Di Wu
2023-11-03
R Markdown
This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.
Mission 1
# List of packages
packages <- c("tidyverse", "modelsummary", "forcats", "RColorBrewer",
"fst", "viridis", "knitr", "rmarkdown", "ggridges", "viridis", "questionr", "flextable", "infer") # add
# Install packages if they aren't installed already
new_packages <- packages[!(packages %in% installed.packages()[,"Package"])]
if(length(new_packages)) install.packages(new_packages)
# Load the packages
lapply(packages, library, character.only = TRUE)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.3 ✔ readr 2.1.4
## ✔ forcats 1.0.0 ✔ stringr 1.5.0
## ✔ ggplot2 3.4.3 ✔ tibble 3.2.1
## ✔ lubridate 1.9.2 ✔ tidyr 1.3.0
## ✔ purrr 1.0.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
## Loading required package: viridisLite
##
##
## Attaching package: 'flextable'
##
##
## The following object is masked from 'package:purrr':
##
## compose## [[1]]
## [1] "lubridate" "forcats" "stringr" "dplyr" "purrr" "readr"
## [7] "tidyr" "tibble" "ggplot2" "tidyverse" "stats" "graphics"
## [13] "grDevices" "utils" "datasets" "methods" "base"
##
## [[2]]
## [1] "modelsummary" "lubridate" "forcats" "stringr" "dplyr"
## [6] "purrr" "readr" "tidyr" "tibble" "ggplot2"
## [11] "tidyverse" "stats" "graphics" "grDevices" "utils"
## [16] "datasets" "methods" "base"
##
## [[3]]
## [1] "modelsummary" "lubridate" "forcats" "stringr" "dplyr"
## [6] "purrr" "readr" "tidyr" "tibble" "ggplot2"
## [11] "tidyverse" "stats" "graphics" "grDevices" "utils"
## [16] "datasets" "methods" "base"
##
## [[4]]
## [1] "RColorBrewer" "modelsummary" "lubridate" "forcats" "stringr"
## [6] "dplyr" "purrr" "readr" "tidyr" "tibble"
## [11] "ggplot2" "tidyverse" "stats" "graphics" "grDevices"
## [16] "utils" "datasets" "methods" "base"
##
## [[5]]
## [1] "fst" "RColorBrewer" "modelsummary" "lubridate" "forcats"
## [6] "stringr" "dplyr" "purrr" "readr" "tidyr"
## [11] "tibble" "ggplot2" "tidyverse" "stats" "graphics"
## [16] "grDevices" "utils" "datasets" "methods" "base"
##
## [[6]]
## [1] "viridis" "viridisLite" "fst" "RColorBrewer" "modelsummary"
## [6] "lubridate" "forcats" "stringr" "dplyr" "purrr"
## [11] "readr" "tidyr" "tibble" "ggplot2" "tidyverse"
## [16] "stats" "graphics" "grDevices" "utils" "datasets"
## [21] "methods" "base"
##
## [[7]]
## [1] "knitr" "viridis" "viridisLite" "fst" "RColorBrewer"
## [6] "modelsummary" "lubridate" "forcats" "stringr" "dplyr"
## [11] "purrr" "readr" "tidyr" "tibble" "ggplot2"
## [16] "tidyverse" "stats" "graphics" "grDevices" "utils"
## [21] "datasets" "methods" "base"
##
## [[8]]
## [1] "rmarkdown" "knitr" "viridis" "viridisLite" "fst"
## [6] "RColorBrewer" "modelsummary" "lubridate" "forcats" "stringr"
## [11] "dplyr" "purrr" "readr" "tidyr" "tibble"
## [16] "ggplot2" "tidyverse" "stats" "graphics" "grDevices"
## [21] "utils" "datasets" "methods" "base"
##
## [[9]]
## [1] "ggridges" "rmarkdown" "knitr" "viridis" "viridisLite"
## [6] "fst" "RColorBrewer" "modelsummary" "lubridate" "forcats"
## [11] "stringr" "dplyr" "purrr" "readr" "tidyr"
## [16] "tibble" "ggplot2" "tidyverse" "stats" "graphics"
## [21] "grDevices" "utils" "datasets" "methods" "base"
##
## [[10]]
## [1] "ggridges" "rmarkdown" "knitr" "viridis" "viridisLite"
## [6] "fst" "RColorBrewer" "modelsummary" "lubridate" "forcats"
## [11] "stringr" "dplyr" "purrr" "readr" "tidyr"
## [16] "tibble" "ggplot2" "tidyverse" "stats" "graphics"
