-
Notifications
You must be signed in to change notification settings - Fork 0
/
update_data_union_budget_2022.R
207 lines (177 loc) · 7.37 KB
/
update_data_union_budget_2022.R
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
library(readr)
library(glue)
library(dplyr)
library(stringr)
master_file_dir <- "datasets/union-budget/master-file/"
data_dir <- "datasets/union-budget/"
source("scripts/update_indicators.R")
source("scripts/source-files.R")
all_datasets <- dir(data_dir)
scheme_datasets <- all_datasets[grepl("scheme-",all_datasets,ignore.case = TRUE)]
scheme_datasets <- scheme_datasets[!grepl("category",scheme_datasets,ignore.case = TRUE)]
# Include scheme categories that are part of the master sheet -------------
include_categories <-
c(
"scheme-category-grants-in-aid-state-law",
"scheme-category-grants-in-aid-state-police",
"scheme-category-grants-in-aid-ut-law",
"scheme-category-grants-in-aid-ut-police"
)
scheme_datasets <- c(scheme_datasets, include_categories)
# Create a master dataset of all metadata files ---------------------------
meta_master <- c()
for (i in 1:length(scheme_datasets)) {
scheme_metadata_path <-
glue::glue("{data_dir}{scheme_datasets[[i]]}/metadata.csv")
meta_file <-
readr::read_csv(scheme_metadata_path,
col_types = cols(),
col_names = FALSE)
schemeName <- meta_file$X2[meta_file$X1 == "Name of the Scheme"]
schemeID <- meta_file$X2[meta_file$X1 == "schemeID"]
indicatorName <-
meta_file$X1[grepl(x = meta_file$X1,
pattern = "Indicator",
ignore.case = TRUE)]
indicatorName <-
indicatorName[grepl(pattern = "Name", x = indicatorName)]
indicatorName <- meta_file$X2[meta_file$X1 %in% indicatorName]
indicatorName <-
indicatorName[!is.na(indicatorName)] %>% stringr::str_squish()
indicatorName <- indicatorName[nchar(indicatorName) > 0]
totalIndicators <- length(indicatorName)
# Check if updated datasheet exists
datasets_present <-
dir(glue::glue("{data_dir}{scheme_datasets[[i]]}/"))
if (TRUE %in% grepl(pattern = "u_datasheet",x = datasets_present,ignore.case = TRUE)) {
dataset_path <-
glue::glue("{data_dir}{scheme_datasets[[i]]}/u_datasheet.csv")
} else {
dataset_path <-
glue::glue("{data_dir}{scheme_datasets[[i]]}/datasheet.csv")
}
meta_df <-
data.frame(
"schemeID" = schemeID,
"schemeName" = schemeName,
"totalIndicators" = totalIndicators,
"datasetPath" = dataset_path
)
meta_master <- dplyr::bind_rows(meta_master, meta_df)
}
# Create a combined dataset of all master files ---------------------------
category_list <- c("law","police","wcd","home")
master_combined <- c()
for(i in 1:length(category_list)){
master_file_path <- glue::glue("{master_file_dir}{category_list[[i]]}.csv")
category_file <- readr::read_csv(master_file_path,col_types = cols())
category_file <- category_file %>%
mutate_all(funs(stringr::str_replace(., "\\.\\.", NA_character_)))
valid_cols <-
c(
"Ministry",
"Head",
"Scheme",
"schemeID",
"Budget 2016-2017 _Revenue",
"Budget 2016-2017 _Capital",
"Budget 2016-2017 _Total",
"Revised 2016-2017 _Revenue",
"Revised 2016-2017 _Capital",
"Revised 2016-2017 _Total",
"Actual 2016-2017 _Revenue",
"Actual 2016-2017 _Capital",
"Actual 2016-2017 _Total",
"Budget 2017-2018 _Revenue",
"Budget 2017-2018 _Capital",
"Budget 2017-2018 _Total",
"Revised 2017-2018 _Revenue",
"Revised 2017-2018 _Capital",
"Revised 2017-2018 _Total",
"Actual 2017-2018 _Revenue",
"Actual 2017-2018 _Capital",
"Actual 2017-2018 _Total",
"Budget 2018-2019 _Revenue",
"Budget 2018-2019 _Capital",
