## 6 AT31 6 93225 5826562500 24.44537 492.61410 468.16873
+## MEAN STD SUM geo
+## 1 59.33579 20.520380 2080550.19 AT11
+## 2 97.49513 43.484832 6410987.08 AT22
+## 3 64.25874 20.290802 10331263.60 AT12
+## 4 49.22190 6.893331 47006.92 AT13
+## 5 101.03633 46.169421 3086255.75 AT21
+## 6 100.91691 56.705409 9407978.51 AT31biol_threats <- st_read(dsn='C:/Users/mu5106sc/Dropbox/STAGS/D1_Database/EU_Farming_Systems_20181015.gdb', layer='nuts2_soil_bio_func_threat_stats')## Reading layer `nuts2_soil_bio_func_threat_stats' from data source `C:\Users\mu5106sc\Dropbox\STAGS\D1_Database\EU_Farming_Systems_20181015.gdb' using driver `OpenFileGDB'## Warning: no simple feature geometries present: returning a data.frame or
+## tbl_dfbiol_threats$geo <- biol_threats$NUTS_ID
+head(biol_threats)## NUTS_ID ZONE_CODE COUNT AREA MIN MAX RANGE
+## 1 AT11 1 35064 2191500000 0.1639321 0.5476973 0.3837653
+## 2 AT22 2 65762 4110125000 0.1518843 0.5750966 0.4232123
+## 3 AT12 3 160779 10048687500 0.1160565 0.8375627 0.7215062
+## 4 AT13 4 955 59687500 0.1727176 0.4496170 0.2768994
+## 5 AT21 5 30605 1912812500 0.1625200 0.4503910 0.2878710
+## 6 AT31 6 93228 5826750000 0.1375850 0.7379893 0.6004044
+## MEAN STD SUM geo
+## 1 0.2693722 0.04402911 9445.267 AT11
+## 2 0.2525372 0.05795605 16607.349 AT22
+## 3 0.2670201 0.06859833 42931.226 AT12
+## 4 0.2611445 0.05979863 249.393 AT13
+## 5 0.2280257 0.04369173 6978.728 AT21
+## 6 0.2672487 0.06388194 24915.058 AT31soil_cov <- read.csv("C:/Users/mu5106sc/Dropbox/STAGS/SDG_data_eurostat/Final_database/Additional_consensus_variables/nuts2_Cfactor_20180822.csv", head=T)
+soil_cov$geo <- soil_cov$NUTS_ID
+head(soil_cov)## X NUTS_ID C_factor C_factor_N Only_Tilla CoverCrop Only_Resid ImAll
+## 1 1 AT11 0.204701 0.279940 0.219316 0.262085 0.279140 0.268766
+## 2 2 AT22 0.305978 0.342173 0.325065 0.323805 0.340448 0.105781
+## 3 3 AT12 0.195147 0.269209 0.210350 0.250382 0.268578 0.275109
+## 4 4 AT13 0.188655 0.265801 0.200734 0.250364 0.265244 0.290240
+## 5 5 AT21 0.278675 0.331689 0.310575 0.299779 0.329530 0.159833
+## 6 6 AT31 0.241675 0.288756 0.263650 0.265361 0.288084 0.163046
+## imTillage imCover ImResid geo
+## 1 0.216560 0.063781 0.002857 AT11
+## 2 0.049996 0.053679 0.005042 AT22
+## 3 0.218636 0.069932 0.002344 AT12
+## 4 0.244795 0.058079 0.002096 AT13
+## 5 0.063657 0.096205 0.006510 AT21
+## 6 0.086944 0.081020 0.002329 AT31###Habitat conservation data
+nat2000_ag <- st_read(dsn='C:/Users/mu5106sc/Dropbox/STAGS/D1_Database/EU_Farming_Systems_20181015.gdb', layer='nuts2_ag_Natura2000')## Reading layer `nuts2_ag_Natura2000' from data source `C:\Users\mu5106sc\Dropbox\STAGS\D1_Database\EU_Farming_Systems_20181015.gdb' using driver `OpenFileGDB'## Warning: no simple feature geometries present: returning a data.frame or
+## tbl_dfnat2000_tot <- st_read(dsn='C:/Users/mu5106sc/Dropbox/STAGS/D1_Database/EU_Farming_Systems_20181015.gdb', layer='nuts2_Natura2000_area')## Reading layer `nuts2_Natura2000_area' from data source `C:\Users\mu5106sc\Dropbox\STAGS\D1_Database\EU_Farming_Systems_20181015.gdb' using driver `OpenFileGDB'## Warning: no simple feature geometries present: returning a data.frame or
+## tbl_dfnat2000_tot$ha <- nat2000_tot$SUM * 6.25 #Sum of number of 250m x 250m (6.25 ha) cells
+nat2000 <- merge(nat2000_ag[,c(1,5)], nat2000_tot[,c(1,6)])
+nat2000$geo <- nat2000$NUTS_ID
+nat2000 <- left_join(nat2000, nuts@data[,c(4,7)])## Joining, by = "NUTS_ID"## Warning: Column `NUTS_ID` joining factors with different levels, coercing
+## to character vectornat2000 <- left_join(nat2000, corine.aa.all.nuts)## Joining, by = "geo"## Warning: Column `geo` joining factor and character vector, coercing into
+## character vectorhead(nat2000) #SUM, ha, and sum_uaa in hectares, Shape_Area in m2## NUTS_ID SUM ha geo Shape_Area sum_uaa
+## 1 AT11 44450.00 110012.50 AT11 3963509482 219300.0
+## 2 AT12 139906.25 425081.25 AT12 19201725666 1004956.2
+## 3 AT13 1106.25 5506.25 AT13 411979159 6075.0
+## 4 AT21 1562.50 58462.50 AT21 9541848203 191312.5
+## 5 AT22 34600.00 250300.00 AT22 16414303341 411556.2
+## 6 AT31 5356.25 78300.00 AT31 11984617500 582587.5nat2000$nat2000_ag <- nat2000$SUM / nat2000$sum_uaa
+nat2000$nat2000_pr <- nat2000$ha / (nat2000$Shape_Area / 10000)
+head(nat2000)## NUTS_ID SUM ha geo Shape_Area sum_uaa nat2000_ag
+## 1 AT11 44450.00 110012.50 AT11 3963509482 219300.0 0.202690378
+## 2 AT12 139906.25 425081.25 AT12 19201725666 1004956.2 0.139216259
+## 3 AT13 1106.25 5506.25 AT13 411979159 6075.0 0.182098765
+## 4 AT21 1562.50 58462.50 AT21 9541848203 191312.5 0.008167266
+## 5 AT22 34600.00 250300.00 AT22 16414303341 411556.2 0.084071132
+## 6 AT31 5356.25 78300.00 AT31 11984617500 582587.5 0.009193898
+## nat2000_pr
+## 1 0.27756336
+## 2 0.22137659
+## 3 0.13365361
+## 4 0.06126958
+## 5 0.15248896
+## 6 0.06533375###Calories data
+calorie_fr <- st_read(dsn='C:/Users/mu5106sc/Dropbox/STAGS/D1_Database/EU_Farming_Systems_20181015.gdb', layer='nuts2_mean_kcalFr')## Reading layer `nuts2_mean_kcalFr' from data source `C:\Users\mu5106sc\Dropbox\STAGS\D1_Database\EU_Farming_Systems_20181015.gdb' using driver `OpenFileGDB'## Warning: no simple feature geometries present: returning a data.frame or
+## tbl_dfcalorie_fr$geo <- calorie_fr$NUTS_ID
+names(calorie_fr)[5] <- 'cal_frac'
+head(calorie_fr)## NUTS_ID ZONE_CODE COUNT AREA cal_frac geo
+## 1 AT11 1 3739 3.7390e+09 0.5245497 AT11
+## 2 AT22 2 6788 6.7880e+09 0.2280712 AT22
+## 3 AT12 3 14292 1.4292e+10 0.5354631 AT12
+## 4 AT13 4 214 2.1400e+08 0.5256335 AT13
+## 5 AT21 5 4113 4.1130e+09 0.2194208 AT21
+## 6 AT31 6 7273 7.2730e+09 0.3612959 AT31###Suitability data
+precip <- st_read(dsn='C:/Users/mu5106sc/Dropbox/STAGS/D1_Database/EU_Farming_Systems_20181015.gdb', layer='nuts2_mean_ann_precip')## Reading layer `nuts2_mean_ann_precip' from data source `C:\Users\mu5106sc\Dropbox\STAGS\D1_Database\EU_Farming_Systems_20181015.gdb' using driver `OpenFileGDB'## Warning: no simple feature geometries present: returning a data.frame or
+## tbl_dfprecip$geo <- precip$NUTS_ID
+names(precip)[5] <- 'precip'
+head(precip)## NUTS_ID ZONE_CODE COUNT AREA precip geo
+## 1 AT11 1 3970 3.9700e+09 666.3237 AT11
+## 2 AT22 2 16416 1.6416e+10 1149.1807 AT22
+## 3 AT12 3 19205 1.9205e+10 714.3840 AT12
+## 4 AT13 4 414 4.1400e+08 580.7077 AT13
+## 5 AT21 5 9538 9.5380e+09 1357.1470 AT21
+## 6 AT31 6 11977 1.1977e+10 1057.0594 AT31deg_days <- st_read(dsn='C:/Users/mu5106sc/Dropbox/STAGS/D1_Database/EU_Farming_Systems_20181015.gdb', layer='nuts2_mean_gdd')## Reading layer `nuts2_mean_gdd' from data source `C:\Users\mu5106sc\Dropbox\STAGS\D1_Database\EU_Farming_Systems_20181015.gdb' using driver `OpenFileGDB'## Warning: no simple feature geometries present: returning a data.frame or
+## tbl_dfdeg_days$geo <- deg_days$NUTS_ID
+names(deg_days)[5] <- 'deg_days'
+head(deg_days)## NUTS_ID ZONE_CODE COUNT AREA deg_days geo
+## 1 AT11 1 3970 3.9700e+09 1965.423 AT11
+## 2 AT22 2 16416 1.6416e+10 1264.833 AT22
+## 3 AT12 3 19205 1.9205e+10 1764.210 AT12
+## 4 AT13 4 414 4.1400e+08 2040.184 AT13
+## 5 AT21 5 9538 9.5380e+09 1095.291 AT21
+## 6 AT31 6 11977 1.1977e+10 1537.084 AT31crop_suit <- st_read(dsn='C:/Users/mu5106sc/Dropbox/STAGS/D1_Database/EU_Farming_Systems_20181015.gdb', layer='nuts2_mean_crop_suit')## Reading layer `nuts2_mean_crop_suit' from data source `C:\Users\mu5106sc\Dropbox\STAGS\D1_Database\EU_Farming_Systems_20181015.gdb' using driver `OpenFileGDB'## Warning: no simple feature geometries present: returning a data.frame or
+## tbl_dfcrop_suit$geo <- crop_suit$NUTS_ID
+names(crop_suit)[5] <- 'crop_suit'
+head(crop_suit)## NUTS_ID ZONE_CODE COUNT AREA crop_suit geo
+## 1 AT11 1 291 2.910e+08 5.319588 AT11
+## 2 AT22 2 1253 1.253e+09 3.217877 AT22
+## 3 AT12 3 1471 1.471e+09 4.347383 AT12
+## 4 AT13 4 30 3.000e+07 5.466667 AT13
+## 5 AT21 5 726 7.260e+08 2.668044 AT21
+## 6 AT31 6 913 9.130e+08 3.925520 AT31#Join all GIS tables
+gis.dat <- soil_cov[,c("geo", "C_factor")] #soil_cov is most complete of these tables (nrow = 320)
+gis.dat <- left_join(gis.dat, emi_co2eq[,c("geo", "MEAN")])## Joining, by = "geo"## Warning: Column `geo` joining factors with different levels, coercing to
+## character vectornames(gis.dat)[3] <- "emi_co2eq"
+gis.dat <- left_join(gis.dat, emi_nh3[,c("geo", "MEAN")])## Joining, by = "geo"## Warning: Column `geo` joining character vector and factor, coercing into
+## character vectornames(gis.dat)[4] <- "emi_nh3"
+gis.dat <- left_join(gis.dat, emi_pm10[,c("geo", "MEAN")])## Joining, by = "geo"## Warning: Column `geo` joining character vector and factor, coercing into
+## character vectornames(gis.dat)[5] <- "emi_pm10"
+gis.dat <- left_join(gis.dat, emi_pm25[,c("geo", "MEAN")])## Joining, by = "geo"## Warning: Column `geo` joining character vector and factor, coercing into
+## character vectornames(gis.dat)[6] <- "emi_pm25"
+gis.dat <- left_join(gis.dat, soc[,c("geo", "MEAN")])## Joining, by = "geo"## Warning: Column `geo` joining character vector and factor, coercing into
+## character vectornames(gis.dat)[7] <- "soc"
+gis.dat <- left_join(gis.dat, biol_threats[,c("geo", "MEAN")])## Joining, by = "geo"## Warning: Column `geo` joining character vector and factor, coercing into
+## character vectornames(gis.dat)[8] <- "biol_threats"
+gis.dat <- left_join(gis.dat, nat2000[,c("geo", "nat2000_ag", "nat2000_pr")])## Joining, by = "geo"gis.dat <- left_join(gis.dat, calorie_fr[,c("geo", "cal_frac")])## Joining, by = "geo"## Warning: Column `geo` joining character vector and factor, coercing into
+## character vectorgis.dat <- left_join(gis.dat, precip[,c("geo", "precip")])## Joining, by = "geo"## Warning: Column `geo` joining character vector and factor, coercing into
+## character vectorgis.dat <- left_join(gis.dat, deg_days[,c("geo", "deg_days")])## Joining, by = "geo"## Warning: Column `geo` joining character vector and factor, coercing into
+## character vectorgis.dat <- left_join(gis.dat, crop_suit[,c("geo", "crop_suit")])## Joining, by = "geo"## Warning: Column `geo` joining character vector and factor, coercing into
+## character vectorhead(gis.dat)## geo C_factor emi_co2eq emi_nh3 emi_pm10 emi_pm25 soc
+## 1 AT11 0.204701 653096.3 8690.371 1025.7531 818.8200 59.33579
+## 2 AT22 0.305978 954802.7 13155.494 850.9032 331.4128 97.49513
+## 3 AT12 0.195147 1136117.0 14253.957 1285.1966 856.1814 64.25874
+## 4 AT13 0.188655 457098.6 6375.132 609.2881 426.0527 49.22190
+## 5 AT21 0.278675 888623.1 11187.491 471.5642 220.7500 101.03633
+## 6 AT31 0.241675 1943324.3 22472.061 1298.3660 629.6217 100.91691
+## biol_threats nat2000_ag nat2000_pr cal_frac precip deg_days
+## 1 0.2693722 0.202690378 0.27756336 0.5245497 666.3237 1965.423
+## 2 0.2525372 0.084071132 0.15248896 0.2280712 1149.1807 1264.833
+## 3 0.2670201 0.139216259 0.22137659 0.5354631 714.3840 1764.210
+## 4 0.2611445 0.182098765 0.13365361 0.5256335 580.7077 2040.184
+## 5 0.2280257 0.008167266 0.06126958 0.2194208 1357.1470 1095.291
+## 6 0.2672487 0.009193898 0.06533375 0.3612959 1057.0594 1537.084
+## crop_suit
+## 1 5.319588
+## 2 3.217877
+## 3 4.347383
+## 4 5.466667
+## 5 2.668044
+## 6 3.925520#Join GIS data to clean database
+names(dbase.clean)## [1] "NUTS_ID" "risk_pov" "train35bas" "train35ful"
+## [5] "train_bas" "train_ful" "nitr_high" "nitr_mod"
+## [9] "nitr_poor" "irrigated" "forest" "artific"
+## [13] "soil_loss" "com_birds" "farm_birds" "org_farm"
+## [17] "energy_rt" "renew_pct" "renew_prod" "gross_N"
+## [21] "gross_P" "conv_till" "cons_till" "zero_till"
+## [25] "nfert" "arable" "grassland" "permanent"
+## [29] "soil_prod" "geo" "irrig_rate" "afi_awu"
+## [33] "gva_awu" "labour_use" "pest_rate" "tot_gdp_cap"
+## [37] "tot_pps_cap" "emp_rate_15_64" "tot_unemp" "yth_unemp"
+## [41] "rur_gdp_cap" "rur_pps_cap" "int_gdp_cap" "int_pps_cap"
+## [45] "urb_gdp_cap" "urb_pps_cap"names(gis.dat)## [1] "geo" "C_factor" "emi_co2eq" "emi_nh3"
+## [5] "emi_pm10" "emi_pm25" "soc" "biol_threats"
+## [9] "nat2000_ag" "nat2000_pr" "cal_frac" "precip"
+## [13] "deg_days" "crop_suit"nrow(dbase.clean)## [1] 320nrow(gis.dat)## [1] 320dbase.clean.gis <- left_join(dbase.clean, gis.dat)## Joining, by = "geo"head(dbase.clean.gis)## NUTS_ID risk_pov train35bas train35ful train_bas train_ful nitr_high
+## 1 AT11 13.73333 0.1375661 0.3333333 0.1243050 0.1779190 64.58924
+## 2 AT22 17.26667 0.2160980 0.3648294 0.2017089 0.2413594 64.58924
+## 3 AT12 13.83333 0.2084775 0.4809689 0.2534787 0.3449437 64.58924
+## 4 AT13 27.23333 0.3750000 0.7500000 0.1753247 0.4740260 64.58924
+## 5 AT21 17.20000 0.2306238 0.3648393 0.2076173 0.2250348 64.58924
+## 6 AT31 15.00000 0.2508418 0.4284512 0.2014381 0.2857610 64.58924
+## nitr_mod nitr_poor irrigated forest artific soil_loss com_birds
+## 1 20.20774 15.20302 5.850 0.3161203 0.04355635 1.842 NA
+## 2 20.20774 15.20302 0.325 0.6127954 0.03306278 5.804 NA
+## 3 20.20774 15.20302 2.650 0.4286079 0.04875064 2.236 NA
+## 4 20.20774 15.20302 10.525 0.1469534 0.73118280 1.014 NA
+## 5 20.20774 15.20302 0.100 0.5998934 0.03047416 11.671 NA
+## 6 20.20774 15.20302 0.125 0.4027358 0.04900973 3.791 NA
+## farm_birds org_farm energy_rt renew_pct renew_prod gross_N gross_P
+## 1 65.98 19.43430 0.08319988 32.65559 7.068917 32.57143 1.833333
+## 2 65.98 12.80858 0.08319988 32.65559 7.068917 32.57143 1.833333
+## 3 65.98 13.41584 0.08319988 32.65559 7.068917 32.57143 1.833333
+## 4 65.98 16.44137 0.08319988 32.65559 7.068917 32.57143 1.833333
+## 5 65.98 10.68078 0.08319988 32.65559 7.068917 32.57143 1.833333
+## 6 65.98 12.31071 0.08319988 32.65559 7.068917 32.57143 1.833333
+## conv_till cons_till zero_till nfert arable grassland permanent
+## 1 0.6182190 0.31992068 0.025012794 7.684000 83.64566 8.715722 7.5451998
+## 2 0.8887161 0.05005656 0.024109163 7.551429 37.02489 58.694493 4.2139773
+## 3 0.6226791 0.32803537 0.019896256 7.452800 76.22380 20.140837 3.5858503
+## 4 0.5109890 0.40476190 0.007326007 7.497000 79.80050 10.099751 10.0997506
+## 5 0.8592546 0.05928605 0.032552288 8.131500 28.48779 71.285286 0.1679223
+## 6 0.8442576 0.12043311 0.014198645 9.138333 56.49367 43.164202 0.2648111
+## soil_prod geo irrig_rate afi_awu gva_awu labour_use pest_rate
+## 1 6 AT11 16.6922025 24788.951 25367.72 0.036978892 1.335093
+## 2 6 AT22 2.2086896 13958.345 18388.41 0.034606425 1.335093
+## 3 6 AT12 10.7753945 23056.271 25423.66 0.035521808 1.335093
+## 4 6 AT13 208.4609053 6431.103 9952.26 0.001572703 1.335093
+## 5 6 AT21 0.5770663 10741.948 11827.48 0.028435272 1.335093
+## 6 6 AT31 0.5491021 15263.545 22028.20 0.030650579 1.335093
+## tot_gdp_cap tot_pps_cap emp_rate_15_64 tot_unemp yth_unemp rur_gdp_cap
+## 1 26700 24600 69.81530 5.7 15.0 26690.97
+## 2 34800 32100 71.37077 5.1 10.2 28015.67
+## 3 31800 29300 73.06232 5.2 9.3 29392.91
+## 4 47300 43700 64.90683 11.3 20.3 NA
+## 5 32700 30200 69.88481 5.4 12.2 27340.58
+## 6 39600 36500 75.46507 4.5 7.6 33453.92
+## rur_pps_cap int_gdp_cap int_pps_cap urb_gdp_cap urb_pps_cap C_factor
+## 1 24628.47 NA NA NA NA 0.204701
+## 2 25851.10 42289.66 39020.69 NA NA 0.305978
+## 3 27122.78 37037.74 34176.67 27574.60 25441.27 0.195147
+## 4 NA NA NA 47307.69 43651.88 0.188655
+## 5 25228.26 38025.00 35085.71 NA NA 0.278675
+## 6 30867.51 48936.17 45154.26 NA NA 0.241675
+## emi_co2eq emi_nh3 emi_pm10 emi_pm25 soc biol_threats
+## 1 653096.3 8690.371 1025.7531 818.8200 59.33579 0.2693722
+## 2 954802.7 13155.494 850.9032 331.4128 97.49513 0.2525372
+## 3 1136117.0 14253.957 1285.1966 856.1814 64.25874 0.2670201
+## 4 457098.6 6375.132 609.2881 426.0527 49.22190 0.2611445
+## 5 888623.1 11187.491 471.5642 220.7500 101.03633 0.2280257
+## 6 1943324.3 22472.061 1298.3660 629.6217 100.91691 0.2672487
+## nat2000_ag nat2000_pr cal_frac precip deg_days crop_suit
+## 1 0.202690378 0.27756336 0.5245497 666.3237 1965.423 5.319588
+## 2 0.084071132 0.15248896 0.2280712 1149.1807 1264.833 3.217877
+## 3 0.139216259 0.22137659 0.5354631 714.3840 1764.210 4.347383
+## 4 0.182098765 0.13365361 0.5256335 580.7077 2040.184 5.466667
+## 5 0.008167266 0.06126958 0.2194208 1357.1470 1095.291 2.668044
+## 6 0.009193898 0.06533375 0.3612959 1057.0594 1537.084 3.925520#First, we work with only those NUTS regions with crop areas > 0 to avoid spurious yield values later
+crop.area.dat <- read.csv("C:/Users/mu5106sc/Dropbox/STAGS/SDG_data_eurostat/Final_database/Crop_area_yield/croparea_no_0s_mean_allnuts.csv", head=T)
+
+names(crop.area.dat)## [1] "geo" "rye_a" "barley_a" "maize_a" "tritic_a"
+## [6] "sorghum_a" "oth_cer_a" "rice_a" "pasture_a" "rape_a"
+## [11] "sunflow_a" "pulses_a" "potato_a" "sugbeet_a" "oth_rt_a"
+## [16] "wheat_a" "oats_a" "oth_oil_a" "fibre_a" "oth_ind_a"
+## [21] "fodder_a"names(geodata@data)## [1] "id" "CNTR_CODE" "NUTS_NAME" "LEVL_CODE" "FID" "NUTS_ID"
+## [7] "geo"crop.area.dat <- left_join(crop.area.dat, geodata@data[,c(4,7)])## Joining, by = "geo"## Warning: Column `geo` joining factor and character vector, coercing into
+## character vector#Need to adjust the NUTS2016 data to NUTS2013 codes
+crop.area.dat.2013nuts <- crop.area.dat
+names(crop.area.dat.2013nuts)## [1] "geo" "rye_a" "barley_a" "maize_a" "tritic_a"
+## [6] "sorghum_a" "oth_cer_a" "rice_a" "pasture_a" "rape_a"
+## [11] "sunflow_a" "pulses_a" "potato_a" "sugbeet_a" "oth_rt_a"
+## [16] "wheat_a" "oats_a" "oth_oil_a" "fibre_a" "oth_ind_a"
+## [21] "fodder_a" "LEVL_CODE"crop.area.dat.2013nuts$geo16 <- crop.area.dat.2013nuts$geo
+nuts.conv <- read.csv("C:/Users/mu5106sc/Dropbox/STAGS/SDG_data_eurostat/Final_database/Crop_area_yield/NUTS2013-NUTS2016_2.csv", head=T)[,1:4]
+head(nuts.conv)## Code.2013 Code.2016 Label
+## 1 IE01 Border, Midland and Western
+## 2 IE04 Northern and Western
+## 3 IE02 Southern and Eastern
+## 4 IE05 Southern
+## 5 IE06 Eastern and Midland
+## 6 FR24 FRB0 Centre Val de Loire
+## Change
+## 1 discontinued
+## 2 new region
+## 3 discontinued
+## 4 new region, made from ex-IE023, IE024 and IE025
+## 5 new region
+## 6 recoded and relabelledlevels(nuts.conv$Change)## [1] ""
+## [2] "boundary shift; lost ex-UKM24"
+## [3] "discontinued"
+## [4] "discontinued; split into new HU11 and HU12"
+## [5] "discontinued; split into new PL91 and PL92"
+## [6] "discontinued; split into new UKM8 and UKM9"
+## [7] "new region"
+## [8] "new region, equals ex-NUTS 3 region HU101"
+## [9] "new region, equals ex-NUTS 3 region HU102"
+## [10] "new region, equals ex-NUTS 3 region LT00A"
+## [11] "new region, equals ex-PL127, PL129 and PL12A minus new PL926"
+## [12] "new region, ex-LT00 minus ex-LT00A"
+## [13] "new region, made from ex-IE023, IE024 and IE025"
+## [14] "new region, made from ex-PL128, PL12B, PL12C, PL12D, PL12E plus new PL926"
+## [15] "new region, made from ex-UKM24, UKM32, UKM33, UKM37 and UKM38"
+## [16] "new region, made from ex-UKM31, UKM34, UKM35 and UKM36"
+## [17] "recoded"
+## [18] "recoded and relabelled"
+## [19] "split into new LT01 and LT02"#straight recodes
+for(e in nuts.conv[nuts.conv$Change == "recoded", 'Code.2016']) {
+ crop.area.dat.2013nuts[crop.area.dat.2013nuts$geo16 == e, 'geo'] <- as.character(nuts.conv[nuts.conv$Code.2016 == e, 'Code.2013'])
+}
+#check
+crop.area.dat.2013nuts[crop.area.dat.2013nuts$geo16 %in% nuts.conv[nuts.conv$Change == "recoded", 'Code.2016'], c('geo', 'geo16')]## geo geo16
+## 195 FR51 FRG0
+## 196 FR52 FRH0
+## 200 FR61 FRI1
+## 201 FR63 FRI2
+## 202 FR53 FRI3
+## 214 FR81 FRJ1
+## 215 FR62 FRJ2
+## 222 FR21 FRF2
+## 223 FR26 FRC1
+## 224 FR43 FRC2
+## 225 FR25 FRD1
+## 226 FR23 FRD2
+## 236 FR41 FRF3
+## 237 FR72 FRK1
+## 238 FR71 FRK2
+## 245 FR82 FRL0
+## 246 FR83 FRM0
+## 247 FRA1 FRY1
+## 259 FRA2 FRY2
+## 260 FRA3 FRY3
+## 261 FRA4 FRY4
+## 262 FRA5 FRY5
+## 317 FR30 FRE1
+## 318 FR22 FRE2
+## 319 FR42 FRF1
+## 441 PL32 PL82
+## 454 PL34 PL84
+## 486 PL11 PL71
+## 487 PL33 PL72
+## 488 PL31 PL81#recode and relabel
+crop.area.dat.2013nuts[crop.area.dat.2013nuts$geo16 == "FRB0", 'geo'] <- "FR24"
+
+#splits
+crop.area.dat.2013nuts[crop.area.dat.2013nuts$geo16 %in% c("LT01", "LT02"), 'geo'] <- "LT00"
+crop.area.dat.2013nuts[crop.area.dat.2013nuts$geo16 %in% c("HU11", "HU12"), 'geo'] <- "HU10"
+crop.area.dat.2013nuts[crop.area.dat.2013nuts$geo16 %in% c("PL91", "PL92"), 'geo'] <- "PL12"
+crop.area.dat.2013nuts[crop.area.dat.2013nuts$geo16 %in% c("UKM8", "UKM9"), 'geo'] <- "UKM3" #approximate split not including NUTS3 UKM24
+crop.area.dat.2013nuts[crop.area.dat.2013nuts$geo16 == "UKM7", 'geo'] <- "UKM2" #approximate recode still including NUTS3 UKM24
+
+#IE
+#Cannot translate data from new regions to old NUTS2013 so use NUTS0 data
+crop.area.dat.2013nuts[crop.area.dat.2013nuts$geo16 == 'IE',]## geo rye_a barley_a maize_a tritic_a sorghum_a oth_cer_a rice_a
+## 17 IE NA 194.4375 NA NA NA NA NA
+## pasture_a rape_a sunflow_a pulses_a potato_a sugbeet_a oth_rt_a
+## 17 96.10625 11.2325 0.01 7.05125 9.81 NA 11.95
+## wheat_a oats_a oth_oil_a fibre_a oth_ind_a fodder_a LEVL_CODE geo16
+## 17 75.315 22.645 0.07 0.02666667 1.96625 19.82042 0 IE## Calculate sum over the split NUTS2 regions
+head(crop.area.dat.2013nuts)## geo rye_a barley_a maize_a tritic_a sorghum_a oth_cer_a rice_a
+## 1 BG 10.707500 186.503750 416.77125 13.81375 4.635 4.0450000 11.2175
+## 2 CH 1.986250 28.315000 15.33500 9.06875 NA 0.1116667 0.0800
+## 3 CY NA 20.810000 NA 0.42500 NA NA NA
+## 4 AL 1.285714 2.742857 56.44286 NA NA NA NA
+## 5 CZ 27.141250 357.867500 98.95625 43.45875 NA 5.3400000 NA
+## 6 BE 0.606250 46.607500 63.19125 5.85875 NA 3.2157143 NA
+## pasture_a rape_a sunflow_a pulses_a potato_a sugbeet_a oth_rt_a
+## 1 0.72750 175.64875 813.4100000 20.115000 12.512500 0.01000 0.1914286
+## 2 117.22000 21.79750 4.1087500 4.702857 11.072500 19.47500 0.6585714
+## 3 0.33500 NA NA 0.413750 4.706250 NA NA
+## 4 143.70000 NA 0.9714286 14.128571 9.585714 0.70000 NA
+## 5 37.74286 388.13375 21.6175000 27.933750 24.236250 60.71125 0.6300000
+## 6 79.00375 11.98875 NA 2.387500 80.837143 58.88000 7.5942857
+## wheat_a oats_a oth_oil_a fibre_a oth_ind_a fodder_a
+## 1 1184.90750 16.499750 20.2690000 1.8728571 64.7175000 110.37167
+## 2 88.57500 1.937917 1.6210357 0.0500000 1.2264286 189.00375
+## 3 9.51375 0.397500 0.0737500 NA NA 34.95625
+## 4 70.64286 14.028571 0.2571429 NA 6.0571429 238.71667
+## 5 834.87625 47.745000 61.8150000 0.3642857 13.1067857 414.21214
+## 6 209.81500 3.721250 0.1466667 12.8037500 0.7129167 181.32375
+## LEVL_CODE geo16
+## 1 0 BG
+## 2 0 CH
+## 3 0 CY
+## 4 0 AL
+## 5 0 CZ
+## 6 0 BEcrop.area.dat.2013nuts.sum <- crop.area.dat.2013nuts %>% group_by(geo) %>% summarise(rye_a = sum(rye_a,na.rm = F),
+ barley_a = sum(barley_a,na.rm = F),
+ maize_a = sum(maize_a,na.rm = F),
+ tritic_a = sum(tritic_a,na.rm = F),
+ sorghum_a = sum(sorghum_a,na.rm = F),
+ oth_cer_a = sum(oth_cer_a,na.rm = F),
+ rice_a = sum(rice_a,na.rm = F),
+ pasture_a = sum(pasture_a,na.rm = F),
+ rape_a = sum(rape_a,na.rm = F),
+ sunflow_a = sum(sunflow_a,na.rm = F),
+ pulses_a = sum(pulses_a,na.rm = F),
+ potato_a = sum(potato_a,na.rm = F),
+ sugbeet_a = sum(sugbeet_a,na.rm = F),
+ oth_rt_a = sum(oth_rt_a,na.rm = F),
+ wheat_a = sum(wheat_a,na.rm = F),
+ oats_a = sum(oats_a,na.rm = F),
+ oth_oil_a = sum(oth_oil_a,na.rm = F),
+ fibre_a = sum(fibre_a,na.rm = F),
+ oth_ind_a = sum(oth_ind_a,na.rm = F),
+ fodder_a = sum(fodder_a,na.rm = F),
+ LEVL_CODE = mean(LEVL_CODE,na.rm = F)
+ )
+head(crop.area.dat.2013nuts.sum)## # A tibble: 6 x 22
+## geo rye_a barley_a maize_a tritic_a sorghum_a oth_cer_a rice_a
+## <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
+## 1 AL 1.29 2.74 56.4 NA NA NA NA
+## 2 AL0 NA NA NA NA NA NA NA
+## 3 AL01 NA NA NA NA NA NA NA
+## 4 AL011 NA NA NA NA NA NA NA
+## 5 AL012 NA NA NA NA NA NA NA
+## 6 AL013 NA NA NA NA NA NA NA
+## # ... with 14 more variables: pasture_a <dbl>, rape_a <dbl>,
+## # sunflow_a <dbl>, pulses_a <dbl>, potato_a <dbl>, sugbeet_a <dbl>,
+## # oth_rt_a <dbl>, wheat_a <dbl>, oats_a <dbl>, oth_oil_a <dbl>,
+## # fibre_a <dbl>, oth_ind_a <dbl>, fodder_a <dbl>, LEVL_CODE <dbl>nrow(crop.area.dat.2013nuts.sum)## [1] 2013#We calculate the fraction of agricultural area within each NUTS0, NUTS1, and NUTS2 area using the UAA from CORINE
+#First, join UAA dataframe to crop area dataframe
+head(corine.aa.all.nuts)## geo sum_uaa
+## 1 AT11 219300.0
+## 2 AT22 411556.2
+## 3 AT12 1004956.2
+## 4 AT13 6075.0
+## 5 AT21 191312.5
+## 6 AT31 582587.5names(crop.area.dat.2013nuts.sum)## [1] "geo" "rye_a" "barley_a" "maize_a" "tritic_a"
+## [6] "sorghum_a" "oth_cer_a" "rice_a" "pasture_a" "rape_a"
+## [11] "sunflow_a" "pulses_a" "potato_a" "sugbeet_a" "oth_rt_a"
+## [16] "wheat_a" "oats_a" "oth_oil_a" "fibre_a" "oth_ind_a"
+## [21] "fodder_a" "LEVL_CODE"crop.area.dat.2013nuts.sum <- left_join(crop.area.dat.2013nuts.sum, corine.aa.all.nuts)## Joining, by = "geo"summary(crop.area.dat.2013nuts.sum)## geo rye_a barley_a
+## Length:2013 Min. : 0.010 Min. : 0.0167
+## Class :character 1st Qu.: 0.339 1st Qu.: 10.8616
+## Mode :character Median : 1.857 Median : 39.5050
+## Mean : 19.286 Mean : 114.3821
+## 3rd Qu.: 11.589 3rd Qu.: 116.1025
+## Max. :1051.300 Max. :2763.5000
+## NA's :1674 NA's :1635
+## maize_a tritic_a sorghum_a
+## Min. : 0.010 Min. : 0.0100 Min. : 0.0100
+## 1st Qu.: 1.977 1st Qu.: 0.8882 1st Qu.: 0.1000
+## Median : 17.253 Median : 4.7900 Median : 0.4175
+## Mean : 93.177 Mean : 27.9156 Mean : 2.6008
+## 3rd Qu.: 82.514 3rd Qu.: 21.7703 3rd Qu.: 1.4600
+## Max. :2506.171 Max. :1289.4300 Max. :50.6700
+## NA's :1675 NA's :1731 NA's :1868
+## oth_cer_a rice_a pasture_a rape_a
+## Min. : 0.0100 Min. : 0.010 Min. : 0.010 Min. : 0.01
+## 1st Qu.: 0.1715 1st Qu.: 0.685 1st Qu.: 4.897 1st Qu.: 1.50
+## Median : 0.7017 Median : 3.410 Median : 15.800 Median : 13.73
+## Mean : 4.2490 Mean : 19.279 Mean : 88.947 Mean : 57.92
+## 3rd Qu.: 2.6938 3rd Qu.: 20.203 3rd Qu.: 66.019 3rd Qu.: 62.53
+## Max. :102.9237 Max. :230.827 Max. :3091.571 Max. :1503.09
+## NA's :1917 NA's :1926 NA's :1744 NA's :1705
+## sunflow_a pulses_a potato_a sugbeet_a
+## Min. : 0.0100 Min. : 0.01 Min. : 0.020 Min. : 0.010
+## 1st Qu.: 0.4097 1st Qu.: 1.00 1st Qu.: 1.197 1st Qu.: 1.000
+## Median : 4.1544 Median : 4.88 Median : 4.686 Median : 6.553
+## Mean : 57.2720 Mean : 20.95 Mean : 14.341 Mean : 20.984
+## 3rd Qu.: 36.7714 3rd Qu.: 18.03 3rd Qu.: 13.900 3rd Qu.: 20.265
+## Max. :997.2763 Max. :663.38 Max. :334.110 Max. :404.298
+## NA's :1747 NA's :1646 NA's :1661 NA's :1749
+## oth_rt_a wheat_a oats_a oth_oil_a
+## Min. : 0.010 Min. : 0.01 Min. : 0.010 Min. : 0.0100
+## 1st Qu.: 0.100 1st Qu.: 23.32 1st Qu.: 1.252 1st Qu.: 0.4012
+## Median : 0.360 Median : 116.42 Median : 5.880 Median : 1.6988
+## Mean : 1.869 Mean : 262.15 Mean : 29.780 Mean : 19.2813
+## 3rd Qu.: 1.127 3rd Qu.: 294.29 3rd Qu.: 18.924 3rd Qu.: 11.8080
+## Max. :40.000 Max. :7997.88 Max. :1488.480 Max. :623.9917
+## NA's :1892 NA's :1634 NA's :1666 NA's :1744
+## fibre_a oth_ind_a fodder_a LEVL_CODE
+## Min. : 0.0100 Min. : 0.0100 Min. : 0.010 Min. :0.000
+## 1st Qu.: 0.0350 1st Qu.: 0.1200 1st Qu.: 8.642 1st Qu.:3.000
+## Median : 0.2225 Median : 0.7718 Median : 33.811 Median :3.000
+## Mean : 16.8706 Mean : 5.2917 Mean : 94.226 Mean :2.658
+## 3rd Qu.: 2.0250 3rd Qu.: 3.6009 3rd Qu.: 92.478 3rd Qu.:3.000
+## Max. :471.5714 Max. :165.9238 Max. :2421.790 Max. :3.000
+## NA's :1852 NA's :1727 NA's :1666
+## sum_uaa
+## Min. : 56
+## 1st Qu.: 256462
+## Median : 701169
+## Mean : 1469382
+## 3rd Qu.: 1522769
+## Max. :33916138
+## NA's :1556#Second, calculate the fraction of area
+crop.frac <- as.data.frame(crop.area.dat.2013nuts.sum)
+names(crop.frac)[2:21] <- gsub("_a", "_f", names(crop.frac)[2:21])
+crop.frac[,2:21] <- 1000 * crop.area.dat.2013nuts.sum[,2:21] / crop.area.dat.2013nuts.sum$sum_uaa
+crop.frac$total_f <- rowSums(crop.frac[,2:21], na.rm = T)
+summary(crop.frac)## geo rye_f barley_f maize_f
+## Length:2013 Min. :0.0000 Min. :0.0003 Min. :0.0001
+## Class :character 1st Qu.:0.0005 1st Qu.:0.0200 1st Qu.:0.0036
+## Mode :character Median :0.0021 Median :0.0421 Median :0.0192
+## Mean :0.0090 Mean :0.0553 Mean :0.0421
+## 3rd Qu.:0.0084 3rd Qu.:0.0768 3rd Qu.:0.0544
+## Max. :0.1271 Max. :0.3657 Max. :0.3190
+## NA's :1696 NA's :1661 NA's :1699
+## tritic_f sorghum_f oth_cer_f rice_f
+## Min. :0.0000 Min. :0.0000 Min. :0.0000 Min. :0.0000
+## 1st Qu.:0.0013 1st Qu.:0.0001 1st Qu.:0.0003 1st Qu.:0.0006
+## Median :0.0045 Median :0.0004 Median :0.0007 Median :0.0024
+## Mean :0.0118 Mean :0.0010 Mean :0.0025 Mean :0.0094
+## 3rd Qu.:0.0116 3rd Qu.:0.0010 3rd Qu.:0.0019 3rd Qu.:0.0080
+## Max. :0.1181 Max. :0.0181 Max. :0.0457 Max. :0.1071
+## NA's :1753 NA's :1880 NA's :1918 NA's :1929
+## pasture_f rape_f sunflow_f pulses_f
+## Min. :0.0000 Min. :0.0000 Min. :0.0000 Min. :0.0001
+## 1st Qu.:0.0087 1st Qu.:0.0020 1st Qu.:0.0004 1st Qu.:0.0021
+## Median :0.0238 Median :0.0176 Median :0.0041 Median :0.0046
+## Mean :0.0597 Mean :0.0298 Mean :0.0232 Mean :0.0087
+## 3rd Qu.:0.0843 3rd Qu.:0.0479 3rd Qu.:0.0222 3rd Qu.:0.0118
+## Max. :0.4127 Max. :0.1676 Max. :0.2186 Max. :0.0648
+## NA's :1771 NA's :1729 NA's :1770 NA's :1673
+## potato_f sugbeet_f oth_rt_f wheat_f
+## Min. :0.0000 Min. :0.0000 Min. :0.0000 Min. :0.0002
+## 1st Qu.:0.0022 1st Qu.:0.0012 1st Qu.:0.0001 1st Qu.:0.0522
+## Median :0.0051 Median :0.0068 Median :0.0003 Median :0.1198
+## Mean :0.0151 Mean :0.0161 Mean :0.0016 Mean :0.1294
+## 3rd Qu.:0.0125 3rd Qu.:0.0171 3rd Qu.:0.0011 3rd Qu.:0.1834
+## Max. :0.3619 Max. :0.3886 Max. :0.0229 Max. :1.1951
+## NA's :1688 NA's :1768 NA's :1893 NA's :1660
+## oats_f oth_oil_f fibre_f oth_ind_f
+## Min. :0.0001 Min. :0.0000 Min. :0.0000 Min. :0.0000
+## 1st Qu.:0.0021 1st Qu.:0.0004 1st Qu.:0.0000 1st Qu.:0.0002
+## Median :0.0063 Median :0.0018 Median :0.0002 Median :0.0007
+## Mean :0.0138 Mean :0.0089 Mean :0.0106 Mean :0.0025
+## 3rd Qu.:0.0152 3rd Qu.:0.0078 3rd Qu.:0.0058 3rd Qu.:0.0023
+## Max. :0.1913 Max. :0.1905 Max. :0.1600 Max. :0.0356
+## NA's :1692 NA's :1766 NA's :1859 NA's :1754
+## fodder_f LEVL_CODE sum_uaa total_f
+## Min. :0.0002 Min. :0.000 Min. : 56 Min. :0.00000
+## 1st Qu.:0.0180 1st Qu.:3.000 1st Qu.: 256462 1st Qu.:0.00000
+## Median :0.0394 Median :3.000 Median : 701169 Median :0.00000
+## Mean :0.0524 Mean :2.658 Mean : 1469382 Mean :0.07534
+## 3rd Qu.:0.0705 3rd Qu.:3.000 3rd Qu.: 1522769 3rd Qu.:0.00000
+## Max. :0.3810 Max. :3.000 Max. :33916138 Max. :3.72082
+## NA's :1693 NA's :1556#Spurious fractions
+crop.frac[which(crop.frac$total_f > 1), 'geo']## [1] "BE1" "BE10"crop.frac[which(crop.frac$wheat_f > 1), 'geo'] ## [1] "BE1" "BE10"as.data.frame(crop.area.dat.2013nuts.sum[which(crop.area.dat.2013nuts.sum$geo %in% c("BE1", "BE10")),]) ## geo rye_a barley_a maize_a tritic_a sorghum_a oth_cer_a rice_a
+## 1 BE1 0.01 0.16 0.08333333 0.025 NA 0.02 NA
+## 2 BE10 0.01 0.16 0.08333333 0.025 NA 0.02 NA
+## pasture_a rape_a sunflow_a pulses_a potato_a sugbeet_a oth_rt_a
+## 1 0.11 0.07333333 NA 0.02333333 0.1583333 0.17 0.01
+## 2 0.11 0.07333333 NA 0.02333333 0.1583333 0.17 0.01
+## wheat_a oats_a oth_oil_a fibre_a oth_ind_a fodder_a LEVL_CODE sum_uaa
+## 1 0.5228571 0.025 NA 0.07 NA 0.1666667 1 437.5
+## 2 0.5228571 0.025 NA 0.07 NA 0.1666667 2 437.5#The Brussels region (BE10) has wheat fraction > 1, and total fraction >> 1, so we will give NA
+crop.frac[which(crop.frac$geo %in% c("BE1", "BE10")), c(2:21,24)] <- NA
+crop.frac[which(crop.frac$geo %in% c("BE1", "BE10")),]## geo rye_f barley_f maize_f tritic_f sorghum_f oth_cer_f rice_f
+## 67 BE1 NA NA NA NA NA NA NA
+## 68 BE10 NA NA NA NA NA NA NA
+## pasture_f rape_f sunflow_f pulses_f potato_f sugbeet_f oth_rt_f wheat_f
+## 67 NA NA NA NA NA NA NA NA
+## 68 NA NA NA NA NA NA NA NA
+## oats_f oth_oil_f fibre_f oth_ind_f fodder_f LEVL_CODE sum_uaa total_f
+## 67 NA NA NA NA NA 1 437.5 NA
+## 68 NA NA NA NA NA 2 437.5 NA#Here we add the NUTS with crop areas equal to zero, which were removed in the first crop.frac calculation due to spurious values when calculating yields. Where NA's exist in crop.frac, we add these new values, which are zeros.