## [21] "grDevices" "utils" "datasets" "methods" "base"
##
## [[11]]
## [1] "questionr" "ggridges" "rmarkdown" "knitr" "viridis"
## [6] "viridisLite" "fst" "RColorBrewer" "modelsummary" "lubridate"
## [11] "forcats" "stringr" "dplyr" "purrr" "readr"
## [16] "tidyr" "tibble" "ggplot2" "tidyverse" "stats"
## [21] "graphics" "grDevices" "utils" "datasets" "methods"
## [26] "base"
##
## [[12]]
## [1] "flextable" "questionr" "ggridges" "rmarkdown" "knitr"
## [6] "viridis" "viridisLite" "fst" "RColorBrewer" "modelsummary"
## [11] "lubridate" "forcats" "stringr" "dplyr" "purrr"
## [16] "readr" "tidyr" "tibble" "ggplot2" "tidyverse"
## [21] "stats" "graphics" "grDevices" "utils" "datasets"
## [26] "methods" "base"
##
## [[13]]
## [1] "infer" "flextable" "questionr" "ggridges" "rmarkdown"
## [6] "knitr" "viridis" "viridisLite" "fst" "RColorBrewer"
## [11] "modelsummary" "lubridate" "forcats" "stringr" "dplyr"
## [16] "purrr" "readr" "tidyr" "tibble" "ggplot2"
## [21] "tidyverse" "stats" "graphics" "grDevices" "utils"
## [26] "datasets" "methods" "base"# read data
setwd("~/Desktop/SOC_202_YAY/")
getwd() ## [1] "/Users/apple/Desktop/SOC_202_YAY"ess <- read_fst("All-ESS-Data.fst")Mission 2
uk_data <- ess %>%
filter(cntry == "GB") write_fst(uk_data, "/Users/apple/Desktop/SOC_202_YAY/uk_data.fst") Mission 3
rm(list=ls()); gc()## used (Mb) gc trigger (Mb) limit (Mb) max used (Mb)
## Ncells 1253155 67.0 2116280 113.1 NA 2116280 113.1
## Vcells 2112785 16.2 1256969650 9590.0 16384 1361143084 10384.7df <- read_fst("uk_data.fst")Mission 4
df$year <- NA
replacements <- c(2002, 2004, 2006, 2008, 2010, 2012, 2014, 2016, 2018, 2020)
for(i in 1:10){
df$year[df$essround == i] <- replacements[i]
}
uk_data <- df
# make sure you know your current folder path. you can do getwd() to check
uk_data_table_subset <- uk_data %>%
mutate(
happy = ifelse(happy == 2, 0, ifelse(happy %in% c(7, 8, 9), NA, happy)),
imprich = ifelse(imprich %in% c(77, 88, 99), NA, imprich),
trstplt = ifelse(trstplt %in% c(77, 88, 99), NA, trstplt)
)
summary_table <- datasummary_skim(uk_data_table_subset %>% select(happy, imprich, trstplt), output = "flextable", title= "uk")## Warning: The histogram argument is only supported for (a) output types "default",
## "html", "kableExtra", or "gt"; (b) writing to file paths with extensions
## ".html", ".jpg", or ".png"; and (c) Rmarkdown, knitr or Quarto documents
## compiled to PDF (via kableExtra) or HTML (via kableExtra or gt). Use
## `histogram=FALSE` to silence this warning.summary_table
| Unique (#) | Missing (%) | Mean | SD | Min | Median | Max |
|---|---|---|---|---|---|---|---|
happy | 10 | 65 | 6.8 | 6.1 | 0.0 | 6.0 | 88.0 |
imprich | 10 | 1 | 4.4 | 1.3 | 1.0 | 5.0 | 9.0 |
trstplt | 12 | 1 | 3.5 | 2.3 | 0.0 | 4.0 | 10.0 |
uk_data_v2 <- uk_data_table_subset %>%
rename(
`How happy are you` = happy,
`Important to be rich, have money and expensive things` = imprich,
`Trust in Politicians` = trstplt
)
summary_table_v2 <- datasummary_skim(uk_data_v2 %>% select(`How happy are you`,`Important to be rich, have money and expensive things`, `Trust in Politicians`), output = "flextable")## Warning: The histogram argument is only supported for (a) output types "default",
## "html", "kableExtra", or "gt"; (b) writing to file paths with extensions
## ".html", ".jpg", or ".png"; and (c) Rmarkdown, knitr or Quarto documents
## compiled to PDF (via kableExtra) or HTML (via kableExtra or gt). Use
## `histogram=FALSE` to silence this warning.summary_table_v2
| Unique (#) | Missing (%) | Mean | SD | Min | Median | Max |
