-
Notifications
You must be signed in to change notification settings - Fork 0
/
.Rhistory
512 lines (512 loc) · 18.3 KB
/
.Rhistory
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
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
# histogram of No. or Reg Props
ggplot(data = df_foi,
mapping = aes(x = NumberOfProperties)) +
geom_histogram() +
ggtitle("Figure 2: Number of registered properties per postcode - Edinburgh") +
theme(plot.title = element_text(size = 14, face = "plain")) +
xlab("Number of Registered Properties in Postcode") +
ylab("Number of Postcodes")
# open postcode directory - gives some errors which we ignore for now
# NB that to fit onto GitHub, have had to cut down to EH pcodes only but left
# code unchanged so assumes it is whole of Scotland
df_pcode <- read_csv(
"data/Scottish_Postcode_Directory_2017_2 (EH).csv",
col_types = cols(
pc7 = col_character(),
pc8 = col_character(),
Grid_Reference_Easting = col_double(),
Grid_Reference_Northing = col_double(),
Latitude = col_double(),
Longitude = col_double(),
DataZone2011 = col_character(),
HHC2011 = col_double(),
Pop2011 = col_double(),
HHC2001 = col_double(),
Pop2001 = col_double()
)
)
# cut df_pcodes to "EH"" and only the vars we need to attach to foi data
df_pcode2 <- subset(df_pcode, str_sub(pc7, 1, 2) == "EH",
select = c(pc7, pc8, DataZone2011, LAU_Level1_2011
)
)
# add data from df_pcode2 to df_foi
df_foi <- df_foi %>%
left_join(df_pcode2, by = "pc8")
# check how many cases have missing values - for pc7 it is 18
sum(is.na(df_foi$pc7))
# check how many properties this affects - 27
sum(df_foi$NumberOfProperties[is.na(df_foi$DataZone2011)])
# check number of rows and valid cases in all cols
# NB there is some drop off in HHC and Pop figs, esp. for 2001
nrow(df_foi)
colSums(!is.na(df_foi))
# aggregate foi data to DZ level, summing number of registered props
df_foi_dz <- df_foi %>%
group_by(DataZone2011) %>%
summarise(
NumberOfProperties = sum(NumberOfProperties, na.rm = TRUE)
)
nrow(df_foi_dz)
# number of properties with missing DZ
sum(df_foi_dz$NumberOfProperties[
is.na(df_foi_dz$DataZone2011)
])
# second cut of df_pcode to those in Edinburgh in order to make list of DZs in city
df_pcode3 <- subset(df_pcode, LAU_Level1_2011 == "S30000008",
select = c(DataZone2011
)
)
# collapse so it is just a list of DZs in Edinburgh
df_dz_Edin <- df_pcode3 %>%
group_by(DataZone2011) %>%
summarise()
# also extract as list
dz_Edin <- (df_dz_Edin$DataZone2011)
# Open census data file with tenure composition for DZs in 2011
df_census <- as_tibble(read_csv("data/tenure DZ2011.csv"))
# make correct PRS and PRSPct figures
df_census <- mutate(df_census,
PRS = PrtRent_2011,
PRSPct = PrtRent_2011/All_HH_2011)
# reduce to DZs in Edinburgh using the list - dz_Edin
df_census <- df_census[df_census$DataZone %in% dz_Edin,]
# rename 'Datazone' as 'Datazone2011' for matching
colnames(df_census)[1] <- "DataZone2011"