+crop.0.area.dat <- read.csv("C:/Users/mu5106sc/Dropbox/STAGS/SDG_data_eurostat/Final_database/Crop_area_yield/croparea_mean_allnuts.csv", head=T)
+
+names(crop.0.area.dat)## [1] "geo" "rye_a" "barley_a" "maize_a" "tritic_a"
+## [6] "sorghum_a" "oth_cer_a" "rice_a" "pasture_a" "rape_a"
+## [11] "sunflow_a" "pulses_a" "potato_a" "sugbeet_a" "oth_rt_a"
+## [16] "wheat_a" "oats_a" "oth_oil_a" "fibre_a" "oth_ind_a"
+## [21] "fodder_a"names(geodata@data)## [1] "id" "CNTR_CODE" "NUTS_NAME" "LEVL_CODE" "FID" "NUTS_ID"
+## [7] "geo"crop.0.area.dat <- left_join(crop.0.area.dat, geodata@data[,c(4,7)])## Joining, by = "geo"## Warning: Column `geo` joining factor and character vector, coercing into
+## character vector#Need to adjust the NUTS2016 data to NUTS2013 codes
+crop.0.area.dat.2013nuts <- crop.0.area.dat
+names(crop.0.area.dat.2013nuts)## [1] "geo" "rye_a" "barley_a" "maize_a" "tritic_a"
+## [6] "sorghum_a" "oth_cer_a" "rice_a" "pasture_a" "rape_a"
+## [11] "sunflow_a" "pulses_a" "potato_a" "sugbeet_a" "oth_rt_a"
+## [16] "wheat_a" "oats_a" "oth_oil_a" "fibre_a" "oth_ind_a"
+## [21] "fodder_a" "LEVL_CODE"crop.0.area.dat.2013nuts$geo16 <- crop.0.area.dat.2013nuts$geo
+
+#straight recodes
+for(e in nuts.conv[nuts.conv$Change == "recoded", 'Code.2016']) {
+ crop.0.area.dat.2013nuts[crop.0.area.dat.2013nuts$geo16 == e, 'geo'] <- as.character(nuts.conv[nuts.conv$Code.2016 == e, 'Code.2013'])
+}
+#check
+crop.0.area.dat.2013nuts[crop.0.area.dat.2013nuts$geo16 %in% nuts.conv[nuts.conv$Change == "recoded", 'Code.2016'], c('geo', 'geo16')]## geo geo16
+## 195 FR51 FRG0
+## 196 FR52 FRH0
+## 200 FR61 FRI1
+## 201 FR63 FRI2
+## 202 FR53 FRI3
+## 214 FR81 FRJ1
+## 215 FR62 FRJ2
+## 222 FR21 FRF2
+## 223 FR26 FRC1
+## 224 FR43 FRC2
+## 225 FR25 FRD1
+## 226 FR23 FRD2
+## 236 FR41 FRF3
+## 237 FR72 FRK1
+## 238 FR71 FRK2
+## 245 FR82 FRL0
+## 246 FR83 FRM0
+## 247 FRA1 FRY1
+## 259 FRA2 FRY2
+## 260 FRA3 FRY3
+## 261 FRA4 FRY4
+## 262 FRA5 FRY5
+## 317 FR30 FRE1
+## 318 FR22 FRE2
+## 319 FR42 FRF1
+## 441 PL32 PL82
+## 454 PL34 PL84
+## 486 PL11 PL71
+## 487 PL33 PL72
+## 488 PL31 PL81#recode and relabel
+crop.0.area.dat.2013nuts[crop.0.area.dat.2013nuts$geo16 == "FRB0", 'geo'] <- "FR24"
+
+#splits
+crop.0.area.dat.2013nuts[crop.0.area.dat.2013nuts$geo16 %in% c("LT01", "LT02"), 'geo'] <- "LT00"
+crop.0.area.dat.2013nuts[crop.0.area.dat.2013nuts$geo16 %in% c("HU11", "HU12"), 'geo'] <- "HU10"
+crop.0.area.dat.2013nuts[crop.0.area.dat.2013nuts$geo16 %in% c("PL91", "PL92"), 'geo'] <- "PL12"
+crop.0.area.dat.2013nuts[crop.0.area.dat.2013nuts$geo16 %in% c("UKM8", "UKM9"), 'geo'] <- "UKM3" #approximate split not including NUTS3 UKM24
+crop.0.area.dat.2013nuts[crop.0.area.dat.2013nuts$geo16 == "UKM7", 'geo'] <- "UKM2" #approximate recode still including NUTS3 UKM24
+
+#IE
+#Cannot translate data from new regions to old NUTS2013 so use NUTS0 data
+crop.0.area.dat.2013nuts[crop.0.area.dat.2013nuts$geo16 == 'IE',]## geo rye_a barley_a maize_a tritic_a sorghum_a oth_cer_a rice_a
+## 17 IE 0 194.4375 0 0 0 0 0
+## pasture_a rape_a sunflow_a pulses_a potato_a sugbeet_a oth_rt_a
+## 17 96.10625 11.2325 0.00125 7.05125 9.81 0 11.95
+## wheat_a oats_a oth_oil_a fibre_a oth_ind_a fodder_a LEVL_CODE geo16
+## 17 75.315 22.645 0.02625 0.01 1.9475 19.70125 0 IE## Calculate sum over the split NUTS2 regions
+head(crop.0.area.dat.2013nuts)## geo rye_a barley_a maize_a tritic_a sorghum_a oth_cer_a rice_a
+## 1 BG 10.707500 186.503750 416.77125 13.81375 4.635 4.04500000 11.2175
+## 2 CH 1.986250 28.315000 15.33500 9.06875 0.000 0.09571429 0.0480
+## 3 CY 0.000000 20.810000 0.00000 0.10625 0.000 0.00000000 0.0000
+## 4 AL 1.285714 2.742857 56.44286 0.00000 0.000 0.00000000 0.0000
+## 5 CZ 27.141250 357.867500 98.95625 43.45875 0.000 5.34000000 0.0000
+## 6 BE 0.606250 46.607500 63.19125 5.85875 0.000 2.81375000 0.0000
+## pasture_a rape_a sunflow_a pulses_a potato_a sugbeet_a oth_rt_a
+## 1 0.72750 175.64875 813.4100000 20.115000 12.512500 0.0012500 0.1675000
+## 2 117.22000 21.79750 4.1087500 4.702857 11.072500 19.4750000 0.6585714
+## 3 0.33500 0.00000 0.0000000 0.413750 4.706250 0.0000000 0.0000000
+## 4 71.85000 0.00000 0.9714286 14.128571 9.585714 0.2333333 0.0000000
+## 5 37.74286 388.13375 21.6175000 27.933750 24.236250 60.7112500 0.6300000
+## 6 79.00375 11.98875 0.0000000 2.387500 80.837143 58.8800000 6.6450000
+## wheat_a oats_a oth_oil_a fibre_a oth_ind_a fodder_a LEVL_CODE
+## 1 1184.90750 16.321250 20.1725714 1.63875 63.2041071 108.49250 0
+## 2 88.57500 1.909821 1.6210357 0.02500 0.9887619 83.44725 0
+## 3 8.63250 0.397500 0.0737500 0.00000 0.0000000 34.95625 0
+## 4 70.64286 14.028571 0.2571429 0.00000 6.0571429 238.71667 0
+## 5 834.87625 47.745000 61.8150000 0.31125 13.1067857 414.21214 0
+## 6 209.81500 3.721250 0.0787500 12.61500 0.7041071 181.32375 0
+## geo16
+## 1 BG
+## 2 CH
+## 3 CY
+## 4 AL
+## 5 CZ
+## 6 BEcrop.0.area.dat.2013nuts.sum <- crop.0.area.dat.2013nuts %>% group_by(geo) %>% summarise(rye_a = sum(rye_a,na.rm = F),
+ barley_a = sum(barley_a,na.rm = F),
+ maize_a = sum(maize_a,na.rm = F),
+ tritic_a = sum(tritic_a,na.rm = F),
+ sorghum_a = sum(sorghum_a,na.rm = F),
+ oth_cer_a = sum(oth_cer_a,na.rm = F),
+ rice_a = sum(rice_a,na.rm = F),
+ pasture_a = sum(pasture_a,na.rm = F),
+ rape_a = sum(rape_a,na.rm = F),
+ sunflow_a = sum(sunflow_a,na.rm = F),
+ pulses_a = sum(pulses_a,na.rm = F),
+ potato_a = sum(potato_a,na.rm = F),
+ sugbeet_a = sum(sugbeet_a,na.rm = F),
+ oth_rt_a = sum(oth_rt_a,na.rm = F),
+ wheat_a = sum(wheat_a,na.rm = F),
+ oats_a = sum(oats_a,na.rm = F),
+ oth_oil_a = sum(oth_oil_a,na.rm = F),
+ fibre_a = sum(fibre_a,na.rm = F),
+ oth_ind_a = sum(oth_ind_a,na.rm = F),
+ fodder_a = sum(fodder_a,na.rm = F),
+ LEVL_CODE = mean(LEVL_CODE,na.rm = F)
+ )
+head(crop.0.area.dat.2013nuts.sum)## # A tibble: 6 x 22
+## geo rye_a barley_a maize_a tritic_a sorghum_a oth_cer_a rice_a
+## <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
+## 1 AL 1.29 2.74 56.4 0 0 0 0
+## 2 AL0 NA NA NA 0 0 0 0
+## 3 AL01 NA NA NA NA NA NA NA
+## 4 AL011 NA NA NA NA NA NA NA
+## 5 AL012 NA NA NA NA NA NA NA
+## 6 AL013 NA NA NA NA NA NA NA
+## # ... with 14 more variables: pasture_a <dbl>, rape_a <dbl>,
+## # sunflow_a <dbl>, pulses_a <dbl>, potato_a <dbl>, sugbeet_a <dbl>,
+## # oth_rt_a <dbl>, wheat_a <dbl>, oats_a <dbl>, oth_oil_a <dbl>,
+## # fibre_a <dbl>, oth_ind_a <dbl>, fodder_a <dbl>, LEVL_CODE <dbl>nrow(crop.0.area.dat.2013nuts.sum)## [1] 2013#We calculate the fraction of agricultural area within each NUTS0, NUTS1, and NUTS2 area using the UAA from CORINE
+#First, join UAA dataframe to crop area dataframe
+head(corine.aa.all.nuts)## geo sum_uaa
+## 1 AT11 219300.0
+## 2 AT22 411556.2
+## 3 AT12 1004956.2
+## 4 AT13 6075.0
+## 5 AT21 191312.5
+## 6 AT31 582587.5names(crop.0.area.dat.2013nuts.sum)## [1] "geo" "rye_a" "barley_a" "maize_a" "tritic_a"
+## [6] "sorghum_a" "oth_cer_a" "rice_a" "pasture_a" "rape_a"
+## [11] "sunflow_a" "pulses_a" "potato_a" "sugbeet_a" "oth_rt_a"
+## [16] "wheat_a" "oats_a" "oth_oil_a" "fibre_a" "oth_ind_a"
+## [21] "fodder_a" "LEVL_CODE"crop.0.area.dat.2013nuts.sum <- left_join(crop.0.area.dat.2013nuts.sum, corine.aa.all.nuts)## Joining, by = "geo"summary(crop.0.area.dat.2013nuts.sum)## geo rye_a barley_a
+## Length:2013 Min. : 0.0000 Min. : 0.000
+## Class :character 1st Qu.: 0.0788 1st Qu.: 6.327
+## Mode :character Median : 1.0375 Median : 34.400
+## Mean : 16.6161 Mean : 109.456
+## 3rd Qu.: 7.8637 3rd Qu.: 110.820
+## Max. :1051.3000 Max. :2763.500
+## NA's :1620 NA's :1618
+## maize_a tritic_a sorghum_a
+## Min. : 0.0000 Min. : 0.0000 Min. : 0.0000
+## 1st Qu.: 0.0303 1st Qu.: 0.0438 1st Qu.: 0.0000
+## Median : 6.6493 Median : 1.8200 Median : 0.0000
+## Mean : 72.5540 Mean : 22.6732 Mean : 0.9113
+## 3rd Qu.: 55.8162 3rd Qu.: 16.0265 3rd Qu.: 0.0991
+## Max. :2506.1712 Max. :1289.4300 Max. :50.6700
+## NA's :1579 NA's :1666 NA's :1601
+## oth_cer_a rice_a pasture_a
+## Min. : 0.000 Min. : 0.000 Min. : 0.000
+## 1st Qu.: 0.000 1st Qu.: 0.000 1st Qu.: 1.541
+## Median : 0.000 Median : 0.000 Median : 11.745
+## Mean : 1.672 Mean : 3.659 Mean : 74.758
+## 3rd Qu.: 0.308 3rd Qu.: 0.000 3rd Qu.: 48.651
+## Max. :102.924 Max. :230.827 Max. :3091.571
+## NA's :1772 NA's :1555 NA's :1694
+## rape_a sunflow_a pulses_a
+## Min. : 0.0000 Min. : 0.0000 Min. : 0.00
+## 1st Qu.: 0.0475 1st Qu.: 0.0000 1st Qu.: 0.70
+## Median : 4.3913 Median : 0.1112 Median : 4.43
+## Mean : 47.0257 Mean : 34.9245 Mean : 19.76
+## 3rd Qu.: 43.8013 3rd Qu.: 11.1494 3rd Qu.: 16.70
+## Max. :1503.0925 Max. :997.2763 Max. :663.38
+## NA's :1634 NA's :1577 NA's :1624
+## potato_a sugbeet_a oth_rt_a wheat_a
+## Min. : 0.0000 Min. : 0.00 Min. : 0.0000 Min. : 0.000
+## 1st Qu.: 0.9975 1st Qu.: 0.00 1st Qu.: 0.0000 1st Qu.: 4.135
+## Median : 4.4000 Median : 0.84 Median : 0.0000 Median : 74.737
+## Mean : 13.8373 Mean : 13.98 Mean : 0.8507 Mean : 225.763
+## 3rd Qu.: 13.8000 3rd Qu.: 12.68 3rd Qu.: 0.2700 3rd Qu.: 241.577
+## Max. :334.1100 Max. :404.30 Max. :40.0000 Max. :7997.875
+## NA's :1649 NA's :1616 NA's :1756 NA's :1573
+## oats_a oth_oil_a fibre_a
+## Min. : 0.0000 Min. : 0.0000 Min. : 0.0000
+## 1st Qu.: 0.0897 1st Qu.: 0.0000 1st Qu.: 0.0000
+## Median : 3.0342 Median : 0.0779 Median : 0.0000
+## Mean : 22.6225 Mean : 9.3354 Mean : 5.6487
+## 3rd Qu.: 14.2528 3rd Qu.: 2.1159 3rd Qu.: 0.0166
+## Max. :1393.6675 Max. :500.5750 Max. :471.5714
+## NA's :1583 NA's :1535 NA's :1535
+## oth_ind_a fodder_a LEVL_CODE sum_uaa
+## Min. : 0.0000 Min. : 0.000 Min. :0.000 Min. : 56
+## 1st Qu.: 0.0000 1st Qu.: 1.748 1st Qu.:3.000 1st Qu.: 256462
+## Median : 0.0752 Median : 19.852 Median :3.000 Median : 701169
+## Mean : 3.4717 Mean : 76.544 Mean :2.658 Mean : 1469382
+## 3rd Qu.: 1.4688 3rd Qu.: 76.551 3rd Qu.:3.000 3rd Qu.: 1522769
+## Max. :165.6381 Max. :2421.790 Max. :3.000 Max. :33916138
+## NA's :1584 NA's :1594 NA's :1556#Second, calculate the fraction of area
+crop.frac.0 <- as.data.frame(crop.0.area.dat.2013nuts.sum)
+names(crop.frac.0)[2:21] <- gsub("_a", "_f", names(crop.frac.0)[2:21])
+crop.frac.0[,2:21] <- 1000 * crop.0.area.dat.2013nuts.sum[,2:21] / crop.0.area.dat.2013nuts.sum$sum_uaa
+crop.frac.0$total_f <- rowSums(crop.frac.0[,2:21], na.rm = T)
+summary(crop.frac.0)## geo rye_f barley_f maize_f
+## Length:2013 Min. :0.0000 Min. :0.0000 Min. :0.0000
+## Class :character 1st Qu.:0.0002 1st Qu.:0.0166 1st Qu.:0.0001
+## Mode :character Median :0.0012 Median :0.0405 Median :0.0078
+## Mean :0.0076 Mean :0.0523 Mean :0.0325
+## 3rd Qu.:0.0063 3rd Qu.:0.0740 3rd Qu.:0.0348
+## Max. :0.1271 Max. :0.2743 Max. :0.3190
+## NA's :1647 NA's :1645 NA's :1608
+## tritic_f sorghum_f oth_cer_f rice_f
+## Min. :0.0000 Min. :0.0000 Min. :0.0000 Min. :0.0000
+## 1st Qu.:0.0002 1st Qu.:0.0000 1st Qu.:0.0000 1st Qu.:0.0000
+## Median :0.0024 Median :0.0000 Median :0.0000 Median :0.0000
+## Mean :0.0094 Mean :0.0003 Mean :0.0007 Mean :0.0018
+## 3rd Qu.:0.0094 3rd Qu.:0.0001 3rd Qu.:0.0004 3rd Qu.:0.0000
+## Max. :0.1181 Max. :0.0181 Max. :0.0178 Max. :0.1071
+## NA's :1694 NA's :1631 NA's :1780 NA's :1585
+## pasture_f rape_f sunflow_f pulses_f
+## Min. :0.0000 Min. :0.0000 Min. :0.0000 Min. :0.0000
+## 1st Qu.:0.0029 1st Qu.:0.0002 1st Qu.:0.0000 1st Qu.:0.0015
+## Median :0.0167 Median :0.0068 Median :0.0001 Median :0.0043
+## Mean :0.0496 Mean :0.0237 Mean :0.0138 Mean :0.0078
+## 3rd Qu.:0.0617 3rd Qu.:0.0379 3rd Qu.:0.0071 3rd Qu.:0.0107
+## Max. :0.4127 Max. :0.1462 Max. :0.2186 Max. :0.0648
+## NA's :1722 NA's :1662 NA's :1606 NA's :1651
+## potato_f sugbeet_f oth_rt_f wheat_f
+## Min. :0.0000 Min. :0.0000 Min. :0.0000 Min. :0.0000
+## 1st Qu.:0.0020 1st Qu.:0.0000 1st Qu.:0.0000 1st Qu.:0.0161
+## Median :0.0049 Median :0.0012 Median :0.0000 Median :0.0993
+## Mean :0.0139 Mean :0.0102 Mean :0.0005 Mean :0.1106
+## 3rd Qu.:0.0120 3rd Qu.:0.0108 3rd Qu.:0.0002 3rd Qu.:0.1718
+## Max. :0.2714 Max. :0.2914 Max. :0.0099 Max. :1.0457
+## NA's :1676 NA's :1644 NA's :1759 NA's :1603
+## oats_f oth_oil_f fibre_f oth_ind_f
+## Min. :0.0000 Min. :0.0000 Min. :0.0000 Min. :0.0000
+## 1st Qu.:0.0003 1st Qu.:0.0000 1st Qu.:0.0000 1st Qu.:0.0000
+## Median :0.0038 Median :0.0001 Median :0.0000 Median :0.0001
+## Mean :0.0108 Mean :0.0042 Mean :0.0033 Mean :0.0016
+## 3rd Qu.:0.0123 3rd Qu.:0.0018 3rd Qu.:0.0000 3rd Qu.:0.0011
+## Max. :0.1913 Max. :0.1905 Max. :0.1514 Max. :0.0356
+## NA's :1613 NA's :1565 NA's :1565 NA's :1614
+## fodder_f LEVL_CODE sum_uaa total_f
+## Min. :0.0000 Min. :0.000 Min. : 56 Min. :0.00000
+## 1st Qu.:0.0073 1st Qu.:3.000 1st Qu.: 256462 1st Qu.:0.00000
+## Median :0.0280 Median :3.000 Median : 701169 Median :0.00000
+## Mean :0.0417 Mean :2.658 Mean : 1469382 Mean :0.07397
+## 3rd Qu.:0.0593 3rd Qu.:3.000 3rd Qu.: 1522769 3rd Qu.:0.00000
+## Max. :0.3323 Max. :3.000 Max. :33916138 Max. :2.89208
+## NA's :1624 NA's :1556#Spurious fractions
+crop.frac.0[which(crop.frac.0$total_f > 1), 'geo']## [1] "BE1" "BE10"crop.frac.0[which(crop.frac.0$wheat_f > 1), 'geo'] ## [1] "BE1" "BE10"as.data.frame(crop.0.area.dat.2013nuts.sum[which(crop.0.area.dat.2013nuts.sum$geo %in% c("BE1", "BE10")),]) ## geo rye_a barley_a maize_a tritic_a sorghum_a oth_cer_a
+## 1 BE1 0.001428571 0.12 0.07142857 0.01428571 0 0.004
+## 2 BE10 0.001428571 0.12 0.07142857 0.01428571 0 0.004
+## rice_a pasture_a rape_a sunflow_a pulses_a potato_a sugbeet_a oth_rt_a
+## 1 0 0.11 0.055 0 0.00875 0.11875 0.1275 0.002
+## 2 0 0.11 0.055 0 0.00875 0.11875 0.1275 0.002
+## wheat_a oats_a oth_oil_a fibre_a oth_ind_a fodder_a LEVL_CODE
+## 1 0.4575 0.01428571 0 0.04 0 0.1203571 1
+## 2 0.4575 0.01428571 0 0.04 0 0.1203571 2
+## sum_uaa
+## 1 437.5
+## 2 437.5#The Brussels region (BE10) has wheat fraction > 1, and total fraction >> 1, so we will give NA
+crop.frac.0[which(crop.frac.0$geo %in% c("BE1", "BE10")), c(2:21,24)] <- NA
+crop.frac.0[which(crop.frac.0$geo %in% c("BE1", "BE10")),]## geo rye_f barley_f maize_f tritic_f sorghum_f oth_cer_f rice_f
+## 67 BE1 NA NA NA NA NA NA NA
+## 68 BE10 NA NA NA NA NA NA NA
+## pasture_f rape_f sunflow_f pulses_f potato_f sugbeet_f oth_rt_f wheat_f
+## 67 NA NA NA NA NA NA NA NA
+## 68 NA NA NA NA NA NA NA NA
+## oats_f oth_oil_f fibre_f oth_ind_f fodder_f LEVL_CODE sum_uaa total_f
+## 67 NA NA NA NA NA 1 437.5 NA
+## 68 NA NA NA NA NA 2 437.5 NA#Next, replace NA's in crop area with zero areas, where data exist
+summary(crop.frac)## geo rye_f barley_f maize_f
+## Length:2013 Min. :0.0000 Min. :0.0003 Min. :0.0001
+## Class :character 1st Qu.:0.0005 1st Qu.:0.0199 1st Qu.:0.0035
+## Mode :character Median :0.0021 Median :0.0420 Median :0.0190
+## Mean :0.0089 Mean :0.0535 Mean :0.0411
+## 3rd Qu.:0.0080 3rd Qu.:0.0761 3rd Qu.:0.0534
+## Max. :0.1271 Max. :0.2253 Max. :0.3190
+## NA's :1698 NA's :1663 NA's :1701
+## tritic_f sorghum_f oth_cer_f rice_f
+## Min. :0.0000 Min. :0.0000 Min. :0.0000 Min. :0.0000
+## 1st Qu.:0.0013 1st Qu.:0.0001 1st Qu.:0.0003 1st Qu.:0.0006
+## Median :0.0045 Median :0.0004 Median :0.0007 Median :0.0024
+## Mean :0.0114 Mean :0.0010 Mean :0.0016 Mean :0.0094
+## 3rd Qu.:0.0116 3rd Qu.:0.0010 3rd Qu.:0.0018 3rd Qu.:0.0080
+## Max. :0.1181 Max. :0.0181 Max. :0.0178 Max. :0.1071
+## NA's :1755 NA's :1880 NA's :1920 NA's :1929
+## pasture_f rape_f sunflow_f pulses_f
+## Min. :0.0000 Min. :0.0000 Min. :0.0000 Min. :0.0001
+## 1st Qu.:0.0086 1st Qu.:0.0020 1st Qu.:0.0004 1st Qu.:0.0021
+## Median :0.0235 Median :0.0176 Median :0.0041 Median :0.0045
+## Mean :0.0581 Mean :0.0288 Mean :0.0232 Mean :0.0085
+## 3rd Qu.:0.0816 3rd Qu.:0.0469 3rd Qu.:0.0222 3rd Qu.:0.0116
+## Max. :0.4127 Max. :0.1462 Max. :0.2186 Max. :0.0648
+## NA's :1773 NA's :1731 NA's :1770 NA's :1675
+## potato_f sugbeet_f oth_rt_f wheat_f
+## Min. :0.0000 Min. :0.0000 Min. :0.0000 Min. :0.0002
+## 1st Qu.:0.0022 1st Qu.:0.0012 1st Qu.:0.0001 1st Qu.:0.0518
+## Median :0.0051 Median :0.0067 Median :0.0003 Median :0.1194
+## Mean :0.0129 Mean :0.0131 Mean :0.0012 Mean :0.1234
+## 3rd Qu.:0.0123 3rd Qu.:0.0164 3rd Qu.:0.0010 3rd Qu.:0.1801
+## Max. :0.1882 Max. :0.1137 Max. :0.0123 Max. :0.3899
+## NA's :1690 NA's :1770 NA's :1895 NA's :1662
+## oats_f oth_oil_f fibre_f oth_ind_f
+## Min. :0.0001 Min. :0.0000 Min. :0.0000 Min. :0.0000
+## 1st Qu.:0.0021 1st Qu.:0.0004 1st Qu.:0.0000 1st Qu.:0.0002
+## Median :0.0063 Median :0.0018 Median :0.0002 Median :0.0007
+## Mean :0.0135 Mean :0.0089 Mean :0.0087 Mean :0.0025
+## 3rd Qu.:0.0150 3rd Qu.:0.0078 3rd Qu.:0.0050 3rd Qu.:0.0023
+## Max. :0.1913 Max. :0.1905 Max. :0.1514 Max. :0.0356
+## NA's :1694 NA's :1766 NA's :1861 NA's :1754
+## fodder_f LEVL_CODE sum_uaa total_f
+## Min. :0.0002 Min. :0.000 Min. : 56 Min. :0.00000
+## 1st Qu.:0.0179 1st Qu.:3.000 1st Qu.: 256462 1st Qu.:0.00000
+## Median :0.0393 Median :3.000 Median : 701169 Median :0.00000
+## Mean :0.0503 Mean :2.658 Mean : 1469382 Mean :0.07172
+## 3rd Qu.:0.0691 3rd Qu.:3.000 3rd Qu.: 1522769 3rd Qu.:0.00000
+## Max. :0.3323 Max. :3.000 Max. :33916138 Max. :0.80077
+## NA's :1695 NA's :1556 NA's :2summary(crop.frac.0)## geo rye_f barley_f maize_f
+## Length:2013 Min. :0.0000 Min. :0.0000 Min. :0.0000
+## Class :character 1st Qu.:0.0002 1st Qu.:0.0165 1st Qu.:0.0001
+## Mode :character Median :0.0012 Median :0.0399 Median :0.0077
+## Mean :0.0077 Mean :0.0510 Mean :0.0318
+## 3rd Qu.:0.0063 3rd Qu.:0.0721 3rd Qu.:0.0346
+## Max. :0.1271 Max. :0.2253 Max. :0.3190
+## NA's :1649 NA's :1647 NA's :1610
+## tritic_f sorghum_f oth_cer_f rice_f
+## Min. :0.0000 Min. :0.0000 Min. :0.0000 Min. :0.0000
+## 1st Qu.:0.0002 1st Qu.:0.0000 1st Qu.:0.0000 1st Qu.:0.0000
+## Median :0.0024 Median :0.0000 Median :0.0000 Median :0.0000
+## Mean :0.0092 Mean :0.0003 Mean :0.0006 Mean :0.0018
+## 3rd Qu.:0.0093 3rd Qu.:0.0001 3rd Qu.:0.0004 3rd Qu.:0.0000
+## Max. :0.1181 Max. :0.0181 Max. :0.0178 Max. :0.1071
+## NA's :1696 NA's :1633 NA's :1782 NA's :1587
+## pasture_f rape_f sunflow_f pulses_f
+## Min. :0.0000 Min. :0.0000 Min. :0.0000 Min. :0.0000
+## 1st Qu.:0.0028 1st Qu.:0.0002 1st Qu.:0.0000 1st Qu.:0.0014
+## Median :0.0165 Median :0.0066 Median :0.0001 Median :0.0042
+## Mean :0.0482 Mean :0.0231 Mean :0.0139 Mean :0.0078
+## 3rd Qu.:0.0604 3rd Qu.:0.0378 3rd Qu.:0.0072 3rd Qu.:0.0104
+## Max. :0.4127 Max. :0.1462 Max. :0.2186 Max. :0.0648
+## NA's :1724 NA's :1664 NA's :1608 NA's :1653
+## potato_f sugbeet_f oth_rt_f wheat_f
+## Min. :0.0000 Min. :0.0000 Min. :0.0000 Min. :0.0000
+## 1st Qu.:0.0019 1st Qu.:0.0000 1st Qu.:0.0000 1st Qu.:0.0158
+## Median :0.0049 Median :0.0012 Median :0.0000 Median :0.0989
+## Mean :0.0124 Mean :0.0086 Mean :0.0005 Mean :0.1060
+## 3rd Qu.:0.0117 3rd Qu.:0.0103 3rd Qu.:0.0002 3rd Qu.:0.1708
+## Max. :0.1882 Max. :0.1137 Max. :0.0099 Max. :0.3899
+## NA's :1678 NA's :1646 NA's :1761 NA's :1605
+## oats_f oth_oil_f fibre_f oth_ind_f
+## Min. :0.0000 Min. :0.0000 Min. :0.0000 Min. :0.0000
+## 1st Qu.:0.0003 1st Qu.:0.0000 1st Qu.:0.0000 1st Qu.:0.0000
+## Median :0.0037 Median :0.0001 Median :0.0000 Median :0.0001
+## Mean :0.0106 Mean :0.0043 Mean :0.0029 Mean :0.0016
+## 3rd Qu.:0.0121 3rd Qu.:0.0019 3rd Qu.:0.0000 3rd Qu.:0.0011
+## Max. :0.1913 Max. :0.1905 Max. :0.1514 Max. :0.0356
+## NA's :1615 NA's :1567 NA's :1567 NA's :1616
+## fodder_f LEVL_CODE sum_uaa total_f
+## Min. :0.0000 Min. :0.000 Min. : 56 Min. :0.00000
+## 1st Qu.:0.0073 1st Qu.:3.000 1st Qu.: 256462 1st Qu.:0.00000
+## Median :0.0276 Median :3.000 Median : 701169 Median :0.00000
+## Mean :0.0405 Mean :2.658 Mean : 1469382 Mean :0.07117
+## 3rd Qu.:0.0582 3rd Qu.:3.000 3rd Qu.: 1522769 3rd Qu.:0.00000
+## Max. :0.3323 Max. :3.000 Max. :33916138 Max. :0.80004
+## NA's :1626 NA's :1556 NA's :2crop.frac.rep <- crop.frac
+for(e in crop.frac.rep$geo) {
+ for(i in names(crop.frac.rep)[2:21]) {
+ crop.frac.rep[crop.frac.rep$geo == e,i] <- ifelse(is.na(crop.frac.rep[crop.frac.rep$geo == e,i]), crop.frac.0[crop.frac.0$geo == e, i], crop.frac[crop.frac$geo == e, i])
+ }
+}
+
+summary(crop.frac.rep)## geo rye_f barley_f maize_f
+## Length:2013 Min. :0.0000 Min. :0.0000 Min. :0.0000
+## Class :character 1st Qu.:0.0003 1st Qu.:0.0167 1st Qu.:0.0002
+## Mode :character Median :0.0012 Median :0.0405 Median :0.0077
+## Mean :0.0077 Mean :0.0512 Mean :0.0319
+## 3rd Qu.:0.0064 3rd Qu.:0.0721 3rd Qu.:0.0346
+## Max. :0.1271 Max. :0.2253 Max. :0.3190
+## NA's :1649 NA's :1647 NA's :1610
+## tritic_f sorghum_f oth_cer_f rice_f
+## Min. :0.0000 Min. :0.0000 Min. :0.0000 Min. :0.0000
+## 1st Qu.:0.0003 1st Qu.:0.0000 1st Qu.:0.0000 1st Qu.:0.0000
+## Median :0.0024 Median :0.0000 Median :0.0000 Median :0.0000
+## Mean :0.0093 Mean :0.0003 Mean :0.0006 Mean :0.0019
+## 3rd Qu.:0.0093 3rd Qu.:0.0001 3rd Qu.:0.0004 3rd Qu.:0.0000
+## Max. :0.1181 Max. :0.0181 Max. :0.0178 Max. :0.1071
+## NA's :1696 NA's :1633 NA's :1782 NA's :1587
+## pasture_f rape_f sunflow_f pulses_f
+## Min. :0.0000 Min. :0.0000 Min. :0.0000 Min. :0.0000
+## 1st Qu.:0.0028 1st Qu.:0.0002 1st Qu.:0.0000 1st Qu.:0.0015
+## Median :0.0167 Median :0.0072 Median :0.0002 Median :0.0043
+## Mean :0.0483 Mean :0.0233 Mean :0.0139 Mean :0.0079
+## 3rd Qu.:0.0604 3rd Qu.:0.0379 3rd Qu.:0.0072 3rd Qu.:0.0106
+## Max. :0.4127 Max. :0.1462 Max. :0.2186 Max. :0.0648
+## NA's :1724 NA's :1664 NA's :1608 NA's :1653
+## potato_f sugbeet_f oth_rt_f wheat_f
+## Min. :0.0000 Min. :0.0000 Min. :0.0000 Min. :0.0000
+## 1st Qu.:0.0020 1st Qu.:0.0000 1st Qu.:0.0000 1st Qu.:0.0158
+## Median :0.0049 Median :0.0012 Median :0.0000 Median :0.0993
+## Mean :0.0124 Mean :0.0087 Mean :0.0006 Mean :0.1061
+## 3rd Qu.:0.0120 3rd Qu.:0.0103 3rd Qu.:0.0002 3rd Qu.:0.1715
+## Max. :0.1882 Max. :0.1137 Max. :0.0123 Max. :0.3899
+## NA's :1678 NA's :1646 NA's :1761 NA's :1605
+## oats_f oth_oil_f fibre_f oth_ind_f
+## Min. :0.0000 Min. :0.0000 Min. :0.0000 Min. :0.0000
+## 1st Qu.:0.0004 1st Qu.:0.0000 1st Qu.:0.0000 1st Qu.:0.0000
+## Median :0.0039 Median :0.0001 Median :0.0000 Median :0.0002
+## Mean :0.0108 Mean :0.0050 Mean :0.0030 Mean :0.0017
+## 3rd Qu.:0.0121 3rd Qu.:0.0024 3rd Qu.:0.0000 3rd Qu.:0.0011
+## Max. :0.1913 Max. :0.1905 Max. :0.1514 Max. :0.0356
+## NA's :1615 NA's :1567 NA's :1567 NA's :1616
+## fodder_f LEVL_CODE sum_uaa total_f
+## Min. :0.0000 Min. :0.000 Min. : 56 Min. :0.00000
+## 1st Qu.:0.0073 1st Qu.:3.000 1st Qu.: 256462 1st Qu.:0.00000
+## Median :0.0287 Median :3.000 Median : 701169 Median :0.00000
+## Mean :0.0413 Mean :2.658 Mean : 1469382 Mean :0.07172
+## 3rd Qu.:0.0599 3rd Qu.:3.000 3rd Qu.: 1522769 3rd Qu.:0.00000
+## Max. :0.3323 Max. :3.000 Max. :33916138 Max. :0.80077
+## NA's :1626 NA's :1556 NA's :2#Finally, run script to allocate NUTS1 or NUTS0 fractions to NUTS2 where needed
+
+#list to summarise where data are NUTS2, 1, 0 for each variable
+data.level.crop.f.0 <- vector("list", 4*length(names(crop.frac.rep)[2:21]))
+names(data.level.crop.f.0) <- c(paste(names(crop.frac.rep)[2:21], 'n2.dat', sep='.'),
+ paste(names(crop.frac.rep)[2:21], 'n1.dat', sep='.'),
+ paste(names(crop.frac.rep)[2:21], 'n0.dat', sep='.'),
+ paste(names(crop.frac.rep)[2:21], 'nuts0.na', sep='.')
+ )
+labels(data.level.crop.f.0)## [1] "rye_f.n2.dat" "barley_f.n2.dat" "maize_f.n2.dat"
+## [4] "tritic_f.n2.dat" "sorghum_f.n2.dat" "oth_cer_f.n2.dat"
+## [7] "rice_f.n2.dat" "pasture_f.n2.dat" "rape_f.n2.dat"
+## [10] "sunflow_f.n2.dat" "pulses_f.n2.dat" "potato_f.n2.dat"
+## [13] "sugbeet_f.n2.dat" "oth_rt_f.n2.dat" "wheat_f.n2.dat"
+## [16] "oats_f.n2.dat" "oth_oil_f.n2.dat" "fibre_f.n2.dat"
+## [19] "oth_ind_f.n2.dat" "fodder_f.n2.dat" "rye_f.n1.dat"
+## [22] "barley_f.n1.dat" "maize_f.n1.dat" "tritic_f.n1.dat"
+## [25] "sorghum_f.n1.dat" "oth_cer_f.n1.dat" "rice_f.n1.dat"
+## [28] "pasture_f.n1.dat" "rape_f.n1.dat" "sunflow_f.n1.dat"
+## [31] "pulses_f.n1.dat" "potato_f.n1.dat" "sugbeet_f.n1.dat"
+## [34] "oth_rt_f.n1.dat" "wheat_f.n1.dat" "oats_f.n1.dat"
+## [37] "oth_oil_f.n1.dat" "fibre_f.n1.dat" "oth_ind_f.n1.dat"
+## [40] "fodder_f.n1.dat" "rye_f.n0.dat" "barley_f.n0.dat"
+## [43] "maize_f.n0.dat" "tritic_f.n0.dat" "sorghum_f.n0.dat"
+## [46] "oth_cer_f.n0.dat" "rice_f.n0.dat" "pasture_f.n0.dat"
+## [49] "rape_f.n0.dat" "sunflow_f.n0.dat" "pulses_f.n0.dat"
+## [52] "potato_f.n0.dat" "sugbeet_f.n0.dat" "oth_rt_f.n0.dat"
+## [55] "wheat_f.n0.dat" "oats_f.n0.dat" "oth_oil_f.n0.dat"
+## [58] "fibre_f.n0.dat" "oth_ind_f.n0.dat" "fodder_f.n0.dat"
+## [61] "rye_f.nuts0.na" "barley_f.nuts0.na" "maize_f.nuts0.na"
+## [64] "tritic_f.nuts0.na" "sorghum_f.nuts0.na" "oth_cer_f.nuts0.na"
+## [67] "rice_f.nuts0.na" "pasture_f.nuts0.na" "rape_f.nuts0.na"
+## [70] "sunflow_f.nuts0.na" "pulses_f.nuts0.na" "potato_f.nuts0.na"
+## [73] "sugbeet_f.nuts0.na" "oth_rt_f.nuts0.na" "wheat_f.nuts0.na"
+## [76] "oats_f.nuts0.na" "oth_oil_f.nuts0.na" "fibre_f.nuts0.na"
+## [79] "oth_ind_f.nuts0.na" "fodder_f.nuts0.na"dbase.crop <- as.data.frame(matrix(nrow=nrow(nuts@data), ncol=(ncol(crop.frac.rep[,2:21]) + 1)))
+dbase.crop[,1] <- nuts@data$NUTS_ID
+names(dbase.crop) <- c("NUTS_ID", names(crop.frac.rep)[2:21])
+head(dbase.crop)## NUTS_ID rye_f barley_f maize_f tritic_f sorghum_f oth_cer_f rice_f
+## 1 AT11 NA NA NA NA NA NA NA
+## 2 AT22 NA NA NA NA NA NA NA
+## 3 AT12 NA NA NA NA NA NA NA
+## 4 AT13 NA NA NA NA NA NA NA
+## 5 AT21 NA NA NA NA NA NA NA
+## 6 AT31 NA NA NA NA NA NA NA
+## pasture_f rape_f sunflow_f pulses_f potato_f sugbeet_f oth_rt_f wheat_f
+## 1 NA NA NA NA NA NA NA NA
+## 2 NA NA NA NA NA NA NA NA
+## 3 NA NA NA NA NA NA NA NA
+## 4 NA NA NA NA NA NA NA NA
+## 5 NA NA NA NA NA NA NA NA
+## 6 NA NA NA NA NA NA NA NA
+## oats_f oth_oil_f fibre_f oth_ind_f fodder_f
+## 1 NA NA NA NA NA
+## 2 NA NA NA NA NA
+## 3 NA NA NA NA NA
+## 4 NA NA NA NA NA
+## 5 NA NA NA NA NA
+## 6 NA NA NA NA NAnrow(dbase.crop)## [1] 320attach(crop.frac.rep)
+for(i in names(crop.frac.rep)[2:21]) {
+ (nuts2.na <- crop.frac.rep[LEVL_CODE == 2 & is.na(crop.frac.rep[,i]), 'geo'])
+ (nuts1 <- crop.frac.rep[LEVL_CODE == 1 & geo %in% gsub(".{1}$", "", nuts2.na), 'geo'])
+ (nuts1.na <- crop.frac.rep[geo %in% nuts1 & is.na(crop.frac.rep[,i]), 'geo'])
+ (nuts0 <- crop.frac.rep[LEVL_CODE == 0 & geo %in% gsub(".{1}$", "", nuts1.na), 'geo'])
+ (nuts0.na <- crop.frac.rep[geo %in% nuts0 & is.na(crop.frac.rep[,i]), 'geo'])
+
+#NUTS2 data
+(n2.dat <- crop.frac.rep[!(geo %in% nuts2.na) & LEVL_CODE == 2, 'geo'])
+#NUTS1 data
+(n1.dat <- nuts1[!nuts1 %in% nuts1.na])
+#NUTS0 data
+(n0.dat <- nuts0[!nuts0 %in% nuts0.na])
+#NO DATA
+nuts0.na
+
+data.level.crop.f.0[[paste(i, 'n2.dat', sep='.')]] <- n2.dat
+data.level.crop.f.0[[paste(i, 'n1.dat', sep='.')]] <- n1.dat
+data.level.crop.f.0[[paste(i, 'n0.dat', sep='.')]] <- n0.dat
+data.level.crop.f.0[[paste(i, 'nuts0.na', sep='.')]] <- nuts0.na
+
+ for(e in n0.dat) {
+ dbase.crop[dbase.crop$NUTS_ID %in% dbase.crop$NUTS_ID[grep(paste(e, '..', sep=''), dbase.crop$NUTS_ID)], i] <- crop.frac.rep[crop.frac.rep$geo == e, i]
+ }
+
+ for(e in n1.dat) {
+ dbase.crop[dbase.crop$NUTS_ID %in% dbase.crop$NUTS_ID[grep(paste(e, '.', sep=''), dbase.crop$NUTS_ID)], i] <- crop.frac.rep[crop.frac.rep$geo == e, i]
+ }
+
+ for(e in n2.dat) {
+ dbase.crop[dbase.crop$NUTS_ID == e, i] <- crop.frac.rep[crop.frac.rep$geo == e, i]
+ }
+}
+detach(crop.frac.rep)
+
+summary(dbase.crop)## NUTS_ID rye_f barley_f maize_f
+## AT11 : 1 Min. :0.0000000 Min. :0.00000 Min. :0.000000
+## AT12 : 1 1st Qu.:0.0001763 1st Qu.:0.01824 1st Qu.:0.000236
+## AT13 : 1 Median :0.0010613 Median :0.04720 Median :0.008416
+## AT21 : 1 Mean :0.0078947 Mean :0.05499 Mean :0.029646
+## AT22 : 1 3rd Qu.:0.0069115 3rd Qu.:0.08157 3rd Qu.:0.033520
+## AT31 : 1 Max. :0.1270547 Max. :0.22525 Max. :0.319030
+## (Other):314 NA's :1 NA's :1 NA's :1
+## tritic_f sorghum_f oth_cer_f
+## Min. :0.0000000 Min. :0.0000000 Min. :0.00000
+## 1st Qu.:0.0006165 1st Qu.:0.0000000 1st Qu.:0.00000
+## Median :0.0028821 Median :0.0000000 Median :0.00008
+## Mean :0.0090348 Mean :0.0003367 Mean :0.00097
+## 3rd Qu.:0.0101557 3rd Qu.:0.0000793 3rd Qu.:0.00128
+## Max. :0.1181380 Max. :0.0180664 Max. :0.01778
+## NA's :1 NA's :1 NA's :65
+## rice_f pasture_f rape_f
+## Min. :0.000000 Min. :0.000000 Min. :0.0000000
+## 1st Qu.:0.000000 1st Qu.:0.006223 1st Qu.:0.0002153
+## Median :0.000000 Median :0.021880 Median :0.0125632
+## Mean :0.001738 Mean :0.047618 Mean :0.0268691
+## 3rd Qu.:0.000000 3rd Qu.:0.084760 3rd Qu.:0.0427553
+## Max. :0.107097 Max. :0.412707 Max. :0.1461908
+## NA's :1 NA's :8 NA's :1
+## sunflow_f pulses_f potato_f
+## Min. :0.000000 Min. :0.000000 Min. :0.000000
+## 1st Qu.:0.000000 1st Qu.:0.001809 1st Qu.:0.002072
+## Median :0.000192 Median :0.004299 Median :0.005518
+## Mean :0.011671 Mean :0.008475 Mean :0.012031
+## 3rd Qu.:0.004120 3rd Qu.:0.011267 3rd Qu.:0.013376
+## Max. :0.218639 Max. :0.064771 Max. :0.188248
+## NA's :1 NA's :1 NA's :1
+## sugbeet_f oth_rt_f wheat_f
+## Min. :0.000000 Min. :0.00000 Min. :0.000000
+## 1st Qu.:0.000000 1st Qu.:0.00000 1st Qu.:0.006516
+## Median :0.001072 Median :0.00015 Median :0.103025
+## Mean :0.009541 Mean :0.00091 Mean :0.103869
+## 3rd Qu.:0.013027 3rd Qu.:0.00108 3rd Qu.:0.170883
+## Max. :0.113660 Max. :0.01231 Max. :0.389937
+## NA's :1 NA's :35 NA's :1
+## oats_f oth_oil_f fibre_f
+## Min. :0.0000000 Min. :0.000000 Min. :0.0000000
+## 1st Qu.:0.0002925 1st Qu.:0.000000 1st Qu.:0.0000000
+## Median :0.0037227 Median :0.000000 Median :0.0000000
+## Mean :0.0096505 Mean :0.004699 Mean :0.0030096
+## 3rd Qu.:0.0106135 3rd Qu.:0.001537 3rd Qu.:0.0000127
+## Max. :0.1912935 Max. :0.190498 Max. :0.1513896
+## NA's :1 NA's :1 NA's :1
+## oth_ind_f fodder_f
+## Min. :0.0000000 Min. :0.000000
+## 1st Qu.:0.0000000 1st Qu.:0.007706
+## Median :0.0002218 Median :0.032609
+## Mean :0.0015573 Mean :0.045518
+## 3rd Qu.:0.0010943 3rd Qu.:0.069995
+## Max. :0.0356431 Max. :0.253901
+## NA's :1 NA's :1head(dbase.crop)## NUTS_ID rye_f barley_f maize_f tritic_f sorghum_f
+## 1 AT11 0.023158915 0.04191746 0.10322047 0.010459416 0.0019037848
+## 2 AT22 0.004659144 0.02072924 0.12555999 0.009728318 0.0014761044
+## 3 AT12 0.031413059 0.08222000 0.06573296 0.023418930 0.0008681970
+## 4 AT13 0.040740741 0.04567901 0.02242798 0.008436214 0.0016460905
+## 5 AT21 0.004181640 0.02944136 0.08118262 0.016478275 0.0003136230
+## 6 AT31 0.013497972 0.07211149 0.08582187 0.027766215 0.0001695024
+## oth_cer_f rice_f pasture_f rape_f sunflow_f pulses_f
+## 1 0.0088828089 0 0.016951664 0.042230962 0.0163702690 0.017379161
+## 2 0.0007775365 0 0.029889596 0.001075187 0.0006074504 0.001716047
+## 3 0.0051265913 0 0.016059157 0.028237548 0.0174845920 0.012741848
+## 4 0.0177777778 0 0.002674897 0.032921811 0.0039976484 0.014403292
+## 5 0.0009722313 0 0.053812480 0.000313623 0.0008232604 0.003711205
+## 6 0.0007895810 0 0.014203875 0.018338447 0.0007960178 0.007065462
+## potato_f sugbeet_f oth_rt_f wheat_f oats_f oth_oil_f
+## 1 0.004103967 0.0187300502 7.295942e-05 0.22119243 0.006499088 0.08481532
+## 2 0.001737308 0.0006074504 4.373643e-05 0.01938374 0.002786982 0.04561345
+## 3 0.017488323 0.0360314193 6.567450e-05 0.19060904 0.014256840 0.02270124
+## 4 0.013374486 0.0467078189 0.000000e+00 0.24773663 0.003621399 0.01255144
+## 5 0.001973211 0.0001045410 0.000000e+00 0.01787216 0.006377001 0.01950996
+## 6 0.002589740 0.0100478469 9.955586e-05 0.08748686 0.017608514 0.02501556
+## fibre_f oth_ind_f fodder_f
+## 1 2.735978e-04 0.0009746922 0.04886001
+## 2 7.289405e-05 0.0005181552 0.04823763
+## 3 4.796229e-04 0.0029031115 0.06777658
+## 4 0.000000e+00 0.0016460905 0.03168724
+## 5 5.227050e-05 0.0002744201 0.07297615
+## 6 1.235866e-04 0.0026176325 0.09126311tail(dbase.crop)## NUTS_ID rye_f barley_f maize_f tritic_f sorghum_f
+## 315 UKD3 0.000000000 0.05408133 0.00000000 0.0012613721 0
+## 316 TRC1 0.000000000 0.10890637 0.01116988 0.0000000000 0
+## 317 TRC2 0.000000000 0.11965185 0.04140112 0.0000000000 0
+## 318 UKD4 0.000000000 0.05408133 0.00000000 0.0012613721 0
+## 319 TRC3 0.000000000 0.04446833 0.06607323 0.0000000000 0
+## 320 UKM6 0.002408652 0.14945685 0.00000000 0.0004817304 0
+## oth_cer_f rice_f pasture_f rape_f sunflow_f
+## 315 0.0000000000 0.000000000 0.08475975 0.006622203 0.000000000
+## 316 0.0002398355 0.000000000 0.00000000 0.000000000 0.001074027
+## 317 0.0004376439 0.001050345 0.00000000 0.000000000 0.001838105
+## 318 0.0000000000 0.000000000 0.08475975 0.006622203 0.000000000
+## 319 0.0002398355 0.000000000 0.00000000 0.000000000 0.001247144
+## 320 0.0000000000 0.000000000 0.08475975 0.017041212 0.000000000
+## pulses_f potato_f sugbeet_f oth_rt_f wheat_f
+## 315 0.002838087 1.009098e-02 0.0010721662 0.002890765 0.0000000
+## 316 0.049190452 2.148055e-04 0.0012888328 0.000000000 0.2053540
+## 317 0.064771304 4.376439e-05 0.0004376439 0.000000000 0.3008364
+## 318 0.002838087 1.009098e-02 0.0010721662 0.002890765 0.0000000
+## 319 0.059570786 0.000000e+00 0.0003357697 0.000000000 0.3899369
+## 320 0.002167787 1.337605e-02 0.0000000000 0.002890765 0.0000000
+## oats_f oth_oil_f fibre_f oth_ind_f fodder_f
+## 315 0.0000000000 0.00000000 0.00000000 0.000000000 0.000000000
+## 316 0.0000000000 0.02577666 0.01997691 0.006444164 0.014320364
+## 317 0.0001750576 0.10809805 0.10678512 0.000000000 0.007294066
+## 318 0.0000000000 0.00000000 0.00000000 0.000000000 0.000000000
+## 319 0.0000000000 0.03356101 0.02202441 0.001048781 0.013284565
+## 320 0.0000000000 0.00000000 0.00000000 0.000000000 0.000000000#check data level for rye_f as an example
+length(data.level.crop.f.0$rye_f.n2.dat)## [1] 229length(data.level.crop.f.0$rye_f.n1.dat)## [1] 34data.level.crop.f.0$rye_f.n0.dat## [1] "BE" "LU" "ME" "MK"data.level.crop.f.0$rye_f.nuts0.na## [1] "AL" "LI" "RS"#Here we manually calculate yields, using only those NUTS regions that have area > 0 for each crop.
