Mission 1
Launch a new R project and R markdown file. Name it “Lastname_Firstname_Project_202”. Set up your environment with packages you will use.
Mission 2
Filter to your country of interest and save the dataset.
packages <- c("tidyverse", "modelsummary", "forcats", "RColorBrewer",
"fst", "viridis", "knitr", "rmarkdown", "ggridges", "viridis", "questionr", "flextable", "infer") # add any you need here
new_packages <- packages[!(packages %in% installed.packages()[,"Package"])]
if(length(new_packages)) install.packages(new_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 1.9.3 ✔ 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
## 载入需要的程辑包：viridisLite
##
##
## 载入程辑包：'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"ess <- read_fst("All-ESS-Data.fst")
UK_data <- ess %>%
filter(cntry == "GB")
write_fst(UK_data, "./UK_data.fst") Mission 3
Clean your environment and load in the filtered dataset.
rm(list=ls()); gc()## used (Mb) gc trigger (Mb) max used (Mb)
## Ncells 1258073 67.2 2271972 121.4 2271972 121.4
## Vcells 2127391 16.3 1257003920 9590.2 1361137282 10384.7df <- read_fst("./UK_data.fst")Mission 4
Produce and save a data summary output (using data summary skim) for potential outcomes of interest on a similar scale (e.g., 0-10, or 1 to 6, or binary). Add a title. You can do so while coding (explore package information for flextable and/or modelsummary) or add it directly in the word file. Title should be something like: Table 1: Descriptive Statistics for outcome variables. You can alter the title as you see fit.
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(
wrkprty = ifelse(wrkprty == 2, 0, ifelse(wrkprty %in% c(7, 8, 9), NA, wrkprty)),
needtru = ifelse(needtru %in% c(7, 8, 9), NA, needtru),
polintr = ifelse(polintr %in% c(7, 8, 9), NA, polintr)
)
UK_summary_table <- datasummary_skim(UK_data_table_subset %>% select(wrkprty, needtru, polintr), 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.UK_summary_table <- add_header_lines(UK_summary_table, values = "Table1 :Descriptive Statistics for outcome variables")
UK_summary_tableflextable::save_as_docx(UK_summary_table, path = "./UK_summary_table.docx",
width = 7.0, height = 7.0)Mission 5
Produce and save a data summary output (using data summary skim) for socio-demographic variables. Add a title. You can do so while coding (explore package information for flextable and/or modelsummary) or add it directly in the word file. Title should be something like: Table 1: Descriptive Statistics for socio-demographic variables. You can alter the title as you see fit.
UK_data_v2 <- UK_data_table_subset %>%
rename(
`Worked in Political Party` = wrkprty,
`Need Strong Trade Union` = needtru,
`Interested in Politics` = polintr
)UK_summary_table_v2 <- datasummary_skim(UK_data_v2 %>% select(`Worked in Political Party`,`Need Strong Trade Union`, `Interested in Politics`), 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.UK_summary_table_v2 <- add_header_lines(UK_summary_table_v2, values = "Table1 :Descriptive Statistics for socio-demographic variables")
UK_summary_table_v2flextable::save_as_docx(UK_summary_table_v2, path = "./UK_summary_table_v2.docx",
width = 7.0, height = 7.0)Mission 6
Produce and save a plot as a PDF for your outcome of interest (any will do here).
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(
wrkprty = ifelse(wrkprty == 2, 0, ifelse(wrkprty %in% c(7, 8, 9), NA, wrkprty)),
polintr = ifelse(polintr %in% c(7, 8, 9), NA, polintr)
)
avg_lintrprty_by_year <- aggregate(polintr ~ year + wrkprty, data=UK_data_table_subset, mean)
p1 <- ggplot(avg_lintrprty_by_year, aes(x=year, y=polintr, color=as.factor(wrkprty))) +
geom_line(aes(group=wrkprty)) +
labs(title="Mean of Interested in Politics",
subtitle = "for those Worked in Political Party or Group in UK",
x="Survey Year",
y="Average Interested in Politics") +
scale_color_discrete(name="Worked in Political Party/Group", labels=c("No", "Yes"))+
theme_minimal()
p1 
ggsave(filename = "./plot1.pdf", plot = p1, device = "pdf", width = 6, height = 4)