# merge census tenure data on to the Edinburgh Datazones file.
df_dz_Edin <- df_dz_Edin %>%
left_join(df_census, by = "DataZone2011")
# merge foi data - use full join
df_dz_Edin <- df_dz_Edin %>%
full_join(df_foi_dz, by = "DataZone2011")
# check number of DZ and number with registered properties
nrow(df_dz_Edin)
# check number in DZ not in Edinburgh or missing DZ
sum(is.na(df_dz_Edin$All_HH_2011))
# put cases outside Edin (or missing DZ) in sep df
df_dz_NotEdin <- df_dz_Edin[
is.na(df_dz_Edin$All_HH_2011),
]
# number of properties lost
sum(df_dz_NotEdin$NumberOfProperties)
# proportion of original total
sprintf("%.2f %%",
100 * sum(df_dz_NotEdin$NumberOfProperties)/
sum(df_foi$NumberOfProperties))
# number of properties lost - no DZ i.e. pcode match failed
sum(df_dz_NotEdin$NumberOfProperties[
is.na(df_dz_NotEdin$DataZone2011)
])
# number of DZ with FOI data but not in Edin
nrow(df_dz_NotEdin[
!is.na(df_dz_NotEdin$DataZone2011),])
# number of properties lost - not in Edin i.e. others
sum(df_dz_NotEdin$NumberOfProperties[
!is.na(df_dz_NotEdin$DataZone2011)
])
# remove cases outside Edin (or missing DZ) from df_dz_Edin
df_dz_Edin <- df_dz_Edin[
!is.na(df_dz_Edin$All_HH_2011),]
# check number of DZ in Edinb without registered properties
sum(is.na(df_dz_Edin$NumberOfProperties))
# where reg props missing for any DZ, set to zero
df_dz_Edin$NumberOfProperties[
is.na(df_dz_Edin$NumberOfProperties)
] <- 0
# number of properties in final dataset
sum(df_dz_Edin$NumberOfProperties)
# DZs with no registered properties
nrow(df_dz_Edin[df_dz_Edin$NumberOfProperties == 0,])
# highest number of props in a DZ
max(df_dz_Edin$NumberOfProperties)
# histogram of No. or Reg Props
ggplot(data = df_dz_Edin,
mapping = aes(x = NumberOfProperties)) +
geom_histogram() +
ggtitle("Figure 3: Number of registered properties per Datazone - Edinburgh") +
theme(plot.title = element_text(size = 14, face = "plain")) +
xlab("Number of Registered Properties in Datazone") +
ylab("Number of Datazones")
# make text for correlation
corr <- signif(
cor(df_dz_Edin$PRS, df_dz_Edin$NumberOfProperties),
digits = 2)
corr_text <- paste("R =", corr)
# num prs props at census
sum(df_census$PRS)
# 'expected' line given number of llord register (sum(df_foi$NumberOfProperties))
# and number at Census
expected_slope <- sum(df_foi$NumberOfProperties)/sum(df_census$PRS)
ggplot(data = df_dz_Edin,
mapping = aes(x = PRS, y = NumberOfProperties)) +
geom_point() +
ggtitle("Figure 4: Registered properties in 2017 vs PRS households in 2011 - Edinburgh") +
xlab("PRS households in 2011 (Census)") +
ylab("No. of registered properties in 2017") +
theme(plot.title = element_text(size = 14, face = "plain")) +
geom_abline(slope=1) +
geom_abline(slope=expected_slope, linetype = "dashed") +
geom_text(x = 25, y = 450,
label = corr_text)
# global options for knit
knitr::opts_chunk$set(fig.width=8, fig.height=6, fig.path='Figs/',
echo=FALSE, include=FALSE, warning=FALSE, message=FALSE)
# install packages - first time only
# packs <- c("tidyverse", "dplyr", "readxl")
# install.packages(packs)
# load libraries
library(dplyr)
library(tidyverse)
library(readxl)
# open csv file from FoI request
df_foi <- as_tibble(read_excel("data/16177 Response Data.xlsx"))
# rename cols to remove spaces
names(df_foi) <- c("PropertyPostcode", "NumberOfProperties")