+
+crop.prod.dat <- read.csv("C:/Users/mu5106sc/Dropbox/STAGS/SDG_data_eurostat/Final_database/Crop_area_yield/cropprod_no_0s_mean_allnuts.csv", head=T)
+
+head(crop.area.dat)## geo rye_a barley_a maize_a tritic_a sorghum_a oth_cer_a rice_a
+## 1 BG 10.707500 186.503750 416.77125 13.81375 4.635 4.0450000 11.2175
+## 2 CH 1.986250 28.315000 15.33500 9.06875 NA 0.1116667 0.0800
+## 3 CY NA 20.810000 NA 0.42500 NA NA NA
+## 4 AL 1.285714 2.742857 56.44286 NA NA NA NA
+## 5 CZ 27.141250 357.867500 98.95625 43.45875 NA 5.3400000 NA
+## 6 BE 0.606250 46.607500 63.19125 5.85875 NA 3.2157143 NA
+## pasture_a rape_a sunflow_a pulses_a potato_a sugbeet_a oth_rt_a
+## 1 0.72750 175.64875 813.4100000 20.115000 12.512500 0.01000 0.1914286
+## 2 117.22000 21.79750 4.1087500 4.702857 11.072500 19.47500 0.6585714
+## 3 0.33500 NA NA 0.413750 4.706250 NA NA
+## 4 143.70000 NA 0.9714286 14.128571 9.585714 0.70000 NA
+## 5 37.74286 388.13375 21.6175000 27.933750 24.236250 60.71125 0.6300000
+## 6 79.00375 11.98875 NA 2.387500 80.837143 58.88000 7.5942857
+## wheat_a oats_a oth_oil_a fibre_a oth_ind_a fodder_a
+## 1 1184.90750 16.499750 20.2690000 1.8728571 64.7175000 110.37167
+## 2 88.57500 1.937917 1.6210357 0.0500000 1.2264286 189.00375
+## 3 9.51375 0.397500 0.0737500 NA NA 34.95625
+## 4 70.64286 14.028571 0.2571429 NA 6.0571429 238.71667
+## 5 834.87625 47.745000 61.8150000 0.3642857 13.1067857 414.21214
+## 6 209.81500 3.721250 0.1466667 12.8037500 0.7129167 181.32375
+## LEVL_CODE
+## 1 0
+## 2 0
+## 3 0
+## 4 0
+## 5 0
+## 6 0head(crop.prod.dat)## geo rye_p barley_p maize_p tritic_p sorghum_p oth_cer_p
+## 1 BG 20.221250 728.001250 2417.0175 41.0550 11.48875 6.30250
+## 2 CH 11.846250 184.607500 141.3250 52.1775 NA 0.34000
+## 3 CY NA 33.743750 NA 0.4400 NA NA
+## 4 AL 2.928571 7.857143 372.7429 NA NA NA
+## 5 CZ 127.265000 1765.546250 758.5862 198.7113 NA 8.05125
+## 6 BE 2.410000 378.551250 717.2150 38.0100 NA 14.16000
+## rice_p pasture_p rape_p sunflow_p pulses_p potato_p sugbeet_p
+## 1 59.1500000 2.39625 451.34000 1742.8525 43.480000 184.2188 0.540
+## 2 0.2566667 1452.92000 76.99375 11.0975 15.947143 429.4575 1533.865
+## 3 NA NA NA NA 0.876250 105.4137 NA
+## 4 NA NA NA 2.1000 25.971429 234.8857 29.600
+## 5 NA 164.70857 1242.46500 50.4650 66.733750 657.4800 3867.503
+## 6 NA 581.97500 48.63875 NA 8.301429 3710.9129 4947.113
+## oth_rt_p wheat_p oats_p oth_oil_p fibre_p oth_ind_p
+## 1 2.275714 5083.4000 32.080000 18.7660000 1.7285714 90.718750
+## 2 62.166667 442.3188 9.760417 4.3605000 0.9700000 1.526071
+## 3 NA 19.1050 0.587500 0.2612500 NA NA
+## 4 NA 284.6571 30.114286 0.5142857 NA 13.925000
+## 5 20.416250 4772.9613 154.703750 61.2250000 0.5428571 23.835357
+## 6 315.505000 1802.9088 19.687500 1.1380000 68.7500000 0.156250
+## fodder_p
+## 1 930.5467
+## 2 719.1500
+## 3 180.6650
+## 4 6887.9417
+## 5 9824.5921
+## 6 7722.9237nrow(crop.area.dat)## [1] 2017nrow(crop.prod.dat)## [1] 2017crop.yield.dat <- left_join(crop.area.dat, crop.prod.dat)## Joining, by = "geo"## Warning: Column `geo` joining character vector and factor, coercing into
+## character vectornames(crop.yield.dat)## [1] "geo" "rye_a" "barley_a" "maize_a" "tritic_a"
+## [6] "sorghum_a" "oth_cer_a" "rice_a" "pasture_a" "rape_a"
+## [11] "sunflow_a" "pulses_a" "potato_a" "sugbeet_a" "oth_rt_a"
+## [16] "wheat_a" "oats_a" "oth_oil_a" "fibre_a" "oth_ind_a"
+## [21] "fodder_a" "LEVL_CODE" "rye_p" "barley_p" "maize_p"
+## [26] "tritic_p" "sorghum_p" "oth_cer_p" "rice_p" "pasture_p"
+## [31] "rape_p" "sunflow_p" "pulses_p" "potato_p" "sugbeet_p"
+## [36] "oth_rt_p" "wheat_p" "oats_p" "oth_oil_p" "fibre_p"
+## [41] "oth_ind_p" "fodder_p"#Need to adjust the NUTS2016 data to NUTS2013 codes
+crop.yield.dat.2013nuts <- crop.yield.dat
+names(crop.yield.dat.2013nuts)## [1] "geo" "rye_a" "barley_a" "maize_a" "tritic_a"
+## [6] "sorghum_a" "oth_cer_a" "rice_a" "pasture_a" "rape_a"
+## [11] "sunflow_a" "pulses_a" "potato_a" "sugbeet_a" "oth_rt_a"
+## [16] "wheat_a" "oats_a" "oth_oil_a" "fibre_a" "oth_ind_a"
+## [21] "fodder_a" "LEVL_CODE" "rye_p" "barley_p" "maize_p"
+## [26] "tritic_p" "sorghum_p" "oth_cer_p" "rice_p" "pasture_p"
+## [31] "rape_p" "sunflow_p" "pulses_p" "potato_p" "sugbeet_p"
+## [36] "oth_rt_p" "wheat_p" "oats_p" "oth_oil_p" "fibre_p"
+## [41] "oth_ind_p" "fodder_p"crop.yield.dat.2013nuts$geo16 <- crop.yield.dat.2013nuts$geo
+
+#straight recodes
+for(e in nuts.conv[nuts.conv$Change == "recoded", 'Code.2016']) {
+ crop.yield.dat.2013nuts[crop.yield.dat.2013nuts$geo16 == e, 'geo'] <- as.character(nuts.conv[nuts.conv$Code.2016 == e, 'Code.2013'])
+}
+#check
+crop.yield.dat.2013nuts[crop.yield.dat.2013nuts$geo16 %in% nuts.conv[nuts.conv$Change == "recoded", 'Code.2016'], c('geo', 'geo16')]## geo geo16
+## 195 FR51 FRG0
+## 196 FR52 FRH0
+## 200 FR61 FRI1
+## 201 FR63 FRI2
+## 202 FR53 FRI3
+## 214 FR81 FRJ1
+## 215 FR62 FRJ2
+## 222 FR21 FRF2
+## 223 FR26 FRC1
+## 224 FR43 FRC2
+## 225 FR25 FRD1
+## 226 FR23 FRD2
+## 236 FR41 FRF3
+## 237 FR72 FRK1
+## 238 FR71 FRK2
+## 245 FR82 FRL0
+## 246 FR83 FRM0
+## 247 FRA1 FRY1
+## 259 FRA2 FRY2
+## 260 FRA3 FRY3
+## 261 FRA4 FRY4
+## 262 FRA5 FRY5
+## 317 FR30 FRE1
+## 318 FR22 FRE2
+## 319 FR42 FRF1
+## 441 PL32 PL82
+## 454 PL34 PL84
+## 486 PL11 PL71
+## 487 PL33 PL72
+## 488 PL31 PL81#recode and relabel
+crop.yield.dat.2013nuts[crop.yield.dat.2013nuts$geo16 == "FRB0", 'geo'] <- "FR24"
+
+#splits
+crop.yield.dat.2013nuts[crop.yield.dat.2013nuts$geo16 %in% c("LT01", "LT02"), 'geo'] <- "LT00"
+crop.yield.dat.2013nuts[crop.yield.dat.2013nuts$geo16 %in% c("HU11", "HU12"), 'geo'] <- "HU10"
+crop.yield.dat.2013nuts[crop.yield.dat.2013nuts$geo16 %in% c("PL91", "PL92"), 'geo'] <- "PL12"
+crop.yield.dat.2013nuts[crop.yield.dat.2013nuts$geo16 %in% c("UKM8", "UKM9"), 'geo'] <- "UKM3" #approximate split not including NUTS3 UKM24
+crop.yield.dat.2013nuts[crop.yield.dat.2013nuts$geo16 == "UKM7", 'geo'] <- "UKM2" #approximate recode still including NUTS3 UKM24
+
+#IE
+#Cannot translate data from new regions to old NUTS2013 so use NUTS0 data
+crop.yield.dat.2013nuts[crop.yield.dat.2013nuts$geo16 == 'IE',]## geo rye_a barley_a maize_a tritic_a sorghum_a oth_cer_a rice_a
+## 17 IE NA 194.4375 NA NA NA NA NA
+## pasture_a rape_a sunflow_a pulses_a potato_a sugbeet_a oth_rt_a
+## 17 96.10625 11.2325 0.01 7.05125 9.81 NA 11.95
+## wheat_a oats_a oth_oil_a fibre_a oth_ind_a fodder_a LEVL_CODE rye_p
+## 17 75.315 22.645 0.07 0.02666667 1.96625 19.82042 0 NA
+## barley_p maize_p tritic_p sorghum_p oth_cer_p rice_p pasture_p rape_p
+## 17 1501.84 NA NA NA NA NA NA 42.7425
+## sunflow_p pulses_p potato_p sugbeet_p oth_rt_p wheat_p oats_p
+## 17 0 41.8825 365.6687 NA NA 699.325 175.1287
+## oth_oil_p fibre_p oth_ind_p fodder_p geo16
+## 17 0 0 25.8875 730.55 IE## Calculate sum over the split NUTS2 regions
+head(crop.yield.dat.2013nuts)## geo rye_a barley_a maize_a tritic_a sorghum_a oth_cer_a rice_a
+## 1 BG 10.707500 186.503750 416.77125 13.81375 4.635 4.0450000 11.2175
+## 2 CH 1.986250 28.315000 15.33500 9.06875 NA 0.1116667 0.0800
+## 3 CY NA 20.810000 NA 0.42500 NA NA NA
+## 4 AL 1.285714 2.742857 56.44286 NA NA NA NA
+## 5 CZ 27.141250 357.867500 98.95625 43.45875 NA 5.3400000 NA
+## 6 BE 0.606250 46.607500 63.19125 5.85875 NA 3.2157143 NA
+## pasture_a rape_a sunflow_a pulses_a potato_a sugbeet_a oth_rt_a
+## 1 0.72750 175.64875 813.4100000 20.115000 12.512500 0.01000 0.1914286
+## 2 117.22000 21.79750 4.1087500 4.702857 11.072500 19.47500 0.6585714
+## 3 0.33500 NA NA 0.413750 4.706250 NA NA
+## 4 143.70000 NA 0.9714286 14.128571 9.585714 0.70000 NA
+## 5 37.74286 388.13375 21.6175000 27.933750 24.236250 60.71125 0.6300000
+## 6 79.00375 11.98875 NA 2.387500 80.837143 58.88000 7.5942857
+## wheat_a oats_a oth_oil_a fibre_a oth_ind_a fodder_a
+## 1 1184.90750 16.499750 20.2690000 1.8728571 64.7175000 110.37167
+## 2 88.57500 1.937917 1.6210357 0.0500000 1.2264286 189.00375
+## 3 9.51375 0.397500 0.0737500 NA NA 34.95625
+## 4 70.64286 14.028571 0.2571429 NA 6.0571429 238.71667
+## 5 834.87625 47.745000 61.8150000 0.3642857 13.1067857 414.21214
+## 6 209.81500 3.721250 0.1466667 12.8037500 0.7129167 181.32375
+## LEVL_CODE rye_p barley_p maize_p tritic_p sorghum_p oth_cer_p
+## 1 0 20.221250 728.001250 2417.0175 41.0550 11.48875 6.30250
+## 2 0 11.846250 184.607500 141.3250 52.1775 NA 0.34000
+## 3 0 NA 33.743750 NA 0.4400 NA NA
+## 4 0 2.928571 7.857143 372.7429 NA NA NA
+## 5 0 127.265000 1765.546250 758.5862 198.7113 NA 8.05125
+## 6 0 2.410000 378.551250 717.2150 38.0100 NA 14.16000
+## rice_p pasture_p rape_p sunflow_p pulses_p potato_p sugbeet_p
+## 1 59.1500000 2.39625 451.34000 1742.8525 43.480000 184.2188 0.540
+## 2 0.2566667 1452.92000 76.99375 11.0975 15.947143 429.4575 1533.865
+## 3 NA NA NA NA 0.876250 105.4137 NA
+## 4 NA NA NA 2.1000 25.971429 234.8857 29.600
+## 5 NA 164.70857 1242.46500 50.4650 66.733750 657.4800 3867.503
+## 6 NA 581.97500 48.63875 NA 8.301429 3710.9129 4947.113
+## oth_rt_p wheat_p oats_p oth_oil_p fibre_p oth_ind_p
+## 1 2.275714 5083.4000 32.080000 18.7660000 1.7285714 90.718750
+## 2 62.166667 442.3188 9.760417 4.3605000 0.9700000 1.526071
+## 3 NA 19.1050 0.587500 0.2612500 NA NA
+## 4 NA 284.6571 30.114286 0.5142857 NA 13.925000
+## 5 20.416250 4772.9613 154.703750 61.2250000 0.5428571 23.835357
+## 6 315.505000 1802.9088 19.687500 1.1380000 68.7500000 0.156250
+## fodder_p geo16
+## 1 930.5467 BG
+## 2 719.1500 CH
+## 3 180.6650 CY
+## 4 6887.9417 AL
+## 5 9824.5921 CZ
+## 6 7722.9237 BEcrop.yield.dat.2013nuts.sum <- crop.yield.dat.2013nuts %>% group_by(geo) %>% summarise(rye_a = sum(rye_a,na.rm = F),
+ barley_a = sum(barley_a,na.rm = F),
+ maize_a = sum(maize_a,na.rm = F),
+ tritic_a = sum(tritic_a,na.rm = F),
+ sorghum_a = sum(sorghum_a,na.rm = F),
+ oth_cer_a = sum(oth_cer_a,na.rm = F),
+ rice_a = sum(rice_a,na.rm = F),
+ pasture_a = sum(pasture_a,na.rm = F),
+ rape_a = sum(rape_a,na.rm = F),
+ sunflow_a = sum(sunflow_a,na.rm = F),
+ pulses_a = sum(pulses_a,na.rm = F),
+ potato_a = sum(potato_a,na.rm = F),
+ sugbeet_a = sum(sugbeet_a,na.rm = F),
+ oth_rt_a = sum(oth_rt_a,na.rm = F),
+ wheat_a = sum(wheat_a,na.rm = F),
+ oats_a = sum(oats_a,na.rm = F),
+ oth_oil_a = sum(oth_oil_a,na.rm = F),
+ fibre_a = sum(fibre_a,na.rm = F),
+ oth_ind_a = sum(oth_ind_a,na.rm = F),
+ fodder_a = sum(fodder_a,na.rm = F),
+ rye_p = sum(rye_p,na.rm = F),
+ barley_p = sum(barley_p,na.rm = F),
+ maize_p = sum(maize_p,na.rm = F),
+ tritic_p = sum(tritic_p,na.rm = F),
+ sorghum_p = sum(sorghum_p,na.rm = F),
+ oth_cer_p = sum(oth_cer_p,na.rm = F),
+ rice_p = sum(rice_p,na.rm = F),
+ pasture_p = sum(pasture_p,na.rm = F),
+ rape_p = sum(rape_p,na.rm = F),
+ sunflow_p = sum(sunflow_p,na.rm = F),
+ pulses_p = sum(pulses_p,na.rm = F),
+ potato_p = sum(potato_p,na.rm = F),
+ sugbeet_p = sum(sugbeet_p,na.rm = F),
+ oth_rt_p = sum(oth_rt_p,na.rm = F),
+ wheat_p = sum(wheat_p,na.rm = F),
+ oats_p = sum(oats_p,na.rm = F),
+ oth_oil_p = sum(oth_oil_p,na.rm = F),
+ fibre_p = sum(fibre_p,na.rm = F),
+ oth_ind_p = sum(oth_ind_p,na.rm = F),
+ fodder_p = sum(fodder_p,na.rm = F),
+ LEVL_CODE = mean(LEVL_CODE,na.rm = F)
+ )
+head(crop.yield.dat.2013nuts.sum)## # A tibble: 6 x 42
+## geo rye_a barley_a maize_a tritic_a sorghum_a oth_cer_a rice_a
+## <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
+## 1 AL 1.29 2.74 56.4 NA NA NA NA
+## 2 AL0 NA NA NA NA NA NA NA
+## 3 AL01 NA NA NA NA NA NA NA
+## 4 AL011 NA NA NA NA NA NA NA
+## 5 AL012 NA NA NA NA NA NA NA
+## 6 AL013 NA NA NA NA NA NA NA
+## # ... with 34 more variables: pasture_a <dbl>, rape_a <dbl>,
+## # sunflow_a <dbl>, pulses_a <dbl>, potato_a <dbl>, sugbeet_a <dbl>,
+## # oth_rt_a <dbl>, wheat_a <dbl>, oats_a <dbl>, oth_oil_a <dbl>,
+## # fibre_a <dbl>, oth_ind_a <dbl>, fodder_a <dbl>, rye_p <dbl>,
+## # barley_p <dbl>, maize_p <dbl>, tritic_p <dbl>, sorghum_p <dbl>,
+## # oth_cer_p <dbl>, rice_p <dbl>, pasture_p <dbl>, rape_p <dbl>,
+## # sunflow_p <dbl>, pulses_p <dbl>, potato_p <dbl>, sugbeet_p <dbl>,
+## # oth_rt_p <dbl>, wheat_p <dbl>, oats_p <dbl>, oth_oil_p <dbl>,
+## # fibre_p <dbl>, oth_ind_p <dbl>, fodder_p <dbl>, LEVL_CODE <dbl>nrow(crop.yield.dat.2013nuts.sum)## [1] 2013#Second, calculate yield in tonnes / ha (original Eurostat area units are 1000 ha and production units are 1000 tonnes)
+crop.yield <- as.data.frame(crop.yield.dat.2013nuts.sum[,c(1:21,42)])
+names(crop.yield)[2:21] <- gsub("_a", "_y", names(crop.yield)[2:21])
+names(crop.yield.dat.2013nuts.sum[,22:41])## [1] "rye_p" "barley_p" "maize_p" "tritic_p" "sorghum_p"
+## [6] "oth_cer_p" "rice_p" "pasture_p" "rape_p" "sunflow_p"
+## [11] "pulses_p" "potato_p" "sugbeet_p" "oth_rt_p" "wheat_p"
+## [16] "oats_p" "oth_oil_p" "fibre_p" "oth_ind_p" "fodder_p"names(crop.yield.dat.2013nuts.sum[,2:21])## [1] "rye_a" "barley_a" "maize_a" "tritic_a" "sorghum_a"
+## [6] "oth_cer_a" "rice_a" "pasture_a" "rape_a" "sunflow_a"
+## [11] "pulses_a" "potato_a" "sugbeet_a" "oth_rt_a" "wheat_a"
+## [16] "oats_a" "oth_oil_a" "fibre_a" "oth_ind_a" "fodder_a"crop.yield[,2:21] <- crop.yield.dat.2013nuts.sum[,22:41] / crop.yield.dat.2013nuts.sum[,2:21]
+summary(crop.yield)## geo rye_y barley_y maize_y
+## Length:2013 Min. :0.000 Min. : 0.1254 Min. : 0.000
+## Class :character 1st Qu.:2.420 1st Qu.: 2.9170 1st Qu.: 6.070
+## Mode :character Median :3.164 Median : 4.1183 Median : 8.147
+## Mean :3.443 Mean : 4.4163 Mean : 7.824
+## 3rd Qu.:4.510 3rd Qu.: 5.7631 3rd Qu.: 9.961
+## Max. :7.422 Max. :30.0000 Max. :12.976
+## NA's :1678 NA's :1638 NA's :1678
+## tritic_y sorghum_y oth_cer_y rice_y
+## Min. :0.000 Min. : 1.000 Min. : 0.000 Min. : 0.000
+## 1st Qu.:3.010 1st Qu.: 3.100 1st Qu.: 1.215 1st Qu.: 4.504
+## Median :3.995 Median : 4.431 Median : 2.080 Median : 5.524
+## Mean :4.045 Mean : 5.062 Mean : 2.678 Mean : 5.442
+## 3rd Qu.:5.223 3rd Qu.: 6.000 3rd Qu.: 3.781 3rd Qu.: 6.456
+## Max. :7.359 Max. :49.133 Max. :11.500 Max. :10.000
+## NA's :1733 NA's :1869 NA's :1917 NA's :1926
+## pasture_y rape_y sunflow_y pulses_y
+## Min. : 0.000 Min. :0.000 Min. :0.000 Min. : 0.000
+## 1st Qu.: 3.655 1st Qu.:2.369 1st Qu.:1.718 1st Qu.: 1.414
+## Median : 6.936 Median :2.914 Median :2.174 Median : 2.040
+## Mean :10.213 Mean :2.883 Mean :2.092 Mean : 2.276
+## 3rd Qu.:12.340 3rd Qu.:3.544 3rd Qu.:2.577 3rd Qu.: 2.752
+## Max. :49.514 Max. :5.333 Max. :4.818 Max. :40.211
+## NA's :1799 NA's :1708 NA's :1749 NA's :1672
+## potato_y sugbeet_y oth_rt_y wheat_y
+## Min. : 4.361 Min. : 0.00 Min. : 0.00 Min. : 0.6667
+## 1st Qu.:21.625 1st Qu.: 54.17 1st Qu.:15.32 1st Qu.: 3.1777
+## Median :27.769 Median : 63.70 Median :25.28 Median : 4.5915
+## Mean :29.052 Mean : 62.67 Mean :29.87 Mean : 4.8646
+## 3rd Qu.:36.514 3rd Qu.: 76.37 3rd Qu.:37.37 3rd Qu.: 6.4084
+## Max. :53.327 Max. :107.50 Max. :94.40 Max. :10.2402
+## NA's :1674 NA's :1753 NA's :1913 NA's :1636
+## oats_y oth_oil_y fibre_y oth_ind_y
+## Min. :0.5367 Min. : 0.000 Min. : 0.000 Min. : 0.0000
+## 1st Qu.:2.2609 1st Qu.: 1.389 1st Qu.: 1.125 1st Qu.: 0.6786
+## Median :3.1395 Median : 2.000 Median : 3.084 Median : 1.4677
+## Mean :3.3915 Mean : 2.288 Mean : 3.537 Mean : 2.2600
+## 3rd Qu.:4.5377 3rd Qu.: 2.670 3rd Qu.: 5.492 3rd Qu.: 2.4167
+## Max. :8.5116 Max. :28.000 Max. :19.400 Max. :78.4444
+## NA's :1669 NA's :1748 NA's :1881 NA's :1772
+## fodder_y LEVL_CODE
+## Min. : 0.00 Min. :0.000
+## 1st Qu.:10.28 1st Qu.:3.000
+## Median :18.69 Median :3.000
+## Mean :22.02 Mean :2.658
+## 3rd Qu.:34.41 3rd Qu.:3.000
+## Max. :51.05 Max. :3.000
+## NA's :1689#is.na(crop.yield) <- sapply(crop.yield, is.infinite) #Remove the infinites
+is.na(crop.yield) <- sapply(crop.yield, is.nan) #Remove NaN
+summary(crop.yield) #still some spurious values## geo rye_y barley_y maize_y
+## Length:2013 Min. :0.000 Min. : 0.1254 Min. : 0.000
+## Class :character 1st Qu.:2.420 1st Qu.: 2.9170 1st Qu.: 6.070
+## Mode :character Median :3.164 Median : 4.1183 Median : 8.147
+## Mean :3.443 Mean : 4.4163 Mean : 7.824
+## 3rd Qu.:4.510 3rd Qu.: 5.7631 3rd Qu.: 9.961
+## Max. :7.422 Max. :30.0000 Max. :12.976
+## NA's :1678 NA's :1638 NA's :1678
+## tritic_y sorghum_y oth_cer_y rice_y
+## Min. :0.000 Min. : 1.000 Min. : 0.000 Min. : 0.000
+## 1st Qu.:3.010 1st Qu.: 3.100 1st Qu.: 1.215 1st Qu.: 4.504
+## Median :3.995 Median : 4.431 Median : 2.080 Median : 5.524
+## Mean :4.045 Mean : 5.062 Mean : 2.678 Mean : 5.442
+## 3rd Qu.:5.223 3rd Qu.: 6.000 3rd Qu.: 3.781 3rd Qu.: 6.456
+## Max. :7.359 Max. :49.133 Max. :11.500 Max. :10.000
+## NA's :1733 NA's :1869 NA's :1917 NA's :1926
+## pasture_y rape_y sunflow_y pulses_y
+## Min. : 0.000 Min. :0.000 Min. :0.000 Min. : 0.000
+## 1st Qu.: 3.655 1st Qu.:2.369 1st Qu.:1.718 1st Qu.: 1.414
+## Median : 6.936 Median :2.914 Median :2.174 Median : 2.040
+## Mean :10.213 Mean :2.883 Mean :2.092 Mean : 2.276
+## 3rd Qu.:12.340 3rd Qu.:3.544 3rd Qu.:2.577 3rd Qu.: 2.752
+## Max. :49.514 Max. :5.333 Max. :4.818 Max. :40.211
+## NA's :1799 NA's :1708 NA's :1749 NA's :1672
+## potato_y sugbeet_y oth_rt_y wheat_y
+## Min. : 4.361 Min. : 0.00 Min. : 0.00 Min. : 0.6667
+## 1st Qu.:21.625 1st Qu.: 54.17 1st Qu.:15.32 1st Qu.: 3.1777
+## Median :27.769 Median : 63.70 Median :25.28 Median : 4.5915
+## Mean :29.052 Mean : 62.67 Mean :29.87 Mean : 4.8646
+## 3rd Qu.:36.514 3rd Qu.: 76.37 3rd Qu.:37.37 3rd Qu.: 6.4084
+## Max. :53.327 Max. :107.50 Max. :94.40 Max. :10.2402
+## NA's :1674 NA's :1753 NA's :1913 NA's :1636
+## oats_y oth_oil_y fibre_y oth_ind_y
+## Min. :0.5367 Min. : 0.000 Min. : 0.000 Min. : 0.0000
+## 1st Qu.:2.2609 1st Qu.: 1.389 1st Qu.: 1.125 1st Qu.: 0.6786
+## Median :3.1395 Median : 2.000 Median : 3.084 Median : 1.4677
+## Mean :3.3915 Mean : 2.288 Mean : 3.537 Mean : 2.2600
+## 3rd Qu.:4.5377 3rd Qu.: 2.670 3rd Qu.: 5.492 3rd Qu.: 2.4167
+## Max. :8.5116 Max. :28.000 Max. :19.400 Max. :78.4444
+## NA's :1669 NA's :1748 NA's :1881 NA's :1772
+## fodder_y LEVL_CODE
+## Min. : 0.00 Min. :0.000
+## 1st Qu.:10.28 1st Qu.:3.000
+## Median :18.69 Median :3.000
+## Mean :22.02 Mean :2.658
+## 3rd Qu.:34.41 3rd Qu.:3.000
+## Max. :51.05 Max. :3.000
+## NA's :1689#Whipe BE1, BE10 because of spurios areas (see above)
+crop.yield[which(crop.yield$geo %in% c("BE1", "BE10")), c(2:21)] <- NA
+
+summary(crop.yield)## geo rye_y barley_y maize_y
+## Length:2013 Min. :0.000 Min. : 0.1254 Min. : 0.000
+## Class :character 1st Qu.:2.431 1st Qu.: 2.9163 1st Qu.: 6.059
+## Mode :character Median :3.169 Median : 4.1115 Median : 8.146
+## Mean :3.451 Mean : 4.3965 Mean : 7.801
+## 3rd Qu.:4.512 3rd Qu.: 5.7152 3rd Qu.: 9.917
+## Max. :7.422 Max. :30.0000 Max. :12.976
+## NA's :1680 NA's :1640 NA's :1680
+## tritic_y sorghum_y oth_cer_y rice_y
+## Min. :0.000 Min. : 1.000 Min. : 0.000 Min. : 0.000
+## 1st Qu.:3.003 1st Qu.: 3.100 1st Qu.: 1.198 1st Qu.: 4.504
+## Median :3.990 Median : 4.431 Median : 2.066 Median : 5.524
+## Mean :4.026 Mean : 5.062 Mean : 2.491 Mean : 5.442
+## 3rd Qu.:5.216 3rd Qu.: 6.000 3rd Qu.: 3.659 3rd Qu.: 6.456
+## Max. :7.359 Max. :49.133 Max. :10.750 Max. :10.000
+## NA's :1735 NA's :1869 NA's :1919 NA's :1926
+## pasture_y rape_y sunflow_y pulses_y
+## Min. : 0.000 Min. :0.000 Min. :0.000 Min. : 0.000
+## 1st Qu.: 3.655 1st Qu.:2.351 1st Qu.:1.718 1st Qu.: 1.413
+## Median : 6.936 Median :2.911 Median :2.174 Median : 2.038
+## Mean :10.213 Mean :2.873 Mean :2.092 Mean : 2.264
+## 3rd Qu.:12.340 3rd Qu.:3.544 3rd Qu.:2.577 3rd Qu.: 2.749
+## Max. :49.514 Max. :5.333 Max. :4.818 Max. :40.211
+## NA's :1799 NA's :1710 NA's :1749 NA's :1674
+## potato_y sugbeet_y oth_rt_y wheat_y
+## Min. : 4.361 Min. : 0.00 Min. : 0.00 Min. : 0.6667
+## 1st Qu.:21.584 1st Qu.: 54.07 1st Qu.:15.11 1st Qu.: 3.1662
+## Median :27.763 Median : 63.52 Median :25.10 Median : 4.5731
+## Mean :28.951 Mean : 62.50 Mean :29.77 Mean : 4.8382
+## 3rd Qu.:36.471 3rd Qu.: 76.07 3rd Qu.:37.46 3rd Qu.: 6.3951
+## Max. :53.327 Max. :107.50 Max. :94.40 Max. :10.2402
+## NA's :1676 NA's :1755 NA's :1915 NA's :1638
+## oats_y oth_oil_y fibre_y oth_ind_y
+## Min. :0.5367 Min. : 0.000 Min. : 0.000 Min. : 0.0000
+## 1st Qu.:2.2544 1st Qu.: 1.389 1st Qu.: 1.103 1st Qu.: 0.6786
+## Median :3.1310 Median : 2.000 Median : 3.077 Median : 1.4677
+## Mean :3.3798 Mean : 2.288 Mean : 3.510 Mean : 2.2600
+## 3rd Qu.:4.5236 3rd Qu.: 2.670 3rd Qu.: 5.497 3rd Qu.: 2.4167
+## Max. :8.5116 Max. :28.000 Max. :19.400 Max. :78.4444
+## NA's :1671 NA's :1748 NA's :1883 NA's :1772
+## fodder_y LEVL_CODE
+## Min. : 0.00 Min. :0.000
+## 1st Qu.:10.27 1st Qu.:3.000
+## Median :18.53 Median :3.000
+## Mean :21.88 Mean :2.658
+## 3rd Qu.:34.33 3rd Qu.:3.000
+## Max. :51.05 Max. :3.000
+## NA's :1691#Spurious values checked by looking at Eurostat database for statistical outliers and spatial outliers based on maps
+
+#Spurious rye
+crop.yield[which(crop.yield$rye_y > 6), c('geo', 'rye_y')]## geo rye_y
+## 449 DE9 6.410551
+## 499 DEA 6.584930
+## 558 DEB 6.195128
+## 639 DEF 7.142828
+## 656 DEG 6.424054
+## 681 DK 6.006277
+## 682 DK0 6.007563
+## 683 DK01 6.311475
+## 688 DK02 6.703985
+## 691 DK03 6.000547
+## 891 FR1 6.062500
+## 892 FR10 6.062500
+## 902 FR22 6.328767
+## 910 FR43 6.243902
+## 949 FRE 6.329114
+## 1118 ITC2 7.000000
+## 1147 ITF3 7.421875
+## 1352 NO0 6.037915
+## 1356 NO02 6.675000
+## 1359 NO03 6.026316
+## 1609 SE2 6.312086
+## 1615 SE22 6.835658
+## 1915 UKJ 6.600000crop.yield[crop.yield$geo %in% crop.yield$geo[grep('ITF', crop.yield$geo)], c('geo', 'rye_y')]## geo rye_y
+## 1138 ITF 3.230439
+## 1139 ITF1 3.041237
+## 1140 ITF11 NA
+## 1141 ITF12 NA
+## 1142 ITF13 NA
+## 1143 ITF14 NA
+## 1144 ITF2 NA
+## 1145 ITF21 NA
+## 1146 ITF22 NA
+## 1147 ITF3 7.421875
+## 1148 ITF31 NA
+## 1149 ITF32 NA
+## 1150 ITF33 NA
+## 1151 ITF34 NA
+## 1152 ITF35 NA
+## 1153 ITF4 2.000000
+## 1154 ITF43 NA
+## 1155 ITF44 NA
+## 1156 ITF45 NA
+## 1157 ITF46 NA
+## 1158 ITF47 NA
+## 1159 ITF48 NA
+## 1160 ITF5 2.000000
+## 1161 ITF51 NA
+## 1162 ITF52 NA
+## 1163 ITF6 3.098109
+## 1164 ITF61 NA
+## 1165 ITF62 NA
+## 1166 ITF63 NA
+## 1167 ITF64 NA
+## 1168 ITF65 NAcrop.yield[crop.yield$geo %in% crop.yield$geo[grep('ITC', crop.yield$geo)], c('geo', 'rye_y')]## geo rye_y
+## 1108 ITC 3.705986
+## 1109 ITC1 3.311782
+## 1110 ITC11 NA
+## 1111 ITC12 NA
+## 1112 ITC13 NA
+## 1113 ITC14 NA
+## 1114 ITC15 NA
+## 1115 ITC16 NA
+## 1116 ITC17 NA
+## 1117 ITC18 NA
+## 1118 ITC2 7.000000
+## 1119 ITC20 NA
+## 1120 ITC3 NA
+## 1121 ITC31 NA
+## 1122 ITC32 NA
+## 1123 ITC33 NA
+## 1124 ITC34 NA
+## 1125 ITC4 3.794393
+## 1126 ITC41 NA
+## 1127 ITC42 NA
+## 1128 ITC43 NA
+## 1129 ITC44 NA
+## 1130 ITC46 NA
+## 1131 ITC47 NA
+## 1132 ITC48 NA
+## 1133 ITC49 NA
+## 1134 ITC4A NA
+## 1135 ITC4B NA
+## 1136 ITC4C NA
+## 1137 ITC4D NAcrop.yield[which(crop.yield$geo == "ITC2"), 'rye_y'] <- crop.yield[which(crop.yield$geo == "ITC"), 'rye_y']
+crop.yield[which(crop.yield$geo == "ITF3"), 'rye_y'] <- crop.yield[which(crop.yield$geo == "ITF"), 'rye_y']
+
+crop.yield[crop.yield$geo %in% crop.yield$geo[grep('SE', crop.yield$geo)], c('geo', 'rye_y')]## geo rye_y
+## 1599 SE 5.953990
+## 1600 SE1 5.588411
+## 1601 SE11 1.090909
+## 1602 SE110 NA
+## 1603 SE12 5.656753
+## 1604 SE121 NA
+## 1605 SE122 NA
+## 1606 SE123 NA
+## 1607 SE124 NA
+## 1608 SE125 NA
+## 1609 SE2 6.312086
+## 1610 SE21 4.584682
+## 1611 SE211 NA
+## 1612 SE212 NA
+## 1613 SE213 NA
+## 1614 SE214 NA
+## 1615 SE22 6.835658
+## 1616 SE221 NA
+## 1617 SE224 NA
+## 1618 SE23 5.424729
+## 1619 SE231 NA
+## 1620 SE232 NA
+## 1621 SE3 2.336957
+## 1622 SE31 1.287671
+## 1623 SE311 NA
+## 1624 SE312 NA
+## 1625 SE313 NA
+## 1626 SE32 0.000000
+## 1627 SE321 NA
+## 1628 SE322 NA
+## 1629 SE33 NA
+## 1630 SE331 NA
+## 1631 SE332 NAcrop.yield[crop.yield$geo == "SE11", 'rye_y'] <- crop.yield[crop.yield$geo == "SE1", 'rye_y']
+
+crop.yield[crop.yield$geo %in% c("SE31", "SE32"), 'rye_y'] <- crop.yield[crop.yield$geo == "SE3", 'rye_y']
+
+#Spurious barley
+crop.yield[which(crop.yield$barley_y > 10), c('geo', 'barley_y')]## geo barley_y
+## 1118 ITC2 30crop.yield[crop.yield$geo %in% crop.yield$geo[grep('ITC', crop.yield$geo)], c('geo', 'barley_y')]## geo barley_y
+## 1108 ITC 4.993019
+## 1109 ITC1 5.053235
+## 1110 ITC11 NA
+## 1111 ITC12 NA
+## 1112 ITC13 NA
+## 1113 ITC14 NA
+## 1114 ITC15 NA
+## 1115 ITC16 NA
+## 1116 ITC17 NA
+## 1117 ITC18 NA
+## 1118 ITC2 30.000000
+## 1119 ITC20 NA
+## 1120 ITC3 2.222222
+## 1121 ITC31 NA
+## 1122 ITC32 NA
+## 1123 ITC33 NA
+## 1124 ITC34 NA
+## 1125 ITC4 4.949255
+## 1126 ITC41 NA
+## 1127 ITC42 NA
+## 1128 ITC43 NA
+## 1129 ITC44 NA
+## 1130 ITC46 NA
+## 1131 ITC47 NA
+## 1132 ITC48 NA
+## 1133 ITC49 NA
+## 1134 ITC4A NA
+## 1135 ITC4B NA
+## 1136 ITC4C NA
+## 1137 ITC4D NAcrop.yield[which(crop.yield$geo == "ITC2"), 'barley_y'] <- crop.yield[which(crop.yield$geo == "ITC"), 'barley_y']
+
+summary(crop.yield)## geo rye_y barley_y maize_y
+## Length:2013 Min. :0.000 Min. :0.1254 Min. : 0.000
+## Class :character 1st Qu.:2.436 1st Qu.:2.9163 1st Qu.: 6.059
+## Mode :character Median :3.172 Median :4.1115 Median : 8.146
+## Mean :3.452 Mean :4.3295 Mean : 7.801
+## 3rd Qu.:4.507 3rd Qu.:5.6912 3rd Qu.: 9.917
+## Max. :7.143 Max. :8.7350 Max. :12.976
+## NA's :1680 NA's :1640 NA's :1680
+## tritic_y sorghum_y oth_cer_y rice_y
