-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathEmployment deprived.R
executable file
·117 lines (92 loc) · 5.83 KB
/
Employment deprived.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
# ScotPHO indicators: working age pop employment deprived, including deprivation.
## Part 1 - Format raw data ready for analysis functions
## Part 2 - calling the analysis functions
###############################################.
## Packages/Filepaths/Functions ----
###############################################.
#Filepaths, change from server to desktop depending on R version you use
if (sessionInfo()$platform %in% c("x86_64-redhat-linux-gnu (64-bit)", "x86_64-pc-linux-gnu (64-bit)")) {
cl_out_depr <- "/conf/linkage/output/lookups/Unicode/Deprivation/"
} else {
cl_out_depr <- "//stats/linkage/output/lookups/Unicode/Deprivation/"
}
source("1.indicator_analysis.R") #Normal indicator functions
source("2.deprivation_analysis.R") # deprivation function
#Small function to standarize each years info. Function parameters:
#Data is for what basefile to use, list_pos is for the position of the data frame
#simd for which simd variables-year to look at, year for what year is the data created.
read_simd <- function(data, simd, year, list_pos) {
datazone <- tolower(substr(data,1,12))
data_simd <- readRDS(paste0(cl_out_depr, data, '.rds')) %>%
setNames(tolower(names(.))) %>% #variables to lower case
select({{simd}}, datazone) %>%
rename(numerator = {{simd}}, datazone = datazone) %>%
mutate(year = year)
data_employ[[list_pos]] <<- data_simd #assigning to list
}
###############################################.
## Part 1 - Format raw data ready for analysis functions ----
###############################################.
data_employ <- list() #creating empty list for placing data created by function
# The function creates the dataset and assigns it to the list
mapply(read_simd, data = "DataZone2001_all_simd", simd = "simd2006_emp_dep_n",
year = 2004:2006, list_pos = 1:3) #simd version 2006
mapply(read_simd, data = "DataZone2001_all_simd", simd = "simd2009v2_emp_dep_n",
year = 2007:2009, list_pos = 4:6) #simd version 2009
mapply(read_simd, data = "DataZone2001_all_simd", simd = "simd2012_emp_dep_n",
year = 2010:2013, list_pos = 7:10) #simd version 2012
mapply(read_simd, data = "DataZone2011_simd2016", simd = "simd2016_emp_dep_n",
year = 2014:2016, list_pos = 11:13) #simd version 2016
mapply(read_simd, data = "DataZone2011_simd2020v2", simd = "simd2020v2_emp_dep_n",
year = 2017:2019, list_pos = 14:16) #simd version 2020
data_employ <- do.call("rbind", data_employ) # converting from list into dataframe
#File for deprivation analysis
saveRDS(data_employ, file = paste0(data_folder, "Prepared Data/employment_deprived_depr_raw.rds"))
#File for DZ11 for 2014 onwards
data_employdz11 <- data_employ %>% filter(year>2013)
saveRDS(data_employdz11, file = paste0(data_folder, "Prepared Data/employment_deprived_dz11_raw.rds"))
#Preparing file for CA for period 2004 to 2013
data_employdz01 <- data_employ %>% filter(year<2014)
#Lookup file for CA
ca_lookup <- read_xlsx(paste0(data_folder, "Lookups/Geography/DataZone2001.xlsx")) %>%
setNames(tolower(names(.))) %>% select(ca, datazone)
#Merging with lookup and aggregating by ca
data_employdz01 <- left_join(data_employdz01, ca_lookup) %>%
group_by(ca, year) %>%
summarise(numerator=sum(numerator, na.rm = T)) %>% ungroup() %>%
#Dealing with changes in ca codes. Transforms old code versions into 2019 ones
mutate(ca = recode(ca, "S12000015"='S12000047', "S12000024"='S12000048',
"S12000046"='S12000049', "S12000044"='S12000050'))
saveRDS(data_employdz01, file = paste0(data_folder, "Prepared Data/employment_deprived_ca_raw.rds"))
###############################################.
## Part 2 - Calling the analysis functions ----
###############################################.
#Normal indicator analysis, first for CA and then DZ11
analyze_first(filename = "employment_deprived_ca", geography = "council", measure = "percent",
yearstart = 2004, yearend = 2013, time_agg = 1, pop = "CA_working_pop")
analyze_first(filename = "employment_deprived_dz11", geography = "datazone11", measure = "percent",
yearstart = 2014, yearend = 2019, time_agg = 1, pop = "DZ11_working_pop")
#Merging CA and DZ11 together
all_data <- rbind(readRDS(paste0(data_folder, "Temporary/employment_deprived_dz11_formatted.rds")),
readRDS(paste0(data_folder, "Temporary/employment_deprived_ca_formatted.rds")))
saveRDS(all_data, file = paste0(data_folder, "Temporary/employment_deprived_all_formatted.rds"))
#Calling second analysis function
analyze_second(filename = "employment_deprived_all", measure = "percent",
time_agg = 1, ind_id = 20702, year_type = "calendar")
###### Save final result before it is overwritten by analyze_deprivation() and filter correct years to include in Plot
data_shiny_filtered <- final_result %>%
select(c(code, ind_id, year, numerator, rate, lowci, upci, def_period, trend_axis)) %>%
filter(year %in% c(2004, 2007, 2010, 2014, 2017))
###############################################.
#Deprivation analysis function
analyze_deprivation(filename="employment_deprived_depr", measure="percent", time_agg=1,
yearstart= 2004, yearend=2019, year_type = "calendar",
pop = "depr_working_pop", ind_id = 20702)
####### Filter depirvation data to include correct years
data_shiny_deprivation_filtered <- final_result %>%
filter(year %in% c(2004, 2007, 2010, 2014, 2017))
# Save to Data to be checked folder
saveRDS(data_shiny_filtered, file = paste0("/PHI_conf/ScotPHO/Profiles/Data/", "Data to be checked/", "employment_deprived_all", "_shiny.rds"))
write_csv(data_shiny_filtered, file = paste0("/PHI_conf/ScotPHO/Profiles/Data/", "Data to be checked/", "employment_deprived_all", "_shiny.csv"))
saveRDS(data_shiny_deprivation_filtered, file = paste0("/PHI_conf/ScotPHO/Profiles/Data/", "Data to be checked/", "employment_deprived_depr_ineq.rds"))
#END