# make id column from row number
df_foi <- tibble::rowid_to_column(df_foi, "ID")
# make pc8 as uppercase version of original - name to match var in pcode lookup
df_foi <- mutate(df_foi,
pc8 = toupper(PropertyPostcode))
# this shows that first two letters in pc8 are always EH
table(str_sub(df_foi$pc8, 1, 2))
# this shows that length of pc8 mostly 7 or 8, but one 9
table(str_length(df_foi$pc8))
# identify the case - "EH16 4 FE"
subset(df_foi, str_length(pc8) > 8)
# change that case
df_foi$pc8[df_foi$pc8 == "EH16 4 FE"] <- "EH16 4FE"
# check that it is fixed
table(str_length(df_foi$pc8))
# quick check on final state of df_foi
head(df_foi)
# histogram of No. or Reg Props
ggplot(data = df_foi,
mapping = aes(x = NumberOfProperties)) +
geom_histogram() +
ggtitle("Figure 2: Number of registered properties per postcode - Edinburgh") +
theme(plot.title = element_text(size = 14, face = "plain")) +
xlab("Number of Registered Properties in Postcode") +
ylab("Number of Postcodes")
# open postcode directory - gives some errors which we ignore for now
# NB that to fit onto GitHub, have had to cut down to EH pcodes only but left
# code unchanged so assumes it is whole of Scotland
df_pcode <- read_csv(
"data/Scottish_Postcode_Directory_2017_2 (EH).csv",
col_types = cols(
pc7 = col_character(),
pc8 = col_character(),
Grid_Reference_Easting = col_double(),
Grid_Reference_Northing = col_double(),
Latitude = col_double(),
Longitude = col_double(),
DataZone2011 = col_character(),
HHC2011 = col_double(),
Pop2011 = col_double(),
HHC2001 = col_double(),
Pop2001 = col_double()
)
)
# cut df_pcodes to "EH"" and only the vars we need to attach to foi data
df_pcode2 <- subset(df_pcode, str_sub(pc7, 1, 2) == "EH",
select = c(pc7, pc8, DataZone2011, LAU_Level1_2011
)
)
# add data from df_pcode2 to df_foi
df_foi <- df_foi %>%
left_join(df_pcode2, by = "pc8")
# check how many cases have missing values - for pc7 it is 18
sum(is.na(df_foi$pc7))
# check how many properties this affects - 27
sum(df_foi$NumberOfProperties[is.na(df_foi$DataZone2011)])
# check number of rows and valid cases in all cols
# NB there is some drop off in HHC and Pop figs, esp. for 2001
nrow(df_foi)
colSums(!is.na(df_foi))
# aggregate foi data to DZ level, summing number of registered props
df_foi_dz <- df_foi %>%
group_by(DataZone2011) %>%
summarise(
NumberOfProperties = sum(NumberOfProperties, na.rm = TRUE)
)
nrow(df_foi_dz)
# number of properties with missing DZ
sum(df_foi_dz$NumberOfProperties[
is.na(df_foi_dz$DataZone2011)
])
# second cut of df_pcode to those in Edinburgh in order to make list of DZs in city
df_pcode3 <- subset(df_pcode, LAU_Level1_2011 == "S30000008",
select = c(DataZone2011
)
)
# collapse so it is just a list of DZs in Edinburgh
df_dz_Edin <- df_pcode3 %>%
group_by(DataZone2011) %>%
summarise()
# also extract as list
dz_Edin <- (df_dz_Edin$DataZone2011)
# Open census data file with tenure composition for DZs in 2011
df_census <- as_tibble(read_csv("data/tenure DZ2011.csv"))
# make correct PRS and PRSPct figures
df_census <- mutate(df_census,
PRS = PrtRent_2011,
PRSPct = PrtRent_2011/All_HH_2011)
# reduce to DZs in Edinburgh using the list - dz_Edin
df_census <- df_census[df_census$DataZone %in% dz_Edin,]
# rename 'Datazone' as 'Datazone2011' for matching
colnames(df_census)[1] <- "DataZone2011"