+## Min. :0.000 Min. : 1.000 Min. : 0.000 Min. : 0.000
+## 1st Qu.:3.003 1st Qu.: 3.100 1st Qu.: 1.198 1st Qu.: 4.504
+## Median :3.990 Median : 4.431 Median : 2.066 Median : 5.524
+## Mean :4.026 Mean : 5.062 Mean : 2.491 Mean : 5.442
+## 3rd Qu.:5.216 3rd Qu.: 6.000 3rd Qu.: 3.659 3rd Qu.: 6.456
+## Max. :7.359 Max. :49.133 Max. :10.750 Max. :10.000
+## NA's :1735 NA's :1869 NA's :1919 NA's :1926
+## pasture_y rape_y sunflow_y pulses_y
+## Min. : 0.000 Min. :0.000 Min. :0.000 Min. : 0.000
+## 1st Qu.: 3.655 1st Qu.:2.351 1st Qu.:1.718 1st Qu.: 1.413
+## Median : 6.936 Median :2.911 Median :2.174 Median : 2.038
+## Mean :10.213 Mean :2.873 Mean :2.092 Mean : 2.264
+## 3rd Qu.:12.340 3rd Qu.:3.544 3rd Qu.:2.577 3rd Qu.: 2.749
+## Max. :49.514 Max. :5.333 Max. :4.818 Max. :40.211
+## NA's :1799 NA's :1710 NA's :1749 NA's :1674
+## potato_y sugbeet_y oth_rt_y wheat_y
+## Min. : 4.361 Min. : 0.00 Min. : 0.00 Min. : 0.6667
+## 1st Qu.:21.584 1st Qu.: 54.07 1st Qu.:15.11 1st Qu.: 3.1662
+## Median :27.763 Median : 63.52 Median :25.10 Median : 4.5731
+## Mean :28.951 Mean : 62.50 Mean :29.77 Mean : 4.8382
+## 3rd Qu.:36.471 3rd Qu.: 76.07 3rd Qu.:37.46 3rd Qu.: 6.3951
+## Max. :53.327 Max. :107.50 Max. :94.40 Max. :10.2402
+## NA's :1676 NA's :1755 NA's :1915 NA's :1638
+## oats_y oth_oil_y fibre_y oth_ind_y
+## Min. :0.5367 Min. : 0.000 Min. : 0.000 Min. : 0.0000
+## 1st Qu.:2.2544 1st Qu.: 1.389 1st Qu.: 1.103 1st Qu.: 0.6786
+## Median :3.1310 Median : 2.000 Median : 3.077 Median : 1.4677
+## Mean :3.3798 Mean : 2.288 Mean : 3.510 Mean : 2.2600
+## 3rd Qu.:4.5236 3rd Qu.: 2.670 3rd Qu.: 5.497 3rd Qu.: 2.4167
+## Max. :8.5116 Max. :28.000 Max. :19.400 Max. :78.4444
+## NA's :1671 NA's :1748 NA's :1883 NA's :1772
+## fodder_y LEVL_CODE
+## Min. : 0.00 Min. :0.000
+## 1st Qu.:10.27 1st Qu.:3.000
+## Median :18.53 Median :3.000
+## Mean :21.88 Mean :2.658
+## 3rd Qu.:34.33 3rd Qu.:3.000
+## Max. :51.05 Max. :3.000
+## NA's :1691#Spurious sorghum
+crop.yield[which(crop.yield$sorghum_y > 8), c('geo', 'sorghum_y')]## geo sorghum_y
+## 34 AT2 8.445507
+## 39 AT22 8.588477
+## 163 CH0 12.500000
+## 168 CH02 11.500000
+## 717 EL4 16.810345
+## 725 EL43 49.133333
+## 793 ES22 14.215686
+## 906 FR26 9.044248
+## 909 FR42 8.590909
+## 910 FR43 9.000000
+## 934 FRC 9.112782crop.yield[crop.yield$geo %in% crop.yield$geo[grep('EL4', crop.yield$geo)], c('geo', 'sorghum_y')]## geo sorghum_y
+## 717 EL4 16.810345
+## 718 EL41 4.810811
+## 719 EL411 NA
+## 720 EL412 NA
+## 721 EL413 NA
+## 722 EL42 3.600000
+## 723 EL421 NA
+## 724 EL422 NA
+## 725 EL43 49.133333
+## 726 EL431 NA
+## 727 EL432 NA
+## 728 EL433 NA
+## 729 EL434 NAcrop.yield[crop.yield$geo %in% c("EL4", "EL43"), 'sorghum_y'] <- mean(crop.yield[crop.yield$geo %in% c("EL41", "EL42"), 'sorghum_y'])
+
+crop.yield[crop.yield$geo %in% crop.yield$geo[grep('ES2', crop.yield$geo)], c('geo', 'sorghum_y')]## geo sorghum_y
+## 788 ES2 5.191443
+## 789 ES21 NA
+## 790 ES211 NA
+## 791 ES212 NA
+## 792 ES213 NA
+## 793 ES22 14.215686
+## 794 ES220 NA
+## 795 ES23 NA
+## 796 ES230 NA
+## 797 ES24 4.847777
+## 798 ES241 NA
+## 799 ES242 NA
+## 800 ES243 NAcrop.yield[crop.yield$geo == "ES22", 'sorghum_y'] <- crop.yield[crop.yield$geo == "ES2", 'sorghum_y']
+
+crop.yield[crop.yield$geo %in% crop.yield$geo[grep('CH', crop.yield$geo)], c('geo', 'sorghum_y')]## geo sorghum_y
+## 162 CH NA
+## 163 CH0 12.5
+## 164 CH01 6.0
+## 165 CH011 NA
+## 166 CH012 NA
+## 167 CH013 NA
+## 168 CH02 11.5
+## 169 CH021 NA
+## 170 CH022 NA
+## 171 CH023 NA
+## 172 CH024 NA
+## 173 CH025 NA
+## 174 CH03 6.0
+## 175 CH031 NA
+## 176 CH032 NA
+## 177 CH033 NA
+## 178 CH04 NA
+## 179 CH040 NA
+## 180 CH05 NA
+## 181 CH051 NA
+## 182 CH052 NA
+## 183 CH053 NA
+## 184 CH054 NA
+## 185 CH055 NA
+## 186 CH056 NA
+## 187 CH057 NA
+## 188 CH06 6.0
+## 189 CH061 NA
+## 190 CH062 NA
+## 191 CH063 NA
+## 192 CH064 NA
+## 193 CH065 NA
+## 194 CH066 NA
+## 195 CH07 NA
+## 196 CH070 NAcrop.yield[crop.yield$geo %in% c("CH0", "CH02"), 'sorghum_y'] <- mean(crop.yield[crop.yield$geo %in% c("CH01", "CH03", "CH06"), 'sorghum_y'])
+
+summary(crop.yield)## geo rye_y barley_y maize_y
+## Length:2013 Min. :0.000 Min. :0.1254 Min. : 0.000
+## Class :character 1st Qu.:2.436 1st Qu.:2.9163 1st Qu.: 6.059
+## Mode :character Median :3.172 Median :4.1115 Median : 8.146
+## Mean :3.452 Mean :4.3295 Mean : 7.801
+## 3rd Qu.:4.507 3rd Qu.:5.6912 3rd Qu.: 9.917
+## Max. :7.143 Max. :8.7350 Max. :12.976
+## NA's :1680 NA's :1640 NA's :1680
+## tritic_y sorghum_y oth_cer_y rice_y
+## Min. :0.000 Min. :1.000 Min. : 0.000 Min. : 0.000
+## 1st Qu.:3.003 1st Qu.:3.100 1st Qu.: 1.198 1st Qu.: 4.504
+## Median :3.990 Median :4.393 Median : 2.066 Median : 5.524
+## Mean :4.026 Mean :4.516 Mean : 2.491 Mean : 5.442
+## 3rd Qu.:5.216 3rd Qu.:5.968 3rd Qu.: 3.659 3rd Qu.: 6.456
+## Max. :7.359 Max. :9.113 Max. :10.750 Max. :10.000
+## NA's :1735 NA's :1869 NA's :1919 NA's :1926
+## pasture_y rape_y sunflow_y pulses_y
+## Min. : 0.000 Min. :0.000 Min. :0.000 Min. : 0.000
+## 1st Qu.: 3.655 1st Qu.:2.351 1st Qu.:1.718 1st Qu.: 1.413
+## Median : 6.936 Median :2.911 Median :2.174 Median : 2.038
+## Mean :10.213 Mean :2.873 Mean :2.092 Mean : 2.264
+## 3rd Qu.:12.340 3rd Qu.:3.544 3rd Qu.:2.577 3rd Qu.: 2.749
+## Max. :49.514 Max. :5.333 Max. :4.818 Max. :40.211
+## NA's :1799 NA's :1710 NA's :1749 NA's :1674
+## potato_y sugbeet_y oth_rt_y wheat_y
+## Min. : 4.361 Min. : 0.00 Min. : 0.00 Min. : 0.6667
+## 1st Qu.:21.584 1st Qu.: 54.07 1st Qu.:15.11 1st Qu.: 3.1662
+## Median :27.763 Median : 63.52 Median :25.10 Median : 4.5731
+## Mean :28.951 Mean : 62.50 Mean :29.77 Mean : 4.8382
+## 3rd Qu.:36.471 3rd Qu.: 76.07 3rd Qu.:37.46 3rd Qu.: 6.3951
+## Max. :53.327 Max. :107.50 Max. :94.40 Max. :10.2402
+## NA's :1676 NA's :1755 NA's :1915 NA's :1638
+## oats_y oth_oil_y fibre_y oth_ind_y
+## Min. :0.5367 Min. : 0.000 Min. : 0.000 Min. : 0.0000
+## 1st Qu.:2.2544 1st Qu.: 1.389 1st Qu.: 1.103 1st Qu.: 0.6786
+## Median :3.1310 Median : 2.000 Median : 3.077 Median : 1.4677
+## Mean :3.3798 Mean : 2.288 Mean : 3.510 Mean : 2.2600
+## 3rd Qu.:4.5236 3rd Qu.: 2.670 3rd Qu.: 5.497 3rd Qu.: 2.4167
+## Max. :8.5116 Max. :28.000 Max. :19.400 Max. :78.4444
+## NA's :1671 NA's :1748 NA's :1883 NA's :1772
+## fodder_y LEVL_CODE
+## Min. : 0.00 Min. :0.000
+## 1st Qu.:10.27 1st Qu.:3.000
+## Median :18.53 Median :3.000
+## Mean :21.88 Mean :2.658
+## 3rd Qu.:34.33 3rd Qu.:3.000
+## Max. :51.05 Max. :3.000
+## NA's :1691#Spurious rape
+crop.yield[which(crop.yield$rape_y > 4), c('geo', 'rape_y')]## geo rape_y
+## 66 BE 4.057033
+## 86 BE24 4.068966
+## 89 BE25 4.436464
+## 98 BE3 4.071088
+## 99 BE31 4.084127
+## 101 BE32 4.064417
+## 109 BE33 4.439338
+## 902 FR22 4.287457
+## 903 FR23 4.096127
+## 905 FR25 4.017380
+## 907 FR30 4.500000
+## 909 FR42 4.209091
+## 943 FRD 4.064926
+## 949 FRE 4.324003
+## 1094 IE05 4.172932
+## 1098 IE06 4.107794
+## 1170 ITG1 5.333333
+## 1735 TR83 5.000000crop.yield[crop.yield$geo %in% c("ITG", "ITG1", "ITG2"), c('geo', 'rape_y')]## geo rape_y
+## 1169 ITG 1.000000
+## 1170 ITG1 5.333333
+## 1180 ITG2 1.000000crop.yield[crop.yield$geo == "ITG1", 'rape_y'] <- crop.yield[crop.yield$geo == "ITG", 'rape_y']
+
+#Spurious sunflower
+crop.yield[which(crop.yield$sunflow_y > 3), c('geo', 'sunflow_y')]## geo sunflow_y
+## 226 DE1 3.060000
+## 499 DEA 4.000000
+## 558 DEB 3.857143
+## 753 EL6 3.296884
+## 754 EL61 4.392677
+## 904 FR24 3.117628
+## 906 FR26 3.016734
+## 908 FR41 3.260991
+## 910 FR43 3.145299
+## 911 FR51 3.105082
+## 927 FRB 3.117628
+## 934 FRC 3.026071
+## 955 FRF 3.128025
+## 966 FRG 3.105082
+## 1108 ITC 3.255319
+## 1109 ITC1 3.147837
+## 1160 ITF5 4.818182
+## 1169 ITG 4.400000
+## 1202 ITH4 3.990476
+## 1700 TR52 3.659236crop.yield[crop.yield$geo %in% c("ITF", "ITF1", "ITF2", "ITF3", "ITF4", "ITF5", "ITF6"), c('geo', 'sunflow_y')]## geo sunflow_y
+## 1138 ITF 1.718640
+## 1139 ITF1 1.915966
+## 1144 ITF2 1.483412
+## 1147 ITF3 2.060811
+## 1153 ITF4 1.902977
+## 1160 ITF5 4.818182
+## 1163 ITF6 2.692308crop.yield[crop.yield$geo %in% c("ITG", "ITG1", "ITG2"), c('geo', 'sunflow_y')]## geo sunflow_y
+## 1169 ITG 4.400000
+## 1170 ITG1 2.500000
+## 1180 ITG2 2.833333crop.yield[crop.yield$geo == "ITF5", 'sunflow_y'] <- mean(crop.yield[crop.yield$geo %in% c("ITF1", "ITF2", "ITF3", "ITF4", "ITF6"), 'sunflow_y'])
+
+crop.yield[crop.yield$geo == "ITG", 'sunflow_y'] <- mean(crop.yield[crop.yield$geo %in% c("ITG1", "ITG2"), 'sunflow_y'])
+
+#Spurious pulses
+crop.yield[which(crop.yield$pulses_y > 5), c('geo', 'pulses_y')]## geo pulses_y
+## 1089 IE 5.939727
+## 1090 IE0 5.939727
+## 1091 IE04 6.000000
+## 1094 IE05 6.705146
+## 1098 IE06 6.411765
+## 1120 ITC3 40.210526
+## 1274 ME 7.526316
+## 1615 SE22 5.002454crop.yield[crop.yield$geo %in% crop.yield$geo[grep('ITC', crop.yield$geo)], c('geo', 'pulses_y')]## geo pulses_y
+## 1108 ITC 3.094511
+## 1109 ITC1 2.313346
+## 1110 ITC11 NA
+## 1111 ITC12 NA
+## 1112 ITC13 NA
+## 1113 ITC14 NA
+## 1114 ITC15 NA
+## 1115 ITC16 NA
+## 1116 ITC17 NA
+## 1117 ITC18 NA
+## 1118 ITC2 NA
+## 1119 ITC20 NA
+## 1120 ITC3 40.210526
+## 1121 ITC31 NA
+## 1122 ITC32 NA
+## 1123 ITC33 NA
+## 1124 ITC34 NA
+## 1125 ITC4 3.730722
+## 1126 ITC41 NA
+## 1127 ITC42 NA
+## 1128 ITC43 NA
+## 1129 ITC44 NA
+## 1130 ITC46 NA
+## 1131 ITC47 NA
+## 1132 ITC48 NA
+## 1133 ITC49 NA
+## 1134 ITC4A NA
+## 1135 ITC4B NA
+## 1136 ITC4C NA
+## 1137 ITC4D NAcrop.yield[crop.yield$geo == "ITC3", 'pulses_y'] <- crop.yield[crop.yield$geo == "ITC", 'pulses_y']
+crop.yield[crop.yield$geo == "ME", 'pulses_y'] <- NA
+
+summary(crop.yield)## geo rye_y barley_y maize_y
+## Length:2013 Min. :0.000 Min. :0.1254 Min. : 0.000
+## Class :character 1st Qu.:2.436 1st Qu.:2.9163 1st Qu.: 6.059
+## Mode :character Median :3.172 Median :4.1115 Median : 8.146
+## Mean :3.452 Mean :4.3295 Mean : 7.801
+## 3rd Qu.:4.507 3rd Qu.:5.6912 3rd Qu.: 9.917
+## Max. :7.143 Max. :8.7350 Max. :12.976
+## NA's :1680 NA's :1640 NA's :1680
+## tritic_y sorghum_y oth_cer_y rice_y
+## Min. :0.000 Min. :1.000 Min. : 0.000 Min. : 0.000
+## 1st Qu.:3.003 1st Qu.:3.100 1st Qu.: 1.198 1st Qu.: 4.504
+## Median :3.990 Median :4.393 Median : 2.066 Median : 5.524
+## Mean :4.026 Mean :4.516 Mean : 2.491 Mean : 5.442
+## 3rd Qu.:5.216 3rd Qu.:5.968 3rd Qu.: 3.659 3rd Qu.: 6.456
+## Max. :7.359 Max. :9.113 Max. :10.750 Max. :10.000
+## NA's :1735 NA's :1869 NA's :1919 NA's :1926
+## pasture_y rape_y sunflow_y pulses_y
+## Min. : 0.000 Min. :0.000 Min. :0.000 Min. :0.000
+## 1st Qu.: 3.655 1st Qu.:2.331 1st Qu.:1.718 1st Qu.:1.413
+## Median : 6.936 Median :2.903 Median :2.169 Median :2.034
+## Mean :10.213 Mean :2.859 Mean :2.074 Mean :2.139
+## 3rd Qu.:12.340 3rd Qu.:3.543 3rd Qu.:2.570 3rd Qu.:2.747
+## Max. :49.514 Max. :5.000 Max. :4.393 Max. :6.705
+## NA's :1799 NA's :1710 NA's :1749 NA's :1675
+## potato_y sugbeet_y oth_rt_y wheat_y
+## Min. : 4.361 Min. : 0.00 Min. : 0.00 Min. : 0.6667
+## 1st Qu.:21.584 1st Qu.: 54.07 1st Qu.:15.11 1st Qu.: 3.1662
+## Median :27.763 Median : 63.52 Median :25.10 Median : 4.5731
+## Mean :28.951 Mean : 62.50 Mean :29.77 Mean : 4.8382
+## 3rd Qu.:36.471 3rd Qu.: 76.07 3rd Qu.:37.46 3rd Qu.: 6.3951
+## Max. :53.327 Max. :107.50 Max. :94.40 Max. :10.2402
+## NA's :1676 NA's :1755 NA's :1915 NA's :1638
+## oats_y oth_oil_y fibre_y oth_ind_y
+## Min. :0.5367 Min. : 0.000 Min. : 0.000 Min. : 0.0000
+## 1st Qu.:2.2544 1st Qu.: 1.389 1st Qu.: 1.103 1st Qu.: 0.6786
+## Median :3.1310 Median : 2.000 Median : 3.077 Median : 1.4677
+## Mean :3.3798 Mean : 2.288 Mean : 3.510 Mean : 2.2600
+## 3rd Qu.:4.5236 3rd Qu.: 2.670 3rd Qu.: 5.497 3rd Qu.: 2.4167
+## Max. :8.5116 Max. :28.000 Max. :19.400 Max. :78.4444
+## NA's :1671 NA's :1748 NA's :1883 NA's :1772
+## fodder_y LEVL_CODE
+## Min. : 0.00 Min. :0.000
+## 1st Qu.:10.27 1st Qu.:3.000
+## Median :18.53 Median :3.000
+## Mean :21.88 Mean :2.658
+## 3rd Qu.:34.33 3rd Qu.:3.000
+## Max. :51.05 Max. :3.000
+## NA's :1691#Spurious sugar beet
+crop.yield[crop.yield$geo %in% crop.yield$geo[grep('SE', crop.yield$geo)], c('geo', 'sugbeet_y')]## geo sugbeet_y
+## 1599 SE 62.51595
+## 1600 SE1 0.00000
+## 1601 SE11 0.00000
+## 1602 SE110 NA
+## 1603 SE12 0.00000
+## 1604 SE121 NA
+## 1605 SE122 NA
+## 1606 SE123 NA
+## 1607 SE124 NA
+## 1608 SE125 NA
+## 1609 SE2 62.45091
+## 1610 SE21 47.68000
+## 1611 SE211 NA
+## 1612 SE212 NA
+## 1613 SE213 NA
+## 1614 SE214 NA
+## 1615 SE22 62.59545
+## 1616 SE221 NA
+## 1617 SE224 NA
+## 1618 SE23 58.27869
+## 1619 SE231 NA
+## 1620 SE232 NA
+## 1621 SE3 NA
+## 1622 SE31 NA
+## 1623 SE311 NA
+## 1624 SE312 NA
+## 1625 SE313 NA
+## 1626 SE32 NA
+## 1627 SE321 NA
+## 1628 SE322 NA
+## 1629 SE33 NA
+## 1630 SE331 NA
+## 1631 SE332 NAcrop.yield[crop.yield$geo %in% crop.yield$geo[grep('SE1', crop.yield$geo)], 'sugbeet_y'] <- crop.yield[crop.yield$geo == "SE", 'sugbeet_y']
+
+#Spurious potatoes
+crop.yield[crop.yield$geo %in% crop.yield$geo[grep('SE', crop.yield$geo)], c('geo', 'potato_y')]## geo potato_y
+## 1599 SE 33.387405
+## 1600 SE1 31.598152
+## 1601 SE11 7.532468
+## 1602 SE110 NA
+## 1603 SE12 32.364603
+## 1604 SE121 NA
+## 1605 SE122 NA
+## 1606 SE123 NA
+## 1607 SE124 NA
+## 1608 SE125 NA
+## 1609 SE2 35.211456
+## 1610 SE21 33.863388
+## 1611 SE211 NA
+## 1612 SE212 NA
+## 1613 SE213 NA
+## 1614 SE214 NA
+## 1615 SE22 36.225223
+## 1616 SE221 NA
+## 1617 SE224 NA
+## 1618 SE23 32.788811
+## 1619 SE231 NA
+## 1620 SE232 NA
+## 1621 SE3 21.584253
+## 1622 SE31 24.928989
+## 1623 SE311 NA
+## 1624 SE312 NA
+## 1625 SE313 NA
+## 1626 SE32 18.534483
+## 1627 SE321 NA
+## 1628 SE322 NA
+## 1629 SE33 16.310241
+## 1630 SE331 NA
+## 1631 SE332 NAcrop.yield[crop.yield$geo == "SE11", 'potato_y'] <- crop.yield[crop.yield$geo == "SE1", 'potato_y']
+
+#Spurious other oil crops
+crop.yield[which(crop.yield$oth_oil_y > 5), c('geo', 'oth_oil_y')]## geo oth_oil_y
+## 66 BE 7.759091
+## 198 CY0 28.000000
+## 199 CY00 28.000000
+## 848 ES62 24.333333
+## 1153 ITF4 9.333333crop.yield[crop.yield$geo %in% crop.yield$geo[grep('BE', crop.yield$geo)], c('geo', 'oth_oil_y')]## geo oth_oil_y
+## 66 BE 7.75909091
+## 67 BE1 NA
+## 68 BE10 NA
+## 69 BE100 NA
+## 70 BE2 0.40322581
+## 71 BE21 NA
+## 72 BE211 NA
+## 73 BE212 NA
+## 74 BE213 NA
+## 75 BE22 0.00000000
+## 76 BE221 NA
+## 77 BE222 NA
+## 78 BE223 NA
+## 79 BE23 0.38461538
+## 80 BE231 NA
+## 81 BE232 NA
+## 82 BE233 NA
+## 83 BE234 NA
+## 84 BE235 NA
+## 85 BE236 NA
+## 86 BE24 0.00000000
+## 87 BE241 NA
+## 88 BE242 NA
+## 89 BE25 0.37500000
+## 90 BE251 NA
+## 91 BE252 NA
+## 92 BE253 NA
+## 93 BE254 NA
+## 94 BE255 NA
+## 95 BE256 NA
+## 96 BE257 NA
+## 97 BE258 NA
+## 98 BE3 0.09140768
+## 99 BE31 0.00000000
+## 100 BE310 NA
+## 101 BE32 0.00000000
+## 102 BE321 NA
+## 103 BE322 NA
+## 104 BE323 NA
+## 105 BE324 NA
+## 106 BE325 NA
+## 107 BE326 NA
+## 108 BE327 NA
+## 109 BE33 0.00000000
+## 110 BE331 NA
+## 111 BE332 NA
+## 112 BE334 NA
+## 113 BE335 NA
+## 114 BE336 NA
+## 115 BE34 0.00000000
+## 116 BE341 NA
+## 117 BE342 NA
+## 118 BE343 NA
+## 119 BE344 NA
+## 120 BE345 NA
+## 121 BE35 0.00000000
+## 122 BE351 NA
+## 123 BE352 NA
+## 124 BE353 NAcrop.yield[crop.yield$geo == "BE", 'oth_oil_y'] <- mean(crop.yield[crop.yield$geo %in% c("BE2", "BE3"), 'oth_oil_y'])
+
+crop.yield.dat.2013nuts.sum[which(crop.yield.dat.2013nuts.sum$geo == "CY"), c('geo', 'oth_oil_a', 'oth_oil_p')]## # A tibble: 1 x 3
+## geo oth_oil_a oth_oil_p
+## <chr> <dbl> <dbl>
+## 1 CY 0.0738 0.261crop.yield[crop.yield$geo %in% c("CY0", "CY00"), 'oth_oil_y'] <- crop.yield[crop.yield$geo == "CY", 'oth_oil_y']
+
+crop.yield[crop.yield$geo %in% crop.yield$geo[grep('ES6', crop.yield$geo)], c('geo', 'oth_oil_y')]## geo oth_oil_y
+## 838 ES6 0.3014466
+## 839 ES61 0.2827409
+## 840 ES611 NA
+## 841 ES612 NA
+## 842 ES613 NA
+## 843 ES614 NA
+## 844 ES615 NA
+## 845 ES616 NA
+## 846 ES617 NA
+## 847 ES618 NA
+## 848 ES62 24.3333333
+## 849 ES620 NA
+## 850 ES63 NA
+## 851 ES630 NA
+## 852 ES64 NA
+## 853 ES640 NAcrop.yield[crop.yield$geo == "ES62", 'oth_oil_y'] <- crop.yield[crop.yield$geo == "ES6", 'oth_oil_y']
+
+crop.yield[crop.yield$geo %in% crop.yield$geo[grep('ITF', crop.yield$geo)], c('geo', 'oth_oil_y')]## geo oth_oil_y
+## 1138 ITF 3.322581
+## 1139 ITF1 2.872727
+## 1140 ITF11 NA
+## 1141 ITF12 NA
+## 1142 ITF13 NA
+## 1143 ITF14 NA
+## 1144 ITF2 NA
+## 1145 ITF21 NA
+## 1146 ITF22 NA
+## 1147 ITF3 NA
+## 1148 ITF31 NA
+## 1149 ITF32 NA
+## 1150 ITF33 NA
+## 1151 ITF34 NA
+## 1152 ITF35 NA
+## 1153 ITF4 9.333333
+## 1154 ITF43 NA
+## 1155 ITF44 NA
+## 1156 ITF45 NA
+## 1157 ITF46 NA
+## 1158 ITF47 NA
+## 1159 ITF48 NA
+## 1160 ITF5 NA
+## 1161 ITF51 NA
+## 1162 ITF52 NA
+## 1163 ITF6 4.045455
+## 1164 ITF61 NA
+## 1165 ITF62 NA
+## 1166 ITF63 NA
+## 1167 ITF64 NA
+## 1168 ITF65 NAcrop.yield[crop.yield$geo == "ITF4", 'oth_oil_y'] <- crop.yield[crop.yield$geo == "ITF", 'oth_oil_y']
+
+summary(crop.yield)## geo rye_y barley_y maize_y
+## Length:2013 Min. :0.000 Min. :0.1254 Min. : 0.000
+## Class :character 1st Qu.:2.436 1st Qu.:2.9163 1st Qu.: 6.059
+## Mode :character Median :3.172 Median :4.1115 Median : 8.146
+## Mean :3.452 Mean :4.3295 Mean : 7.801
+## 3rd Qu.:4.507 3rd Qu.:5.6912 3rd Qu.: 9.917
+## Max. :7.143 Max. :8.7350 Max. :12.976
+## NA's :1680 NA's :1640 NA's :1680
+## tritic_y sorghum_y oth_cer_y rice_y
+## Min. :0.000 Min. :1.000 Min. : 0.000 Min. : 0.000
+## 1st Qu.:3.003 1st Qu.:3.100 1st Qu.: 1.198 1st Qu.: 4.504
+## Median :3.990 Median :4.393 Median : 2.066 Median : 5.524
+## Mean :4.026 Mean :4.516 Mean : 2.491 Mean : 5.442
+## 3rd Qu.:5.216 3rd Qu.:5.968 3rd Qu.: 3.659 3rd Qu.: 6.456
+## Max. :7.359 Max. :9.113 Max. :10.750 Max. :10.000
+## NA's :1735 NA's :1869 NA's :1919 NA's :1926
+## pasture_y rape_y sunflow_y pulses_y
+## Min. : 0.000 Min. :0.000 Min. :0.000 Min. :0.000
+## 1st Qu.: 3.655 1st Qu.:2.331 1st Qu.:1.718 1st Qu.:1.413
+## Median : 6.936 Median :2.903 Median :2.169 Median :2.034
+## Mean :10.213 Mean :2.859 Mean :2.074 Mean :2.139
+## 3rd Qu.:12.340 3rd Qu.:3.543 3rd Qu.:2.570 3rd Qu.:2.747
+## Max. :49.514 Max. :5.000 Max. :4.393 Max. :6.705
+## NA's :1799 NA's :1710 NA's :1749 NA's :1675
+## potato_y sugbeet_y oth_rt_y wheat_y
+## Min. : 4.361 Min. : 5.00 Min. : 0.00 Min. : 0.6667
+## 1st Qu.:21.667 1st Qu.: 55.42 1st Qu.:15.11 1st Qu.: 3.1662
+## Median :27.769 Median : 62.66 Median :25.10 Median : 4.5731
+## Mean :29.023 Mean : 63.21 Mean :29.77 Mean : 4.8382
+## 3rd Qu.:36.471 3rd Qu.: 75.22 3rd Qu.:37.46 3rd Qu.: 6.3951
+## Max. :53.327 Max. :107.50 Max. :94.40 Max. :10.2402
+## NA's :1676 NA's :1749 NA's :1915 NA's :1638
+## oats_y oth_oil_y fibre_y oth_ind_y
+## Min. :0.5367 Min. :0.000 Min. : 0.000 Min. : 0.0000
+## 1st Qu.:2.2544 1st Qu.:1.327 1st Qu.: 1.103 1st Qu.: 0.6786
+## Median :3.1310 Median :2.000 Median : 3.077 Median : 1.4677
+## Mean :3.3798 Mean :1.962 Mean : 3.510 Mean : 2.2600
+## 3rd Qu.:4.5236 3rd Qu.:2.661 3rd Qu.: 5.497 3rd Qu.: 2.4167
+## Max. :8.5116 Max. :5.000 Max. :19.400 Max. :78.4444
+## NA's :1671 NA's :1748 NA's :1883 NA's :1772
+## fodder_y LEVL_CODE
+## Min. : 0.00 Min. :0.000
+## 1st Qu.:10.27 1st Qu.:3.000
+## Median :18.53 Median :3.000
+## Mean :21.88 Mean :2.658
+## 3rd Qu.:34.33 3rd Qu.:3.000
+## Max. :51.05 Max. :3.000
+## NA's :1691#Spurious fibre crops
+crop.yield[which(crop.yield$fibre_y > 6), c('geo', 'fibre_y')]## geo fibre_y
+## 20 AT11 7.777778
+## 39 AT22 7.666667
+## 79 BE23 6.067623
+## 162 CH 19.400000
+## 890 FR 6.637914
+## 901 FR21 6.508475
+## 903 FR23 6.304694
+## 907 FR30 6.100000
+## 912 FR52 6.666667
+## 943 FRD 6.229119
+## 972 FRH 6.666667
+## 1294 NL 6.129700
+## 1295 NL1 7.838207
+## 1652 SK02 8.333333crop.yield[which(crop.yield$geo == "CH"), 'fibre_y'] <- NA
+
+summary(crop.yield)## geo rye_y barley_y maize_y
+## Length:2013 Min. :0.000 Min. :0.1254 Min. : 0.000
+## Class :character 1st Qu.:2.436 1st Qu.:2.9163 1st Qu.: 6.059
+## Mode :character Median :3.172 Median :4.1115 Median : 8.146
+## Mean :3.452 Mean :4.3295 Mean : 7.801
+## 3rd Qu.:4.507 3rd Qu.:5.6912 3rd Qu.: 9.917
+## Max. :7.143 Max. :8.7350 Max. :12.976
+## NA's :1680 NA's :1640 NA's :1680
+## tritic_y sorghum_y oth_cer_y rice_y
+## Min. :0.000 Min. :1.000 Min. : 0.000 Min. : 0.000
+## 1st Qu.:3.003 1st Qu.:3.100 1st Qu.: 1.198 1st Qu.: 4.504
+## Median :3.990 Median :4.393 Median : 2.066 Median : 5.524
+## Mean :4.026 Mean :4.516 Mean : 2.491 Mean : 5.442
+## 3rd Qu.:5.216 3rd Qu.:5.968 3rd Qu.: 3.659 3rd Qu.: 6.456
+## Max. :7.359 Max. :9.113 Max. :10.750 Max. :10.000
+## NA's :1735 NA's :1869 NA's :1919 NA's :1926
+## pasture_y rape_y sunflow_y pulses_y
+## Min. : 0.000 Min. :0.000 Min. :0.000 Min. :0.000
+## 1st Qu.: 3.655 1st Qu.:2.331 1st Qu.:1.718 1st Qu.:1.413
+## Median : 6.936 Median :2.903 Median :2.169 Median :2.034
+## Mean :10.213 Mean :2.859 Mean :2.074 Mean :2.139
+## 3rd Qu.:12.340 3rd Qu.:3.543 3rd Qu.:2.570 3rd Qu.:2.747
+## Max. :49.514 Max. :5.000 Max. :4.393 Max. :6.705
+## NA's :1799 NA's :1710 NA's :1749 NA's :1675
+## potato_y sugbeet_y oth_rt_y wheat_y
+## Min. : 4.361 Min. : 5.00 Min. : 0.00 Min. : 0.6667
+## 1st Qu.:21.667 1st Qu.: 55.42 1st Qu.:15.11 1st Qu.: 3.1662
+## Median :27.769 Median : 62.66 Median :25.10 Median : 4.5731
+## Mean :29.023 Mean : 63.21 Mean :29.77 Mean : 4.8382
+## 3rd Qu.:36.471 3rd Qu.: 75.22 3rd Qu.:37.46 3rd Qu.: 6.3951
+## Max. :53.327 Max. :107.50 Max. :94.40 Max. :10.2402
+## NA's :1676 NA's :1749 NA's :1915 NA's :1638
+## oats_y oth_oil_y fibre_y oth_ind_y
+## Min. :0.5367 Min. :0.000 Min. :0.000 Min. : 0.0000
+## 1st Qu.:2.2544 1st Qu.:1.327 1st Qu.:1.093 1st Qu.: 0.6786
+## Median :3.1310 Median :2.000 Median :3.077 Median : 1.4677
+## Mean :3.3798 Mean :1.962 Mean :3.387 Mean : 2.2600
+## 3rd Qu.:4.5236 3rd Qu.:2.661 3rd Qu.:5.489 3rd Qu.: 2.4167
+## Max. :8.5116 Max. :5.000 Max. :8.333 Max. :78.4444
+## NA's :1671 NA's :1748 NA's :1884 NA's :1772
+## fodder_y LEVL_CODE
+## Min. : 0.00 Min. :0.000
+## 1st Qu.:10.27 1st Qu.:3.000
+## Median :18.53 Median :3.000
+## Mean :21.88 Mean :2.658
+## 3rd Qu.:34.33 3rd Qu.:3.000
+## Max. :51.05 Max. :3.000
+## NA's :1691#Spurious other industrial crops
+crop.yield[which(crop.yield$oth_ind_y > 10), c('geo', 'oth_ind_y')]## geo oth_ind_y
+## 35 AT21 10.95238
+## 758 EL62 78.44444
+## 1089 IE 13.16592
+## 1090 IE0 13.36992crop.yield[crop.yield$geo == "EL62", 'oth_ind_y'] <- crop.yield[crop.yield$geo == "EL6", 'oth_ind_y']
+
+summary(crop.yield)## geo rye_y barley_y maize_y
+## Length:2013 Min. :0.000 Min. :0.1254 Min. : 0.000
+## Class :character 1st Qu.:2.436 1st Qu.:2.9163 1st Qu.: 6.059
+## Mode :character Median :3.172 Median :4.1115 Median : 8.146
+## Mean :3.452 Mean :4.3295 Mean : 7.801
+## 3rd Qu.:4.507 3rd Qu.:5.6912 3rd Qu.: 9.917
+## Max. :7.143 Max. :8.7350 Max. :12.976
+## NA's :1680 NA's :1640 NA's :1680
+## tritic_y sorghum_y oth_cer_y rice_y
+## Min. :0.000 Min. :1.000 Min. : 0.000 Min. : 0.000
+## 1st Qu.:3.003 1st Qu.:3.100 1st Qu.: 1.198 1st Qu.: 4.504
+## Median :3.990 Median :4.393 Median : 2.066 Median : 5.524
+## Mean :4.026 Mean :4.516 Mean : 2.491 Mean : 5.442
+## 3rd Qu.:5.216 3rd Qu.:5.968 3rd Qu.: 3.659 3rd Qu.: 6.456
+## Max. :7.359 Max. :9.113 Max. :10.750 Max. :10.000
+## NA's :1735 NA's :1869 NA's :1919 NA's :1926
+## pasture_y rape_y sunflow_y pulses_y
+## Min. : 0.000 Min. :0.000 Min. :0.000 Min. :0.000
+## 1st Qu.: 3.655 1st Qu.:2.331 1st Qu.:1.718 1st Qu.:1.413
+## Median : 6.936 Median :2.903 Median :2.169 Median :2.034
+## Mean :10.213 Mean :2.859 Mean :2.074 Mean :2.139
+## 3rd Qu.:12.340 3rd Qu.:3.543 3rd Qu.:2.570 3rd Qu.:2.747
+## Max. :49.514 Max. :5.000 Max. :4.393 Max. :6.705
+## NA's :1799 NA's :1710 NA's :1749 NA's :1675
+## potato_y sugbeet_y oth_rt_y wheat_y
+## Min. : 4.361 Min. : 5.00 Min. : 0.00 Min. : 0.6667
+## 1st Qu.:21.667 1st Qu.: 55.42 1st Qu.:15.11 1st Qu.: 3.1662
+## Median :27.769 Median : 62.66 Median :25.10 Median : 4.5731
+## Mean :29.023 Mean : 63.21 Mean :29.77 Mean : 4.8382
+## 3rd Qu.:36.471 3rd Qu.: 75.22 3rd Qu.:37.46 3rd Qu.: 6.3951
+## Max. :53.327 Max. :107.50 Max. :94.40 Max. :10.2402
+## NA's :1676 NA's :1749 NA's :1915 NA's :1638
+## oats_y oth_oil_y fibre_y oth_ind_y
+## Min. :0.5367 Min. :0.000 Min. :0.000 Min. : 0.0000
+## 1st Qu.:2.2544 1st Qu.:1.327 1st Qu.:1.093 1st Qu.: 0.6786
+## Median :3.1310 Median :2.000 Median :3.077 Median : 1.4677
+## Mean :3.3798 Mean :1.962 Mean :3.387 Mean : 1.9474
+## 3rd Qu.:4.5236 3rd Qu.:2.661 3rd Qu.:5.489 3rd Qu.: 2.4167
+## Max. :8.5116 Max. :5.000 Max. :8.333 Max. :13.3699
+## NA's :1671 NA's :1748 NA's :1884 NA's :1772
+## fodder_y LEVL_CODE
+## Min. : 0.00 Min. :0.000
+## 1st Qu.:10.27 1st Qu.:3.000
+## Median :18.53 Median :3.000
+## Mean :21.88 Mean :2.658
+## 3rd Qu.:34.33 3rd Qu.:3.000
+## Max. :51.05 Max. :3.000
+## NA's :1691#Finally, run script to allocate NUTS1 or NUTS0 fractions to NUTS2 where needed
+
+#list to summarise where data are NUTS2, 1, 0 for each variable
+data.level.crop.y <- vector("list", 4*length(names(crop.yield)[2:21]))
+names(data.level.crop.y) <- c(paste(names(crop.yield)[2:21], 'n2.dat', sep='.'),
+ paste(names(crop.yield)[2:21], 'n1.dat', sep='.'),
+ paste(names(crop.yield)[2:21], 'n0.dat', sep='.'),
+ paste(names(crop.yield)[2:21], 'nuts0.na', sep='.')
