communityprofiles/data_clean.R at master · UCRCSI/communityprofiles · GitHub

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
library(tidyverse)
library(readr)

# data clean --------------------------------------------------------------

raw <- read_csv("dta/community_profile_raw.csv")
final <- raw %>%
  select(-variable, -code) %>%
  write_rds("dta/final_dta.rds")


#generate lookup table
group_lookup <- raw %>%
  select(group, variable, code)
#save lookup table
saveRDS(group_lookup, "dta/group_lookup.rds")
#cleanup the data
dta <- raw %>%
  filter(variable == "aapi_alone" | variable == "detailed_hisp") %>%
  select(-group) %>%
  gather(label, estimate, -variable, -code)

#Cutting the dataset by topics
poverty <- dta %>%
  filter(label %in% c("pov", "kpov", "spov"))
saveRDS(poverty, "dta/cleaned_poverty.rds")

cvap <- dta %>%
  filter(label == "cvap")
saveRDS(cvap, "dta/cleaned_cvap.rds")

age <- dta %>%
# poverty -----------------------------------------------------------------
#pull raw data
dta1 <- read_csv("/Users/sunnyshao/Dropbox/AAPIData HQ/Other Sites/Racial Data/geoprofile_ipums/output tables/aapi_alone_kpov.csv", skip = 2) %>%
  rename(group=`0`, estimate = `X2`) %>%
  mutate(label = "pov_k")
dta2 <- read_csv("/Users/sunnyshao/Dropbox/AAPIData HQ/Other Sites/Racial Data/geoprofile_ipums/output tables/aapi_alone_pov.csv", skip = 2) %>%
  rename(group=`0`, estimate = `X2`) %>%
  mutate(label = "pov")
dta3 <- read_csv("/Users/sunnyshao/Dropbox/AAPIData HQ/Other Sites/Racial Data/geoprofile_ipums/output tables/aapi_alone_spov.csv", skip = 2) %>%
  rename(group=`0`, estimate = `X2`) %>%
  mutate(label = "pov_s")
dta4 <- read_csv("/Users/sunnyshao/Dropbox/AAPIData HQ/Other Sites/Racial Data/geoprofile_ipums/output tables/detailed_hisp_kpov.csv", skip = 2) %>%
  rename(group=`0`, estimate = `X2`) %>%
  mutate(label = "pov_k")
dta5 <- read_csv("/Users/sunnyshao/Dropbox/AAPIData HQ/Other Sites/Racial Data/geoprofile_ipums/output tables/detailed_hisp_pov.csv", skip = 2) %>%
  rename(group=`0`, estimate = `X2`) %>%
  mutate(label = "pov")
dta6 <- read_csv("/Users/sunnyshao/Dropbox/AAPIData HQ/Other Sites/Racial Data/geoprofile_ipums/output tables/detailed_hisp_spov.csv", skip = 2) %>%
  rename(group=`0`, estimate = `X2`) %>%
  mutate(label = "pov_s")
#merge into one
poverty <- rbind(dta1, dta2, dta3, dta4, dta5, dta6)
saveRDS(poverty, "dta/cleaned_poverty.RDS")


# cvap --------------------------------------------------------------------