# merge census tenure data on to the Edinburgh Datazones file.
df_dz_Edin <- df_dz_Edin %>%
left_join(df_census, by = "DataZone2011")
# merge foi data - use full join
df_dz_Edin <- df_dz_Edin %>%
full_join(df_foi_dz, by = "DataZone2011")
# check number of DZ and number with registered properties
nrow(df_dz_Edin)
# check number in DZ not in Edinburgh or missing DZ
sum(is.na(df_dz_Edin$All_HH_2011))
# put cases outside Edin (or missing DZ) in sep df
df_dz_NotEdin <- df_dz_Edin[
is.na(df_dz_Edin$All_HH_2011),
]
# number of properties lost
sum(df_dz_NotEdin$NumberOfProperties)
# proportion of original total
sprintf("%.2f %%",
100 * sum(df_dz_NotEdin$NumberOfProperties)/
sum(df_foi$NumberOfProperties))
# number of properties lost - no DZ i.e. pcode match failed
sum(df_dz_NotEdin$NumberOfProperties[
is.na(df_dz_NotEdin$DataZone2011)
])
# number of DZ with FOI data but not in Edin
nrow(df_dz_NotEdin[
!is.na(df_dz_NotEdin$DataZone2011),])
# number of properties lost - not in Edin i.e. others
sum(df_dz_NotEdin$NumberOfProperties[
!is.na(df_dz_NotEdin$DataZone2011)
])
# remove cases outside Edin (or missing DZ) from df_dz_Edin
df_dz_Edin <- df_dz_Edin[
!is.na(df_dz_Edin$All_HH_2011),]
# check number of DZ in Edinb without registered properties
sum(is.na(df_dz_Edin$NumberOfProperties))
# where reg props missing for any DZ, set to zero
df_dz_Edin$NumberOfProperties[
is.na(df_dz_Edin$NumberOfProperties)
] <- 0
# number of properties in final dataset
sum(df_dz_Edin$NumberOfProperties)
# DZs with no registered properties
nrow(df_dz_Edin[df_dz_Edin$NumberOfProperties == 0,])
# highest number of props in a DZ
max(df_dz_Edin$NumberOfProperties)
# histogram of No. or Reg Props
ggplot(data = df_dz_Edin,
mapping = aes(x = NumberOfProperties)) +
geom_histogram() +
ggtitle("Figure 3: Number of registered properties per Datazone - Edinburgh") +
theme(plot.title = element_text(size = 14, face = "plain")) +
xlab("Number of Registered Properties in Datazone") +
ylab("Number of Datazones")
# make text for correlation
corr <- signif(
cor(df_dz_Edin$PRS, df_dz_Edin$NumberOfProperties),
digits = 2)
corr_text <- paste("R =", corr)
# num prs props at census
sum(df_census$PRS)
# 'expected' line given number of llord register (sum(df_foi$NumberOfProperties))
# and number at Census
expected_slope <- sum(df_foi$NumberOfProperties)/sum(df_census$PRS)
ggplot(data = df_dz_Edin,
mapping = aes(x = PRS, y = NumberOfProperties)) +
geom_point() +
ggtitle("Figure 4: Registered properties in 2017 vs PRS households in 2011 - Edinburgh") +
xlab("PRS households in 2011 (Census)") +
ylab("No. of registered properties in 2017") +
theme(plot.title = element_text(size = 14, face = "plain")) +
geom_abline(slope=1) +
geom_abline(slope=expected_slope, linetype = "dashed") +
geom_text(x = 25, y = 450,
label = corr_text)
# global options for knit
knitr::opts_chunk$set(fig.width=8, fig.height=6, fig.path='Figs/',
echo=FALSE, include=FALSE, warning=FALSE, message=FALSE)
# install packages - first time only
# packs <- c("tidyverse", "dplyr", "readxl")
# install.packages(packs)
# load libraries
library(dplyr)
library(tidyverse)
library(readxl)
# open csv file from FoI request
df_foi <- as_tibble(read_excel("data/16177 Response Data.xlsx"))
# rename cols to remove spaces
names(df_foi) <- c("PropertyPostcode", "NumberOfProperties")