+ )
+labels(data.level.crop.y)## [1] "rye_y.n2.dat" "barley_y.n2.dat" "maize_y.n2.dat"
+## [4] "tritic_y.n2.dat" "sorghum_y.n2.dat" "oth_cer_y.n2.dat"
+## [7] "rice_y.n2.dat" "pasture_y.n2.dat" "rape_y.n2.dat"
+## [10] "sunflow_y.n2.dat" "pulses_y.n2.dat" "potato_y.n2.dat"
+## [13] "sugbeet_y.n2.dat" "oth_rt_y.n2.dat" "wheat_y.n2.dat"
+## [16] "oats_y.n2.dat" "oth_oil_y.n2.dat" "fibre_y.n2.dat"
+## [19] "oth_ind_y.n2.dat" "fodder_y.n2.dat" "rye_y.n1.dat"
+## [22] "barley_y.n1.dat" "maize_y.n1.dat" "tritic_y.n1.dat"
+## [25] "sorghum_y.n1.dat" "oth_cer_y.n1.dat" "rice_y.n1.dat"
+## [28] "pasture_y.n1.dat" "rape_y.n1.dat" "sunflow_y.n1.dat"
+## [31] "pulses_y.n1.dat" "potato_y.n1.dat" "sugbeet_y.n1.dat"
+## [34] "oth_rt_y.n1.dat" "wheat_y.n1.dat" "oats_y.n1.dat"
+## [37] "oth_oil_y.n1.dat" "fibre_y.n1.dat" "oth_ind_y.n1.dat"
+## [40] "fodder_y.n1.dat" "rye_y.n0.dat" "barley_y.n0.dat"
+## [43] "maize_y.n0.dat" "tritic_y.n0.dat" "sorghum_y.n0.dat"
+## [46] "oth_cer_y.n0.dat" "rice_y.n0.dat" "pasture_y.n0.dat"
+## [49] "rape_y.n0.dat" "sunflow_y.n0.dat" "pulses_y.n0.dat"
+## [52] "potato_y.n0.dat" "sugbeet_y.n0.dat" "oth_rt_y.n0.dat"
+## [55] "wheat_y.n0.dat" "oats_y.n0.dat" "oth_oil_y.n0.dat"
+## [58] "fibre_y.n0.dat" "oth_ind_y.n0.dat" "fodder_y.n0.dat"
+## [61] "rye_y.nuts0.na" "barley_y.nuts0.na" "maize_y.nuts0.na"
+## [64] "tritic_y.nuts0.na" "sorghum_y.nuts0.na" "oth_cer_y.nuts0.na"
+## [67] "rice_y.nuts0.na" "pasture_y.nuts0.na" "rape_y.nuts0.na"
+## [70] "sunflow_y.nuts0.na" "pulses_y.nuts0.na" "potato_y.nuts0.na"
+## [73] "sugbeet_y.nuts0.na" "oth_rt_y.nuts0.na" "wheat_y.nuts0.na"
+## [76] "oats_y.nuts0.na" "oth_oil_y.nuts0.na" "fibre_y.nuts0.na"
+## [79] "oth_ind_y.nuts0.na" "fodder_y.nuts0.na"dbase.yield <- as.data.frame(matrix(nrow=nrow(nuts@data), ncol=(ncol(crop.yield[,2:21]) + 1)))
+dbase.yield[,1] <- nuts@data$NUTS_ID
+names(dbase.yield) <- c("NUTS_ID", names(crop.yield)[2:21])
+head(dbase.yield)## NUTS_ID rye_y barley_y maize_y tritic_y sorghum_y oth_cer_y rice_y
+## 1 AT11 NA NA NA NA NA NA NA
+## 2 AT22 NA NA NA NA NA NA NA
+## 3 AT12 NA NA NA NA NA NA NA
+## 4 AT13 NA NA NA NA NA NA NA
+## 5 AT21 NA NA NA NA NA NA NA
+## 6 AT31 NA NA NA NA NA NA NA
+## pasture_y rape_y sunflow_y pulses_y potato_y sugbeet_y oth_rt_y wheat_y
+## 1 NA NA NA NA NA NA NA NA
+## 2 NA NA NA NA NA NA NA NA
+## 3 NA NA NA NA NA NA NA NA
+## 4 NA NA NA NA NA NA NA NA
+## 5 NA NA NA NA NA NA NA NA
+## 6 NA NA NA NA NA NA NA NA
+## oats_y oth_oil_y fibre_y oth_ind_y fodder_y
+## 1 NA NA NA NA NA
+## 2 NA NA NA NA NA
+## 3 NA NA NA NA NA
+## 4 NA NA NA NA NA
+## 5 NA NA NA NA NA
+## 6 NA NA NA NA NAnrow(dbase.yield)## [1] 320attach(crop.yield)
+for(i in names(crop.yield)[2:21]) {
+ (nuts2.na <- crop.yield[LEVL_CODE == 2 & is.na(crop.yield[,i]), 'geo'])
+ (nuts1 <- crop.yield[LEVL_CODE == 1 & geo %in% gsub(".{1}$", "", nuts2.na), 'geo'])
+ (nuts1.na <- crop.yield[geo %in% nuts1 & is.na(crop.yield[,i]), 'geo'])
+ (nuts0 <- crop.yield[LEVL_CODE == 0 & geo %in% gsub(".{1}$", "", nuts1.na), 'geo'])
+ (nuts0.na <- crop.yield[geo %in% nuts0 & is.na(crop.yield[,i]), 'geo'])
+
+#NUTS2 data
+(n2.dat <- crop.yield[!(geo %in% nuts2.na) & LEVL_CODE == 2, 'geo'])
+#NUTS1 data
+(n1.dat <- nuts1[!nuts1 %in% nuts1.na])
+#NUTS0 data
+(n0.dat <- nuts0[!nuts0 %in% nuts0.na])
+#NO DATA
+nuts0.na
+
+data.level.crop.y[[paste(i, 'n2.dat', sep='.')]] <- n2.dat
+data.level.crop.y[[paste(i, 'n1.dat', sep='.')]] <- n1.dat
+data.level.crop.y[[paste(i, 'n0.dat', sep='.')]] <- n0.dat
+data.level.crop.y[[paste(i, 'nuts0.na', sep='.')]] <- nuts0.na
+
+ for(e in n0.dat) {
+ dbase.yield[dbase.yield$NUTS_ID %in% dbase.yield$NUTS_ID[grep(paste(e, '..', sep=''), dbase.yield$NUTS_ID)], i] <- crop.yield[crop.yield$geo == e, i]
+ }
+
+ for(e in n1.dat) {
+ dbase.yield[dbase.yield$NUTS_ID %in% dbase.yield$NUTS_ID[grep(paste(e, '.', sep=''), dbase.yield$NUTS_ID)], i] <- crop.yield[crop.yield$geo == e, i]
+ }
+
+ for(e in n2.dat) {
+ dbase.yield[dbase.yield$NUTS_ID == e, i] <- crop.yield[crop.yield$geo == e, i]
+ }
+}
+detach(crop.yield)
+
+summary(dbase.yield)## NUTS_ID rye_y barley_y maize_y
+## AT11 : 1 Min. :0.000 Min. :0.1254 Min. : 0.000
+## AT12 : 1 1st Qu.:2.584 1st Qu.:3.0000 1st Qu.: 6.320
+## AT13 : 1 Median :3.436 Median :4.6743 Median : 7.973
+## AT21 : 1 Mean :3.652 Mean :4.5982 Mean : 7.795
+## AT22 : 1 3rd Qu.:4.934 3rd Qu.:6.1262 3rd Qu.: 9.835
+## AT31 : 1 Max. :7.143 Max. :8.4666 Max. :12.976
+## (Other):314 NA's :10 NA's :9 NA's :23
+## tritic_y sorghum_y oth_cer_y rice_y
+## Min. :0.000 Min. :1.000 Min. : 0.000 Min. : 0.000
+## 1st Qu.:2.933 1st Qu.:3.173 1st Qu.: 1.363 1st Qu.: 4.567
+## Median :4.000 Median :4.000 Median : 2.114 Median : 5.051
+## Mean :3.966 Mean :4.349 Mean : 2.181 Mean : 5.314
+## 3rd Qu.:5.218 3rd Qu.:5.675 3rd Qu.: 3.045 3rd Qu.: 5.977
+## Max. :7.359 Max. :9.044 Max. :10.750 Max. :10.000
+## NA's :22 NA's :175 NA's :130 NA's :178
+## pasture_y rape_y sunflow_y pulses_y
+## Min. : 0.000 Min. :0.000 Min. :0.000 Min. :0.000
+## 1st Qu.: 4.320 1st Qu.:2.417 1st Qu.:1.667 1st Qu.:1.544
+## Median : 7.339 Median :3.186 Median :2.159 Median :2.162
+## Mean : 9.295 Mean :2.946 Mean :2.102 Mean :2.173
+## 3rd Qu.:10.125 3rd Qu.:3.544 3rd Qu.:2.644 3rd Qu.:2.762
+## Max. :49.514 Max. :5.000 Max. :4.393 Max. :5.002
+## NA's :99 NA's :19 NA's :91 NA's :16
+## potato_y sugbeet_y oth_rt_y wheat_y
+## Min. : 4.361 Min. : 5.00 Min. : 0.00 Min. :0.6667
+## 1st Qu.:24.144 1st Qu.: 57.45 1st Qu.: 0.00 1st Qu.:3.3922
+## Median :31.598 Median : 67.95 Median :13.27 Median :5.1819
+## Mean :31.469 Mean : 65.07 Mean :22.73 Mean :5.3029
+## 3rd Qu.:40.329 3rd Qu.: 76.28 3rd Qu.:30.83 3rd Qu.:7.4295
+## Max. :53.327 Max. :107.50 Max. :94.40 Max. :9.2898
+## NA's :7 NA's :34 NA's :111 NA's :9
+## oats_y oth_oil_y fibre_y oth_ind_y
+## Min. :0.5367 Min. :0.000 Min. :0.000 Min. : 0.0000
+## 1st Qu.:2.3067 1st Qu.:1.342 1st Qu.:1.345 1st Qu.: 0.9845
+## Median :3.4671 Median :1.972 Median :2.073 Median : 1.8333
+## Mean :3.5414 Mean :1.947 Mean :2.951 Mean : 2.7491
+## 3rd Qu.:4.7295 3rd Qu.:2.782 3rd Qu.:4.819 3rd Qu.: 3.2637
+## Max. :7.2000 Max. :5.000 Max. :8.333 Max. :13.3699
+## NA's :9 NA's :18 NA's :137 NA's :31
+## fodder_y
+## Min. : 0.00
+## 1st Qu.:12.50
+## Median :25.97
+## Mean :25.70
+## 3rd Qu.:38.13
+## Max. :51.05
+## NA's :11head(dbase.yield)## NUTS_ID rye_y barley_y maize_y tritic_y sorghum_y oth_cer_y rice_y
+## 1 AT11 3.516367 4.435137 8.744878 3.649591 5.164671 3.868583 NA
+## 2 AT22 4.700782 5.715165 11.440518 6.234155 8.588477 3.681250 NA
+## 3 AT12 4.357949 4.924511 9.361459 5.100860 6.237822 3.901009 NA
+## 4 AT13 4.030303 4.468468 8.798165 5.024390 3.000000 3.944444 NA
+## 5 AT21 4.592187 5.394585 10.736016 5.808485 6.694444 3.817204 NA
+## 6 AT31 4.503259 6.279062 10.027501 5.474152 5.848101 3.869565 NA
+## pasture_y rape_y sunflow_y pulses_y potato_y sugbeet_y oth_rt_y
+## 1 5.264291 2.800108 2.344708 2.020007 34.06111 68.85210 47.12500
+## 2 6.965349 3.519774 2.430000 2.610619 27.19406 67.16500 51.00000
+## 3 6.666021 3.139327 2.623319 2.295685 31.89232 71.15838 61.30303
+## 4 5.615385 2.918750 2.647059 2.214286 34.87692 69.50661 58.60976
+## 5 7.327343 2.416667 1.912698 3.035211 24.40728 57.81250 40.91667
+## 6 7.502266 3.812215 2.097035 2.751594 30.02403 77.22785 63.89655
+## wheat_y oats_y oth_oil_y fibre_y oth_ind_y fodder_y
+## 1 4.418312 3.320119 2.106922 7.777778 1.333333 18.05331
+## 2 6.405516 3.681343 1.061669 7.666667 6.587339 29.00264
+## 3 5.197458 3.752801 1.601008 4.966805 1.894773 23.44168
+## 4 4.702658 2.909091 2.016393 5.134100 0.000000 11.72727
+## 5 5.443334 3.707787 2.669792 4.800000 10.952381 31.81458
+## 6 6.893955 4.364527 2.660348 5.361111 3.804918 28.50815tail(dbase.yield)## NUTS_ID rye_y barley_y maize_y tritic_y sorghum_y oth_cer_y
+## 315 UKD3 2.908474 5.037901 6.320472 4.000000 NA NA
+## 316 TRC1 2.747730 2.887574 7.846154 3.321429 4 2
+## 317 TRC2 2.747730 2.147769 7.972516 3.321429 4 2
+## 318 UKD4 2.908474 5.037901 6.320472 4.000000 NA NA
+## 319 TRC3 2.747730 2.910377 9.320635 3.321429 4 2
+## 320 UKM6 2.908474 5.879533 6.320472 3.000000 NA NA
+## rice_y pasture_y rape_y sunflow_y pulses_y potato_y sugbeet_y
+## 315 NA NA 3.309524 NA 2.666667 40.32860 61.76471
+## 316 3.333333 NA 3.462185 2.200000 1.528384 25.00000 77.83333
+## 317 3.333333 NA 3.462185 1.714286 1.560811 30.00000 24.00000
+## 318 NA NA 3.309524 NA 2.666667 40.32860 61.76471
+## 319 3.333333 NA 3.462185 1.807692 1.996479 31.48791 82.00000
+## 320 NA NA 3.185760 NA 2.666667 40.32860 69.90356
+## oth_rt_y wheat_y oats_y oth_oil_y fibre_y oth_ind_y fodder_y
+## 315 0 5.985455 4.695652 1.760192 NA 8.0254104 38.12607
+## 316 12 2.744770 2.355556 2.833333 1.784946 0.7666667 25.17500
+## 317 12 3.103288 2.500000 2.704453 1.713115 0.9090909 38.80000
+## 318 0 5.985455 4.695652 1.760192 NA 8.0254104 38.12607
+## 319 12 3.337816 2.355556 2.781250 1.847619 2.0000000 15.97368
+## 320 0 8.106808 5.888889 1.760192 NA 8.0254104 38.12607#check data level for rye_f as an example
+data.level.crop.y$rye_y.n2.dat## [1] "AT11" "AT12" "AT13" "AT21" "AT22" "AT31" "AT32" "AT33" "AT34" "BE21"
+## [11] "BE22" "BE23" "BE24" "BE25" "BE31" "BE32" "BE33" "BE34" "BE35" "BG31"
+## [21] "BG32" "BG33" "BG34" "BG41" "BG42" "CH01" "CH02" "CH03" "CH04" "CH05"
+## [31] "CH06" "CH07" "CZ01" "CZ02" "CZ03" "CZ04" "CZ05" "CZ06" "CZ07" "CZ08"
+## [41] "DK01" "DK02" "DK03" "DK04" "DK05" "EL41" "EL42" "EL43" "EL51" "EL52"
+## [51] "EL53" "EL54" "EL61" "EL63" "EL64" "EL65" "ES11" "ES13" "ES21" "ES22"
+## [61] "ES23" "ES24" "ES30" "ES41" "ES42" "ES43" "ES51" "ES52" "ES53" "ES61"
+## [71] "ES62" "ES70" "FI19" "FI1B" "FI1C" "FI1D" "FI20" "FR10" "FR21" "FR22"
+## [81] "FR23" "FR24" "FR25" "FR26" "FR30" "FR41" "FR42" "FR43" "FR51" "FR52"
+## [91] "FR53" "FR61" "FR62" "FR63" "FR71" "FR72" "FR81" "FR82" "HR03" "HR04"
+## [101] "HU10" "HU21" "HU22" "HU23" "HU31" "HU32" "HU33" "ITC1" "ITC2" "ITC4"
+## [111] "ITF1" "ITF3" "ITF4" "ITF5" "ITF6" "ITG1" "ITH1" "ITH3" "ITH5" "ITI1"
+## [121] "ITI4" "LT00" "NL11" "NL12" "NL13" "NL21" "NL22" "NL23" "NL31" "NL32"
+## [131] "NL33" "NL34" "NL41" "NL42" "NO01" "NO02" "NO03" "NO06" "PL11" "PL12"
+## [141] "PL21" "PL22" "PL31" "PL32" "PL33" "PL34" "PL41" "PL42" "PL43" "PL51"
+## [151] "PL52" "PL61" "PL62" "PL63" "PT11" "PT15" "PT16" "PT18" "RO11" "RO12"
+## [161] "RO21" "RO22" "RO31" "RO32" "RO41" "RO42" "RS11" "RS12" "RS21" "RS22"
+## [171] "SE11" "SE12" "SE21" "SE22" "SE23" "SE31" "SE32" "SI03" "SI04" "SK01"
+## [181] "SK02" "SK03" "SK04" "TR21" "TR22" "TR31" "TR32" "TR33" "TR41" "TR51"
+## [191] "TR52" "TR61" "TR62" "TR71" "TR72" "TR82" "TR83" "TR90" "TRA1" "TRA2"
+## [201] "TRB2"data.level.crop.y$rye_y.n1.dat## [1] "DE1" "DE2" "DE4" "DE7" "DE8" "DE9" "DEA" "DEB" "DEC" "DED" "DEE"
+## [12] "DEF" "DEG" "EE0" "EL6" "ES1" "ES6" "IE0" "ITC" "ITF" "ITG" "ITH"
+## [23] "ITI" "LV0" "NO0" "PT1" "SE3" "TR4" "TR6" "TR8" "TRB" "UKE" "UKF"
+## [34] "UKH" "UKJ" "UKK" "UKL"data.level.crop.y$rye_y.n0.dat## [1] "AL" "BE" "DE" "EL" "LU" "ME" "MK" "PT" "TR" "UK"data.level.crop.y$rye_y.nuts0.na## [1] "CY" "IS" "LI" "MT"#Final fix of spurious data
+#London region (UKI)
+dbase.yield[dbase.yield$NUTS_ID %in% dbase.yield$NUTS_ID[grep('UK', dbase.yield$NUTS_ID)],c('NUTS_ID', 'oats_y', 'rye_y', 'barley_y')]## NUTS_ID oats_y rye_y barley_y
+## 275 UKK1 5.0294118 6.000000 5.756677
+## 276 UKN0 5.8750000 2.908474 5.573684
+## 277 UKM2 5.8888889 2.908474 5.879533
+## 278 UKM3 5.8888889 2.908474 5.879533
+## 279 UKM5 5.8888889 2.908474 5.879533
+## 280 UKJ2 5.3936170 6.600000 6.171761
+## 281 UKK2 5.0294118 6.000000 5.756677
+## 282 UKJ3 5.3936170 6.600000 6.171761
+## 283 UKL1 5.0547945 0.000000 5.500000
+## 284 UKJ4 5.3936170 6.600000 6.171761
+## 285 UKK3 5.0294118 6.000000 5.756677
+## 286 UKK4 5.0294118 6.000000 5.756677
+## 287 UKL2 5.0547945 0.000000 5.500000
+## 288 UKD6 4.6956522 2.908474 5.037901
+## 289 UKD7 4.6956522 2.908474 5.037901
+## 290 UKE2 5.6052632 3.500000 6.554737
+## 291 UKE3 5.6052632 3.500000 6.554737
+## 292 UKE4 5.6052632 3.500000 6.554737
+## 293 UKG3 5.9036145 2.908474 5.956710
+## 294 UKF1 5.4038462 5.000000 6.232624
+## 295 UKE1 5.6052632 3.500000 6.554737
+## 296 UKF2 5.4038462 5.000000 6.232624
+## 297 UKG1 5.9036145 2.908474 5.956710
+## 298 UKH2 6.0204082 5.800000 6.150485
+## 299 UKF3 5.4038462 5.000000 6.232624
+## 300 UKI5 0.5367472 2.908474 3.000000
+## 301 UKI6 0.5367472 2.908474 3.000000
+## 302 UKI3 0.5367472 2.908474 3.000000
+## 303 UKI4 0.5367472 2.908474 3.000000
+## 304 UKH3 6.0204082 5.800000 6.150485
+## 305 UKG2 5.9036145 2.908474 5.956710
+## 306 UKI7 0.5367472 2.908474 3.000000
+## 307 UKJ1 5.3936170 6.600000 6.171761
+## 308 UKH1 6.0204082 5.800000 6.150485
+## 310 UKC1 5.8648649 2.908474 6.072674
+## 311 UKC2 5.8648649 2.908474 6.072674
+## 314 UKD1 4.6956522 2.908474 5.037901
+## 315 UKD3 4.6956522 2.908474 5.037901
+## 318 UKD4 4.6956522 2.908474 5.037901
+## 320 UKM6 5.8888889 2.908474 5.879533dbase.yield[dbase.yield$NUTS_ID %in% dbase.yield$NUTS_ID[grep('UKI', dbase.yield$NUTS_ID)], c('oats_y', 'rye_y', 'barley_y')] <- NA
+
+#Make all zero yields NAs
+names(dbase.yield)## [1] "NUTS_ID" "rye_y" "barley_y" "maize_y" "tritic_y"
+## [6] "sorghum_y" "oth_cer_y" "rice_y" "pasture_y" "rape_y"
+## [11] "sunflow_y" "pulses_y" "potato_y" "sugbeet_y" "oth_rt_y"
+## [16] "wheat_y" "oats_y" "oth_oil_y" "fibre_y" "oth_ind_y"
+## [21] "fodder_y"for(e in names(dbase.yield)[-1]) {
+ dbase.yield[which(dbase.yield[,e] == 0), e] <- NA
+}#Crop areas
+berries_a <- st_read(dsn='C:/Users/mu5106sc/Dropbox/STAGS/D1_Database/EU_Farming_Systems_20181015.gdb', layer='crop_berries_a')## Reading layer `crop_berries_a' from data source `C:\Users\mu5106sc\Dropbox\STAGS\D1_Database\EU_Farming_Systems_20181015.gdb' using driver `OpenFileGDB'## Warning: no simple feature geometries present: returning a data.frame or
+## tbl_dfnames(berries_a)[5] <- 'berries_a'
+head(berries_a)## NUTS_ID ZONE_CODE COUNT AREA berries_a
+## 1 AT11 1 70 0.48611111 698.93634
+## 2 AT22 2 284 1.97222222 626.17569
+## 3 AT12 3 333 2.31250000 2923.26766
+## 4 AT13 4 7 0.04861111 12.07276
+## 5 AT21 5 161 1.11805556 267.40934
+## 6 AT31 6 207 1.43750000 1198.84000brassic_a <- st_read(dsn='C:/Users/mu5106sc/Dropbox/STAGS/D1_Database/EU_Farming_Systems_20181015.gdb', layer='crop_brassic_a')## Reading layer `crop_brassic_a' from data source `C:\Users\mu5106sc\Dropbox\STAGS\D1_Database\EU_Farming_Systems_20181015.gdb' using driver `OpenFileGDB'## Warning: no simple feature geometries present: returning a data.frame or
+## tbl_dfnames(brassic_a)[5] <- 'brassic_a'
+head(brassic_a)## NUTS_ID ZONE_CODE COUNT AREA brassic_a
+## 1 AT11 1 70 0.48611111 224.465054
+## 2 AT22 2 284 1.97222222 217.960795
+## 3 AT12 3 333 2.31250000 938.814305
+## 4 AT13 4 7 0.04861111 3.877195
+## 5 AT21 5 161 1.11805556 85.879142
+## 6 AT31 6 207 1.43750000 385.010299citrus_a <- st_read(dsn='C:/Users/mu5106sc/Dropbox/STAGS/D1_Database/EU_Farming_Systems_20181015.gdb', layer='crop_citrus_a')## Reading layer `crop_citrus_a' from data source `C:\Users\mu5106sc\Dropbox\STAGS\D1_Database\EU_Farming_Systems_20181015.gdb' using driver `OpenFileGDB'## Warning: no simple feature geometries present: returning a data.frame or
+## tbl_dfnames(citrus_a)[5] <- 'citrus_a'
+head(citrus_a)## NUTS_ID ZONE_CODE COUNT AREA citrus_a
+## 1 AT11 1 70 0.48611111 0
+## 2 AT22 2 284 1.97222222 0
+## 3 AT12 3 333 2.31250000 0
+## 4 AT13 4 7 0.04861111 0
+## 5 AT21 5 161 1.11805556 0
+## 6 AT31 6 207 1.43750000 0frtrees_a <- st_read(dsn='C:/Users/mu5106sc/Dropbox/STAGS/D1_Database/EU_Farming_Systems_20181015.gdb', layer='crop_frtrees_a')## Reading layer `crop_frtrees_a' from data source `C:\Users\mu5106sc\Dropbox\STAGS\D1_Database\EU_Farming_Systems_20181015.gdb' using driver `OpenFileGDB'## Warning: no simple feature geometries present: returning a data.frame or
+## tbl_dfnames(frtrees_a)[5] <- 'frtrees_a'
+head(frtrees_a)## NUTS_ID ZONE_CODE COUNT AREA frtrees_a
+## 1 AT11 1 70 0.48611111 3395.05625
+## 2 AT22 2 284 1.97222222 3106.60397
+## 3 AT12 3 333 2.31250000 14199.65974
+## 4 AT13 4 7 0.04861111 58.64296
+## 5 AT21 5 161 1.11805556 1298.93051
+## 6 AT31 6 207 1.43750000 5823.31900grapes_a <- st_read(dsn='C:/Users/mu5106sc/Dropbox/STAGS/D1_Database/EU_Farming_Systems_20181015.gdb', layer='crop_grapes_a')## Reading layer `crop_grapes_a' from data source `C:\Users\mu5106sc\Dropbox\STAGS\D1_Database\EU_Farming_Systems_20181015.gdb' using driver `OpenFileGDB'## Warning: no simple feature geometries present: returning a data.frame or
+## tbl_dfnames(grapes_a)[5] <- 'grapes_a'
+head(grapes_a)## NUTS_ID ZONE_CODE COUNT AREA grapes_a
+## 1 AT11 1 70 0.48611111 8087.4269
+## 2 AT22 2 284 1.97222222 2473.9556
+## 3 AT12 3 333 2.31250000 34108.5900
+## 4 AT13 4 7 0.04861111 142.7438
+## 5 AT21 5 161 1.11805556 962.3650
+## 6 AT31 6 207 1.43750000 0.0000greens_a <- st_read(dsn='C:/Users/mu5106sc/Dropbox/STAGS/D1_Database/EU_Farming_Systems_20181015.gdb', layer='crop_greens_a')## Reading layer `crop_greens_a' from data source `C:\Users\mu5106sc\Dropbox\STAGS\D1_Database\EU_Farming_Systems_20181015.gdb' using driver `OpenFileGDB'## Warning: no simple feature geometries present: returning a data.frame or
+## tbl_dfnames(greens_a)[5] <- 'greens_a'
+head(greens_a)## NUTS_ID ZONE_CODE COUNT AREA greens_a
+## 1 AT11 1 70 0.48611111 262.024673
+## 2 AT22 2 284 1.97222222 239.331023
+## 3 AT12 3 333 2.31250000 1095.905600
+## 4 AT13 4 7 0.04861111 4.525964
+## 5 AT21 5 161 1.11805556 100.249250
+## 6 AT31 6 207 1.43750000 449.433863nuts_a <- st_read(dsn='C:/Users/mu5106sc/Dropbox/STAGS/D1_Database/EU_Farming_Systems_20181015.gdb', layer='crop_nuts_a')## Reading layer `crop_nuts_a' from data source `C:\Users\mu5106sc\Dropbox\STAGS\D1_Database\EU_Farming_Systems_20181015.gdb' using driver `OpenFileGDB'## Warning: no simple feature geometries present: returning a data.frame or
+## tbl_dfnames(nuts_a)[5] <- 'nuts_a'
+head(nuts_a)## NUTS_ID ZONE_CODE COUNT AREA nuts_a
+## 1 AT11 1 70 0.48611111 663.34164
+## 2 AT22 2 284 1.97222222 594.96624
+## 3 AT12 3 333 2.31250000 2774.39450
+## 4 AT13 4 7 0.04861111 11.45793
+## 5 AT21 5 161 1.11805556 253.79100
+## 6 AT31 6 207 1.43750000 1137.78673olives_a <- st_read(dsn='C:/Users/mu5106sc/Dropbox/STAGS/D1_Database/EU_Farming_Systems_20181015.gdb', layer='crop_olives_a')## Reading layer `crop_olives_a' from data source `C:\Users\mu5106sc\Dropbox\STAGS\D1_Database\EU_Farming_Systems_20181015.gdb' using driver `OpenFileGDB'## Warning: no simple feature geometries present: returning a data.frame or
+## tbl_dfnames(olives_a)[5] <- 'olives_a'
+head(olives_a)## NUTS_ID ZONE_CODE COUNT AREA olives_a
+## 1 AT11 1 70 0.48611111 8.965376e-21
+## 2 AT22 2 284 1.97222222 8.295056e+00
+## 3 AT12 3 333 2.31250000 0.000000e+00
+## 4 AT13 4 7 0.04861111 0.000000e+00
+## 5 AT21 5 161 1.11805556 4.135479e-21
+## 6 AT31 6 207 1.43750000 0.000000e+00oth_veg_a <- st_read(dsn='C:/Users/mu5106sc/Dropbox/STAGS/D1_Database/EU_Farming_Systems_20181015.gdb', layer='crop_oth_veg_a')## Reading layer `crop_oth_veg_a' from data source `C:\Users\mu5106sc\Dropbox\STAGS\D1_Database\EU_Farming_Systems_20181015.gdb' using driver `OpenFileGDB'## Warning: no simple feature geometries present: returning a data.frame or
+## tbl_dfnames(oth_veg_a)[5] <- 'oth_veg_a'
+head(oth_veg_a)## NUTS_ID ZONE_CODE COUNT AREA oth_veg_a
+## 1 AT11 1 70 0.48611111 343.710066
+## 2 AT22 2 284 1.97222222 307.406884
+## 3 AT12 3 333 2.31250000 1437.550844
+## 4 AT13 4 7 0.04861111 5.936919
+## 5 AT21 5 161 1.11805556 131.501650
+## 6 AT31 6 207 1.43750000 589.543502peas_a <- st_read(dsn='C:/Users/mu5106sc/Dropbox/STAGS/D1_Database/EU_Farming_Systems_20181015.gdb', layer='crop_peas_a')## Reading layer `crop_peas_a' from data source `C:\Users\mu5106sc\Dropbox\STAGS\D1_Database\EU_Farming_Systems_20181015.gdb' using driver `OpenFileGDB'## Warning: no simple feature geometries present: returning a data.frame or
+## tbl_dfnames(peas_a)[5] <- 'peas_a'
+head(peas_a)## NUTS_ID ZONE_CODE COUNT AREA peas_a
+## 1 AT11 1 70 0.48611111 183.341788
+## 2 AT22 2 284 1.97222222 168.840186
+## 3 AT12 3 333 2.31250000 766.818212
+## 4 AT13 4 7 0.04861111 3.166871
+## 5 AT21 5 161 1.11805556 70.145596
+## 6 AT31 6 207 1.43750000 314.474229rootveg_a <- st_read(dsn='C:/Users/mu5106sc/Dropbox/STAGS/D1_Database/EU_Farming_Systems_20181015.gdb', layer='crop_rootveg_a')## Reading layer `crop_rootveg_a' from data source `C:\Users\mu5106sc\Dropbox\STAGS\D1_Database\EU_Farming_Systems_20181015.gdb' using driver `OpenFileGDB'## Warning: no simple feature geometries present: returning a data.frame or
+## tbl_dfnames(rootveg_a)[5] <- 'rootveg_a'
+head(rootveg_a)## NUTS_ID ZONE_CODE COUNT AREA rootveg_a
+## 1 AT11 1 70 0.48611111 411.738891
+## 2 AT22 2 284 1.97222222 376.291177
+## 3 AT12 3 333 2.31250000 1722.078127
+## 4 AT13 4 7 0.04861111 7.111984
+## 5 AT21 5 161 1.11805556 157.529120
+## 6 AT31 6 207 1.43750000 706.228918tropfr_a <- st_read(dsn='C:/Users/mu5106sc/Dropbox/STAGS/D1_Database/EU_Farming_Systems_20181015.gdb', layer='crop_tropfr_a')## Reading layer `crop_tropfr_a' from data source `C:\Users\mu5106sc\Dropbox\STAGS\D1_Database\EU_Farming_Systems_20181015.gdb' using driver `OpenFileGDB'## Warning: no simple feature geometries present: returning a data.frame or
+## tbl_dfnames(tropfr_a)[5] <- 'tropfr_a'
+head(tropfr_a)## NUTS_ID ZONE_CODE COUNT AREA tropfr_a
+## 1 AT11 1 70 0.48611111 0.000000
+## 2 AT22 2 284 1.97222222 1.265173
+## 3 AT12 3 333 2.31250000 0.000000
+## 4 AT13 4 7 0.04861111 0.000000
+## 5 AT21 5 161 1.11805556 0.000000
+## 6 AT31 6 207 1.43750000 0.000000vfruits_a <- st_read(dsn='C:/Users/mu5106sc/Dropbox/STAGS/D1_Database/EU_Farming_Systems_20181015.gdb', layer='crop_vfruits_a')## Reading layer `crop_vfruits_a' from data source `C:\Users\mu5106sc\Dropbox\STAGS\D1_Database\EU_Farming_Systems_20181015.gdb' using driver `OpenFileGDB'## Warning: no simple feature geometries present: returning a data.frame or
+## tbl_dfnames(vfruits_a)[5] <- 'vfruits_a'
+head(vfruits_a)## NUTS_ID ZONE_CODE COUNT AREA vfruits_a
+## 1 AT11 1 70 0.48611111 98.185651
+## 2 AT22 2 284 1.97222222 97.545471
+## 3 AT12 3 333 2.31250000 410.656773
+## 4 AT13 4 7 0.04861111 1.695965
+## 5 AT21 5 161 1.11805556 37.565311
+## 6 AT31 6 207 1.43750000 168.411455#Crop yields
+berries_y <- st_read(dsn='C:/Users/mu5106sc/Dropbox/STAGS/D1_Database/EU_Farming_Systems_20181015.gdb', layer='crop_berries_y')## Reading layer `crop_berries_y' from data source `C:\Users\mu5106sc\Dropbox\STAGS\D1_Database\EU_Farming_Systems_20181015.gdb' using driver `OpenFileGDB'## Warning: no simple feature geometries present: returning a data.frame or
+## tbl_dfnames(berries_y)[5] <- 'berries_y'
+head(berries_y)## NUTS_ID ZONE_CODE COUNT AREA berries_y
+## 1 AT11 1 70 0.48611111 29.18171
+## 2 AT22 2 284 1.97222222 12.23637
+## 3 AT12 3 333 2.31250000 23.90570
+## 4 AT13 4 7 0.04861111 17.16571
+## 5 AT21 5 161 1.11805556 14.36696
+## 6 AT31 6 207 1.43750000 20.89739brassic_y <- st_read(dsn='C:/Users/mu5106sc/Dropbox/STAGS/D1_Database/EU_Farming_Systems_20181015.gdb', layer='crop_brassic_y')## Reading layer `crop_brassic_y' from data source `C:\Users\mu5106sc\Dropbox\STAGS\D1_Database\EU_Farming_Systems_20181015.gdb' using driver `OpenFileGDB'## Warning: no simple feature geometries present: returning a data.frame or
+## tbl_dfnames(brassic_y)[5] <- 'brassic_y'
+head(brassic_y)## NUTS_ID ZONE_CODE COUNT AREA brassic_y
+## 1 AT11 1 70 0.48611111 44.06400
+## 2 AT22 2 284 1.97222222 18.54004
+## 3 AT12 3 333 2.31250000 36.09730
+## 4 AT13 4 7 0.04861111 25.92000
+## 5 AT21 5 161 1.11805556 21.69391
+## 6 AT31 6 207 1.43750000 31.55478citrus_y <- st_read(dsn='C:/Users/mu5106sc/Dropbox/STAGS/D1_Database/EU_Farming_Systems_20181015.gdb', layer='crop_citrus_y')## Reading layer `crop_citrus_y' from data source `C:\Users\mu5106sc\Dropbox\STAGS\D1_Database\EU_Farming_Systems_20181015.gdb' using driver `OpenFileGDB'## Warning: no simple feature geometries present: returning a data.frame or
+## tbl_dfnames(citrus_y)[5] <- 'citrus_y'
+head(citrus_y)## NUTS_ID ZONE_CODE COUNT AREA citrus_y
+## 1 AT11 1 70 0.48611111 0
+## 2 AT22 2 284 1.97222222 0
+## 3 AT12 3 333 2.31250000 0
+## 4 AT13 4 7 0.04861111 0
+## 5 AT21 5 161 1.11805556 0
+## 6 AT31 6 207 1.43750000 0frtrees_y <- st_read(dsn='C:/Users/mu5106sc/Dropbox/STAGS/D1_Database/EU_Farming_Systems_20181015.gdb', layer='crop_frtrees_y')## Reading layer `crop_frtrees_y' from data source `C:\Users\mu5106sc\Dropbox\STAGS\D1_Database\EU_Farming_Systems_20181015.gdb' using driver `OpenFileGDB'## Warning: no simple feature geometries present: returning a data.frame or
+## tbl_dfnames(frtrees_y)[5] <- 'frtrees_y'
+head(frtrees_y)## NUTS_ID ZONE_CODE COUNT AREA frtrees_y
+## 1 AT11 1 70 0.48611111 106.98343
+## 2 AT22 2 284 1.97222222 45.09310
+## 3 AT12 3 333 2.31250000 87.64099
+## 4 AT13 4 7 0.04861111 62.93143
+## 5 AT21 5 161 1.11805556 52.67087
+## 6 AT31 6 207 1.43750000 76.61217grapes_y <- st_read(dsn='C:/Users/mu5106sc/Dropbox/STAGS/D1_Database/EU_Farming_Systems_20181015.gdb', layer='crop_grapes_y')## Reading layer `crop_grapes_y' from data source `C:\Users\mu5106sc\Dropbox\STAGS\D1_Database\EU_Farming_Systems_20181015.gdb' using driver `OpenFileGDB'## Warning: no simple feature geometries present: returning a data.frame or
+## tbl_dfnames(grapes_y)[5] <- 'grapes_y'
+head(grapes_y)## NUTS_ID ZONE_CODE COUNT AREA grapes_y
+## 1 AT11 1 70 0.48611111 8.273220
+## 2 AT22 2 284 1.97222222 3.134204
+## 3 AT12 3 333 2.31250000 5.295910
+## 4 AT13 4 7 0.04861111 3.012085
+## 5 AT21 5 161 1.11805556 4.908311
+## 6 AT31 6 207 1.43750000 0.000000greens_y <- st_read(dsn='C:/Users/mu5106sc/Dropbox/STAGS/D1_Database/EU_Farming_Systems_20181015.gdb', layer='crop_greens_y')## Reading layer `crop_greens_y' from data source `C:\Users\mu5106sc\Dropbox\STAGS\D1_Database\EU_Farming_Systems_20181015.gdb' using driver `OpenFileGDB'## Warning: no simple feature geometries present: returning a data.frame or
+## tbl_dfnames(greens_y)[5] <- 'greens_y'
+head(greens_y)## NUTS_ID ZONE_CODE COUNT AREA greens_y
+## 1 AT11 1 70 0.48611111 61.19029
+## 2 AT22 2 284 1.97222222 25.61430
+## 3 AT12 3 333 2.31250000 50.12718
+## 4 AT13 4 7 0.04861111 35.99429
+## 5 AT21 5 161 1.11805556 30.12565
+## 6 AT31 6 207 1.43750000 43.81913nuts_y <- st_read(dsn='C:/Users/mu5106sc/Dropbox/STAGS/D1_Database/EU_Farming_Systems_20181015.gdb', layer='crop_nuts_y')## Reading layer `crop_nuts_y' from data source `C:\Users\mu5106sc\Dropbox\STAGS\D1_Database\EU_Farming_Systems_20181015.gdb' using driver `OpenFileGDB'## Warning: no simple feature geometries present: returning a data.frame or
+## tbl_dfnames(nuts_y)[5] <- 'nuts_y'
+head(nuts_y)## NUTS_ID ZONE_CODE COUNT AREA nuts_y
+## 1 AT11 1 70 0.48611111 2.632571
+## 2 AT22 2 284 1.97222222 1.210000
+## 3 AT12 3 333 2.31250000 2.156607
+## 4 AT13 4 7 0.04861111 1.548571
+## 5 AT21 5 161 1.11805556 1.296087
+## 6 AT31 6 207 1.43750000 1.885217olives_y <- st_read(dsn='C:/Users/mu5106sc/Dropbox/STAGS/D1_Database/EU_Farming_Systems_20181015.gdb', layer='crop_olives_y')## Reading layer `crop_olives_y' from data source `C:\Users\mu5106sc\Dropbox\STAGS\D1_Database\EU_Farming_Systems_20181015.gdb' using driver `OpenFileGDB'## Warning: no simple feature geometries present: returning a data.frame or
+## tbl_dfnames(olives_y)[5] <- 'olives_y'
+head(olives_y)## NUTS_ID ZONE_CODE COUNT AREA olives_y
+## 1 AT11 1 70 0.48611111 0.000000000
+## 2 AT22 2 284 1.97222222 0.007077465
+## 3 AT12 3 333 2.31250000 0.000000000
+## 4 AT13 4 7 0.04861111 0.000000000
+## 5 AT21 5 161 1.11805556 0.000000000
+## 6 AT31 6 207 1.43750000 0.000000000oth_veg_y <- st_read(dsn='C:/Users/mu5106sc/Dropbox/STAGS/D1_Database/EU_Farming_Systems_20181015.gdb', layer='crop_oth_veg_y')## Reading layer `crop_oth_veg_y' from data source `C:\Users\mu5106sc\Dropbox\STAGS\D1_Database\EU_Farming_Systems_20181015.gdb' using driver `OpenFileGDB'## Warning: no simple feature geometries present: returning a data.frame or
+## tbl_dfnames(oth_veg_y)[5] <- 'oth_veg_y'
+head(oth_veg_y)## NUTS_ID ZONE_CODE COUNT AREA oth_veg_y
+## 1 AT11 1 70 0.48611111 29.05543
+## 2 AT22 2 284 1.97222222 12.11144
+## 3 AT12 3 333 2.31250000 23.80225
+## 4 AT13 4 7 0.04861111 17.09143
+## 5 AT21 5 161 1.11805556 14.30478
+## 6 AT31 6 207 1.43750000 20.80696peas_y <- st_read(dsn='C:/Users/mu5106sc/Dropbox/STAGS/D1_Database/EU_Farming_Systems_20181015.gdb', layer='crop_peas_y')## Reading layer `crop_peas_y' from data source `C:\Users\mu5106sc\Dropbox\STAGS\D1_Database\EU_Farming_Systems_20181015.gdb' using driver `OpenFileGDB'## Warning: no simple feature geometries present: returning a data.frame or
+## tbl_dfnames(peas_y)[5] <- 'peas_y'
+head(peas_y)## NUTS_ID ZONE_CODE COUNT AREA peas_y
+## 1 AT11 1 70 0.48611111 18.087999
+## 2 AT22 2 284 1.97222222 7.590493
+## 3 AT12 3 333 2.31250000 14.817717
+## 4 AT13 4 7 0.04861111 10.639999
+## 5 AT21 5 161 1.11805556 8.905217
+## 6 AT31 6 207 1.43750000 12.953043rootveg_y <- st_read(dsn='C:/Users/mu5106sc/Dropbox/STAGS/D1_Database/EU_Farming_Systems_20181015.gdb', layer='crop_rootveg_y')## Reading layer `crop_rootveg_y' from data source `C:\Users\mu5106sc\Dropbox\STAGS\D1_Database\EU_Farming_Systems_20181015.gdb' using driver `OpenFileGDB'## Warning: no simple feature geometries present: returning a data.frame or
+## tbl_dfnames(rootveg_y)[5] <- 'rootveg_y'
+head(rootveg_y)## NUTS_ID ZONE_CODE COUNT AREA rootveg_y
+## 1 AT11 1 70 0.48611111 93.43200
+## 2 AT22 2 284 1.97222222 39.11891
+## 3 AT12 3 333 2.31250000 76.53964
+## 4 AT13 4 7 0.04861111 54.96000
+## 5 AT21 5 161 1.11805556 45.99913
+## 6 AT31 6 207 1.43750000 66.90783tropfr_y <- st_read(dsn='C:/Users/mu5106sc/Dropbox/STAGS/D1_Database/EU_Farming_Systems_20181015.gdb', layer='crop_tropfr_y')## Reading layer `crop_tropfr_y' from data source `C:\Users\mu5106sc\Dropbox\STAGS\D1_Database\EU_Farming_Systems_20181015.gdb' using driver `OpenFileGDB'## Warning: no simple feature geometries present: returning a data.frame or
+## tbl_dfnames(tropfr_y)[5] <- 'tropfr_y'
+head(tropfr_y)## NUTS_ID ZONE_CODE COUNT AREA tropfr_y
+## 1 AT11 1 70 0.48611111 0.000000000
+## 2 AT22 2 284 1.97222222 0.002429577
+## 3 AT12 3 333 2.31250000 0.000000000
+## 4 AT13 4 7 0.04861111 0.000000000
+## 5 AT21 5 161 1.11805556 0.000000000
+## 6 AT31 6 207 1.43750000 0.000000000vfruits_y <- st_read(dsn='C:/Users/mu5106sc/Dropbox/STAGS/D1_Database/EU_Farming_Systems_20181015.gdb', layer='crop_vfruits_y')## Reading layer `crop_vfruits_y' from data source `C:\Users\mu5106sc\Dropbox\STAGS\D1_Database\EU_Farming_Systems_20181015.gdb' using driver `OpenFileGDB'## Warning: no simple feature geometries present: returning a data.frame or
+## tbl_dfnames(vfruits_y)[5] <- 'vfruits_y'
+head(vfruits_y)## NUTS_ID ZONE_CODE COUNT AREA vfruits_y
+## 1 AT11 1 70 0.48611111 258.4971
+## 2 AT22 2 284 1.97222222 107.9879
+## 3 AT12 3 333 2.31250000 211.7612
+## 4 AT13 4 7 0.04861111 152.0571
+## 5 AT21 5 161 1.11805556 127.2652
+## 6 AT31 6 207 1.43750000 185.1130#Merge all tables
+crop.earthstat <- berries_a[,c(1,5)]
+crop.earthstat <- left_join(crop.earthstat, brassic_a[,c(1,5)])## Joining, by = "NUTS_ID"crop.earthstat <- left_join(crop.earthstat, citrus_a[,c(1,5)])## Joining, by = "NUTS_ID"crop.earthstat <- left_join(crop.earthstat, frtrees_a[,c(1,5)])## Joining, by = "NUTS_ID"crop.earthstat <- left_join(crop.earthstat, grapes_a[,c(1,5)])## Joining, by = "NUTS_ID"crop.earthstat <- left_join(crop.earthstat, greens_a[,c(1,5)])## Joining, by = "NUTS_ID"crop.earthstat <- left_join(crop.earthstat, nuts_a[,c(1,5)])## Joining, by = "NUTS_ID"crop.earthstat <- left_join(crop.earthstat, olives_a[,c(1,5)])## Joining, by = "NUTS_ID"crop.earthstat <- left_join(crop.earthstat, oth_veg_a[,c(1,5)])## Joining, by = "NUTS_ID"crop.earthstat <- left_join(crop.earthstat, peas_a[,c(1,5)])## Joining, by = "NUTS_ID"crop.earthstat <- left_join(crop.earthstat, rootveg_a[,c(1,5)])## Joining, by = "NUTS_ID"crop.earthstat <- left_join(crop.earthstat, tropfr_a[,c(1,5)])## Joining, by = "NUTS_ID"crop.earthstat <- left_join(crop.earthstat, vfruits_a[,c(1,5)])## Joining, by = "NUTS_ID"crop.earthstat <- left_join(crop.earthstat, berries_y[,c(1,5)])## Joining, by = "NUTS_ID"crop.earthstat <- left_join(crop.earthstat, brassic_y[,c(1,5)])## Joining, by = "NUTS_ID"crop.earthstat <- left_join(crop.earthstat, citrus_y[,c(1,5)])## Joining, by = "NUTS_ID"crop.earthstat <- left_join(crop.earthstat, frtrees_y[,c(1,5)])## Joining, by = "NUTS_ID"crop.earthstat <- left_join(crop.earthstat, grapes_y[,c(1,5)])## Joining, by = "NUTS_ID"crop.earthstat <- left_join(crop.earthstat, greens_y[,c(1,5)])## Joining, by = "NUTS_ID"crop.earthstat <- left_join(crop.earthstat, nuts_y[,c(1,5)])## Joining, by = "NUTS_ID"crop.earthstat <- left_join(crop.earthstat, olives_y[,c(1,5)])## Joining, by = "NUTS_ID"crop.earthstat <- left_join(crop.earthstat, oth_veg_y[,c(1,5)])## Joining, by = "NUTS_ID"crop.earthstat <- left_join(crop.earthstat, peas_y[,c(1,5)])## Joining, by = "NUTS_ID"crop.earthstat <- left_join(crop.earthstat, rootveg_y[,c(1,5)])## Joining, by = "NUTS_ID"crop.earthstat <- left_join(crop.earthstat, tropfr_y[,c(1,5)])## Joining, by = "NUTS_ID"crop.earthstat <- left_join(crop.earthstat, vfruits_y[,c(1,5)])## Joining, by = "NUTS_ID"head(crop.earthstat)## NUTS_ID berries_a brassic_a citrus_a frtrees_a grapes_a
+## 1 AT11 698.93634 224.465054 0 3395.05625 8087.4269
+## 2 AT22 626.17569 217.960795 0 3106.60397 2473.9556
+## 3 AT12 2923.26766 938.814305 0 14199.65974 34108.5900