|---|---|---|---|---|---|---|---|
How happy are you | 10 | 65 | 6.8 | 6.1 | 0.0 | 6.0 | 88.0 |
Important to be rich, have money and expensive things | 10 | 1 | 4.4 | 1.3 | 1.0 | 5.0 | 9.0 |
Trust in Politicians | 12 | 1 | 3.5 | 2.3 | 0.0 | 4.0 | 10.0 |
flextable::save_as_docx(summary_table_v2, path = "summary_table_v2.docx", # change name to whatever you would like
width = 7.0, height = 7.0) Mission 5
df$year <- NA
replacements <- c(2002, 2004, 2006, 2008, 2010, 2012, 2014, 2016, 2018, 2020)
for(i in 1:10){
df$year[df$essround == i] <- replacements[i]
}
uk_data <- df
uk_data <- uk_data %>%
mutate(religion = case_when(
rlgblg == 2 ~ "No",
rlgblg == 1 ~ "Yes",
rlgblg %in% c(7, 8, 9) ~ NA_character_,
TRUE ~ as.character(rlgblg)
))
table(uk_data$religion)##
## No Yes
## 10923 10020table(uk_data$rlgblg)##
## 1 2 7 8
## 10020 10923 9 27uk_data <- uk_data %>%
mutate(geo = recode(as.character(domicil),
'1' = "Urban",
'2' = "Peri-Urban", # or set to Urban | Regardless decision needs to be justified
'3' = "Rural",
'4' = "Rural",
'5' = "Rural",
'7' = NA_character_,
'8' = NA_character_,
'9' = NA_character_))
table(uk_data$geo)##
## Peri-Urban Rural Urban
## 4615 14550 1761table(uk_data$domicil)##
## 1 2 3 4 5 7 8 9
## 1761 4615 9559 4250 741 6 37 10summary_table <- datasummary_skim(uk_data_table_subset %>% select(rlgblg, domicil), output = "flextable", title ="Socio-demographic variables")## Warning: The histogram argument is only supported for (a) output types "default",
## "html", "kableExtra", or "gt"; (b) writing to file paths with extensions
## ".html", ".jpg", or ".png"; and (c) Rmarkdown, knitr or Quarto documents
## compiled to PDF (via kableExtra) or HTML (via kableExtra or gt). Use
## `histogram=FALSE` to silence this warning.summary_table
| Unique (#) | Missing (%) | Mean | SD | Min | Median | Max |
|---|---|---|---|---|---|---|---|
rlgblg | 4 | 0 | 1.5 | 0.6 | 1.0 | 2.0 | 8.0 |
domicil | 8 | 0 | 2.9 | 1.0 | 1.0 | 3.0 | 9.0 |
Mission 6
set_flextable_defaults(fonts_ignore=TRUE)
print(summary_table_v2, preview = "word")## a flextable object.
## col_keys: ` `, `Unique (#)`, `Missing (%)`, `Mean`, `SD`, `Min`, `Median`, `Max`
## header has 1 row(s)
## body has 3 row(s)
## original dataset sample:
## Unique (#) Missing (%)
## 1 How happy are you 10 65
## 2 Important to be rich, have money and expensive things 10 1
## 3 Trust in Politicians 12 1
## Mean SD Min Median Max
## 1 6.8 6.1 0.0 6.0 88.0
## 2 4.4 1.3 1.0 5.0 9.0
## 3 3.5 2.3 0.0 4.0 10.0Mission 7
df$year <- NA
replacements <- c(2002, 2004, 2006, 2008, 2010, 2012, 2014, 2016, 2018, 2020)
for(i in 1:10){
df$year[df$essround == i] <- replacements[i]
}
uk_data <- df
uk_data_table_subset <- uk_data %>%
mutate(
rlgblg = ifelse(rlgblg== 2, 0, ifelse(rlgblg %in% c(7, 8, 9), NA, rlgblg)),
domicil = ifelse(domicil %in% c(7, 8, 9), NA, domicil)
)
avg_domicil_by_year <- aggregate(domicil ~ year + rlgblg, data=uk_data_table_subset, mean)
p1 <- ggplot(avg_domicil_by_year, aes(x=year, y=domicil, color=as.factor(rlgblg))) +
geom_line(aes(group=rlgblg)) +
labs(title="Mean of Interested in Politics",
subtitle = "for those Worked rural or urban in UK",
x="Survey Year",
y="Average Interested in Politics") +
scale_color_discrete(name="Worked in Political in rural/ urban", labels=c("No", "Yes"))+
theme_minimal()
p1