# make id column from row number
df_foi <- tibble::rowid_to_column(df_foi, "ID")
# make pc8 as uppercase version of original - name to match var in pcode lookup
df_foi <- mutate(df_foi,
pc8 = toupper(PropertyPostcode))
# this shows that first two letters in pc8 are always EH
table(str_sub(df_foi$pc8, 1, 2))
# this shows that length of pc8 mostly 7 or 8, but one 9
table(str_length(df_foi$pc8))
# identify the case - "EH16 4 FE"
subset(df_foi, str_length(pc8) > 8)
# change that case
df_foi$pc8[df_foi$pc8 == "EH16 4 FE"] <- "EH16 4FE"
# check that it is fixed
table(str_length(df_foi$pc8))
# quick check on final state of df_foi
head(df_foi)
# histogram of No. or Reg Props
ggplot(data = df_foi,
mapping = aes(x = NumberOfProperties)) +
geom_histogram() +
ggtitle("Figure 2: Number of registered properties per postcode - Edinburgh") +
theme(plot.title = element_text(size = 14, face = "plain")) +
xlab("Number of Registered Properties in Postcode") +
ylab("Number of Postcodes")
# open postcode directory - gives some errors which we ignore for now
# NB that to fit onto GitHub, have had to cut down to EH pcodes only but left
# code unchanged so assumes it is whole of Scotland
df_pcode <- read_csv(
"data/Scottish_Postcode_Directory_2017_2 (EH).csv",
col_types = cols(
pc7 = col_character(),
pc8 = col_character(),
Grid_Reference_Easting = col_double(),
Grid_Reference_Northing = col_double(),
Latitude = col_double(),
Longitude = col_double(),
DataZone2011 = col_character(),
HHC2011 = col_double(),
Pop2011 = col_double(),
HHC2001 = col_double(),
Pop2001 = col_double()
)
)
# cut df_pcodes to "EH"" and only the vars we need to attach to foi data
df_pcode2 <- subset(df_pcode, str_sub(pc7, 1, 2) == "EH",
select = c(pc7, pc8, DataZone2011, LAU_Level1_2011
)
)
# add data from df_pcode2 to df_foi
df_foi <- df_foi %>%
left_join(df_pcode2, by = "pc8")
# check how many cases have missing values - for pc7 it is 18
sum(is.na(df_foi$pc7))
# check how many properties this affects - 27
sum(df_foi$NumberOfProperties[is.na(df_foi$DataZone2011)])
# check number of rows and valid cases in all cols
# NB there is some drop off in HHC and Pop figs, esp. for 2001
nrow(df_foi)
colSums(!is.na(df_foi))
# aggregate foi data to DZ level, summing number of registered props
df_foi_dz <- df_foi %>%
group_by(DataZone2011) %>%
summarise(
NumberOfProperties = sum(NumberOfProperties, na.rm = TRUE)
)
nrow(df_foi_dz)
# number of properties with missing DZ
sum(df_foi_dz$NumberOfProperties[
is.na(df_foi_dz$DataZone2011)
])
# second cut of df_pcode to those in Edinburgh in order to make list of DZs in city
df_pcode3 <- subset(df_pcode, LAU_Level1_2011 == "S30000008",
select = c(DataZone2011
)
)
# collapse so it is just a list of DZs in Edinburgh
df_dz_Edin <- df_pcode3 %>%
group_by(DataZone2011) %>%
summarise()
# also extract as list
dz_Edin <- (df_dz_Edin$DataZone2011)
# Open census data file with tenure composition for DZs in 2011
df_census <- as_tibble(read_csv("data/tenure DZ2011.csv"))
# make correct PRS and PRSPct figures
df_census <- mutate(df_census,
PRS = PrtRent_2011,
PRSPct = PrtRent_2011/All_HH_2011)
# reduce to DZs in Edinburgh using the list - dz_Edin
df_census <- df_census[df_census$DataZone %in% dz_Edin,]
# rename 'Datazone' as 'Datazone2011' for matching
colnames(df_census)[1] <- "DataZone2011"