+## 4 AT13 12.07276 3.877195 0 58.64296 142.7438
+## 5 AT21 267.40934 85.879142 0 1298.93051 962.3650
+## 6 AT31 1198.84000 385.010299 0 5823.31900 0.0000
+## greens_a nuts_a olives_a oth_veg_a peas_a rootveg_a
+## 1 262.024673 663.34164 8.965376e-21 343.710066 183.341788 411.738891
+## 2 239.331023 594.96624 8.295056e+00 307.406884 168.840186 376.291177
+## 3 1095.905600 2774.39450 0.000000e+00 1437.550844 766.818212 1722.078127
+## 4 4.525964 11.45793 0.000000e+00 5.936919 3.166871 7.111984
+## 5 100.249250 253.79100 4.135479e-21 131.501650 70.145596 157.529120
+## 6 449.433863 1137.78673 0.000000e+00 589.543502 314.474229 706.228918
+## tropfr_a vfruits_a berries_y brassic_y citrus_y frtrees_y grapes_y
+## 1 0.000000 98.185651 29.18171 44.06400 0 106.98343 8.273220
+## 2 1.265173 97.545471 12.23637 18.54004 0 45.09310 3.134204
+## 3 0.000000 410.656773 23.90570 36.09730 0 87.64099 5.295910
+## 4 0.000000 1.695965 17.16571 25.92000 0 62.93143 3.012085
+## 5 0.000000 37.565311 14.36696 21.69391 0 52.67087 4.908311
+## 6 0.000000 168.411455 20.89739 31.55478 0 76.61217 0.000000
+## greens_y nuts_y olives_y oth_veg_y peas_y rootveg_y tropfr_y
+## 1 61.19029 2.632571 0.000000000 29.05543 18.087999 93.43200 0.000000000
+## 2 25.61430 1.210000 0.007077465 12.11144 7.590493 39.11891 0.002429577
+## 3 50.12718 2.156607 0.000000000 23.80225 14.817717 76.53964 0.000000000
+## 4 35.99429 1.548571 0.000000000 17.09143 10.639999 54.96000 0.000000000
+## 5 30.12565 1.296087 0.000000000 14.30478 8.905217 45.99913 0.000000000
+## 6 43.81913 1.885217 0.000000000 20.80696 12.953043 66.90783 0.000000000
+## vfruits_y
+## 1 258.4971
+## 2 107.9879
+## 3 211.7612
+## 4 152.0571
+## 5 127.2652
+## 6 185.1130summary(crop.earthstat)## NUTS_ID berries_a brassic_a citrus_a
+## AT11 : 1 Min. : 0.00 Min. : 0.0 Min. : 0.0
+## AT12 : 1 1st Qu.: 91.16 1st Qu.: 255.2 1st Qu.: 0.0
+## AT13 : 1 Median : 344.64 Median : 642.6 Median : 0.0
+## AT21 : 1 Mean : 838.48 Mean :1213.3 Mean : 1959.2
+## AT22 : 1 3rd Qu.: 760.38 3rd Qu.:1521.2 3rd Qu.: 468.2
+## AT31 : 1 Max. :13842.40 Max. :7754.3 Max. :63996.0
+## (Other):312
+## frtrees_a grapes_a greens_a
+## Min. : 0.0 Min. : 0.0 Min. : 0.00
+## 1st Qu.: 490.4 1st Qu.: 0.0 1st Qu.: 65.56
+## Median : 2976.8 Median : 108.6 Median : 297.01
+## Mean : 6512.1 Mean : 13319.7 Mean : 1058.31
+## 3rd Qu.: 9645.0 3rd Qu.: 12667.6 3rd Qu.: 1032.31
+## Max. :50265.7 Max. :582102.2 Max. :16478.72
+##
+## nuts_a olives_a oth_veg_a
+## Min. : 0.0 Min. : 0.0 Min. : 0.0
+## 1st Qu.: 0.0 1st Qu.: 0.0 1st Qu.: 263.1
+## Median : 100.8 Median : 0.0 Median : 748.2
+## Mean : 4828.6 Mean : 14648.2 Mean : 2079.2
+## 3rd Qu.: 1915.0 3rd Qu.: 234.3 3rd Qu.: 2197.1
+## Max. :149274.3 Max. :1416618.8 Max. :21937.9
+##
+## peas_a rootveg_a tropfr_a vfruits_a
+## Min. : 0.0 Min. : 0.0 Min. : 0.0 Min. : 0.00
+## 1st Qu.: 116.9 1st Qu.: 215.3 1st Qu.: 0.0 1st Qu.: 29.81
+## Median : 607.3 Median : 705.4 Median : 0.0 Median : 297.76
+## Mean : 1284.3 Mean : 1703.2 Mean : 814.5 Mean : 4691.09
+## 3rd Qu.: 1775.3 3rd Qu.: 2039.5 3rd Qu.: 297.5 3rd Qu.: 3972.33
+## Max. :19403.6 Max. :32140.5 Max. :50414.8 Max. :59073.51
+##
+## berries_y brassic_y citrus_y frtrees_y
+## Min. : 0.00 Min. : 0.00 Min. : 0.00 Min. : 0.00
+## 1st Qu.:17.09 1st Qu.:27.92 1st Qu.: 0.00 1st Qu.: 39.70
+## Median :25.00 Median :36.53 Median : 0.00 Median : 59.41
+## Mean :24.65 Mean :36.71 Mean : 26.52 Mean : 60.62
+## 3rd Qu.:34.64 3rd Qu.:42.06 3rd Qu.: 52.47 3rd Qu.: 87.56
+## Max. :57.13 Max. :77.33 Max. :122.23 Max. :180.73
+##
+## grapes_y greens_y nuts_y olives_y
+## Min. : 0.000000 Min. : 0.00 Min. : 0.000 Min. :0.0000
+## 1st Qu.: 0.007437 1st Qu.:20.73 1st Qu.: 0.000 1st Qu.:0.0000
+## Median : 2.495389 Median :35.52 Median : 3.073 Median :0.0000
+## Mean : 3.456924 Mean :31.97 Mean : 4.232 Mean :0.4511
+## 3rd Qu.: 6.183397 3rd Qu.:43.31 3rd Qu.: 7.779 3rd Qu.:0.8111
+## Max. :13.714184 Max. :71.30 Max. :22.863 Max. :4.2988
+##
+## oth_veg_y peas_y rootveg_y tropfr_y
+## Min. : 0.000 Min. : 0.00 Min. : 0.00 Min. : 0.00
+## 1st Qu.: 9.276 1st Qu.:12.10 1st Qu.: 41.92 1st Qu.: 0.00
+## Median :14.125 Median :20.78 Median : 68.70 Median : 0.00
+## Mean :16.035 Mean :20.47 Mean : 67.66 Mean :16.12
+## 3rd Qu.:18.919 3rd Qu.:28.03 3rd Qu.: 86.82 3rd Qu.:32.13
+## Max. :41.340 Max. :44.57 Max. :170.17 Max. :98.40
+##
+## vfruits_y
+## Min. : 0.00
+## 1st Qu.: 94.11
+## Median : 177.77
+## Mean : 281.39
+## 3rd Qu.: 303.62
+## Max. :1194.74
+## #Calculate fraction of agricultural area
+head(corine.aa.all.nuts)## geo sum_uaa
+## 1 AT11 219300.0
+## 2 AT22 411556.2
+## 3 AT12 1004956.2
+## 4 AT13 6075.0
+## 5 AT21 191312.5
+## 6 AT31 582587.5crop.earthstat$geo <- crop.earthstat$NUTS_ID
+crop.earthstat <- left_join(crop.earthstat, corine.aa.all.nuts)## Joining, by = "geo"## Warning: Column `geo` joining factor and character vector, coercing into
+## character vectorcrop.earthstat$berries_f <- crop.earthstat$berries_a / crop.earthstat$sum_uaa
+crop.earthstat$brassic_f <- crop.earthstat$brassic_a / crop.earthstat$sum_uaa
+crop.earthstat$citrus_f <- crop.earthstat$citrus_a / crop.earthstat$sum_uaa
+crop.earthstat$frtrees_f <- crop.earthstat$frtrees_a / crop.earthstat$sum_uaa
+crop.earthstat$grapes_f <- crop.earthstat$grapes_a / crop.earthstat$sum_uaa
+crop.earthstat$greens_f <- crop.earthstat$greens_a / crop.earthstat$sum_uaa
+crop.earthstat$nuts_f <- crop.earthstat$nuts_a / crop.earthstat$sum_uaa
+crop.earthstat$olives_f <- crop.earthstat$olives_a / crop.earthstat$sum_uaa
+crop.earthstat$oth_veg_f <- crop.earthstat$oth_veg_a / crop.earthstat$sum_uaa
+crop.earthstat$peas_f <- crop.earthstat$peas_a / crop.earthstat$sum_uaa
+crop.earthstat$rootveg_f <- crop.earthstat$rootveg_a / crop.earthstat$sum_uaa
+crop.earthstat$tropfr_f <- crop.earthstat$tropfr_a / crop.earthstat$sum_uaa
+crop.earthstat$vfruits_f <- crop.earthstat$vfruits_a / crop.earthstat$sum_uaa
+
+summary(crop.earthstat)## NUTS_ID berries_a brassic_a citrus_a
+## AT11 : 1 Min. : 0.00 Min. : 0.0 Min. : 0.0
+## AT12 : 1 1st Qu.: 91.16 1st Qu.: 255.2 1st Qu.: 0.0
+## AT13 : 1 Median : 344.64 Median : 642.6 Median : 0.0
+## AT21 : 1 Mean : 838.48 Mean :1213.3 Mean : 1959.2
+## AT22 : 1 3rd Qu.: 760.38 3rd Qu.:1521.2 3rd Qu.: 468.2
+## AT31 : 1 Max. :13842.40 Max. :7754.3 Max. :63996.0
+## (Other):312
+## frtrees_a grapes_a greens_a
+## Min. : 0.0 Min. : 0.0 Min. : 0.00
+## 1st Qu.: 490.4 1st Qu.: 0.0 1st Qu.: 65.56
+## Median : 2976.8 Median : 108.6 Median : 297.01
+## Mean : 6512.1 Mean : 13319.7 Mean : 1058.31
+## 3rd Qu.: 9645.0 3rd Qu.: 12667.6 3rd Qu.: 1032.31
+## Max. :50265.7 Max. :582102.2 Max. :16478.72
+##
+## nuts_a olives_a oth_veg_a
+## Min. : 0.0 Min. : 0.0 Min. : 0.0
+## 1st Qu.: 0.0 1st Qu.: 0.0 1st Qu.: 263.1
+## Median : 100.8 Median : 0.0 Median : 748.2
+## Mean : 4828.6 Mean : 14648.2 Mean : 2079.2
+## 3rd Qu.: 1915.0 3rd Qu.: 234.3 3rd Qu.: 2197.1
+## Max. :149274.3 Max. :1416618.8 Max. :21937.9
+##
+## peas_a rootveg_a tropfr_a vfruits_a
+## Min. : 0.0 Min. : 0.0 Min. : 0.0 Min. : 0.00
+## 1st Qu.: 116.9 1st Qu.: 215.3 1st Qu.: 0.0 1st Qu.: 29.81
+## Median : 607.3 Median : 705.4 Median : 0.0 Median : 297.76
+## Mean : 1284.3 Mean : 1703.2 Mean : 814.5 Mean : 4691.09
+## 3rd Qu.: 1775.3 3rd Qu.: 2039.5 3rd Qu.: 297.5 3rd Qu.: 3972.33
+## Max. :19403.6 Max. :32140.5 Max. :50414.8 Max. :59073.51
+##
+## berries_y brassic_y citrus_y frtrees_y
+## Min. : 0.00 Min. : 0.00 Min. : 0.00 Min. : 0.00
+## 1st Qu.:17.09 1st Qu.:27.92 1st Qu.: 0.00 1st Qu.: 39.70
+## Median :25.00 Median :36.53 Median : 0.00 Median : 59.41
+## Mean :24.65 Mean :36.71 Mean : 26.52 Mean : 60.62
+## 3rd Qu.:34.64 3rd Qu.:42.06 3rd Qu.: 52.47 3rd Qu.: 87.56
+## Max. :57.13 Max. :77.33 Max. :122.23 Max. :180.73
+##
+## grapes_y greens_y nuts_y olives_y
+## Min. : 0.000000 Min. : 0.00 Min. : 0.000 Min. :0.0000
+## 1st Qu.: 0.007437 1st Qu.:20.73 1st Qu.: 0.000 1st Qu.:0.0000
+## Median : 2.495389 Median :35.52 Median : 3.073 Median :0.0000
+## Mean : 3.456924 Mean :31.97 Mean : 4.232 Mean :0.4511
+## 3rd Qu.: 6.183397 3rd Qu.:43.31 3rd Qu.: 7.779 3rd Qu.:0.8111
+## Max. :13.714184 Max. :71.30 Max. :22.863 Max. :4.2988
+##
+## oth_veg_y peas_y rootveg_y tropfr_y
+## Min. : 0.000 Min. : 0.00 Min. : 0.00 Min. : 0.00
+## 1st Qu.: 9.276 1st Qu.:12.10 1st Qu.: 41.92 1st Qu.: 0.00
+## Median :14.125 Median :20.78 Median : 68.70 Median : 0.00
+## Mean :16.035 Mean :20.47 Mean : 67.66 Mean :16.12
+## 3rd Qu.:18.919 3rd Qu.:28.03 3rd Qu.: 86.82 3rd Qu.:32.13
+## Max. :41.340 Max. :44.57 Max. :170.17 Max. :98.40
+##
+## vfruits_y geo sum_uaa
+## Min. : 0.00 Length:318 Min. : 438
+## 1st Qu.: 94.11 Class :character 1st Qu.: 214006
+## Median : 177.77 Mode :character Median : 514169
+## Mean : 281.39 Mean : 756028
+## 3rd Qu.: 303.62 3rd Qu.:1015952
+## Max. :1194.74 Max. :5007938
+## NA's :2
+## berries_f brassic_f citrus_f
+## Min. :0.0000000 Min. :0.0000000 Min. :0.000000
+## 1st Qu.:0.0002767 1st Qu.:0.0007169 1st Qu.:0.000000
+## Median :0.0005373 Median :0.0011628 Median :0.000000
+## Mean :0.0010681 Mean :0.0016514 Mean :0.002161
+## 3rd Qu.:0.0013782 3rd Qu.:0.0021024 3rd Qu.:0.001833
+## Max. :0.0093737 Max. :0.0115583 Max. :0.029824
+## NA's :2 NA's :2 NA's :2
+## frtrees_f grapes_f greens_f
+## Min. :0.000000 Min. :0.0000000 Min. :0.0000000
+## 1st Qu.:0.001741 1st Qu.:0.0000001 1st Qu.:0.0002412
+## Median :0.007025 Median :0.0003219 Median :0.0008391
+## Mean :0.007964 Mean :0.0149535 Mean :0.0013980
+## 3rd Qu.:0.010316 3rd Qu.:0.0173696 3rd Qu.:0.0013922
+## Max. :0.092826 Max. :0.2683389 Max. :0.0156956
+## NA's :2 NA's :2 NA's :2
+## nuts_f olives_f oth_veg_f
+## Min. :0.0000000 Min. :0.000000 Min. :0.000000
+## 1st Qu.:0.0000000 1st Qu.:0.000000 1st Qu.:0.000530
+## Median :0.0002118 Median :0.000000 Median :0.001639
+## Mean :0.0043429 Mean :0.015398 Mean :0.002617
+## 3rd Qu.:0.0025973 3rd Qu.:0.000905 3rd Qu.:0.003725
+## Max. :0.0360333 Max. :0.452390 Max. :0.019446
+## NA's :2 NA's :2 NA's :2
+## peas_f rootveg_f tropfr_f
+## Min. :0.0000000 Min. :0.0000000 Min. :0.0000000
+## 1st Qu.:0.0003897 1st Qu.:0.0006968 1st Qu.:0.0000000
+## Median :0.0013164 Median :0.0014379 Median :0.0000000
+## Mean :0.0018037 Mean :0.0021119 Mean :0.0010535
+## 3rd Qu.:0.0025984 3rd Qu.:0.0026550 3rd Qu.:0.0003944
+## Max. :0.0210358 Max. :0.0182248 Max. :0.0434730
+## NA's :2 NA's :2 NA's :2
+## vfruits_f
+## Min. :0.0000000
+## 1st Qu.:0.0001177
+## Median :0.0008814
+## Mean :0.0047733
+## 3rd Qu.:0.0068120
+## Max. :0.0417147
+## NA's :2#Remove zero yields from regions with zero crop areas
+names(crop.earthstat)## [1] "NUTS_ID" "berries_a" "brassic_a" "citrus_a" "frtrees_a"
+## [6] "grapes_a" "greens_a" "nuts_a" "olives_a" "oth_veg_a"
+## [11] "peas_a" "rootveg_a" "tropfr_a" "vfruits_a" "berries_y"
+## [16] "brassic_y" "citrus_y" "frtrees_y" "grapes_y" "greens_y"
+## [21] "nuts_y" "olives_y" "oth_veg_y" "peas_y" "rootveg_y"
+## [26] "tropfr_y" "vfruits_y" "geo" "sum_uaa" "berries_f"
+## [31] "brassic_f" "citrus_f" "frtrees_f" "grapes_f" "greens_f"
+## [36] "nuts_f" "olives_f" "oth_veg_f" "peas_f" "rootveg_f"
+## [41] "tropfr_f" "vfruits_f"for(e in gsub('_a', '', names(crop.earthstat)[2:14])) {
+ crop.earthstat[crop.earthstat[,paste(e, '_a', sep='')] == 0, paste(e, '_y', sep='')] <- NA
+}
+
+#Check for berries
+crop.earthstat[crop.earthstat$berries_a == 0, c('NUTS_ID', 'berries_a', 'berries_y')]## NUTS_ID berries_a berries_y
+## 12 BE10 0 NA
+## 28 CY00 0 NA
+## 108 FI20 0 NA
+## 117 ES70 0 NA
+## 125 FRA1 0 NA
+## 128 FRA2 0 NA
+## 148 IS00 0 NA
+## 164 FRA4 0 NA
+## 165 FRA5 0 NA
+## 174 MT00 0 NA
+## 187 LI00 0 NA
+## 204 NO06 0 NA
+## 205 NO07 0 NA
+## 228 PT20 0 NA
+## 229 PT30 0 NA
+## 268 SE33 0 NA
+## 298 UKI5 0 NA
+## 300 UKI3 0 NA
+## 301 UKI4 0 NAlivestock <- read.csv("C:/Users/mu5106sc/Dropbox/STAGS/SDG_data_eurostat/Final_database/Livestock/livestock_mean_allnuts.csv", head=T)
+head(livestock)## geo bovine milk_cows pigs sheep goats
+## 1 BG 561.070 294.86250 594.0500 1230.0863 293.1725
+## 2 CH 1560.403 572.43667 1458.1100 NA NA
+## 3 CY 59.265 25.80625 378.5325 333.1833 264.8317
+## 4 AL NA NA NA NA NA
+## 5 CZ 1344.674 370.75875 1573.4913 NA NA
+## 6 BE 2492.199 518.07875 6383.0975 109.5025 39.2350#Need to adjust the NUTS2016 data to NUTS2013 codes
+livestock.2013nuts <- livestock
+names(livestock.2013nuts)## [1] "geo" "bovine" "milk_cows" "pigs" "sheep" "goats"livestock.2013nuts$geo16 <- livestock.2013nuts$geo
+livestock.2013nuts$geo <- as.character(livestock.2013nuts$geo)
+livestock.2013nuts <- left_join(livestock.2013nuts, geodata@data[,c(4,7)])## Joining, by = "geo"#straight recodes
+for(e in nuts.conv[nuts.conv$Change == "recoded", 'Code.2016']) {
+ livestock.2013nuts[livestock.2013nuts$geo16 == e, 'geo'] <- as.character(nuts.conv[nuts.conv$Code.2016 == e, 'Code.2013'])
+}
+#check
+livestock.2013nuts[livestock.2013nuts$geo16 %in% nuts.conv[nuts.conv$Change == "recoded", 'Code.2016'], c('geo', 'geo16')]## geo geo16
+## 195 FR51 FRG0
+## 196 FR52 FRH0
+## 200 FR61 FRI1
+## 201 FR63 FRI2
+## 202 FR53 FRI3
+## 214 FR81 FRJ1
+## 215 FR62 FRJ2
+## 222 FR21 FRF2
+## 223 FR26 FRC1
+## 224 FR43 FRC2
+## 225 FR25 FRD1
+## 226 FR23 FRD2
+## 236 FR41 FRF3
+## 237 FR72 FRK1
+## 238 FR71 FRK2
+## 245 FR82 FRL0
+## 246 FR83 FRM0
+## 247 FRA1 FRY1
+## 259 FRA2 FRY2
+## 260 FRA3 FRY3
+## 261 FRA4 FRY4
+## 262 FRA5 FRY5
+## 317 FR30 FRE1
+## 318 FR22 FRE2
+## 319 FR42 FRF1
+## 441 PL32 PL82
+## 454 PL34 PL84
+## 486 PL11 PL71
+## 487 PL33 PL72
+## 488 PL31 PL81#recode and relabel
+livestock.2013nuts[livestock.2013nuts$geo16 == "FRB0", 'geo'] <- "FR24"
+
+#splits
+livestock.2013nuts[livestock.2013nuts$geo16 %in% c("LT01", "LT02"), 'geo'] <- "LT00"
+livestock.2013nuts[livestock.2013nuts$geo16 %in% c("HU11", "HU12"), 'geo'] <- "HU10"
+livestock.2013nuts[livestock.2013nuts$geo16 %in% c("PL91", "PL92"), 'geo'] <- "PL12"
+livestock.2013nuts[livestock.2013nuts$geo16 %in% c("UKM8", "UKM9"), 'geo'] <- "UKM3" #approximate split not including NUTS3 UKM24
+livestock.2013nuts[livestock.2013nuts$geo16 == "UKM7", 'geo'] <- "UKM2" #approximate recode still including NUTS3 UKM24
+
+#IE
+#Cannot translate data from new regions to old NUTS2013 so use NUTS0 data
+livestock.2013nuts[livestock.2013nuts$geo16 == 'IE',]## geo bovine milk_cows pigs sheep goats geo16 LEVL_CODE
+## 17 IE 6294.701 1148.925 1517.544 3395.07 0 IE 0## Calculate sum over the split NUTS2 regions
+head(livestock.2013nuts)## geo bovine milk_cows pigs sheep goats geo16 LEVL_CODE
+## 1 BG 561.070 294.86250 594.0500 1230.0863 293.1725 BG 0
+## 2 CH 1560.403 572.43667 1458.1100 NA NA CH 0
+## 3 CY 59.265 25.80625 378.5325 333.1833 264.8317 CY 0
+## 4 AL NA NA NA NA NA AL 0
+## 5 CZ 1344.674 370.75875 1573.4913 NA NA CZ 0
+## 6 BE 2492.199 518.07875 6383.0975 109.5025 39.2350 BE 0livestock.2013nuts.sum <- livestock.2013nuts %>% group_by(geo) %>% summarise(bovine = sum(bovine,na.rm = F),
+ milk_cows = sum(milk_cows,na.rm = F),
+ pigs = sum(pigs,na.rm = F),
+ sheep = sum(sheep,na.rm = F),
+ goats = sum(goats,na.rm = F),
+ LEVL_CODE = mean(LEVL_CODE,na.rm = F)
+ )
+head(livestock.2013nuts.sum)## # A tibble: 6 x 7
+## geo bovine milk_cows pigs sheep goats LEVL_CODE
+## <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
+## 1 AL NA NA NA NA NA 0
+## 2 AL0 NA NA NA NA NA 1
+## 3 AL01 NA NA NA NA NA 2
+## 4 AL011 NA NA NA NA NA 3
+## 5 AL012 NA NA NA NA NA 3
+## 6 AL013 NA NA NA NA NA 3nrow(livestock.2013nuts.sum)## [1] 2013#Next, we calculate livestock density
+#Join UAA dataframe to livestock dataframe
+head(corine.aa.all.nuts)## geo sum_uaa
+## 1 AT11 219300.0
+## 2 AT22 411556.2
+## 3 AT12 1004956.2
+## 4 AT13 6075.0
+## 5 AT21 191312.5
+## 6 AT31 582587.5names(livestock.2013nuts.sum)## [1] "geo" "bovine" "milk_cows" "pigs" "sheep" "goats"
+## [7] "LEVL_CODE"livestock.2013nuts.sum <- left_join(livestock.2013nuts.sum, corine.aa.all.nuts)## Joining, by = "geo"livestock.dens <- as.data.frame(livestock.2013nuts.sum[,1:7])
+livestock.dens[,2:6] <- 1000 * livestock.2013nuts.sum[,2:6] / livestock.2013nuts.sum$sum_uaa
+
+summary(livestock.dens)## geo bovine milk_cows pigs
+## Length:2013 Min. :0.0000 Min. :0.0000 Min. : 0.0000
+## Class :character 1st Qu.:0.1716 1st Qu.:0.0423 1st Qu.: 0.1459
+## Mode :character Median :0.3327 Median :0.0865 Median : 0.3490
+## Mean :0.5387 Mean :0.1582 Mean : 0.9125
+## 3rd Qu.:0.7559 3rd Qu.:0.1951 3rd Qu.: 0.7265
+## Max. :2.8302 Max. :1.0433 Max. :17.2590
+## NA's :1676 NA's :1676 NA's :1684
+## sheep goats LEVL_CODE
+## Min. : 0.0000 Min. : 0.0000 Min. :0.000
+## 1st Qu.: 0.0698 1st Qu.: 0.0069 1st Qu.:3.000
+## Median : 0.2423 Median : 0.0335 Median :3.000
+## Mean : 0.5418 Mean : 0.1705 Mean :2.658
+## 3rd Qu.: 0.6588 3rd Qu.: 0.1024 3rd Qu.:3.000
+## Max. :15.6759 Max. :10.7158 Max. :3.000
+## NA's :1721 NA's :1721#Spurious sheep and goats
+livestock.dens[which(livestock.dens$sheep > 3), c('geo', 'sheep', 'goats')]## geo sheep goats
+## 32 AT13 15.675926 10.715843621
+## 717 EL4 3.771622 1.438400015
+## 718 EL41 3.010956 0.713143534
+## 725 EL43 5.225374 1.715879417
+## 749 EL54 3.422067 0.864509519
+## 763 EL63 3.081964 0.999435086
+## 1958 UKL 4.718953 0.007285458as.data.frame(livestock.2013nuts.sum[livestock.2013nuts.sum$geo %in% livestock.2013nuts.sum$geo[grep('AT', livestock.2013nuts.sum$geo)], c('geo', 'sheep', 'goats', 'sum_uaa')])## geo sheep goats sum_uaa
+## 1 AT 365.54375 76.32625 2677543.8
+## 2 AT1 78.67625 16.50000 1230331.2
+## 3 AT11 5.56375 241.68000 219300.0
+## 4 AT111 NA NA NA
+## 5 AT112 NA NA NA
+## 6 AT113 NA NA NA
+## 7 AT12 72.91375 15.29125 1004956.2
+## 8 AT121 NA NA NA
+## 9 AT122 NA NA NA
+## 10 AT123 NA NA NA
+## 11 AT124 NA NA NA
+## 12 AT125 NA NA NA
+## 13 AT126 NA NA NA
+## 14 AT127 NA NA NA
+## 15 AT13 95.23125 65.09875 6075.0
+## 16 AT130 NA NA NA
+## 17 AT2 111.83750 11.94250 602868.8
+## 18 AT21 44.95125 4.60375 191312.5
+## 19 AT211 NA NA NA
+## 20 AT212 NA NA NA
+## 21 AT213 NA NA NA
+## 22 AT22 66.88500 7.33750 411556.2
+## 23 AT221 NA NA NA
+## 24 AT222 NA NA NA
+## 25 AT223 NA NA NA
+## 26 AT224 NA NA NA
+## 27 AT225 NA NA NA
+## 28 AT226 NA NA NA
+## 29 AT3 175.02875 47.88500 844343.8
+## 30 AT31 55.56000 23.02125 582587.5
+## 31 AT311 NA NA NA
+## 32 AT312 NA NA NA
+## 33 AT313 NA NA NA
+## 34 AT314 NA NA NA
+## 35 AT315 NA NA NA
+## 36 AT32 28.94375 5.47375 115275.0
+## 37 AT321 NA NA NA
+## 38 AT322 NA NA NA
+## 39 AT323 NA NA NA
+## 40 AT33 79.39125 15.08125 112431.2
+## 41 AT331 NA NA NA
+## 42 AT332 NA NA NA
+## 43 AT333 NA NA NA
+## 44 AT334 NA NA NA
+## 45 AT335 NA NA NA
+## 46 AT34 11.13375 4.30875 34050.0
+## 47 AT341 NA NA NA
+## 48 AT342 NA NA NAlivestock.dens[which(livestock.dens$geo %in% livestock.2013nuts.sum$geo[grep('AT', livestock.2013nuts.sum$geo)]), c('geo', 'sheep', 'goats')]## geo sheep goats
+## 18 AT 0.13652205 0.02850607
+## 19 AT1 0.06394721 0.01341102
+## 20 AT11 0.02537050 1.10205198
+## 21 AT111 NA NA
+## 22 AT112 NA NA
+## 23 AT113 NA NA
+## 24 AT12 0.07255415 0.01521584
+## 25 AT121 NA NA
+## 26 AT122 NA NA
+## 27 AT123 NA NA
+## 28 AT124 NA NA
+## 29 AT125 NA NA
+## 30 AT126 NA NA
+## 31 AT127 NA NA
+## 32 AT13 15.67592593 10.71584362
+## 33 AT130 NA NA
+## 34 AT2 0.18550887 0.01980945
+## 35 AT21 0.23496243 0.02406403
+## 36 AT211 NA NA
+## 37 AT212 NA NA
+## 38 AT213 NA NA
+## 39 AT22 0.16251727 0.01782867
+## 40 AT221 NA NA
+## 41 AT222 NA NA
+## 42 AT223 NA NA
+## 43 AT224 NA NA
+## 44 AT225 NA NA
+## 45 AT226 NA NA
+## 46 AT3 0.20729561 0.05671268
+## 47 AT31 0.09536765 0.03951552
+## 48 AT311 NA NA
+## 49 AT312 NA NA
+## 50 AT313 NA NA
+## 51 AT314 NA NA
+## 52 AT315 NA NA
+## 53 AT32 0.25108436 0.04748428
+## 54 AT321 NA NA
+## 55 AT322 NA NA
+## 56 AT323 NA NA
+## 57 AT33 0.70613152 0.13413753
+## 58 AT331 NA NA
+## 59 AT332 NA NA
+## 60 AT333 NA NA
+## 61 AT334 NA NA
+## 62 AT335 NA NA
+## 63 AT34 0.32698238 0.12654185
+## 64 AT341 NA NA
+## 65 AT342 NA NAlivestock.dens[livestock.dens$geo == "AT13", c('sheep', 'goats')] <- livestock.dens[livestock.dens$geo == "AT1", c('sheep', 'goats')]
+
+livestock.dens[livestock.dens$geo == "AT11", 'goats'] <- livestock.dens[livestock.dens$geo == "AT1", 'goats']
+
+#Finally, run script to allocate NUTS1 or NUTS0 densities to NUTS2 where needed
+#list to summarise where data are NUTS2, 1, 0 for each variable
+data.level.livestock <- vector("list", 4*length(names(livestock.dens)[2:6]))
+names(data.level.livestock) <- c(paste(names(livestock.dens)[2:6], 'n2.dat', sep='.'),
+ paste(names(livestock.dens)[2:6], 'n1.dat', sep='.'),
+ paste(names(livestock.dens)[2:6], 'n0.dat', sep='.'),
+ paste(names(livestock.dens)[2:6], 'nuts0.na', sep='.')
+ )
+labels(data.level.livestock)## [1] "bovine.n2.dat" "milk_cows.n2.dat" "pigs.n2.dat"
+## [4] "sheep.n2.dat" "goats.n2.dat" "bovine.n1.dat"
+## [7] "milk_cows.n1.dat" "pigs.n1.dat" "sheep.n1.dat"
+## [10] "goats.n1.dat" "bovine.n0.dat" "milk_cows.n0.dat"
+## [13] "pigs.n0.dat" "sheep.n0.dat" "goats.n0.dat"
+## [16] "bovine.nuts0.na" "milk_cows.nuts0.na" "pigs.nuts0.na"
+## [19] "sheep.nuts0.na" "goats.nuts0.na"dbase.livestock <- as.data.frame(matrix(nrow=nrow(nuts@data), ncol=(ncol(livestock.dens[,2:6]) + 1)))
+dbase.livestock[,1] <- nuts@data$NUTS_ID
+names(dbase.livestock) <- c("NUTS_ID", names(livestock.dens)[2:6])
+head(dbase.livestock)## NUTS_ID bovine milk_cows pigs sheep goats
+## 1 AT11 NA NA NA NA NA
+## 2 AT22 NA NA NA NA NA
+## 3 AT12 NA NA NA NA NA
+## 4 AT13 NA NA NA NA NA
+## 5 AT21 NA NA NA NA NA
+## 6 AT31 NA NA NA NA NAnrow(dbase.livestock)## [1] 320attach(livestock.dens)
+for(i in names(livestock.dens)[2:6]) {
+ (nuts2.na <- livestock.dens[LEVL_CODE == 2 & is.na(livestock.dens[,i]), 'geo'])
+ (nuts1 <- livestock.dens[LEVL_CODE == 1 & geo %in% gsub(".{1}$", "", nuts2.na), 'geo'])
+ (nuts1.na <- livestock.dens[geo %in% nuts1 & is.na(livestock.dens[,i]), 'geo'])
+ (nuts0 <- livestock.dens[LEVL_CODE == 0 & geo %in% gsub(".{1}$", "", nuts1.na), 'geo'])
+ (nuts0.na <- livestock.dens[geo %in% nuts0 & is.na(livestock.dens[,i]), 'geo'])
+
+#NUTS2 data
+(n2.dat <- livestock.dens[!(geo %in% nuts2.na) & LEVL_CODE == 2, 'geo'])
+#NUTS1 data
+(n1.dat <- nuts1[!nuts1 %in% nuts1.na])
+#NUTS0 data
+(n0.dat <- nuts0[!nuts0 %in% nuts0.na])
+#NO DATA
+nuts0.na
+
+data.level.livestock[[paste(i, 'n2.dat', sep='.')]] <- n2.dat
+data.level.livestock[[paste(i, 'n1.dat', sep='.')]] <- n1.dat
+data.level.livestock[[paste(i, 'n0.dat', sep='.')]] <- n0.dat
+data.level.livestock[[paste(i, 'nuts0.na', sep='.')]] <- nuts0.na
+
+ for(e in n0.dat) {
+ dbase.livestock[dbase.livestock$NUTS_ID %in% dbase.livestock$NUTS_ID[grep(paste(e, '..', sep=''), dbase.livestock$NUTS_ID)], i] <- livestock.dens[livestock.dens$geo == e, i]
+ }
+
+ for(e in n1.dat) {
+ dbase.livestock[dbase.livestock$NUTS_ID %in% dbase.livestock$NUTS_ID[grep(paste(e, '.', sep=''), dbase.livestock$NUTS_ID)], i] <- livestock.dens[livestock.dens$geo == e, i]
+ }
+
+ for(e in n2.dat) {
+ dbase.livestock[dbase.livestock$NUTS_ID == e, i] <- livestock.dens[livestock.dens$geo == e, i]
+ }
+}
+detach(livestock.dens)
+
+summary(dbase.livestock)## NUTS_ID bovine milk_cows pigs
+## AT11 : 1 Min. :0.0000 Min. :0.00000 Min. : 0.0000
+## AT12 : 1 1st Qu.:0.1913 1st Qu.:0.04591 1st Qu.: 0.1446
+## AT13 : 1 Median :0.4288 Median :0.10738 Median : 0.2961
+## AT21 : 1 Mean :0.5536 Mean :0.16021 Mean : 0.8674
+## AT22 : 1 3rd Qu.:0.7943 3rd Qu.:0.19825 3rd Qu.: 0.7611
+## AT31 : 1 Max. :2.8302 Max. :1.04331 Max. :17.2590
+## (Other):314 NA's :8 NA's :8 NA's :34
+## sheep goats
+## Min. :0.00000 Min. :0.00000
+## 1st Qu.:0.07257 1st Qu.:0.00660
+## Median :0.27634 Median :0.02031
+## Mean :0.58262 Mean :0.11852
+## 3rd Qu.:0.90416 3rd Qu.:0.12719
+## Max. :5.22537 Max. :2.33485
+## NA's :36 NA's :36head(dbase.livestock)## NUTS_ID bovine milk_cows pigs sheep goats
+## 1 AT11 0.09572503 0.019237346 0.2189751 0.02537050 0.01341102
+## 2 AT22 0.78983432 0.197439597 1.9225909 0.16251727 0.01782867
+## 3 AT12 0.44254290 0.103387585 0.7942592 0.07255415 0.01521584
+## 4 AT13 0.01646091 0.004320988 0.0308642 0.06394721 0.01341102
+## 5 AT21 0.99191114 0.177059784 0.6761058 0.23496243 0.02406403
+## 6 AT31 0.98488639 0.287276589 1.9368813 0.09536765 0.03951552tail(dbase.livestock)## NUTS_ID bovine milk_cows pigs sheep goats
+## 315 UKD3 1.1849014 0.35018842 0.1661858 2.6134052 0.007820507
+## 316 TRC1 0.4287780 0.16379951 NA 0.9041624 0.291533492
+## 317 TRC2 0.4287780 0.16379951 NA 0.9041624 0.291533492
+## 318 UKD4 1.1849014 0.35018842 0.1661858 2.6134052 0.007820507
+## 319 TRC3 0.4287780 0.16379951 NA 0.9041624 0.291533492
+## 320 UKM6 0.8339355 0.08490498 0.1671604 2.3316352 0.001830575#check data level for bovine as an example
+data.level.livestock$bovine.n2.dat## [1] "AT11" "AT12" "AT13" "AT21" "AT22" "AT31" "AT32" "AT33" "AT34" "BE10"
+## [11] "BE21" "BE22" "BE23" "BE24" "BE25" "BE31" "BE32" "BE33" "BE34" "BE35"
+## [21] "BG31" "BG32" "BG33" "BG34" "BG41" "BG42" "CH01" "CH02" "CH03" "CH04"
+## [31] "CH05" "CH06" "CH07" "CY00" "CZ01" "CZ02" "CZ03" "CZ04" "CZ05" "CZ06"
+## [41] "CZ07" "CZ08" "DE30" "DE50" "DE60" "DE80" "DEE0" "DEF0" "DEG0" "DK01"
+## [51] "DK02" "DK03" "DK04" "DK05" "EE00" "EL30" "EL41" "EL42" "EL43" "EL51"
+## [61] "EL52" "EL53" "EL54" "EL61" "EL62" "EL63" "EL64" "EL65" "ES11" "ES12"
+## [71] "ES13" "ES21" "ES22" "ES23" "ES24" "ES30" "ES41" "ES42" "ES43" "ES51"
+## [81] "ES52" "ES53" "ES61" "ES62" "ES63" "ES64" "ES70" "FI19" "FI1B" "FI1C"
+## [91] "FI1D" "FI20" "FR10" "FR21" "FR22" "FR23" "FR24" "FR25" "FR26" "FR30"
+## [101] "FR41" "FR42" "FR43" "FR51" "FR52" "FR53" "FR61" "FR62" "FR63" "FR71"
+## [111] "FR72" "FR81" "FR82" "FR83" "FRA1" "FRA2" "FRA3" "FRA4" "FRA5" "HR03"
+## [121] "HR04" "HU10" "HU21" "HU22" "HU23" "HU31" "HU32" "HU33" "IS00" "ITC1"
+## [131] "ITC2" "ITC3" "ITC4" "ITF1" "ITF2" "ITF3" "ITF4" "ITF5" "ITF6" "ITG1"
+## [141] "ITG2" "ITH1" "ITH2" "ITH3" "ITH4" "ITH5" "ITI1" "ITI2" "ITI3" "ITI4"
+## [151] "LT00" "LU00" "LV00" "ME00" "MK00" "MT00" "NL11" "NL12" "NL13" "NL21"
+## [161] "NL22" "NL23" "NL31" "NL32" "NL33" "NL34" "NL41" "NL42" "PL11" "PL12"
+## [171] "PL21" "PL22" "PL31" "PL32" "PL33" "PL34" "PL41" "PL42" "PL43" "PL51"
+## [181] "PL52" "PL61" "PL62" "PL63" "PT11" "PT15" "PT16" "PT17" "PT18" "PT20"
+## [191] "PT30" "RO11" "RO12" "RO21" "RO22" "RO31" "RO32" "RO41" "RO42" "SE11"
+## [201] "SE12" "SE21" "SE22" "SE23" "SE31" "SE32" "SE33" "SI03" "SI04" "SK01"
+## [211] "SK02" "SK03" "SK04" "UKN0"data.level.livestock$bovine.n1.dat## [1] "DE1" "DE2" "DE4" "DE7" "DE9" "DEA" "DEB" "DEC" "DED" "IE0" "UKC"
+## [12] "UKD" "UKE" "UKF" "UKG" "UKH" "UKI" "UKJ" "UKK" "UKL" "UKM"data.level.livestock$bovine.n0.dat## [1] "TR"data.level.livestock$bovine.nuts0.na## [1] "AL" "LI" "NO" "RS"names(dbase.clean.gis)## [1] "NUTS_ID" "risk_pov" "train35bas" "train35ful"
+## [5] "train_bas" "train_ful" "nitr_high" "nitr_mod"
+## [9] "nitr_poor" "irrigated" "forest" "artific"
+## [13] "soil_loss" "com_birds" "farm_birds" "org_farm"
+## [17] "energy_rt" "renew_pct" "renew_prod" "gross_N"
+## [21] "gross_P" "conv_till" "cons_till" "zero_till"
+## [25] "nfert" "arable" "grassland" "permanent"
+## [29] "soil_prod" "geo" "irrig_rate" "afi_awu"
+## [33] "gva_awu" "labour_use" "pest_rate" "tot_gdp_cap"
+## [37] "tot_pps_cap" "emp_rate_15_64" "tot_unemp" "yth_unemp"
+## [41] "rur_gdp_cap" "rur_pps_cap" "int_gdp_cap" "int_pps_cap"
+## [45] "urb_gdp_cap" "urb_pps_cap" "C_factor" "emi_co2eq"
+## [49] "emi_nh3" "emi_pm10" "emi_pm25" "soc"
+## [53] "biol_threats" "nat2000_ag" "nat2000_pr" "cal_frac"
+## [57] "precip" "deg_days" "crop_suit"#Edit a few names to avoid truncation
+names(dbase.clean.gis)[c(36,37,41:46)] <- c("gdp_cap", "pps_cap", sub("_cap", "", names(dbase.clean.gis)[41:46]))
+names(dbase.clean.gis)[38] <- "emp_rate"
+names(dbase.clean.gis)[53] <- "bio_threat"
+
+names(dbase.crop)## [1] "NUTS_ID" "rye_f" "barley_f" "maize_f" "tritic_f"
+## [6] "sorghum_f" "oth_cer_f" "rice_f" "pasture_f" "rape_f"
+## [11] "sunflow_f" "pulses_f" "potato_f" "sugbeet_f" "oth_rt_f"
+## [16] "wheat_f" "oats_f" "oth_oil_f" "fibre_f" "oth_ind_f"
+## [21] "fodder_f"names(dbase.yield)## [1] "NUTS_ID" "rye_y" "barley_y" "maize_y" "tritic_y"
+## [6] "sorghum_y" "oth_cer_y" "rice_y" "pasture_y" "rape_y"
+## [11] "sunflow_y" "pulses_y" "potato_y" "sugbeet_y" "oth_rt_y"
+## [16] "wheat_y" "oats_y" "oth_oil_y" "fibre_y" "oth_ind_y"
+## [21] "fodder_y"names(crop.earthstat)## [1] "NUTS_ID" "berries_a" "brassic_a" "citrus_a" "frtrees_a"
+## [6] "grapes_a" "greens_a" "nuts_a" "olives_a" "oth_veg_a"
+## [11] "peas_a" "rootveg_a" "tropfr_a" "vfruits_a" "berries_y"
+## [16] "brassic_y" "citrus_y" "frtrees_y" "grapes_y" "greens_y"
+## [21] "nuts_y" "olives_y" "oth_veg_y" "peas_y" "rootveg_y"
+## [26] "tropfr_y" "vfruits_y" "geo" "sum_uaa" "berries_f"
+## [31] "brassic_f" "citrus_f" "frtrees_f" "grapes_f" "greens_f"
+## [36] "nuts_f" "olives_f" "oth_veg_f" "peas_f" "rootveg_f"
+## [41] "tropfr_f" "vfruits_f"names(dbase.livestock)## [1] "NUTS_ID" "bovine" "milk_cows" "pigs" "sheep" "goats"dbase.final <- left_join(dbase.clean.gis[,-30], dbase.crop)## Joining, by = "NUTS_ID"dbase.final <- left_join(dbase.final, dbase.yield)## Joining, by = "NUTS_ID"dbase.final <- left_join(dbase.final, crop.earthstat[,-c(2:14,28,29)])## Joining, by = "NUTS_ID"## Warning: Column `NUTS_ID` joining factors with different levels, coercing
+## to character vectordbase.final <- left_join(dbase.final, dbase.livestock)## Joining, by = "NUTS_ID"## Warning: Column `NUTS_ID` joining character vector and factor, coercing
+## into character vectorhead(dbase.final)## NUTS_ID risk_pov train35bas train35ful train_bas train_ful nitr_high
+## 1 AT11 13.73333 0.1375661 0.3333333 0.1243050 0.1779190 64.58924
+## 2 AT22 17.26667 0.2160980 0.3648294 0.2017089 0.2413594 64.58924
+## 3 AT12 13.83333 0.2084775 0.4809689 0.2534787 0.3449437 64.58924
+## 4 AT13 27.23333 0.3750000 0.7500000 0.1753247 0.4740260 64.58924
+## 5 AT21 17.20000 0.2306238 0.3648393 0.2076173 0.2250348 64.58924
+## 6 AT31 15.00000 0.2508418 0.4284512 0.2014381 0.2857610 64.58924
+## nitr_mod nitr_poor irrigated forest artific soil_loss com_birds
+## 1 20.20774 15.20302 5.850 0.3161203 0.04355635 1.842 NA
+## 2 20.20774 15.20302 0.325 0.6127954 0.03306278 5.804 NA
+## 3 20.20774 15.20302 2.650 0.4286079 0.04875064 2.236 NA
+## 4 20.20774 15.20302 10.525 0.1469534 0.73118280 1.014 NA
+## 5 20.20774 15.20302 0.100 0.5998934 0.03047416 11.671 NA
+## 6 20.20774 15.20302 0.125 0.4027358 0.04900973 3.791 NA
+## farm_birds org_farm energy_rt renew_pct renew_prod gross_N gross_P
+## 1 65.98 19.43430 0.08319988 32.65559 7.068917 32.57143 1.833333
+## 2 65.98 12.80858 0.08319988 32.65559 7.068917 32.57143 1.833333
+## 3 65.98 13.41584 0.08319988 32.65559 7.068917 32.57143 1.833333
+## 4 65.98 16.44137 0.08319988 32.65559 7.068917 32.57143 1.833333
+## 5 65.98 10.68078 0.08319988 32.65559 7.068917 32.57143 1.833333
+## 6 65.98 12.31071 0.08319988 32.65559 7.068917 32.57143 1.833333
+## conv_till cons_till zero_till nfert arable grassland permanent
+## 1 0.6182190 0.31992068 0.025012794 7.684000 83.64566 8.715722 7.5451998
+## 2 0.8887161 0.05005656 0.024109163 7.551429 37.02489 58.694493 4.2139773
+## 3 0.6226791 0.32803537 0.019896256 7.452800 76.22380 20.140837 3.5858503
+## 4 0.5109890 0.40476190 0.007326007 7.497000 79.80050 10.099751 10.0997506
+## 5 0.8592546 0.05928605 0.032552288 8.131500 28.48779 71.285286 0.1679223
+## 6 0.8442576 0.12043311 0.014198645 9.138333 56.49367 43.164202 0.2648111
+## soil_prod irrig_rate afi_awu gva_awu labour_use pest_rate gdp_cap
+## 1 6 16.6922025 24788.951 25367.72 0.036978892 1.335093 26700
+## 2 6 2.2086896 13958.345 18388.41 0.034606425 1.335093 34800
+## 3 6 10.7753945 23056.271 25423.66 0.035521808 1.335093 31800
+## 4 6 208.4609053 6431.103 9952.26 0.001572703 1.335093 47300
+## 5 6 0.5770663 10741.948 11827.48 0.028435272 1.335093 32700
+## 6 6 0.5491021 15263.545 22028.20 0.030650579 1.335093 39600
+## pps_cap emp_rate tot_unemp yth_unemp rur_gdp rur_pps int_gdp int_pps
+## 1 24600 69.81530 5.7 15.0 26690.97 24628.47 NA NA
+## 2 32100 71.37077 5.1 10.2 28015.67 25851.10 42289.66 39020.69
+## 3 29300 73.06232 5.2 9.3 29392.91 27122.78 37037.74 34176.67
+## 4 43700 64.90683 11.3 20.3 NA NA NA NA
+## 5 30200 69.88481 5.4 12.2 27340.58 25228.26 38025.00 35085.71
+## 6 36500 75.46507 4.5 7.6 33453.92 30867.51 48936.17 45154.26
+## urb_gdp urb_pps C_factor emi_co2eq emi_nh3 emi_pm10 emi_pm25
+## 1 NA NA 0.204701 653096.3 8690.371 1025.7531 818.8200
+## 2 NA NA 0.305978 954802.7 13155.494 850.9032 331.4128
+## 3 27574.60 25441.27 0.195147 1136117.0 14253.957 1285.1966 856.1814
+## 4 47307.69 43651.88 0.188655 457098.6 6375.132 609.2881 426.0527
+## 5 NA NA 0.278675 888623.1 11187.491 471.5642 220.7500
+## 6 NA NA 0.241675 1943324.3 22472.061 1298.3660 629.6217
+## soc bio_threat nat2000_ag nat2000_pr cal_frac precip deg_days
+## 1 59.33579 0.2693722 0.202690378 0.27756336 0.5245497 666.3237 1965.423
+## 2 97.49513 0.2525372 0.084071132 0.15248896 0.2280712 1149.1807 1264.833
+## 3 64.25874 0.2670201 0.139216259 0.22137659 0.5354631 714.3840 1764.210
+## 4 49.22190 0.2611445 0.182098765 0.13365361 0.5256335 580.7077 2040.184
+## 5 101.03633 0.2280257 0.008167266 0.06126958 0.2194208 1357.1470 1095.291
+## 6 100.91691 0.2672487 0.009193898 0.06533375 0.3612959 1057.0594 1537.084
+## crop_suit rye_f barley_f maize_f tritic_f sorghum_f
+## 1 5.319588 0.023158915 0.04191746 0.10322047 0.010459416 0.0019037848
+## 2 3.217877 0.004659144 0.02072924 0.12555999 0.009728318 0.0014761044
+## 3 4.347383 0.031413059 0.08222000 0.06573296 0.023418930 0.0008681970
