Dong_Lyra_Project_202
Lyra Dong
2023-10-19
Mission 1:
# List of packages
packages <- c("tidyverse", "modelsummary", "forcats", "RColorBrewer",
"fst", "viridis", "knitr", "rmarkdown", "ggridges", "viridis", "questionr", "flextable", "infer")
# 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"ess <- read_fst("All-ESS-Data.fst")Mission 2:
germany_data <- ess %>%
filter(cntry == "DE") write_fst(germany_data, "~/SOC 202/Dong_Lyra_Project_202/germany_data.fst")Mission 3:
rm(list=ls()); gc()## used (Mb) gc trigger (Mb) max used (Mb)
## Ncells 1258518 67.3 2128192 113.7 2128192 113.7
## Vcells 2128699 16.3 1256997452 9590.2 1396872228 10657.3df <- read_fst("~/SOC 202/Dong_Lyra_Project_202/germany_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]
}
germany_data <- df
# make sure you know your current folder path. you can do getwd() to check
germany_data_table_subset <- germany_data %>%
mutate(
aesfdrk = ifelse(aesfdrk == 2, 0, ifelse(aesfdrk %in% c(7, 8, 9), NA, aesfdrk)),
sclmeet = ifelse(sclmeet %in% c(77, 88, 99), NA, sclmeet),
trstplt = ifelse(trstplt %in% c(77, 88, 99), NA, trstplt)
)
summary_table <- datasummary_skim(germany_data_table_subset %>% select(aesfdrk, sclmeet, trstplt), 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
| Unique (#) | Missing (%) | Mean | SD | Min | Median | Max |
|---|---|---|---|---|---|---|---|
aesfdrk | 5 | 1 | 1.1 | 1.3 | 0.0 | 0.0 | 4.0 |
sclmeet | 8 | 0 | 4.7 | 1.4 | 1.0 | 5.0 | 7.0 |
trstplt | 12 | 1 | 3.6 | 2.2 | 0.0 | 4.0 | 10.0 |
germany_data_v2 <- germany_data_table_subset %>%
rename(
`Feeling of safety of walking alone in local area after dark` = aesfdrk,
`How often socially meet with friends, relatives or colleagues` = sclmeet,
`Trust in Politicians` = trstplt
)summary_table_v2 <- datasummary_skim(germany_data_v2 %>% select(`Feeling of safety of walking alone in local area after dark`,`How often socially meet with friends, relatives or colleagues`, `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 <- add_header_lines(summary_table_v2, values = "Table 1: Descriptive Statistics for outcome variables")
summary_table_v2Table 1: Descriptive Statistics for outcome variables | |||||||
|---|---|---|---|---|---|---|---|
| Unique (#) | Missing (%) | Mean | SD | Min | Median | Max |
Feeling of safety of walking alone in local area after dark | 5 | 1 | 1.1 | 1.3 | 0.0 | 0.0 | 4.0 |
How often socially meet with friends, relatives or colleagues | 8 | 0 | 4.7 | 1.4 | 1.0 | 5.0 | 7.0 |
Trust in Politicians | 12 | 1 | 3.6 | 2.2 | 0.0 | 4.0 | 10.0 |
flextable::save_as_docx(summary_table_v2, path = "ip_summary_table_v2.docx",
width = 7.0, height = 7.0)Mission 9:
ess <- read_fst("All-ESS-Data.fst")# Filter the data for Millennials and Boomers
millennials_data <- ess %>%
filter(cntry == "DE", yrbrn > 1980 & yrbrn < 1997)
boomers_data <- ess %>%
filter(cntry == "DE", yrbrn > 1945 & yrbrn < 1965)# Clean the variables
millennials_data_cleaned <- millennials_data %>%
mutate(
aesfdrk = ifelse(aesfdrk %in% c(7, 8, 9), NA, aesfdrk),
sclmeet = ifelse(sclmeet %in% c(7, 8, 9), NA, sclmeet),
trstplt = ifelse(trstplt %in% c(7, 8, 9), NA, trstplt)
) %>%
group_by(yrbrn) %>%
summarise(
avg_sclmeet = mean(sclmeet, na.rm = TRUE),
avg_aesfdrk = mean(aesfdrk, na.rm = TRUE),
avg_trstplt = mean(trstplt, na.rm = TRUE)
)
boomers_data_cleaned <- boomers_data %>%
mutate(
aesfdrk = ifelse(aesfdrk %in% c(7, 8, 9), NA, aesfdrk),
sclmeet = ifelse(sclmeet %in% c(7, 8, 9), NA, sclmeet),
trstplt = ifelse(trstplt %in% c(7, 8, 9), NA, trstplt)
) %>%
group_by(yrbrn) %>%
summarise(
avg_sclmeet = mean(sclmeet, na.rm = TRUE),
avg_aesfdrk = mean(aesfdrk, na.rm = TRUE),
avg_trstplt = mean(trstplt, na.rm = TRUE)
)# Create scatterplots with trend lines for average scores
ggplot() +
geom_point(data = millennials_data_cleaned, aes(x = yrbrn, y = avg_sclmeet), color = "pink", alpha = 0.6) +
geom_point(data = boomers_data_cleaned, aes(x = yrbrn, y = avg_sclmeet), color = "pink", alpha = 0.6) +
geom_smooth(data = millennials_data_cleaned, aes(x = yrbrn, y = avg_sclmeet), method = "lm", formula = y ~ poly(x, 1), color = "pink") +
geom_smooth(data = boomers_data_cleaned, aes(x = yrbrn, y = avg_sclmeet), method = "lm", formula = y ~ poly(x, 1), color = "pink") +
labs(
title = "Average sclmeet Score by Birth Year (Millennials vs. Boomers)",
x = "Year of Birth",
y = "Average sclmeet"
) +
scale_color_manual(values = c("pink", "pink")) +
theme_bw()