# merge census tenure data on to the Edinburgh Datazones file.
df_dz_Edin <- df_dz_Edin %>%
left_join(df_census, by = "DataZone2011")
# merge foi data - use full join
df_dz_Edin <- df_dz_Edin %>%
full_join(df_foi_dz, by = "DataZone2011")
# check number of DZ and number with registered properties
nrow(df_dz_Edin)
# check number in DZ not in Edinburgh or missing DZ
sum(is.na(df_dz_Edin$All_HH_2011))
# put cases outside Edin (or missing DZ) in sep df
df_dz_NotEdin <- df_dz_Edin[
is.na(df_dz_Edin$All_HH_2011),
]
# number of properties lost
sum(df_dz_NotEdin$NumberOfProperties)
# proportion of original total
sprintf("%.2f %%",
100 * sum(df_dz_NotEdin$NumberOfProperties)/
sum(df_foi$NumberOfProperties))
# number of properties lost - no DZ i.e. pcode match failed
sum(df_dz_NotEdin$NumberOfProperties[
is.na(df_dz_NotEdin$DataZone2011)
])
# number of DZ with FOI data but not in Edin
nrow(df_dz_NotEdin[
!is.na(df_dz_NotEdin$DataZone2011),])
# number of properties lost - not in Edin i.e. others
sum(df_dz_NotEdin$NumberOfProperties[
!is.na(df_dz_NotEdin$DataZone2011)
])
# remove cases outside Edin (or missing DZ) from df_dz_Edin
df_dz_Edin <- df_dz_Edin[
!is.na(df_dz_Edin$All_HH_2011),]
# check number of DZ in Edinb without registered properties
sum(is.na(df_dz_Edin$NumberOfProperties))
# where reg props missing for any DZ, set to zero
df_dz_Edin$NumberOfProperties[
is.na(df_dz_Edin$NumberOfProperties)
] <- 0
# number of properties in final dataset
sum(df_dz_Edin$NumberOfProperties)
# DZs with no registered properties
nrow(df_dz_Edin[df_dz_Edin$NumberOfProperties == 0,])
# highest number of props in a DZ
max(df_dz_Edin$NumberOfProperties)
# histogram of No. or Reg Props
ggplot(data = df_dz_Edin,
mapping = aes(x = NumberOfProperties)) +
geom_histogram() +
ggtitle("Figure 3: Number of registered properties per Datazone - Edinburgh") +
theme(plot.title = element_text(size = 14, face = "plain")) +
xlab("Number of Registered Properties in Datazone") +
ylab("Number of Datazones")
# make text for correlation
corr <- signif(
cor(df_dz_Edin$PRS, df_dz_Edin$NumberOfProperties),
digits = 2)
corr_text <- paste("R =", corr)
# num prs props at census
sum(df_census$PRS)
# 'expected' line given number of llord register (sum(df_foi$NumberOfProperties))
# and number at Census
expected_slope <- sum(df_foi$NumberOfProperties)/sum(df_census$PRS)
ggplot(data = df_dz_Edin,
mapping = aes(x = PRS, y = NumberOfProperties)) +
geom_point() +
ggtitle("Figure 4: Registered properties in 2017 vs PRS households in 2011 - Edinburgh") +
xlab("PRS households in 2011 (Census)") +
ylab("No. of registered properties in 2017") +
theme(plot.title = element_text(size = 14, face = "plain")) +
geom_abline(slope=1) +
geom_abline(slope=expected_slope, linetype = "dashed") +
geom_text(x = 25, y = 450,
label = corr_text)