+## 4 5.466667 0.040740741 0.04567901 0.02242798 0.008436214 0.0016460905
+## 5 2.668044 0.004181640 0.02944136 0.08118262 0.016478275 0.0003136230
+## 6 3.925520 0.013497972 0.07211149 0.08582187 0.027766215 0.0001695024
+## oth_cer_f rice_f pasture_f rape_f sunflow_f pulses_f
+## 1 0.0088828089 0 0.016951664 0.042230962 0.0163702690 0.017379161
+## 2 0.0007775365 0 0.029889596 0.001075187 0.0006074504 0.001716047
+## 3 0.0051265913 0 0.016059157 0.028237548 0.0174845920 0.012741848
+## 4 0.0177777778 0 0.002674897 0.032921811 0.0039976484 0.014403292
+## 5 0.0009722313 0 0.053812480 0.000313623 0.0008232604 0.003711205
+## 6 0.0007895810 0 0.014203875 0.018338447 0.0007960178 0.007065462
+## potato_f sugbeet_f oth_rt_f wheat_f oats_f oth_oil_f
+## 1 0.004103967 0.0187300502 7.295942e-05 0.22119243 0.006499088 0.08481532
+## 2 0.001737308 0.0006074504 4.373643e-05 0.01938374 0.002786982 0.04561345
+## 3 0.017488323 0.0360314193 6.567450e-05 0.19060904 0.014256840 0.02270124
+## 4 0.013374486 0.0467078189 0.000000e+00 0.24773663 0.003621399 0.01255144
+## 5 0.001973211 0.0001045410 0.000000e+00 0.01787216 0.006377001 0.01950996
+## 6 0.002589740 0.0100478469 9.955586e-05 0.08748686 0.017608514 0.02501556
+## fibre_f oth_ind_f fodder_f rye_y barley_y maize_y
+## 1 2.735978e-04 0.0009746922 0.04886001 3.516367 4.435137 8.744878
+## 2 7.289405e-05 0.0005181552 0.04823763 4.700782 5.715165 11.440518
+## 3 4.796229e-04 0.0029031115 0.06777658 4.357949 4.924511 9.361459
+## 4 0.000000e+00 0.0016460905 0.03168724 4.030303 4.468468 8.798165
+## 5 5.227050e-05 0.0002744201 0.07297615 4.592187 5.394585 10.736016
+## 6 1.235866e-04 0.0026176325 0.09126311 4.503259 6.279062 10.027501
+## tritic_y sorghum_y oth_cer_y rice_y pasture_y rape_y sunflow_y
+## 1 3.649591 5.164671 3.868583 NA 5.264291 2.800108 2.344708
+## 2 6.234155 8.588477 3.681250 NA 6.965349 3.519774 2.430000
+## 3 5.100860 6.237822 3.901009 NA 6.666021 3.139327 2.623319
+## 4 5.024390 3.000000 3.944444 NA 5.615385 2.918750 2.647059
+## 5 5.808485 6.694444 3.817204 NA 7.327343 2.416667 1.912698
+## 6 5.474152 5.848101 3.869565 NA 7.502266 3.812215 2.097035
+## pulses_y potato_y sugbeet_y oth_rt_y wheat_y oats_y oth_oil_y
+## 1 2.020007 34.06111 68.85210 47.12500 4.418312 3.320119 2.106922
+## 2 2.610619 27.19406 67.16500 51.00000 6.405516 3.681343 1.061669
+## 3 2.295685 31.89232 71.15838 61.30303 5.197458 3.752801 1.601008
+## 4 2.214286 34.87692 69.50661 58.60976 4.702658 2.909091 2.016393
+## 5 3.035211 24.40728 57.81250 40.91667 5.443334 3.707787 2.669792
+## 6 2.751594 30.02403 77.22785 63.89655 6.893955 4.364527 2.660348
+## fibre_y oth_ind_y fodder_y berries_y brassic_y citrus_y frtrees_y
+## 1 7.777778 1.333333 18.05331 29.18171 44.06400 NA 106.98343
+## 2 7.666667 6.587339 29.00264 12.23637 18.54004 NA 45.09310
+## 3 4.966805 1.894773 23.44168 23.90570 36.09730 NA 87.64099
+## 4 5.134100 NA 11.72727 17.16571 25.92000 NA 62.93143
+## 5 4.800000 10.952381 31.81458 14.36696 21.69391 NA 52.67087
+## 6 5.361111 3.804918 28.50815 20.89739 31.55478 NA 76.61217
+## grapes_y greens_y nuts_y olives_y oth_veg_y peas_y rootveg_y
+## 1 8.273220 61.19029 2.632571 0.000000000 29.05543 18.087999 93.43200
+## 2 3.134204 25.61430 1.210000 0.007077465 12.11144 7.590493 39.11891
+## 3 5.295910 50.12718 2.156607 NA 23.80225 14.817717 76.53964
+## 4 3.012085 35.99429 1.548571 NA 17.09143 10.639999 54.96000
+## 5 4.908311 30.12565 1.296087 0.000000000 14.30478 8.905217 45.99913
+## 6 NA 43.81913 1.885217 NA 20.80696 12.953043 66.90783
+## tropfr_y vfruits_y berries_f brassic_f citrus_f frtrees_f
+## 1 NA 258.4971 0.003187124 0.0010235525 0 0.015481333
+## 2 0.002429577 107.9879 0.001521483 0.0005296015 0 0.007548431
+## 3 NA 211.7612 0.002908851 0.0009341843 0 0.014129630
+## 4 NA 152.0571 0.001987285 0.0006382214 0 0.009653162
+## 5 NA 127.2652 0.001397762 0.0004488946 0 0.006789575
+## 6 NA 185.1130 0.002057785 0.0006608626 0 0.009995613
+## grapes_f greens_f nuts_f olives_f oth_veg_f
+## 1 0.036878371 0.0011948229 0.003024814 4.088179e-26 0.0015673054
+## 2 0.006011221 0.0005815269 0.001445650 2.015534e-05 0.0007469377
+## 3 0.033940373 0.0010905008 0.002760712 0.000000e+00 0.0014304611
+## 4 0.023496916 0.0007450146 0.001886079 0.000000e+00 0.0009772707
+## 5 0.005030330 0.0005240078 0.001326578 2.161636e-26 0.0006873657
+## 6 0.000000000 0.0007714444 0.001952989 0.000000e+00 0.0010119398
+## peas_f rootveg_f tropfr_f vfruits_f bovine
+## 1 0.0008360319 0.0018775143 0.00000e+00 0.0004477230 0.09572503
+## 2 0.0004102481 0.0009143129 3.07412e-06 0.0002370161 0.78983432
+## 3 0.0007630364 0.0017135852 0.00000e+00 0.0004086315 0.44254290
+## 4 0.0005212956 0.0011706969 0.00000e+00 0.0002791712 0.01646091
+## 5 0.0003666545 0.0008234126 0.00000e+00 0.0001963558 0.99191114
+## 6 0.0005397888 0.0012122281 0.00000e+00 0.0002890750 0.98488639
+## milk_cows pigs sheep goats
+## 1 0.019237346 0.2189751 0.02537050 0.01341102
+## 2 0.197439597 1.9225909 0.16251727 0.01782867
+## 3 0.103387585 0.7942592 0.07255415 0.01521584
+## 4 0.004320988 0.0308642 0.06394721 0.01341102
+## 5 0.177059784 0.6761058 0.23496243 0.02406403
+## 6 0.287276589 1.9368813 0.09536765 0.03951552names(dbase.final)## [1] "NUTS_ID" "risk_pov" "train35bas" "train35ful" "train_bas"
+## [6] "train_ful" "nitr_high" "nitr_mod" "nitr_poor" "irrigated"
+## [11] "forest" "artific" "soil_loss" "com_birds" "farm_birds"
+## [16] "org_farm" "energy_rt" "renew_pct" "renew_prod" "gross_N"
+## [21] "gross_P" "conv_till" "cons_till" "zero_till" "nfert"
+## [26] "arable" "grassland" "permanent" "soil_prod" "irrig_rate"
+## [31] "afi_awu" "gva_awu" "labour_use" "pest_rate" "gdp_cap"
+## [36] "pps_cap" "emp_rate" "tot_unemp" "yth_unemp" "rur_gdp"
+## [41] "rur_pps" "int_gdp" "int_pps" "urb_gdp" "urb_pps"
+## [46] "C_factor" "emi_co2eq" "emi_nh3" "emi_pm10" "emi_pm25"
+## [51] "soc" "bio_threat" "nat2000_ag" "nat2000_pr" "cal_frac"
+## [56] "precip" "deg_days" "crop_suit" "rye_f" "barley_f"
+## [61] "maize_f" "tritic_f" "sorghum_f" "oth_cer_f" "rice_f"
+## [66] "pasture_f" "rape_f" "sunflow_f" "pulses_f" "potato_f"
+## [71] "sugbeet_f" "oth_rt_f" "wheat_f" "oats_f" "oth_oil_f"
+## [76] "fibre_f" "oth_ind_f" "fodder_f" "rye_y" "barley_y"
+## [81] "maize_y" "tritic_y" "sorghum_y" "oth_cer_y" "rice_y"
+## [86] "pasture_y" "rape_y" "sunflow_y" "pulses_y" "potato_y"
+## [91] "sugbeet_y" "oth_rt_y" "wheat_y" "oats_y" "oth_oil_y"
+## [96] "fibre_y" "oth_ind_y" "fodder_y" "berries_y" "brassic_y"
+## [101] "citrus_y" "frtrees_y" "grapes_y" "greens_y" "nuts_y"
+## [106] "olives_y" "oth_veg_y" "peas_y" "rootveg_y" "tropfr_y"
+## [111] "vfruits_y" "berries_f" "brassic_f" "citrus_f" "frtrees_f"
+## [116] "grapes_f" "greens_f" "nuts_f" "olives_f" "oth_veg_f"
+## [121] "peas_f" "rootveg_f" "tropfr_f" "vfruits_f" "bovine"
+## [126] "milk_cows" "pigs" "sheep" "goats"summary(dbase.final)## NUTS_ID risk_pov train35bas train35ful
+## Length:320 Min. : 9.971 Min. :0.00000 Min. :0.0000
+## Class :character 1st Qu.:18.586 1st Qu.:0.09613 1st Qu.:0.1264
+## Mode :character Median :23.514 Median :0.22800 Median :0.2600
+## Mean :25.960 Mean :0.26424 Mean :0.2738
+## 3rd Qu.:29.680 3rd Qu.:0.35996 3rd Qu.:0.3825
+## Max. :54.150 Max. :0.88217 Max. :0.8550
+## NA's :2 NA's :52 NA's :52
+## train_bas train_ful nitr_high nitr_mod
+## Min. :0.01171 Min. :0.00188 Min. : 4.082 Min. : 0.000
+## 1st Qu.:0.10627 1st Qu.:0.04939 1st Qu.: 66.302 1st Qu.: 6.533
+## Median :0.19961 Median :0.12807 Median : 70.505 Median :15.896
+## Mean :0.26250 Mean :0.15796 Mean : 75.328 Mean :13.773
+## 3rd Qu.:0.36488 3rd Qu.:0.25108 3rd Qu.: 87.591 3rd Qu.:18.416
+## Max. :0.94840 Max. :0.50303 Max. :100.000 Max. :60.000
+## NA's :50 NA's :50 NA's :44 NA's :44
+## nitr_poor irrigated forest artific
+## Min. : 0.000 Min. : 0.0000 Min. :0.00000 Min. :0.00000
+## 1st Qu.: 4.106 1st Qu.: 0.3312 1st Qu.:0.08957 1st Qu.:0.02056
+## Median : 8.883 Median : 1.2250 Median :0.24904 Median :0.04020
+## Mean :10.898 Mean : 5.7571 Mean :0.25141 Mean :0.09023
+## 3rd Qu.:15.385 3rd Qu.: 6.5000 3rd Qu.:0.37365 3rd Qu.:0.08193
+## Max. :68.367 Max. :74.5500 Max. :0.75860 Max. :1.00000
+## NA's :44 NA's :28
+## soil_loss com_birds farm_birds org_farm
+## Min. : 0.0300 Min. :54.92 Min. : 63.78 Min. : 0.000
+## 1st Qu.: 0.7047 1st Qu.:62.14 1st Qu.: 81.34 1st Qu.: 1.200
+## Median : 1.5005 Median :69.50 Median : 83.82 Median : 2.687
+## Mean : 2.5482 Mean :69.70 Mean : 81.90 Mean : 4.056
+## 3rd Qu.: 2.9420 3rd Qu.:81.30 3rd Qu.: 85.30 3rd Qu.: 5.204
+## Max. :17.6050 Max. :97.22 Max. :116.60 Max. :27.487
+## NA's :44 NA's :158 NA's :94 NA's :28
+## energy_rt renew_pct renew_prod gross_N
+## Min. :0.00000 Min. : 0.000 Min. : 0.8855 Min. : 2.857
+## 1st Qu.:0.03503 1st Qu.: 3.074 1st Qu.: 6.2422 1st Qu.: 41.821
+## Median :0.06128 Median : 6.124 Median : 8.3156 Median : 67.333
+## Mean :0.15052 Mean :11.225 Mean :12.4318 Mean : 67.553
+## 3rd Qu.:0.09725 3rd Qu.:22.515 3rd Qu.:18.0797 3rd Qu.: 85.988
+## Max. :1.75149 Max. :41.011 Max. :37.7797 Max. :190.167
+## NA's :44 NA's :82 NA's :45 NA's :30
+## gross_P conv_till cons_till zero_till
+## Min. :-6.500 Min. :0.08646 Min. :0.00000 Min. :0.00000
+## 1st Qu.:-1.667 1st Qu.:0.46182 1st Qu.:0.05077 1st Qu.:0.00920
+## Median : 1.833 Median :0.61740 Median :0.12499 Median :0.01843
+## Mean : 1.941 Mean :0.60410 Mean :0.18031 Mean :0.03000
+## 3rd Qu.: 4.714 3rd Qu.:0.73832 3rd Qu.:0.28382 3rd Qu.:0.04003
+## Max. :31.000 Max. :0.99752 Max. :0.65066 Max. :0.19303
+## NA's :30 NA's :53 NA's :53 NA's :53
+## nfert arable grassland permanent
+## Min. : 0.000 Min. : 0.00 Min. : 0.00 Min. : 0.0000
+## 1st Qu.: 6.448 1st Qu.:39.68 1st Qu.:17.20 1st Qu.: 0.3546
+## Median : 9.917 Median :62.28 Median :32.97 Median : 1.1324
+## Mean :10.975 Mean :57.72 Mean :35.74 Mean : 5.7197
+## 3rd Qu.:14.254 3rd Qu.:78.19 3rd Qu.:48.62 3rd Qu.: 5.6520
+## Max. :29.456 Max. :99.28 Max. :98.84 Max. :64.6743
+## NA's :11 NA's :44 NA's :44 NA's :44
+## soil_prod irrig_rate afi_awu gva_awu
+## Min. :3.00 Min. : 0.000 Min. : -3221 Min. : 697.4
+## 1st Qu.:6.00 1st Qu.: 1.181 1st Qu.: 11878 1st Qu.: 10428.3
+## Median :6.00 Median : 7.396 Median : 20559 Median : 24639.3
+## Mean :6.45 Mean : 157.441 Mean : 24680 Mean : 26611.6
+## 3rd Qu.:7.00 3rd Qu.: 82.321 3rd Qu.: 34388 3rd Qu.: 38162.3
+## Max. :8.00 Max. :4156.725 Max. :107266 Max. :122952.6
+## NA's :51 NA's :22 NA's :29 NA's :29
+## labour_use pest_rate gdp_cap pps_cap
+## Min. :0.00000 Min. : 0.3874 Min. : 3800 Min. : 8200
+## 1st Qu.:0.01049 1st Qu.: 1.2195 1st Qu.: 16350 1st Qu.: 19750
+## Median :0.01976 Median : 1.8836 Median : 26500 Median : 24750
+## Mean :0.03594 Mean : 2.4120 Mean : 26832 Mean : 26526
+## 3rd Qu.:0.04539 3rd Qu.: 3.1595 3rd Qu.: 33750 3rd Qu.: 31025
+## Max. :0.22557 Max. :13.1415 Max. :191400 Max. :163500
+## NA's :44 NA's :37 NA's :44 NA's :44
+## emp_rate tot_unemp yth_unemp rur_gdp
+## Min. :37.87 Min. : 2.100 Min. : 4.20 Min. : 3117
+## 1st Qu.:62.16 1st Qu.: 4.700 1st Qu.:10.60 1st Qu.:11513
+## Median :67.91 Median : 6.850 Median :17.00 Median :22369
+## Mean :66.82 Mean : 8.767 Mean :21.39 Mean :20844
+## 3rd Qu.:73.84 3rd Qu.:10.600 3rd Qu.:29.10 3rd Qu.:27611
+## Max. :81.42 Max. :31.300 Max. :69.10 Max. :46295
+## NA's :44 NA's :44 NA's :44 NA's :164
+## rur_pps int_gdp int_pps urb_gdp
+## Min. : 6723 Min. : 3585 Min. : 7737 Min. : 5329
+## 1st Qu.:15264 1st Qu.:13307 1st Qu.:17891 1st Qu.: 23998
+## Median :20976 Median :25837 Median :24042 Median : 30497
+## Mean :21122 Mean :24197 Mean :24202 Mean : 33196
+## 3rd Qu.:25354 3rd Qu.:32205 3rd Qu.:28793 3rd Qu.: 39796
+## Max. :42716 Max. :88303 Max. :73498 Max. :191423
+## NA's :164 NA's :112 NA's :112 NA's :184
+## urb_pps C_factor emi_co2eq emi_nh3
+## Min. : 10761 Min. :0.1477 Min. : 0 Min. : 0
+## 1st Qu.: 24530 1st Qu.:0.1959 1st Qu.: 745804 1st Qu.: 8322
+## Median : 29715 Median :0.2249 Median :1121468 Median :13177
+## Mean : 32561 Mean :0.2356 Mean :1466069 Mean :16252
+## 3rd Qu.: 37017 3rd Qu.:0.2631 3rd Qu.:1804807 3rd Qu.:19954
+## Max. :163515 Max. :0.4395 Max. :7270058 Max. :88272
+## NA's :184 NA's :54 NA's :2 NA's :2
+## emi_pm10 emi_pm25 soc bio_threat
+## Min. : 0 Min. : 0.0 Min. : 31.86 Min. :0.1920
+## 1st Qu.: 434 1st Qu.: 228.1 1st Qu.: 61.59 1st Qu.:0.2507
+## Median :1012 Median : 608.9 Median : 81.03 Median :0.2858
+## Mean :1269 Mean : 765.3 Mean : 92.96 Mean :0.2981
+## 3rd Qu.:1759 3rd Qu.:1096.7 3rd Qu.:109.75 3rd Qu.:0.3192
+## Max. :7418 Max. :4020.6 Max. :374.18 Max. :0.6029
+## NA's :2 NA's :2 NA's :40 NA's :43
+## nat2000_ag nat2000_pr cal_frac precip
+## Min. :0.000000 Min. :0.00000 Min. :0.1612 Min. : 261.3
+## 1st Qu.:0.006678 1st Qu.:0.03956 1st Qu.:0.3928 1st Qu.: 610.6
+## Median :0.044534 Median :0.12229 Median :0.4986 Median : 745.8
+## Mean :0.065957 Mean :0.13586 Mean :0.5239 Mean : 800.3
+## 3rd Qu.:0.097822 3rd Qu.:0.21187 3rd Qu.:0.6305 3rd Qu.: 882.9
+## Max. :0.507382 Max. :0.49982 Max. :0.9640 Max. :2707.9
+## NA's :2 NA's :2 NA's :8
+## deg_days crop_suit rye_f barley_f
+## Min. : 242 Min. :0.000 Min. :0.0000000 Min. :0.00000
+## 1st Qu.:1536 1st Qu.:3.141 1st Qu.:0.0001763 1st Qu.:0.01824
+## Median :1711 Median :4.267 Median :0.0010613 Median :0.04720
+## Mean :2016 Mean :4.149 Mean :0.0078947 Mean :0.05499
+## 3rd Qu.:2246 3rd Qu.:5.202 3rd Qu.:0.0069115 3rd Qu.:0.08157
+## Max. :7765 Max. :6.000 Max. :0.1270547 Max. :0.22525
+## NA's :2 NA's :1 NA's :1
+## maize_f tritic_f sorghum_f
+## Min. :0.000000 Min. :0.0000000 Min. :0.0000000
+## 1st Qu.:0.000236 1st Qu.:0.0006165 1st Qu.:0.0000000
+## Median :0.008416 Median :0.0028821 Median :0.0000000
+## Mean :0.029646 Mean :0.0090348 Mean :0.0003367
+## 3rd Qu.:0.033520 3rd Qu.:0.0101557 3rd Qu.:0.0000793
+## Max. :0.319030 Max. :0.1181380 Max. :0.0180664
+## NA's :1 NA's :1 NA's :1
+## oth_cer_f rice_f pasture_f
+## Min. :0.00000 Min. :0.000000 Min. :0.000000
+## 1st Qu.:0.00000 1st Qu.:0.000000 1st Qu.:0.006223
+## Median :0.00008 Median :0.000000 Median :0.021880
+## Mean :0.00097 Mean :0.001738 Mean :0.047618
+## 3rd Qu.:0.00128 3rd Qu.:0.000000 3rd Qu.:0.084760
+## Max. :0.01778 Max. :0.107097 Max. :0.412707
+## NA's :65 NA's :1 NA's :8
+## rape_f sunflow_f pulses_f
+## Min. :0.0000000 Min. :0.000000 Min. :0.000000
+## 1st Qu.:0.0002153 1st Qu.:0.000000 1st Qu.:0.001809
+## Median :0.0125632 Median :0.000192 Median :0.004299
+## Mean :0.0268691 Mean :0.011671 Mean :0.008475
+## 3rd Qu.:0.0427553 3rd Qu.:0.004120 3rd Qu.:0.011267
+## Max. :0.1461908 Max. :0.218639 Max. :0.064771
+## NA's :1 NA's :1 NA's :1
+## potato_f sugbeet_f oth_rt_f
+## Min. :0.000000 Min. :0.000000 Min. :0.00000
+## 1st Qu.:0.002072 1st Qu.:0.000000 1st Qu.:0.00000
+## Median :0.005518 Median :0.001072 Median :0.00015
+## Mean :0.012031 Mean :0.009541 Mean :0.00091
+## 3rd Qu.:0.013376 3rd Qu.:0.013027 3rd Qu.:0.00108
+## Max. :0.188248 Max. :0.113660 Max. :0.01231
+## NA's :1 NA's :1 NA's :35
+## wheat_f oats_f oth_oil_f
+## Min. :0.000000 Min. :0.0000000 Min. :0.000000
+## 1st Qu.:0.006516 1st Qu.:0.0002925 1st Qu.:0.000000
+## Median :0.103025 Median :0.0037227 Median :0.000000
+## Mean :0.103869 Mean :0.0096505 Mean :0.004699
+## 3rd Qu.:0.170883 3rd Qu.:0.0106135 3rd Qu.:0.001537
+## Max. :0.389937 Max. :0.1912935 Max. :0.190498
+## NA's :1 NA's :1 NA's :1
+## fibre_f oth_ind_f fodder_f
+## Min. :0.0000000 Min. :0.0000000 Min. :0.000000
+## 1st Qu.:0.0000000 1st Qu.:0.0000000 1st Qu.:0.007706
+## Median :0.0000000 Median :0.0002218 Median :0.032609
+## Mean :0.0030096 Mean :0.0015573 Mean :0.045518
+## 3rd Qu.:0.0000127 3rd Qu.:0.0010943 3rd Qu.:0.069995
+## Max. :0.1513896 Max. :0.0356431 Max. :0.253901
+## NA's :1 NA's :1 NA's :1
+## rye_y barley_y maize_y tritic_y
+## Min. :0.4454 Min. :0.1254 Min. : 1.000 Min. :0.5839
+## 1st Qu.:2.6135 1st Qu.:3.0860 1st Qu.: 6.320 1st Qu.:2.9683
+## Median :3.5000 Median :4.7376 Median : 8.100 Median :4.0000
+## Mean :3.7258 Mean :4.6243 Mean : 7.929 Mean :3.9796
+## 3rd Qu.:5.0000 3rd Qu.:6.1387 3rd Qu.: 9.876 3rd Qu.:5.2188
+## Max. :7.1428 Max. :8.4666 Max. :12.976 Max. :7.3594
+## NA's :20 NA's :14 NA's :28 NA's :23
+## sorghum_y oth_cer_y rice_y pasture_y
+## Min. :1.000 Min. : 0.500 Min. : 1.857 Min. : 0.0003
+## 1st Qu.:3.173 1st Qu.: 1.465 1st Qu.: 4.567 1st Qu.: 4.3362
+## Median :4.000 Median : 2.174 Median : 5.051 Median : 7.3664
+## Mean :4.349 Mean : 2.423 Mean : 5.352 Mean : 9.6893
+## 3rd Qu.:5.675 3rd Qu.: 3.272 3rd Qu.: 5.985 3rd Qu.:10.1248
+## Max. :9.044 Max. :10.750 Max. :10.000 Max. :49.5135
+## NA's :175 NA's :149 NA's :179 NA's :108
+## rape_y sunflow_y pulses_y potato_y
+## Min. :0.006547 Min. :0.700 Min. :0.09302 Min. : 4.361
+## 1st Qu.:2.460195 1st Qu.:1.866 1st Qu.:1.65220 1st Qu.:24.144
+## Median :3.185760 Median :2.203 Median :2.20927 Median :31.598
+## Mean :2.975625 Mean :2.239 Mean :2.23948 Mean :31.469
+## 3rd Qu.:3.544947 3rd Qu.:2.686 3rd Qu.:2.77736 3rd Qu.:40.329
+## Max. :5.000000 Max. :4.393 Max. :5.00245 Max. :53.327
+## NA's :22 NA's :105 NA's :25 NA's :7
+## sugbeet_y oth_rt_y wheat_y oats_y
+## Min. : 5.00 Min. : 9.333 Min. :0.6667 Min. :0.5543
+## 1st Qu.: 57.45 1st Qu.:12.000 1st Qu.:3.3922 1st Qu.:2.3556
+## Median : 67.95 Median :24.857 Median :5.1819 Median :3.6032
+## Mean : 65.07 Mean :32.544 Mean :5.3029 Mean :3.5905
+## 3rd Qu.: 76.28 3rd Qu.:52.350 3rd Qu.:7.4295 3rd Qu.:4.7295
+## Max. :107.50 Max. :94.396 Max. :9.2898 Max. :7.2000
+## NA's :34 NA's :174 NA's :9 NA's :14
+## oth_oil_y fibre_y oth_ind_y fodder_y
+## Min. :0.1428 Min. :0.350 Min. : 0.02671 Min. : 0.6603
+## 1st Qu.:1.6668 1st Qu.:1.523 1st Qu.: 0.98452 1st Qu.:12.5398
+## Median :2.0000 Median :2.750 Median : 1.88764 Median :26.1963
+## Mean :2.1776 Mean :3.104 Mean : 2.98676 Mean :25.7794
+## 3rd Qu.:2.8162 3rd Qu.:4.838 3rd Qu.: 3.26371 3rd Qu.:38.1261
+## Max. :5.0000 Max. :8.333 Max. :13.36992 Max. :51.0516
+## NA's :50 NA's :146 NA's :54 NA's :12
+## berries_y brassic_y citrus_y
+## Min. : 0.00396 Min. : 0.03086 Min. : 0.02187
+## 1st Qu.:18.60179 1st Qu.:29.19964 1st Qu.: 43.38803
+## Median :25.99651 Median :37.54545 Median : 73.80700
+## Mean :26.03682 Mean :38.47796 Mean : 67.53417
+## 3rd Qu.:34.90468 3rd Qu.:43.59471 3rd Qu.:101.62819
+## Max. :57.13000 Max. :77.33000 Max. :122.22785
+## NA's :21 NA's :21 NA's :198
+## frtrees_y grapes_y greens_y nuts_y
+## Min. : 0.00316 Min. : 0.000 Min. : 0.0116 Min. : 0.0000
+## 1st Qu.: 41.05565 1st Qu.: 1.878 1st Qu.:23.1703 1st Qu.: 0.4243
+## Median : 62.58810 Median : 4.266 Median :37.2801 Median : 3.2225
+## Mean : 63.80520 Mean : 4.486 Mean :34.3396 Mean : 4.8389
+## 3rd Qu.: 88.15527 3rd Qu.: 6.531 3rd Qu.:43.8130 3rd Qu.: 8.3606
+## Max. :180.73000 Max. :13.714 Max. :71.3000 Max. :22.8630
+## NA's :20 NA's :79 NA's :28 NA's :44
+## olives_y oth_veg_y peas_y rootveg_y
+## Min. :0.0000 Min. : 0.00974 Min. : 0.00246 Min. : 0.0421
+## 1st Qu.:0.8311 1st Qu.: 9.32000 1st Qu.:12.93950 1st Qu.: 43.9722
+## Median :1.5341 Median :14.55378 Median :21.42656 Median : 71.1353
+## Mean :1.3702 Mean :16.73389 Mean :21.45191 Mean : 71.1527
+## 3rd Qu.:1.8099 3rd Qu.:18.99319 3rd Qu.:28.22034 3rd Qu.: 93.5171
+## Max. :4.2988 Max. :41.34000 Max. :44.57000 Max. :170.1700
+## NA's :216 NA's :20 NA's :20 NA's :21
+## tropfr_y vfruits_y berries_f
+## Min. : 0.00243 Min. : 0.1976 Min. :0.000000
+## 1st Qu.:25.81930 1st Qu.: 117.0439 1st Qu.:0.000277
+## Median :37.45034 Median : 181.0226 Median :0.000537
+## Mean :36.78523 Mean : 296.2257 Mean :0.001068
+## 3rd Qu.:48.14715 3rd Qu.: 307.1032 3rd Qu.:0.001378
+## Max. :88.52000 Max. :1194.7400 Max. :0.009374
+## NA's :189 NA's :20 NA's :4
+## brassic_f citrus_f frtrees_f
+## Min. :0.000000 Min. :0.000000 Min. :0.000000
+## 1st Qu.:0.000717 1st Qu.:0.000000 1st Qu.:0.001741
+## Median :0.001163 Median :0.000000 Median :0.007025
+## Mean :0.001651 Mean :0.002161 Mean :0.007964
+## 3rd Qu.:0.002102 3rd Qu.:0.001833 3rd Qu.:0.010316
+## Max. :0.011558 Max. :0.029824 Max. :0.092826
+## NA's :4 NA's :4 NA's :4
+## grapes_f greens_f nuts_f
+## Min. :0.000000 Min. :0.000000 Min. :0.000000
+## 1st Qu.:0.000000 1st Qu.:0.000241 1st Qu.:0.000000
+## Median :0.000322 Median :0.000839 Median :0.000212
+## Mean :0.014954 Mean :0.001398 Mean :0.004343
+## 3rd Qu.:0.017370 3rd Qu.:0.001392 3rd Qu.:0.002597
+## Max. :0.268339 Max. :0.015696 Max. :0.036033
+## NA's :4 NA's :4 NA's :4
+## olives_f oth_veg_f peas_f
+## Min. :0.000000 Min. :0.000000 Min. :0.000000
+## 1st Qu.:0.000000 1st Qu.:0.000530 1st Qu.:0.000390
+## Median :0.000000 Median :0.001639 Median :0.001316
+## Mean :0.015398 Mean :0.002617 Mean :0.001804
+## 3rd Qu.:0.000905 3rd Qu.:0.003725 3rd Qu.:0.002598
+## Max. :0.452390 Max. :0.019446 Max. :0.021036
+## NA's :4 NA's :4 NA's :4
+## rootveg_f tropfr_f vfruits_f bovine
+## Min. :0.000000 Min. :0.000000 Min. :0.000000 Min. :0.0000
+## 1st Qu.:0.000697 1st Qu.:0.000000 1st Qu.:0.000118 1st Qu.:0.1913
+## Median :0.001438 Median :0.000000 Median :0.000881 Median :0.4288
+## Mean :0.002112 Mean :0.001053 Mean :0.004773 Mean :0.5536
+## 3rd Qu.:0.002655 3rd Qu.:0.000394 3rd Qu.:0.006812 3rd Qu.:0.7943
+## Max. :0.018225 Max. :0.043473 Max. :0.041715 Max. :2.8302
+## NA's :4 NA's :4 NA's :4 NA's :8
+## milk_cows pigs sheep goats
+## Min. :0.00000 Min. : 0.0000 Min. :0.00000 Min. :0.00000
+## 1st Qu.:0.04591 1st Qu.: 0.1446 1st Qu.:0.07257 1st Qu.:0.00660
+## Median :0.10738 Median : 0.2961 Median :0.27634 Median :0.02031
+## Mean :0.16021 Mean : 0.8674 Mean :0.58262 Mean :0.11852
+## 3rd Qu.:0.19825 3rd Qu.: 0.7611 3rd Qu.:0.90416 3rd Qu.:0.12719
+## Max. :1.04331 Max. :17.2590 Max. :5.22537 Max. :2.33485
+## NA's :8 NA's :34 NA's :36 NA's :36head(dbase.final)## NUTS_ID risk_pov train35bas train35ful train_bas train_ful nitr_high
+## 1 AT11 13.73333 0.1375661 0.3333333 0.1243050 0.1779190 64.58924
+## 2 AT22 17.26667 0.2160980 0.3648294 0.2017089 0.2413594 64.58924
+## 3 AT12 13.83333 0.2084775 0.4809689 0.2534787 0.3449437 64.58924
+## 4 AT13 27.23333 0.3750000 0.7500000 0.1753247 0.4740260 64.58924
+## 5 AT21 17.20000 0.2306238 0.3648393 0.2076173 0.2250348 64.58924
+## 6 AT31 15.00000 0.2508418 0.4284512 0.2014381 0.2857610 64.58924
+## nitr_mod nitr_poor irrigated forest artific soil_loss com_birds
+## 1 20.20774 15.20302 5.850 0.3161203 0.04355635 1.842 NA
+## 2 20.20774 15.20302 0.325 0.6127954 0.03306278 5.804 NA
+## 3 20.20774 15.20302 2.650 0.4286079 0.04875064 2.236 NA
+## 4 20.20774 15.20302 10.525 0.1469534 0.73118280 1.014 NA
+## 5 20.20774 15.20302 0.100 0.5998934 0.03047416 11.671 NA
+## 6 20.20774 15.20302 0.125 0.4027358 0.04900973 3.791 NA
+## farm_birds org_farm energy_rt renew_pct renew_prod gross_N gross_P
+## 1 65.98 19.43430 0.08319988 32.65559 7.068917 32.57143 1.833333
+## 2 65.98 12.80858 0.08319988 32.65559 7.068917 32.57143 1.833333
+## 3 65.98 13.41584 0.08319988 32.65559 7.068917 32.57143 1.833333
+## 4 65.98 16.44137 0.08319988 32.65559 7.068917 32.57143 1.833333
+## 5 65.98 10.68078 0.08319988 32.65559 7.068917 32.57143 1.833333
+## 6 65.98 12.31071 0.08319988 32.65559 7.068917 32.57143 1.833333
+## conv_till cons_till zero_till nfert arable grassland permanent
+## 1 0.6182190 0.31992068 0.025012794 7.684000 83.64566 8.715722 7.5451998
+## 2 0.8887161 0.05005656 0.024109163 7.551429 37.02489 58.694493 4.2139773
+## 3 0.6226791 0.32803537 0.019896256 7.452800 76.22380 20.140837 3.5858503
+## 4 0.5109890 0.40476190 0.007326007 7.497000 79.80050 10.099751 10.0997506
+## 5 0.8592546 0.05928605 0.032552288 8.131500 28.48779 71.285286 0.1679223
+## 6 0.8442576 0.12043311 0.014198645 9.138333 56.49367 43.164202 0.2648111
+## soil_prod irrig_rate afi_awu gva_awu labour_use pest_rate gdp_cap
+## 1 6 16.6922025 24788.951 25367.72 0.036978892 1.335093 26700
+## 2 6 2.2086896 13958.345 18388.41 0.034606425 1.335093 34800
+## 3 6 10.7753945 23056.271 25423.66 0.035521808 1.335093 31800
+## 4 6 208.4609053 6431.103 9952.26 0.001572703 1.335093 47300
+## 5 6 0.5770663 10741.948 11827.48 0.028435272 1.335093 32700
+## 6 6 0.5491021 15263.545 22028.20 0.030650579 1.335093 39600
+## pps_cap emp_rate tot_unemp yth_unemp rur_gdp rur_pps int_gdp int_pps
+## 1 24600 69.81530 5.7 15.0 26690.97 24628.47 NA NA
+## 2 32100 71.37077 5.1 10.2 28015.67 25851.10 42289.66 39020.69
+## 3 29300 73.06232 5.2 9.3 29392.91 27122.78 37037.74 34176.67
+## 4 43700 64.90683 11.3 20.3 NA NA NA NA
+## 5 30200 69.88481 5.4 12.2 27340.58 25228.26 38025.00 35085.71
+## 6 36500 75.46507 4.5 7.6 33453.92 30867.51 48936.17 45154.26
+## urb_gdp urb_pps C_factor emi_co2eq emi_nh3 emi_pm10 emi_pm25
+## 1 NA NA 0.204701 653096.3 8690.371 1025.7531 818.8200
+## 2 NA NA 0.305978 954802.7 13155.494 850.9032 331.4128
+## 3 27574.60 25441.27 0.195147 1136117.0 14253.957 1285.1966 856.1814
+## 4 47307.69 43651.88 0.188655 457098.6 6375.132 609.2881 426.0527
+## 5 NA NA 0.278675 888623.1 11187.491 471.5642 220.7500
+## 6 NA NA 0.241675 1943324.3 22472.061 1298.3660 629.6217
+## soc bio_threat nat2000_ag nat2000_pr cal_frac precip deg_days
+## 1 59.33579 0.2693722 0.202690378 0.27756336 0.5245497 666.3237 1965.423
+## 2 97.49513 0.2525372 0.084071132 0.15248896 0.2280712 1149.1807 1264.833
+## 3 64.25874 0.2670201 0.139216259 0.22137659 0.5354631 714.3840 1764.210
+## 4 49.22190 0.2611445 0.182098765 0.13365361 0.5256335 580.7077 2040.184
+## 5 101.03633 0.2280257 0.008167266 0.06126958 0.2194208 1357.1470 1095.291
+## 6 100.91691 0.2672487 0.009193898 0.06533375 0.3612959 1057.0594 1537.084
+## crop_suit rye_f barley_f maize_f tritic_f sorghum_f
+## 1 5.319588 0.023158915 0.04191746 0.10322047 0.010459416 0.0019037848
+## 2 3.217877 0.004659144 0.02072924 0.12555999 0.009728318 0.0014761044
+## 3 4.347383 0.031413059 0.08222000 0.06573296 0.023418930 0.0008681970
+## 4 5.466667 0.040740741 0.04567901 0.02242798 0.008436214 0.0016460905
+## 5 2.668044 0.004181640 0.02944136 0.08118262 0.016478275 0.0003136230
+## 6 3.925520 0.013497972 0.07211149 0.08582187 0.027766215 0.0001695024
+## oth_cer_f rice_f pasture_f rape_f sunflow_f pulses_f
+## 1 0.0088828089 0 0.016951664 0.042230962 0.0163702690 0.017379161
+## 2 0.0007775365 0 0.029889596 0.001075187 0.0006074504 0.001716047
+## 3 0.0051265913 0 0.016059157 0.028237548 0.0174845920 0.012741848
+## 4 0.0177777778 0 0.002674897 0.032921811 0.0039976484 0.014403292
+## 5 0.0009722313 0 0.053812480 0.000313623 0.0008232604 0.003711205
+## 6 0.0007895810 0 0.014203875 0.018338447 0.0007960178 0.007065462
+## potato_f sugbeet_f oth_rt_f wheat_f oats_f oth_oil_f
+## 1 0.004103967 0.0187300502 7.295942e-05 0.22119243 0.006499088 0.08481532
+## 2 0.001737308 0.0006074504 4.373643e-05 0.01938374 0.002786982 0.04561345
+## 3 0.017488323 0.0360314193 6.567450e-05 0.19060904 0.014256840 0.02270124
+## 4 0.013374486 0.0467078189 0.000000e+00 0.24773663 0.003621399 0.01255144
+## 5 0.001973211 0.0001045410 0.000000e+00 0.01787216 0.006377001 0.01950996
+## 6 0.002589740 0.0100478469 9.955586e-05 0.08748686 0.017608514 0.02501556
+## fibre_f oth_ind_f fodder_f rye_y barley_y maize_y
+## 1 2.735978e-04 0.0009746922 0.04886001 3.516367 4.435137 8.744878
+## 2 7.289405e-05 0.0005181552 0.04823763 4.700782 5.715165 11.440518
+## 3 4.796229e-04 0.0029031115 0.06777658 4.357949 4.924511 9.361459
+## 4 0.000000e+00 0.0016460905 0.03168724 4.030303 4.468468 8.798165
+## 5 5.227050e-05 0.0002744201 0.07297615 4.592187 5.394585 10.736016
+## 6 1.235866e-04 0.0026176325 0.09126311 4.503259 6.279062 10.027501
+## tritic_y sorghum_y oth_cer_y rice_y pasture_y rape_y sunflow_y
+## 1 3.649591 5.164671 3.868583 NA 5.264291 2.800108 2.344708
+## 2 6.234155 8.588477 3.681250 NA 6.965349 3.519774 2.430000
+## 3 5.100860 6.237822 3.901009 NA 6.666021 3.139327 2.623319
+## 4 5.024390 3.000000 3.944444 NA 5.615385 2.918750 2.647059
+## 5 5.808485 6.694444 3.817204 NA 7.327343 2.416667 1.912698
+## 6 5.474152 5.848101 3.869565 NA 7.502266 3.812215 2.097035
+## pulses_y potato_y sugbeet_y oth_rt_y wheat_y oats_y oth_oil_y
+## 1 2.020007 34.06111 68.85210 47.12500 4.418312 3.320119 2.106922
+## 2 2.610619 27.19406 67.16500 51.00000 6.405516 3.681343 1.061669
+## 3 2.295685 31.89232 71.15838 61.30303 5.197458 3.752801 1.601008
+## 4 2.214286 34.87692 69.50661 58.60976 4.702658 2.909091 2.016393
+## 5 3.035211 24.40728 57.81250 40.91667 5.443334 3.707787 2.669792
+## 6 2.751594 30.02403 77.22785 63.89655 6.893955 4.364527 2.660348
+## fibre_y oth_ind_y fodder_y berries_y brassic_y citrus_y frtrees_y
+## 1 7.777778 1.333333 18.05331 29.18171 44.06400 NA 106.98343
+## 2 7.666667 6.587339 29.00264 12.23637 18.54004 NA 45.09310
+## 3 4.966805 1.894773 23.44168 23.90570 36.09730 NA 87.64099
+## 4 5.134100 NA 11.72727 17.16571 25.92000 NA 62.93143
+## 5 4.800000 10.952381 31.81458 14.36696 21.69391 NA 52.67087
+## 6 5.361111 3.804918 28.50815 20.89739 31.55478 NA 76.61217
+## grapes_y greens_y nuts_y olives_y oth_veg_y peas_y rootveg_y
+## 1 8.273220 61.19029 2.632571 0.000000000 29.05543 18.087999 93.43200
+## 2 3.134204 25.61430 1.210000 0.007077465 12.11144 7.590493 39.11891
+## 3 5.295910 50.12718 2.156607 NA 23.80225 14.817717 76.53964
+## 4 3.012085 35.99429 1.548571 NA 17.09143 10.639999 54.96000
+## 5 4.908311 30.12565 1.296087 0.000000000 14.30478 8.905217 45.99913
+## 6 NA 43.81913 1.885217 NA 20.80696 12.953043 66.90783
+## tropfr_y vfruits_y berries_f brassic_f citrus_f frtrees_f
+## 1 NA 258.4971 0.003187124 0.0010235525 0 0.015481333
+## 2 0.002429577 107.9879 0.001521483 0.0005296015 0 0.007548431
+## 3 NA 211.7612 0.002908851 0.0009341843 0 0.014129630
+## 4 NA 152.0571 0.001987285 0.0006382214 0 0.009653162
+## 5 NA 127.2652 0.001397762 0.0004488946 0 0.006789575
+## 6 NA 185.1130 0.002057785 0.0006608626 0 0.009995613
+## grapes_f greens_f nuts_f olives_f oth_veg_f
+## 1 0.036878371 0.0011948229 0.003024814 4.088179e-26 0.0015673054
+## 2 0.006011221 0.0005815269 0.001445650 2.015534e-05 0.0007469377
+## 3 0.033940373 0.0010905008 0.002760712 0.000000e+00 0.0014304611
+## 4 0.023496916 0.0007450146 0.001886079 0.000000e+00 0.0009772707
+## 5 0.005030330 0.0005240078 0.001326578 2.161636e-26 0.0006873657
+## 6 0.000000000 0.0007714444 0.001952989 0.000000e+00 0.0010119398
+## peas_f rootveg_f tropfr_f vfruits_f bovine
+## 1 0.0008360319 0.0018775143 0.00000e+00 0.0004477230 0.09572503
+## 2 0.0004102481 0.0009143129 3.07412e-06 0.0002370161 0.78983432
+## 3 0.0007630364 0.0017135852 0.00000e+00 0.0004086315 0.44254290
+## 4 0.0005212956 0.0011706969 0.00000e+00 0.0002791712 0.01646091
+## 5 0.0003666545 0.0008234126 0.00000e+00 0.0001963558 0.99191114
+## 6 0.0005397888 0.0012122281 0.00000e+00 0.0002890750 0.98488639
+## milk_cows pigs sheep goats
+## 1 0.019237346 0.2189751 0.02537050 0.01341102
+## 2 0.197439597 1.9225909 0.16251727 0.01782867
+## 3 0.103387585 0.7942592 0.07255415 0.01521584
+## 4 0.004320988 0.0308642 0.06394721 0.01341102
+## 5 0.177059784 0.6761058 0.23496243 0.02406403
+## 6 0.287276589 1.9368813 0.09536765 0.03951552head(nuts@data)## CNTR_CODE FID_1 LEVL_CODE NUTS_ID NUTS_NAME Shape_Length
+## 1 AT AT11 2 AT11 Burgenland (AT) 628921.6
+## 2 AT AT22 2 AT22 Steiermark 814700.6
+## 3 AT AT12 2 AT12 Niederösterreich 1044711.5
+## 4 AT AT13 2 AT13 Wien 116902.7
+## 5 AT AT21 2 AT21 Kärnten 625727.5
+## 6 AT AT31 2 AT31 Oberösterreich 790984.0
+## Shape_Area
+## 1 3963509482
+## 2 16414303341
+## 3 19201725666
+## 4 411979159
+## 5 9541848203
+## 6 11984617500sp.dbase <- nuts
+sp.dbase@data <- left_join(nuts@data, dbase.final)## Joining, by = "NUTS_ID"## Warning: Column `NUTS_ID` joining factor and character vector, coercing
+## into character vectornames(sp.dbase@data) ## [1] "CNTR_CODE" "FID_1" "LEVL_CODE" "NUTS_ID"
+## [5] "NUTS_NAME" "Shape_Length" "Shape_Area" "risk_pov"
+## [9] "train35bas" "train35ful" "train_bas" "train_ful"
+## [13] "nitr_high" "nitr_mod" "nitr_poor" "irrigated"
+## [17] "forest" "artific" "soil_loss" "com_birds"
+## [21] "farm_birds" "org_farm" "energy_rt" "renew_pct"
+## [25] "renew_prod" "gross_N" "gross_P" "conv_till"
+## [29] "cons_till" "zero_till" "nfert" "arable"
+## [33] "grassland" "permanent" "soil_prod" "irrig_rate"
+## [37] "afi_awu" "gva_awu" "labour_use" "pest_rate"
+## [41] "gdp_cap" "pps_cap" "emp_rate" "tot_unemp"
+## [45] "yth_unemp" "rur_gdp" "rur_pps" "int_gdp"
+## [49] "int_pps" "urb_gdp" "urb_pps" "C_factor"
+## [53] "emi_co2eq" "emi_nh3" "emi_pm10" "emi_pm25"
+## [57] "soc" "bio_threat" "nat2000_ag" "nat2000_pr"
+## [61] "cal_frac" "precip" "deg_days" "crop_suit"
+## [65] "rye_f" "barley_f" "maize_f" "tritic_f"
+## [69] "sorghum_f" "oth_cer_f" "rice_f" "pasture_f"
+## [73] "rape_f" "sunflow_f" "pulses_f" "potato_f"
+## [77] "sugbeet_f" "oth_rt_f" "wheat_f" "oats_f"
+## [81] "oth_oil_f" "fibre_f" "oth_ind_f" "fodder_f"
+## [85] "rye_y" "barley_y" "maize_y" "tritic_y"
+## [89] "sorghum_y" "oth_cer_y" "rice_y" "pasture_y"
+## [93] "rape_y" "sunflow_y" "pulses_y" "potato_y"
+## [97] "sugbeet_y" "oth_rt_y" "wheat_y" "oats_y"
+## [101] "oth_oil_y" "fibre_y" "oth_ind_y" "fodder_y"
+## [105] "berries_y" "brassic_y" "citrus_y" "frtrees_y"
+## [109] "grapes_y" "greens_y" "nuts_y" "olives_y"
+## [113] "oth_veg_y" "peas_y" "rootveg_y" "tropfr_y"
+## [117] "vfruits_y" "berries_f" "brassic_f" "citrus_f"
+## [121] "frtrees_f" "grapes_f" "greens_f" "nuts_f"
+## [125] "olives_f" "oth_veg_f" "peas_f" "rootveg_f"
+## [129] "tropfr_f" "vfruits_f" "bovine" "milk_cows"
+## [133] "pigs" "sheep" "goats"dbase.shp <- sp.dbase
+names(dbase.shp@data)## [1] "CNTR_CODE" "FID_1" "LEVL_CODE" "NUTS_ID"
+## [5] "NUTS_NAME" "Shape_Length" "Shape_Area" "risk_pov"
+## [9] "train35bas" "train35ful" "train_bas" "train_ful"