"Budget 2018-2019 _Total",
"Revised 2018-2019 _Revenue",
"Revised 2018-2019 _Capital",
"Revised 2018-2019 _Total",
"Actual 2018-2019 _Revenue",
"Actual 2018-2019 _Capital",
"Actual 2018-2019 _Total",
"Budget 2019-2020 _Revenue",
"Budget 2019-2020 _Capital",
"Budget 2019-2020 _Total",
"Revised 2019-2020 _Revenue",
"Revised 2019-2020 _Capital",
"Revised 2019-2020 _Total",
"Actual 2019-2020 _Revenue",
"Actual 2019-2020 _Capital",
"Actual 2019-2020 _Total",
"Budget 2020-2021 _Revenue",
"Budget 2020-2021 _Capital",
"Budget 2020-2021 _Total",
"Revised 2020-2021 _Revenue",
"Revised 2020-2021 _Capital",
"Revised 2020-2021 _Total",
"Actual 2020-2021 _Revenue",
"Actual 2020-2021 _Capital",
"Actual 2020-2021 _Total",
"Budget 2021-2022 _Revenue",
"Budget 2021-2022 _Capital",
"Budget 2021-2022 _Total",
"Revised 2021-2022 _Revenue",
"Revised 2021-2022 _Capital",
"Revised 2021-2022 _Total",
"Budget 2022-2023 _Revenue",
"Budget 2022-2023 _Capital",
"Budget 2022-2023 _Total"
)
category_file <- category_file[,valid_cols]
master_combined <- dplyr::bind_rows(master_combined, category_file)
}
# schemeID <- "W12"
update_data <- function(schemeID){
print(glue::glue("Processing Scheme -- {schemeID} \n "))
scheme_file_path <- meta_master$datasetPath[meta_master$schemeID==schemeID]
scheme_file <- readr::read_csv(scheme_file_path, col_types = cols())
# Only update those files where data for 2022-23 has not been udpates
if(!"2022-2023" %in% scheme_file$fiscalYear){
scheme_file$value <- as.character(scheme_file$value)
indicators <- unique(scheme_file$indicators)
budgetFor <- meta_master$schemeName[meta_master$schemeID==schemeID]
type <- jh_links$Type[jh_links$schemeID==schemeID]
indicator_master <- c()
for(i in 1:length(indicators)){
indicator_name <- indicators[i]
indicator_df <- switch (indicator_name,
"Budget Estimates" = update_budget_estimates(schemeID),
"Revised Estimates" = update_revised_estimate(schemeID),
"Actual Expenditure" = update_actual_expenditure(schemeID),
"Actual Expenditure as a % of Ministry" = update_actual_expenditure_as_percent(schemeID),
"Actual Expenditure as a % of Department" = update_actual_expenditure_as_percent(schemeID),
"Fund Utilisation" = update_fund_utilisation_percent(schemeID)
)
indicator_master <- dplyr::bind_rows(indicator_master,indicator_df)
}
indicator_master$budgetFor <- budgetFor
indicator_master$type <- type
scheme_file_updated <- dplyr::bind_rows(scheme_file, indicator_master)
} else {
scheme_file_updated <- scheme_file
scheme_file_updated$value <- as.character(scheme_file_updated$value)
}
updated_file_path <- stringr::str_split_fixed(scheme_file_path,pattern = "/",n = 4)
dataset_title <- updated_file_path[[3]]
updated_file_path <- glue::glue("{updated_file_path[[1]]}/{updated_file_path[[2]]}/data_2022_23/update-100222/{dataset_title}.csv")
readr::write_csv(x = scheme_file_updated,file = updated_file_path)
jh_links$file_title[jh_links$schemeID==schemeID] <<- glue::glue("{dataset_title}.csv")
print(glue("{jh_links$file_title[jh_links$schemeID==schemeID]} \n"))
scheme_file_updated$schemeID <- schemeID
return(scheme_file_updated)
}
# Create updated files and write to disk ----------------------------------
updated_datasets <- lapply(meta_master$schemeID, update_data) %>% dplyr::bind_rows()
readr::write_csv(updated_datasets, "datasets/union-budget/data_2022_23/updated_datasets.csv")
readr::write_csv(jh_links,"datasets/union-budget/master-file/jh-links-file-title.csv")