+## [13] "nitr_high" "nitr_mod" "nitr_poor" "irrigated"
+## [17] "forest" "artific" "soil_loss" "com_birds"
+## [21] "farm_birds" "org_farm" "energy_rt" "renew_pct"
+## [25] "renew_prod" "gross_N" "gross_P" "conv_till"
+## [29] "cons_till" "zero_till" "nfert" "arable"
+## [33] "grassland" "permanent" "soil_prod" "irrig_rate"
+## [37] "afi_awu" "gva_awu" "labour_use" "pest_rate"
+## [41] "gdp_cap" "pps_cap" "emp_rate" "tot_unemp"
+## [45] "yth_unemp" "rur_gdp" "rur_pps" "int_gdp"
+## [49] "int_pps" "urb_gdp" "urb_pps" "C_factor"
+## [53] "emi_co2eq" "emi_nh3" "emi_pm10" "emi_pm25"
+## [57] "soc" "bio_threat" "nat2000_ag" "nat2000_pr"
+## [61] "cal_frac" "precip" "deg_days" "crop_suit"
+## [65] "rye_f" "barley_f" "maize_f" "tritic_f"
+## [69] "sorghum_f" "oth_cer_f" "rice_f" "pasture_f"
+## [73] "rape_f" "sunflow_f" "pulses_f" "potato_f"
+## [77] "sugbeet_f" "oth_rt_f" "wheat_f" "oats_f"
+## [81] "oth_oil_f" "fibre_f" "oth_ind_f" "fodder_f"
+## [85] "rye_y" "barley_y" "maize_y" "tritic_y"
+## [89] "sorghum_y" "oth_cer_y" "rice_y" "pasture_y"
+## [93] "rape_y" "sunflow_y" "pulses_y" "potato_y"
+## [97] "sugbeet_y" "oth_rt_y" "wheat_y" "oats_y"
+## [101] "oth_oil_y" "fibre_y" "oth_ind_y" "fodder_y"
+## [105] "berries_y" "brassic_y" "citrus_y" "frtrees_y"
+## [109] "grapes_y" "greens_y" "nuts_y" "olives_y"
+## [113] "oth_veg_y" "peas_y" "rootveg_y" "tropfr_y"
+## [117] "vfruits_y" "berries_f" "brassic_f" "citrus_f"
+## [121] "frtrees_f" "grapes_f" "greens_f" "nuts_f"
+## [125] "olives_f" "oth_veg_f" "peas_f" "rootveg_f"
+## [129] "tropfr_f" "vfruits_f" "bovine" "milk_cows"
+## [133] "pigs" "sheep" "goats"#We exclude some variables
+dbase.shp@data <- dbase.shp@data[,-c(2,3)]
+
+#Make NAs -99999 for shapefile
+summary(dbase.shp@data)## CNTR_CODE NUTS_ID NUTS_NAME
+## UK : 40 Length:320 Ãstra Mellansverige : 1
+## DE : 38 Class :character Ãvre Norrland : 1
+## FR : 27 Mode :character Ã
land : 1
+## TR : 26 Ãszak-Alföld : 1
+## IT : 21 Ãszak-Magyarország : 1
+## ES : 19 Ã\201rea Metropolitana de Lisboa: 1
+## (Other):149 (Other) :314
+## Shape_Length Shape_Area risk_pov train35bas
+## Min. : 15458 Min. :1.304e+07 Min. : 9.971 Min. :0.00000
+## 1st Qu.: 545979 1st Qu.:5.074e+09 1st Qu.:18.586 1st Qu.:0.09613
+## Median : 836914 Median :1.131e+10 Median :23.514 Median :0.22800
+## Mean : 1114048 Mean :1.799e+10 Mean :25.960 Mean :0.26424
+## 3rd Qu.: 1200811 3rd Qu.:2.403e+10 3rd Qu.:29.680 3rd Qu.:0.35996
+## Max. :18760323 Max. :2.271e+11 Max. :54.150 Max. :0.88217
+## NA's :2 NA's :52
+## train35ful train_bas train_ful nitr_high
+## Min. :0.0000 Min. :0.01171 Min. :0.00188 Min. : 4.082
+## 1st Qu.:0.1264 1st Qu.:0.10627 1st Qu.:0.04939 1st Qu.: 66.302
+## Median :0.2600 Median :0.19961 Median :0.12807 Median : 70.505
+## Mean :0.2738 Mean :0.26250 Mean :0.15796 Mean : 75.328
+## 3rd Qu.:0.3825 3rd Qu.:0.36488 3rd Qu.:0.25108 3rd Qu.: 87.591
+## Max. :0.8550 Max. :0.94840 Max. :0.50303 Max. :100.000
+## NA's :52 NA's :50 NA's :50 NA's :44
+## nitr_mod nitr_poor irrigated forest
+## Min. : 0.000 Min. : 0.000 Min. : 0.0000 Min. :0.00000
+## 1st Qu.: 6.533 1st Qu.: 4.106 1st Qu.: 0.3312 1st Qu.:0.08957
+## Median :15.896 Median : 8.883 Median : 1.2250 Median :0.24904
+## Mean :13.773 Mean :10.898 Mean : 5.7571 Mean :0.25141
+## 3rd Qu.:18.416 3rd Qu.:15.385 3rd Qu.: 6.5000 3rd Qu.:0.37365
+## Max. :60.000 Max. :68.367 Max. :74.5500 Max. :0.75860
+## NA's :44 NA's :44 NA's :28
+## artific soil_loss com_birds farm_birds
+## Min. :0.00000 Min. : 0.0300 Min. :54.92 Min. : 63.78
+## 1st Qu.:0.02056 1st Qu.: 0.7047 1st Qu.:62.14 1st Qu.: 81.34
+## Median :0.04020 Median : 1.5005 Median :69.50 Median : 83.82
+## Mean :0.09023 Mean : 2.5482 Mean :69.70 Mean : 81.90
+## 3rd Qu.:0.08193 3rd Qu.: 2.9420 3rd Qu.:81.30 3rd Qu.: 85.30
+## Max. :1.00000 Max. :17.6050 Max. :97.22 Max. :116.60
+## NA's :44 NA's :158 NA's :94
+## org_farm energy_rt renew_pct renew_prod
+## Min. : 0.000 Min. :0.00000 Min. : 0.000 Min. : 0.8855
+## 1st Qu.: 1.200 1st Qu.:0.03503 1st Qu.: 3.074 1st Qu.: 6.2422
+## Median : 2.687 Median :0.06128 Median : 6.124 Median : 8.3156
+## Mean : 4.056 Mean :0.15052 Mean :11.225 Mean :12.4318
+## 3rd Qu.: 5.204 3rd Qu.:0.09725 3rd Qu.:22.515 3rd Qu.:18.0797
+## Max. :27.487 Max. :1.75149 Max. :41.011 Max. :37.7797
+## NA's :28 NA's :44 NA's :82 NA's :45
+## gross_N gross_P conv_till cons_till
+## Min. : 2.857 Min. :-6.500 Min. :0.08646 Min. :0.00000
+## 1st Qu.: 41.821 1st Qu.:-1.667 1st Qu.:0.46182 1st Qu.:0.05077
+## Median : 67.333 Median : 1.833 Median :0.61740 Median :0.12499
+## Mean : 67.553 Mean : 1.941 Mean :0.60410 Mean :0.18031
+## 3rd Qu.: 85.988 3rd Qu.: 4.714 3rd Qu.:0.73832 3rd Qu.:0.28382
+## Max. :190.167 Max. :31.000 Max. :0.99752 Max. :0.65066
+## NA's :30 NA's :30 NA's :53 NA's :53
+## zero_till nfert arable grassland
+## Min. :0.00000 Min. : 0.000 Min. : 0.00 Min. : 0.00
+## 1st Qu.:0.00920 1st Qu.: 6.448 1st Qu.:39.68 1st Qu.:17.20
+## Median :0.01843 Median : 9.917 Median :62.28 Median :32.97
+## Mean :0.03000 Mean :10.975 Mean :57.72 Mean :35.74
+## 3rd Qu.:0.04003 3rd Qu.:14.254 3rd Qu.:78.19 3rd Qu.:48.62
+## Max. :0.19303 Max. :29.456 Max. :99.28 Max. :98.84
+## NA's :53 NA's :11 NA's :44 NA's :44
+## permanent soil_prod irrig_rate afi_awu
+## Min. : 0.0000 Min. :3.00 Min. : 0.000 Min. : -3221
+## 1st Qu.: 0.3546 1st Qu.:6.00 1st Qu.: 1.181 1st Qu.: 11878
+## Median : 1.1324 Median :6.00 Median : 7.396 Median : 20559
+## Mean : 5.7197 Mean :6.45 Mean : 157.441 Mean : 24680
+## 3rd Qu.: 5.6520 3rd Qu.:7.00 3rd Qu.: 82.321 3rd Qu.: 34388
+## Max. :64.6743 Max. :8.00 Max. :4156.725 Max. :107266
+## NA's :44 NA's :51 NA's :22 NA's :29
+## gva_awu labour_use pest_rate gdp_cap
+## Min. : 697.4 Min. :0.00000 Min. : 0.3874 Min. : 3800
+## 1st Qu.: 10428.3 1st Qu.:0.01049 1st Qu.: 1.2195 1st Qu.: 16350
+## Median : 24639.3 Median :0.01976 Median : 1.8836 Median : 26500
+## Mean : 26611.6 Mean :0.03594 Mean : 2.4120 Mean : 26832
+## 3rd Qu.: 38162.3 3rd Qu.:0.04539 3rd Qu.: 3.1595 3rd Qu.: 33750
+## Max. :122952.6 Max. :0.22557 Max. :13.1415 Max. :191400
+## NA's :29 NA's :44 NA's :37 NA's :44
+## pps_cap emp_rate tot_unemp yth_unemp
+## Min. : 8200 Min. :37.87 Min. : 2.100 Min. : 4.20
+## 1st Qu.: 19750 1st Qu.:62.16 1st Qu.: 4.700 1st Qu.:10.60
+## Median : 24750 Median :67.91 Median : 6.850 Median :17.00
+## Mean : 26526 Mean :66.82 Mean : 8.767 Mean :21.39
+## 3rd Qu.: 31025 3rd Qu.:73.84 3rd Qu.:10.600 3rd Qu.:29.10
+## Max. :163500 Max. :81.42 Max. :31.300 Max. :69.10
+## NA's :44 NA's :44 NA's :44 NA's :44
+## rur_gdp rur_pps int_gdp int_pps
+## Min. : 3117 Min. : 6723 Min. : 3585 Min. : 7737
+## 1st Qu.:11513 1st Qu.:15264 1st Qu.:13307 1st Qu.:17891
+## Median :22369 Median :20976 Median :25837 Median :24042
+## Mean :20844 Mean :21122 Mean :24197 Mean :24202
+## 3rd Qu.:27611 3rd Qu.:25354 3rd Qu.:32205 3rd Qu.:28793
+## Max. :46295 Max. :42716 Max. :88303 Max. :73498
+## NA's :164 NA's :164 NA's :112 NA's :112
+## urb_gdp urb_pps C_factor emi_co2eq
+## Min. : 5329 Min. : 10761 Min. :0.1477 Min. : 0
+## 1st Qu.: 23998 1st Qu.: 24530 1st Qu.:0.1959 1st Qu.: 745804
+## Median : 30497 Median : 29715 Median :0.2249 Median :1121468
+## Mean : 33196 Mean : 32561 Mean :0.2356 Mean :1466069
+## 3rd Qu.: 39796 3rd Qu.: 37017 3rd Qu.:0.2631 3rd Qu.:1804807
+## Max. :191423 Max. :163515 Max. :0.4395 Max. :7270058
+## NA's :184 NA's :184 NA's :54 NA's :2
+## emi_nh3 emi_pm10 emi_pm25 soc
+## Min. : 0 Min. : 0 Min. : 0.0 Min. : 31.86
+## 1st Qu.: 8322 1st Qu.: 434 1st Qu.: 228.1 1st Qu.: 61.59
+## Median :13177 Median :1012 Median : 608.9 Median : 81.03
+## Mean :16252 Mean :1269 Mean : 765.3 Mean : 92.96
+## 3rd Qu.:19954 3rd Qu.:1759 3rd Qu.:1096.7 3rd Qu.:109.75
+## Max. :88272 Max. :7418 Max. :4020.6 Max. :374.18
+## NA's :2 NA's :2 NA's :2 NA's :40
+## bio_threat nat2000_ag nat2000_pr cal_frac
+## Min. :0.1920 Min. :0.000000 Min. :0.00000 Min. :0.1612
+## 1st Qu.:0.2507 1st Qu.:0.006678 1st Qu.:0.03956 1st Qu.:0.3928
+## Median :0.2858 Median :0.044534 Median :0.12229 Median :0.4986
+## Mean :0.2981 Mean :0.065957 Mean :0.13586 Mean :0.5239
+## 3rd Qu.:0.3192 3rd Qu.:0.097822 3rd Qu.:0.21187 3rd Qu.:0.6305
+## Max. :0.6029 Max. :0.507382 Max. :0.49982 Max. :0.9640
+## NA's :43 NA's :2 NA's :2 NA's :8
+## precip deg_days crop_suit rye_f
+## Min. : 261.3 Min. : 242 Min. :0.000 Min. :0.0000000
+## 1st Qu.: 610.6 1st Qu.:1536 1st Qu.:3.141 1st Qu.:0.0001763
+## Median : 745.8 Median :1711 Median :4.267 Median :0.0010613
+## Mean : 800.3 Mean :2016 Mean :4.149 Mean :0.0078947
+## 3rd Qu.: 882.9 3rd Qu.:2246 3rd Qu.:5.202 3rd Qu.:0.0069115
+## Max. :2707.9 Max. :7765 Max. :6.000 Max. :0.1270547
+## NA's :2 NA's :1
+## barley_f maize_f tritic_f
+## Min. :0.00000 Min. :0.000000 Min. :0.0000000
+## 1st Qu.:0.01824 1st Qu.:0.000236 1st Qu.:0.0006165
+## Median :0.04720 Median :0.008416 Median :0.0028821
+## Mean :0.05499 Mean :0.029646 Mean :0.0090348
+## 3rd Qu.:0.08157 3rd Qu.:0.033520 3rd Qu.:0.0101557
+## Max. :0.22525 Max. :0.319030 Max. :0.1181380
+## NA's :1 NA's :1 NA's :1
+## sorghum_f oth_cer_f rice_f
+## Min. :0.0000000 Min. :0.00000 Min. :0.000000
+## 1st Qu.:0.0000000 1st Qu.:0.00000 1st Qu.:0.000000
+## Median :0.0000000 Median :0.00008 Median :0.000000
+## Mean :0.0003367 Mean :0.00097 Mean :0.001738
+## 3rd Qu.:0.0000793 3rd Qu.:0.00128 3rd Qu.:0.000000
+## Max. :0.0180664 Max. :0.01778 Max. :0.107097
+## NA's :1 NA's :65 NA's :1
+## pasture_f rape_f sunflow_f
+## Min. :0.000000 Min. :0.0000000 Min. :0.000000
+## 1st Qu.:0.006223 1st Qu.:0.0002153 1st Qu.:0.000000
+## Median :0.021880 Median :0.0125632 Median :0.000192
+## Mean :0.047618 Mean :0.0268691 Mean :0.011671
+## 3rd Qu.:0.084760 3rd Qu.:0.0427553 3rd Qu.:0.004120
+## Max. :0.412707 Max. :0.1461908 Max. :0.218639
+## NA's :8 NA's :1 NA's :1
+## pulses_f potato_f sugbeet_f
+## Min. :0.000000 Min. :0.000000 Min. :0.000000
+## 1st Qu.:0.001809 1st Qu.:0.002072 1st Qu.:0.000000
+## Median :0.004299 Median :0.005518 Median :0.001072
+## Mean :0.008475 Mean :0.012031 Mean :0.009541
+## 3rd Qu.:0.011267 3rd Qu.:0.013376 3rd Qu.:0.013027
+## Max. :0.064771 Max. :0.188248 Max. :0.113660
+## NA's :1 NA's :1 NA's :1
+## oth_rt_f wheat_f oats_f
+## Min. :0.00000 Min. :0.000000 Min. :0.0000000
+## 1st Qu.:0.00000 1st Qu.:0.006516 1st Qu.:0.0002925
+## Median :0.00015 Median :0.103025 Median :0.0037227
+## Mean :0.00091 Mean :0.103869 Mean :0.0096505
+## 3rd Qu.:0.00108 3rd Qu.:0.170883 3rd Qu.:0.0106135
+## Max. :0.01231 Max. :0.389937 Max. :0.1912935
+## NA's :35 NA's :1 NA's :1
+## oth_oil_f fibre_f oth_ind_f
+## Min. :0.000000 Min. :0.0000000 Min. :0.0000000
+## 1st Qu.:0.000000 1st Qu.:0.0000000 1st Qu.:0.0000000
+## Median :0.000000 Median :0.0000000 Median :0.0002218
+## Mean :0.004699 Mean :0.0030096 Mean :0.0015573
+## 3rd Qu.:0.001537 3rd Qu.:0.0000127 3rd Qu.:0.0010943
+## Max. :0.190498 Max. :0.1513896 Max. :0.0356431
+## NA's :1 NA's :1 NA's :1
+## fodder_f rye_y barley_y maize_y
+## Min. :0.000000 Min. :0.4454 Min. :0.1254 Min. : 1.000
+## 1st Qu.:0.007706 1st Qu.:2.6135 1st Qu.:3.0860 1st Qu.: 6.320
+## Median :0.032609 Median :3.5000 Median :4.7376 Median : 8.100
+## Mean :0.045518 Mean :3.7258 Mean :4.6243 Mean : 7.929
+## 3rd Qu.:0.069995 3rd Qu.:5.0000 3rd Qu.:6.1387 3rd Qu.: 9.876
+## Max. :0.253901 Max. :7.1428 Max. :8.4666 Max. :12.976
+## NA's :1 NA's :20 NA's :14 NA's :28
+## tritic_y sorghum_y oth_cer_y rice_y
+## Min. :0.5839 Min. :1.000 Min. : 0.500 Min. : 1.857
+## 1st Qu.:2.9683 1st Qu.:3.173 1st Qu.: 1.465 1st Qu.: 4.567
+## Median :4.0000 Median :4.000 Median : 2.174 Median : 5.051
+## Mean :3.9796 Mean :4.349 Mean : 2.423 Mean : 5.352
+## 3rd Qu.:5.2188 3rd Qu.:5.675 3rd Qu.: 3.272 3rd Qu.: 5.985
+## Max. :7.3594 Max. :9.044 Max. :10.750 Max. :10.000
+## NA's :23 NA's :175 NA's :149 NA's :179
+## pasture_y rape_y sunflow_y pulses_y
+## Min. : 0.0003 Min. :0.006547 Min. :0.700 Min. :0.09302
+## 1st Qu.: 4.3362 1st Qu.:2.460195 1st Qu.:1.866 1st Qu.:1.65220
+## Median : 7.3664 Median :3.185760 Median :2.203 Median :2.20927
+## Mean : 9.6893 Mean :2.975625 Mean :2.239 Mean :2.23948
+## 3rd Qu.:10.1248 3rd Qu.:3.544947 3rd Qu.:2.686 3rd Qu.:2.77736
+## Max. :49.5135 Max. :5.000000 Max. :4.393 Max. :5.00245
+## NA's :108 NA's :22 NA's :105 NA's :25
+## potato_y sugbeet_y oth_rt_y wheat_y
+## Min. : 4.361 Min. : 5.00 Min. : 9.333 Min. :0.6667
+## 1st Qu.:24.144 1st Qu.: 57.45 1st Qu.:12.000 1st Qu.:3.3922
+## Median :31.598 Median : 67.95 Median :24.857 Median :5.1819
+## Mean :31.469 Mean : 65.07 Mean :32.544 Mean :5.3029
+## 3rd Qu.:40.329 3rd Qu.: 76.28 3rd Qu.:52.350 3rd Qu.:7.4295
+## Max. :53.327 Max. :107.50 Max. :94.396 Max. :9.2898
+## NA's :7 NA's :34 NA's :174 NA's :9
+## oats_y oth_oil_y fibre_y oth_ind_y
+## Min. :0.5543 Min. :0.1428 Min. :0.350 Min. : 0.02671
+## 1st Qu.:2.3556 1st Qu.:1.6668 1st Qu.:1.523 1st Qu.: 0.98452
+## Median :3.6032 Median :2.0000 Median :2.750 Median : 1.88764
+## Mean :3.5905 Mean :2.1776 Mean :3.104 Mean : 2.98676
+## 3rd Qu.:4.7295 3rd Qu.:2.8162 3rd Qu.:4.838 3rd Qu.: 3.26371
+## Max. :7.2000 Max. :5.0000 Max. :8.333 Max. :13.36992
+## NA's :14 NA's :50 NA's :146 NA's :54
+## fodder_y berries_y brassic_y
+## Min. : 0.6603 Min. : 0.00396 Min. : 0.03086
+## 1st Qu.:12.5398 1st Qu.:18.60179 1st Qu.:29.19964
+## Median :26.1963 Median :25.99651 Median :37.54545
+## Mean :25.7794 Mean :26.03682 Mean :38.47796
+## 3rd Qu.:38.1261 3rd Qu.:34.90468 3rd Qu.:43.59471
+## Max. :51.0516 Max. :57.13000 Max. :77.33000
+## NA's :12 NA's :21 NA's :21
+## citrus_y frtrees_y grapes_y
+## Min. : 0.02187 Min. : 0.00316 Min. : 0.000
+## 1st Qu.: 43.38803 1st Qu.: 41.05565 1st Qu.: 1.878
+## Median : 73.80700 Median : 62.58810 Median : 4.266
+## Mean : 67.53417 Mean : 63.80520 Mean : 4.486
+## 3rd Qu.:101.62819 3rd Qu.: 88.15527 3rd Qu.: 6.531
+## Max. :122.22785 Max. :180.73000 Max. :13.714
+## NA's :198 NA's :20 NA's :79
+## greens_y nuts_y olives_y oth_veg_y
+## Min. : 0.0116 Min. : 0.0000 Min. :0.0000 Min. : 0.00974
+## 1st Qu.:23.1703 1st Qu.: 0.4243 1st Qu.:0.8311 1st Qu.: 9.32000
+## Median :37.2801 Median : 3.2225 Median :1.5341 Median :14.55378
+## Mean :34.3396 Mean : 4.8389 Mean :1.3702 Mean :16.73389
+## 3rd Qu.:43.8130 3rd Qu.: 8.3606 3rd Qu.:1.8099 3rd Qu.:18.99319
+## Max. :71.3000 Max. :22.8630 Max. :4.2988 Max. :41.34000
+## NA's :28 NA's :44 NA's :216 NA's :20
+## peas_y rootveg_y tropfr_y
+## Min. : 0.00246 Min. : 0.0421 Min. : 0.00243
+## 1st Qu.:12.93950 1st Qu.: 43.9722 1st Qu.:25.81930
+## Median :21.42656 Median : 71.1353 Median :37.45034
+## Mean :21.45191 Mean : 71.1527 Mean :36.78523
+## 3rd Qu.:28.22034 3rd Qu.: 93.5171 3rd Qu.:48.14715
+## Max. :44.57000 Max. :170.1700 Max. :88.52000
+## NA's :20 NA's :21 NA's :189
+## vfruits_y berries_f brassic_f
+## Min. : 0.1976 Min. :0.000000 Min. :0.000000
+## 1st Qu.: 117.0439 1st Qu.:0.000277 1st Qu.:0.000717
+## Median : 181.0226 Median :0.000537 Median :0.001163
+## Mean : 296.2257 Mean :0.001068 Mean :0.001651
+## 3rd Qu.: 307.1032 3rd Qu.:0.001378 3rd Qu.:0.002102
+## Max. :1194.7400 Max. :0.009374 Max. :0.011558
+## NA's :20 NA's :4 NA's :4
+## citrus_f frtrees_f grapes_f
+## Min. :0.000000 Min. :0.000000 Min. :0.000000
+## 1st Qu.:0.000000 1st Qu.:0.001741 1st Qu.:0.000000
+## Median :0.000000 Median :0.007025 Median :0.000322
+## Mean :0.002161 Mean :0.007964 Mean :0.014954
+## 3rd Qu.:0.001833 3rd Qu.:0.010316 3rd Qu.:0.017370
+## Max. :0.029824 Max. :0.092826 Max. :0.268339
+## NA's :4 NA's :4 NA's :4
+## greens_f nuts_f olives_f
+## Min. :0.000000 Min. :0.000000 Min. :0.000000
+## 1st Qu.:0.000241 1st Qu.:0.000000 1st Qu.:0.000000
+## Median :0.000839 Median :0.000212 Median :0.000000
+## Mean :0.001398 Mean :0.004343 Mean :0.015398
+## 3rd Qu.:0.001392 3rd Qu.:0.002597 3rd Qu.:0.000905
+## Max. :0.015696 Max. :0.036033 Max. :0.452390
+## NA's :4 NA's :4 NA's :4
+## oth_veg_f peas_f rootveg_f
+## Min. :0.000000 Min. :0.000000 Min. :0.000000
+## 1st Qu.:0.000530 1st Qu.:0.000390 1st Qu.:0.000697
+## Median :0.001639 Median :0.001316 Median :0.001438
+## Mean :0.002617 Mean :0.001804 Mean :0.002112
+## 3rd Qu.:0.003725 3rd Qu.:0.002598 3rd Qu.:0.002655
+## Max. :0.019446 Max. :0.021036 Max. :0.018225
+## NA's :4 NA's :4 NA's :4
+## tropfr_f vfruits_f bovine milk_cows
+## Min. :0.000000 Min. :0.000000 Min. :0.0000 Min. :0.00000
+## 1st Qu.:0.000000 1st Qu.:0.000118 1st Qu.:0.1913 1st Qu.:0.04591
+## Median :0.000000 Median :0.000881 Median :0.4288 Median :0.10738
+## Mean :0.001053 Mean :0.004773 Mean :0.5536 Mean :0.16021
+## 3rd Qu.:0.000394 3rd Qu.:0.006812 3rd Qu.:0.7943 3rd Qu.:0.19825
+## Max. :0.043473 Max. :0.041715 Max. :2.8302 Max. :1.04331
+## NA's :4 NA's :4 NA's :8 NA's :8
+## pigs sheep goats
+## Min. : 0.0000 Min. :0.00000 Min. :0.00000
+## 1st Qu.: 0.1446 1st Qu.:0.07257 1st Qu.:0.00660
+## Median : 0.2961 Median :0.27634 Median :0.02031
+## Mean : 0.8674 Mean :0.58262 Mean :0.11852
+## 3rd Qu.: 0.7611 3rd Qu.:0.90416 3rd Qu.:0.12719
+## Max. :17.2590 Max. :5.22537 Max. :2.33485
+## NA's :34 NA's :36 NA's :36dbase.shp@data[is.na(dbase.shp@data)] <- -99999
+summary(dbase.shp@data)## CNTR_CODE NUTS_ID NUTS_NAME
+## UK : 40 Length:320 Ãstra Mellansverige : 1
+## DE : 38 Class :character Ãvre Norrland : 1
+## FR : 27 Mode :character Ã
land : 1
+## TR : 26 Ãszak-Alföld : 1
+## IT : 21 Ãszak-Magyarország : 1
+## ES : 19 Ã\201rea Metropolitana de Lisboa: 1
+## (Other):149 (Other) :314
+## Shape_Length Shape_Area risk_pov
+## Min. : 15458 Min. :1.304e+07 Min. :-99999.00
+## 1st Qu.: 545979 1st Qu.:5.074e+09 1st Qu.: 18.59
+## Median : 836914 Median :1.131e+10 Median : 23.41
+## Mean : 1114048 Mean :1.799e+10 Mean : -599.20
+## 3rd Qu.: 1200811 3rd Qu.:2.403e+10 3rd Qu.: 29.68
+## Max. :18760323 Max. :2.271e+11 Max. : 54.15
+##
+## train35bas train35ful train_bas
+## Min. :-99999.00 Min. :-99999.00 Min. :-99999.00
+## 1st Qu.: 0.06 1st Qu.: 0.03 1st Qu.: 0.07
+## Median : 0.17 Median : 0.21 Median : 0.16
+## Mean :-16249.62 Mean :-16249.61 Mean :-15624.62
+## 3rd Qu.: 0.29 3rd Qu.: 0.36 3rd Qu.: 0.33
+## Max. : 0.88 Max. : 0.86 Max. : 0.95
+##
+## train_ful nitr_high nitr_mod
+## Min. :-99999.00 Min. :-99999.00 Min. :-99999.00
+## 1st Qu.: 0.02 1st Qu.: 63.59 1st Qu.: 2.39
+## Median : 0.09 Median : 66.58 Median : 11.50
+## Mean :-15624.71 Mean :-13684.89 Mean :-13737.98
+## 3rd Qu.: 0.23 3rd Qu.: 87.59 3rd Qu.: 18.42
+## Max. : 0.50 Max. : 100.00 Max. : 60.00
+##
+## nitr_poor irrigated forest
+## Min. :-99999.00 Min. :-99999.00 Min. :0.00000
+## 1st Qu.: 0.45 1st Qu.: 0.22 1st Qu.:0.08957
+## Median : 8.37 Median : 0.86 Median :0.24904
+## Mean :-13740.46 Mean : -8744.66 Mean :0.25141
+## 3rd Qu.: 15.20 3rd Qu.: 5.79 3rd Qu.:0.37365
+## Max. : 68.37 Max. : 74.55 Max. :0.75860
+##
+## artific soil_loss com_birds
+## Min. :0.00000 Min. :-99999.00 Min. :-99999.00
+## 1st Qu.:0.02056 1st Qu.: 0.39 1st Qu.:-99999.00
+## Median :0.04020 Median : 1.32 Median : 54.92
+## Mean :0.09023 Mean :-13747.66 Mean :-49339.22
+## 3rd Qu.:0.08193 3rd Qu.: 2.48 3rd Qu.: 69.50
+## Max. :1.00000 Max. : 17.61 Max. : 97.22
+##
+## farm_birds org_farm energy_rt
+## Min. :-99999.00 Min. :-99999.00 Min. :-99999.00
+## 1st Qu.:-99999.00 1st Qu.: 0.75 1st Qu.: 0.00
+## Median : 81.84 Median : 2.41 Median : 0.05
+## Mean :-29316.86 Mean : -8746.21 Mean :-13749.73
+## 3rd Qu.: 84.12 3rd Qu.: 5.04 3rd Qu.: 0.10
+## Max. : 116.60 Max. : 27.49 Max. : 1.75
+##
+## renew_pct renew_prod gross_N
+## Min. :-99999.00 Min. :-99999.00 Min. :-99999.00
+## 1st Qu.:-99999.00 1st Qu.: 4.57 1st Qu.: 34.71
+## Median : 3.39 Median : 7.18 Median : 57.83
+## Mean :-25616.39 Mean :-14051.68 Mean : -9313.69
+## 3rd Qu.: 14.33 3rd Qu.: 11.85 3rd Qu.: 80.29
+## Max. : 41.01 Max. : 37.78 Max. : 190.17
+##
+## gross_P conv_till cons_till
+## Min. :-99999.00 Min. :-99999.00 Min. :-99999.00
+## 1st Qu.: -1.83 1st Qu.: 0.35 1st Qu.: 0.02
+## Median : 0.57 Median : 0.55 Median : 0.08
+## Mean : -9373.15 Mean :-16561.83 Mean :-16562.18
+## 3rd Qu.: 4.71 3rd Qu.: 0.73 3rd Qu.: 0.25
+## Max. : 31.00 Max. : 1.00 Max. : 0.65
+##
+## zero_till nfert arable
+## Min. :-99999.00 Min. :-99999.00 Min. :-99999.00
+## 1st Qu.: 0.00 1st Qu.: 6.34 1st Qu.: 26.90
+## Median : 0.01 Median : 9.57 Median : 58.37
+## Mean :-16562.31 Mean : -3426.87 Mean :-13700.08
+## 3rd Qu.: 0.03 3rd Qu.: 14.07 3rd Qu.: 74.18
+## Max. : 0.19 Max. : 29.46 Max. : 99.28
+##
+## grassland permanent soil_prod
+## Min. :-99999.00 Min. :-99999.00 Min. :-99999
+## 1st Qu.: 11.45 1st Qu.: 0.12 1st Qu.: 5
+## Median : 27.66 Median : 0.81 Median : 6
+## Mean :-13719.04 Mean :-13744.93 Mean :-15932
+## 3rd Qu.: 43.29 3rd Qu.: 3.94 3rd Qu.: 7
+## Max. : 98.84 Max. : 64.67 Max. : 8
+##
+## irrig_rate afi_awu gva_awu labour_use
+## Min. :-99999.00 Min. :-99999 Min. :-99999 Min. :-99999.00
+## 1st Qu.: 1.18 1st Qu.: 8079 1st Qu.: 8085 1st Qu.: 0.01
+## Median : 6.26 Median : 19953 Median : 22316 Median : 0.02
+## Mean : -6728.31 Mean : 13381 Mean : 15137 Mean :-13749.83
+## 3rd Qu.: 72.59 3rd Qu.: 34388 3rd Qu.: 36813 3rd Qu.: 0.04
+## Max. : 4156.72 Max. :107266 Max. :122953 Max. : 0.23
+##
+## pest_rate gdp_cap pps_cap emp_rate
+## Min. :-99999.00 Min. :-99999 Min. :-99999 Min. :-99999.00
+## 1st Qu.: 1.21 1st Qu.: 11100 1st Qu.: 16075 1st Qu.: 56.43
+## Median : 1.59 Median : 24500 Median : 23300 Median : 65.76
+## Mean :-11560.25 Mean : 9393 Mean : 9129 Mean :-13692.23
+## 3rd Qu.: 2.74 3rd Qu.: 32225 3rd Qu.: 29625 3rd Qu.: 73.05
+## Max. : 13.14 Max. :191400 Max. :163500 Max. : 81.42
+##
+## tot_unemp yth_unemp rur_gdp rur_pps
+## Min. :-99999.00 Min. :-99999.00 Min. :-99999 Min. :-99999
+## 1st Qu.: 3.70 1st Qu.: 8.50 1st Qu.:-99999 1st Qu.:-99999
+## Median : 5.80 Median : 14.95 Median :-99999 Median :-99999
+## Mean :-13742.30 Mean :-13731.41 Mean :-41088 Mean :-40953
+## 3rd Qu.: 9.53 3rd Qu.: 26.18 3rd Qu.: 22148 3rd Qu.: 20730
+## Max. : 31.30 Max. : 69.10 Max. : 46295 Max. : 42716
+##
+## int_gdp int_pps urb_gdp urb_pps
+## Min. :-99999 Min. :-99999 Min. :-99999 Min. :-99999
+## 1st Qu.:-99999 1st Qu.:-99999 1st Qu.:-99999 1st Qu.:-99999
+## Median : 12526 Median : 17513 Median :-99999 Median :-99999
+## Mean :-19271 Mean :-19268 Mean :-43391 Mean :-43661
+## 3rd Qu.: 28298 3rd Qu.: 26526 3rd Qu.: 29111 3rd Qu.: 28289
+## Max. : 88303 Max. : 73498 Max. :191423 Max. :163515
+##
+## C_factor emi_co2eq emi_nh3 emi_pm10
+## Min. :-99999.00 Min. : -99999 Min. :-99999 Min. :-99999.0
+## 1st Qu.: 0.18 1st Qu.: 715768 1st Qu.: 8216 1st Qu.: 424.2
+## Median : 0.21 Median :1113299 Median : 13149 Median : 994.7
+## Mean :-16874.64 Mean :1456282 Mean : 15525 Mean : 636.4
+## 3rd Qu.: 0.25 3rd Qu.:1800482 3rd Qu.: 19949 3rd Qu.: 1756.6
+## Max. : 0.44 Max. :7270058 Max. : 88272 Max. : 7417.5
+##
+## emi_pm25 soc bio_threat
+## Min. :-99999.0 Min. :-99999.00 Min. :-99999.00
+## 1st Qu.: 223.8 1st Qu.: 52.99 1st Qu.: 0.23
+## Median : 602.1 Median : 73.82 Median : 0.27
+## Mean : 135.5 Mean :-12418.53 Mean :-13437.11
+## 3rd Qu.: 1090.5 3rd Qu.: 104.25 3rd Qu.: 0.31
+## Max. : 4020.6 Max. : 374.18 Max. : 0.60
+##
+## nat2000_ag nat2000_pr cal_frac
+## Min. :-99999.00 Min. :-99999.00 Min. :-99999.00
+## 1st Qu.: 0.01 1st Qu.: 0.04 1st Qu.: 0.39
+## Median : 0.04 Median : 0.12 Median : 0.49
+## Mean : -624.93 Mean : -624.86 Mean : -2499.46
+## 3rd Qu.: 0.10 3rd Qu.: 0.21 3rd Qu.: 0.63
+## Max. : 0.51 Max. : 0.50 Max. : 0.96
+##
+## precip deg_days crop_suit rye_f
+## Min. : 261.3 Min. : 242 Min. :-99999.00 Min. :-99999.00
+## 1st Qu.: 610.6 1st Qu.:1536 1st Qu.: 3.13 1st Qu.: 0.00
+## Median : 745.8 Median :1711 Median : 4.25 Median : 0.00
+## Mean : 800.3 Mean :2016 Mean : -620.87 Mean : -312.49
+## 3rd Qu.: 882.9 3rd Qu.:2246 3rd Qu.: 5.20 3rd Qu.: 0.01
+## Max. :2707.9 Max. :7765 Max. : 6.00 Max. : 0.13
+##
+## barley_f maize_f tritic_f
+## Min. :-99999.00 Min. :-99999.00 Min. :-99999.00
+## 1st Qu.: 0.02 1st Qu.: 0.00 1st Qu.: 0.00
+## Median : 0.05 Median : 0.01 Median : 0.00
+## Mean : -312.44 Mean : -312.47 Mean : -312.49
+## 3rd Qu.: 0.08 3rd Qu.: 0.03 3rd Qu.: 0.01
+## Max. : 0.23 Max. : 0.32 Max. : 0.12
+##
+## sorghum_f oth_cer_f rice_f
+## Min. :-99999.00 Min. :-99999.00 Min. :-99999.00
+## 1st Qu.: 0.00 1st Qu.: 0.00 1st Qu.: 0.00
+## Median : 0.00 Median : 0.00 Median : 0.00
+## Mean : -312.50 Mean :-20312.30 Mean : -312.50
+## 3rd Qu.: 0.00 3rd Qu.: 0.00 3rd Qu.: 0.00
+## Max. : 0.02 Max. : 0.02 Max. : 0.11
+##
+## pasture_f rape_f sunflow_f
+## Min. :-1.0e+05 Min. :-99999.00 Min. :-99999.00
+## 1st Qu.: 1.0e-02 1st Qu.: 0.00 1st Qu.: 0.00
+## Median : 2.0e-02 Median : 0.01 Median : 0.00
+## Mean :-2.5e+03 Mean : -312.47 Mean : -312.49
+## 3rd Qu.: 8.0e-02 3rd Qu.: 0.04 3rd Qu.: 0.00
+## Max. : 4.1e-01 Max. : 0.15 Max. : 0.22
+##
+## pulses_f potato_f sugbeet_f
+## Min. :-99999.00 Min. :-99999.00 Min. :-99999.00
+## 1st Qu.: 0.00 1st Qu.: 0.00 1st Qu.: 0.00
+## Median : 0.00 Median : 0.01 Median : 0.00
+## Mean : -312.49 Mean : -312.48 Mean : -312.49
+## 3rd Qu.: 0.01 3rd Qu.: 0.01 3rd Qu.: 0.01
+## Max. : 0.06 Max. : 0.19 Max. : 0.11
+##
+## oth_rt_f wheat_f oats_f
+## Min. :-99999.00 Min. :-99999.00 Min. :-99999.00
+## 1st Qu.: 0.00 1st Qu.: 0.01 1st Qu.: 0.00
+## Median : 0.00 Median : 0.10 Median : 0.00
+## Mean :-10937.39 Mean : -312.39 Mean : -312.49
+## 3rd Qu.: 0.00 3rd Qu.: 0.17 3rd Qu.: 0.01
+## Max. : 0.01 Max. : 0.39 Max. : 0.19
+##
+## oth_oil_f fibre_f oth_ind_f
+## Min. :-99999.00 Min. :-99999.00 Min. :-99999.00
+## 1st Qu.: 0.00 1st Qu.: 0.00 1st Qu.: 0.00
+## Median : 0.00 Median : 0.00 Median : 0.00
+## Mean : -312.49 Mean : -312.49 Mean : -312.50
+## 3rd Qu.: 0.00 3rd Qu.: 0.00 3rd Qu.: 0.00
+## Max. : 0.19 Max. : 0.15 Max. : 0.04
+##
+## fodder_f rye_y barley_y
+## Min. :-99999.00 Min. :-99999.00 Min. :-99999.00
+## 1st Qu.: 0.01 1st Qu.: 2.41 1st Qu.: 2.89
+## Median : 0.03 Median : 3.33 Median : 4.59
+## Mean : -312.45 Mean : -6246.44 Mean : -4370.53
+## 3rd Qu.: 0.07 3rd Qu.: 4.91 3rd Qu.: 6.12
+## Max. : 0.25 Max. : 7.14 Max. : 8.47
+##
+## maize_y tritic_y sorghum_y
+## Min. :-99999.00 Min. :-99999.00 Min. :-99999.00
+## 1st Qu.: 5.95 1st Qu.: 2.40 1st Qu.:-99999.00
+## Median : 7.35 Median : 3.82 Median :-99999.00
+## Mean : -8742.68 Mean : -7183.73 Mean :-54684.98
+## 3rd Qu.: 9.83 3rd Qu.: 5.05 3rd Qu.: 4.00
+## Max. : 12.98 Max. : 7.36 Max. : 9.04
+##
+## oth_cer_y rice_y pasture_y
+## Min. :-99999.00 Min. :-99999.00 Min. :-99999.00
+## 1st Qu.:-99999.00 1st Qu.:-99999.00 1st Qu.:-99999.00
+## Median : 1.00 Median :-99999.00 Median : 4.32
+## Mean :-46560.74 Mean :-55934.58 Mean :-33743.24
+## 3rd Qu.: 2.17 3rd Qu.: 5.05 3rd Qu.: 8.46
+## Max. : 10.75 Max. : 10.00 Max. : 49.51
+##
+## rape_y sunflow_y pulses_y
+## Min. :-99999.00 Min. :-99999.00 Min. :-99999.00
+## 1st Qu.: 2.23 1st Qu.:-99999.00 1st Qu.: 1.41
+## Median : 3.14 Median : 1.88 Median : 2.12
+## Mean : -6872.16 Mean :-32810.67 Mean : -7810.36
+## 3rd Qu.: 3.53 3rd Qu.: 2.39 3rd Qu.: 2.75
+## Max. : 5.00 Max. : 4.39 Max. : 5.00
+##
+## potato_y sugbeet_y oth_rt_y
+## Min. :-99999.00 Min. :-99999.00 Min. :-99999.00
+## 1st Qu.: 22.96 1st Qu.: 50.47 1st Qu.:-99999.00
+## Median : 30.52 Median : 64.07 Median :-99999.00
+## Mean : -2156.70 Mean :-10566.73 Mean :-54359.61
+## 3rd Qu.: 40.33 3rd Qu.: 74.69 3rd Qu.: 22.96
+## Max. : 53.33 Max. : 107.50 Max. : 94.40
+##
+## wheat_y oats_y oth_oil_y
+## Min. :-99999.00 Min. :-99999.00 Min. :-99999.00
+## 1st Qu.: 3.21 1st Qu.: 2.21 1st Qu.: 1.05
+## Median : 5.15 Median : 3.37 Median : 1.92
+## Mean : -2807.32 Mean : -4371.52 Mean :-15623.01
+## 3rd Qu.: 7.39 3rd Qu.: 4.72 3rd Qu.: 2.71
+## Max. : 9.29 Max. : 7.20 Max. : 5.00
+##
+## fibre_y oth_ind_y fodder_y
+## Min. :-99999.00 Min. :-99999.00 Min. :-99999.00
+## 1st Qu.:-99999.00 1st Qu.: 0.72 1st Qu.: 12.34
+## Median : 1.00 Median : 1.46 Median : 24.85
+## Mean :-45622.86 Mean :-16872.35 Mean : -3725.15
+## 3rd Qu.: 3.08 3rd Qu.: 3.14 3rd Qu.: 38.13
+## Max. : 8.33 Max. : 13.37 Max. : 51.05
+##
+## berries_y brassic_y citrus_y
+## Min. :-99999.00 Min. :-99999.00 Min. :-99999.0
+## 1st Qu.: 16.55 1st Qu.: 27.35 1st Qu.:-99999.0
+## Median : 24.95 Median : 36.47 Median :-99999.0
+## Mean : -6538.11 Mean : -6526.48 Mean :-61848.6
+## 3rd Qu.: 34.52 3rd Qu.: 41.87 3rd Qu.: 52.3
+## Max. : 57.13 Max. : 77.33 Max. : 122.2
+##
+## frtrees_y grapes_y greens_y
+## Min. :-99999.00 Min. :-99999.00 Min. :-99999.00
+## 1st Qu.: 38.96 1st Qu.: 0.00 1st Qu.: 18.83
+## Median : 58.94 Median : 2.27 Median : 35.35
+## Mean : -6190.12 Mean :-24683.87 Mean : -8718.58
+## 3rd Qu.: 87.48 3rd Qu.: 6.17 3rd Qu.: 43.23
+## Max. : 180.73 Max. : 13.71 Max. : 71.30
+##
+## nuts_y olives_y oth_veg_y
+## Min. :-99999.00 Min. :-99999.00 Min. :-99999.00
+## 1st Qu.: 0.00 1st Qu.:-99999.00 1st Qu.: 9.18
+## Median : 2.91 Median :-99999.00 Median : 14.06
+## Mean :-13745.69 Mean :-67498.88 Mean : -6234.25
+## 3rd Qu.: 7.72 3rd Qu.: 0.73 3rd Qu.: 18.92
+## Max. : 22.86 Max. : 4.30 Max. : 41.34
+##
+## peas_y rootveg_y tropfr_y
+## Min. :-99999.00 Min. :-99999.00 Min. :-99999.00
+## 1st Qu.: 11.77 1st Qu.: 39.14 1st Qu.:-99999.00
+## Median : 20.68 Median : 68.36 Median :-99999.00
+## Mean : -6229.83 Mean : -6495.95 Mean :-59046.85
+## 3rd Qu.: 27.97 3rd Qu.: 86.35 3rd Qu.: 31.82
+## Max. : 44.57 Max. : 170.17 Max. : 88.52
+##
+## vfruits_y berries_f brassic_f
+## Min. :-99999.00 Min. :-99999.00 Min. :-99999.00
+## 1st Qu.: 81.08 1st Qu.: 0.00 1st Qu.: 0.00
+## Median : 177.67 Median : 0.00 Median : 0.00
+## Mean : -5972.23 Mean : -1249.99 Mean : -1249.99
+## 3rd Qu.: 301.98 3rd Qu.: 0.00 3rd Qu.: 0.00
+## Max. : 1194.74 Max. : 0.01 Max. : 0.01
+##
+## citrus_f frtrees_f grapes_f
+## Min. :-99999.00 Min. :-99999.00 Min. :-99999.00
+## 1st Qu.: 0.00 1st Qu.: 0.00 1st Qu.: 0.00
+## Median : 0.00 Median : 0.01 Median : 0.00
+## Mean : -1249.99 Mean : -1249.98 Mean : -1249.97
+## 3rd Qu.: 0.00 3rd Qu.: 0.01 3rd Qu.: 0.02
+## Max. : 0.03 Max. : 0.09 Max. : 0.27
+##
+## greens_f nuts_f olives_f
+## Min. :-99999.00 Min. :-99999.00 Min. :-99999.00
+## 1st Qu.: 0.00 1st Qu.: 0.00 1st Qu.: 0.00
+## Median : 0.00 Median : 0.00 Median : 0.00
+## Mean : -1249.99 Mean : -1249.98 Mean : -1249.97
+## 3rd Qu.: 0.00 3rd Qu.: 0.00 3rd Qu.: 0.00
+## Max. : 0.02 Max. : 0.04 Max. : 0.45
+##
+## oth_veg_f peas_f rootveg_f
+## Min. :-99999.00 Min. :-99999.00 Min. :-99999.00
+## 1st Qu.: 0.00 1st Qu.: 0.00 1st Qu.: 0.00
+## Median : 0.00 Median : 0.00 Median : 0.00
+## Mean : -1249.98 Mean : -1249.99 Mean : -1249.99
+## 3rd Qu.: 0.00 3rd Qu.: 0.00 3rd Qu.: 0.00
+## Max. : 0.02 Max. : 0.02 Max. : 0.02
+##
+## tropfr_f vfruits_f bovine
+## Min. :-99999.00 Min. :-99999.00 Min. :-99999.00
+## 1st Qu.: 0.00 1st Qu.: 0.00 1st Qu.: 0.18
+## Median : 0.00 Median : 0.00 Median : 0.43
+## Mean : -1249.99 Mean : -1249.98 Mean : -2499.44
+## 3rd Qu.: 0.00 3rd Qu.: 0.01 3rd Qu.: 0.78
+## Max. : 0.04 Max. : 0.04 Max. : 2.83
+##
+## milk_cows pigs sheep
+## Min. :-99999.00 Min. :-99999.00 Min. :-99999.00
+## 1st Qu.: 0.04 1st Qu.: 0.11 1st Qu.: 0.05
+## Median : 0.10 Median : 0.23 Median : 0.17
+## Mean : -2499.82 Mean :-10624.12 Mean :-11249.37
+## 3rd Qu.: 0.20 3rd Qu.: 0.67 3rd Qu.: 0.76
+## Max. : 1.04 Max. : 17.26 Max. : 5.23
+##
+## goats
+## Min. :-99999.00
+## 1st Qu.: 0.00
+## Median : 0.01
+## Mean :-11249.78
+## 3rd Qu.: 0.10
+## Max. : 2.33
+## save.image("C:/Users/mu5106sc/Dropbox/STAGS/D1_Database/Database_20190130.RData")
+write.csv(dbase.final, "C:/Users/mu5106sc/Dropbox/STAGS/D1_Database/Database_20190130.csv")
+
+names(dbase.shp)## [1] "CNTR_CODE" "NUTS_ID" "NUTS_NAME" "Shape_Length"
+## [5] "Shape_Area" "risk_pov" "train35bas" "train35ful"
+## [9] "train_bas" "train_ful" "nitr_high" "nitr_mod"
+## [13] "nitr_poor" "irrigated" "forest" "artific"
+## [17] "soil_loss" "com_birds" "farm_birds" "org_farm"
+## [21] "energy_rt" "renew_pct" "renew_prod" "gross_N"
+## [25] "gross_P" "conv_till" "cons_till" "zero_till"
+## [29] "nfert" "arable" "grassland" "permanent"
+## [33] "soil_prod" "irrig_rate" "afi_awu" "gva_awu"
+## [37] "labour_use" "pest_rate" "gdp_cap" "pps_cap"
+## [41] "emp_rate" "tot_unemp" "yth_unemp" "rur_gdp"
+## [45] "rur_pps" "int_gdp" "int_pps" "urb_gdp"
+## [49] "urb_pps" "C_factor" "emi_co2eq" "emi_nh3"
+## [53] "emi_pm10" "emi_pm25" "soc" "bio_threat"
+## [57] "nat2000_ag" "nat2000_pr" "cal_frac" "precip"
+## [61] "deg_days" "crop_suit" "rye_f" "barley_f"
+## [65] "maize_f" "tritic_f" "sorghum_f" "oth_cer_f"
+## [69] "rice_f" "pasture_f" "rape_f" "sunflow_f"
+## [73] "pulses_f" "potato_f" "sugbeet_f" "oth_rt_f"
+## [77] "wheat_f" "oats_f" "oth_oil_f" "fibre_f"
+## [81] "oth_ind_f" "fodder_f" "rye_y" "barley_y"
+## [85] "maize_y" "tritic_y" "sorghum_y" "oth_cer_y"
+## [89] "rice_y" "pasture_y" "rape_y" "sunflow_y"
+## [93] "pulses_y" "potato_y" "sugbeet_y" "oth_rt_y"
+## [97] "wheat_y" "oats_y" "oth_oil_y" "fibre_y"
+## [101] "oth_ind_y" "fodder_y" "berries_y" "brassic_y"
+## [105] "citrus_y" "frtrees_y" "grapes_y" "greens_y"
+## [109] "nuts_y" "olives_y" "oth_veg_y" "peas_y"
+## [113] "rootveg_y" "tropfr_y" "vfruits_y" "berries_f"
+## [117] "brassic_f" "citrus_f" "frtrees_f" "grapes_f"
+## [121] "greens_f" "nuts_f" "olives_f" "oth_veg_f"
+## [125] "peas_f" "rootveg_f" "tropfr_f" "vfruits_f"
+## [129] "bovine" "milk_cows" "pigs" "sheep"
+## [133] "goats"writeOGR(dbase.shp, dsn="C:/Users/mu5106sc/Dropbox/STAGS/D1_Database/Shapefiles/D1_database_20190130.shp", layer="D1_database_20190130", driver="ESRI Shapefile")## Warning in writeOGR(dbase.shp, dsn = "C:/Users/mu5106sc/Dropbox/STAGS/
+## D1_Database/Shapefiles/D1_database_20190130.shp", : Field names abbreviated
+## for ESRI Shapefile driver