Problem set 2
ziyi su
2024-07-15
# List of packages
packages <- c("tidyverse", "fst", "modelsummary", "viridis", "kableExtra", "flextable", "officer") # add any you need here
# 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)## Warning: package 'ggplot2' was built under R version 4.3.3## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.2 ✔ readr 2.1.5
## ✔ forcats 1.0.0 ✔ stringr 1.5.0
## ✔ ggplot2 3.5.1 ✔ tibble 3.2.1
## ✔ lubridate 1.9.2 ✔ tidyr 1.3.0
## ✔ purrr 1.0.1
## ── 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## Warning: package 'fst' was built under R version 4.3.3## Warning: package 'modelsummary' was built under R version 4.3.3## `modelsummary` 2.0.0 now uses `tinytable` as its default table-drawing
## backend. Learn more at: https://vincentarelbundock.github.io/tinytable/
##
## Revert to `kableExtra` for one session:
##
## options(modelsummary_factory_default = 'kableExtra')
## options(modelsummary_factory_latex = 'kableExtra')
## options(modelsummary_factory_html = 'kableExtra')
##
## Silence this message forever:
##
## config_modelsummary(startup_message = FALSE)## Warning: package 'viridis' was built under R version 4.3.3## Loading required package: viridisLite
##
## Attaching package: 'kableExtra'
##
## The following object is masked from 'package:dplyr':
##
## group_rows## Warning: package 'flextable' was built under R version 4.3.3##
## Attaching package: 'flextable'
##
## The following objects are masked from 'package:kableExtra':
##
## as_image, footnote
##
## The following object is masked from 'package:purrr':
##
## compose## Warning: package 'officer' was built under R version 4.3.3## [[1]]
## [1] "lubridate" "forcats" "stringr" "dplyr" "purrr" "readr"
## [7] "tidyr" "tibble" "ggplot2" "tidyverse" "stats" "graphics"
## [13] "grDevices" "utils" "datasets" "methods" "base"
##
## [[2]]
## [1] "fst" "lubridate" "forcats" "stringr" "dplyr" "purrr"
## [7] "readr" "tidyr" "tibble" "ggplot2" "tidyverse" "stats"
## [13] "graphics" "grDevices" "utils" "datasets" "methods" "base"
##
## [[3]]
## [1] "modelsummary" "fst" "lubridate" "forcats" "stringr"
## [6] "dplyr" "purrr" "readr" "tidyr" "tibble"
## [11] "ggplot2" "tidyverse" "stats" "graphics" "grDevices"
## [16] "utils" "datasets" "methods" "base"
##
## [[4]]
## [1] "viridis" "viridisLite" "modelsummary" "fst" "lubridate"
## [6] "forcats" "stringr" "dplyr" "purrr" "readr"
## [11] "tidyr" "tibble" "ggplot2" "tidyverse" "stats"
## [16] "graphics" "grDevices" "utils" "datasets" "methods"
## [21] "base"
##
## [[5]]
## [1] "kableExtra" "viridis" "viridisLite" "modelsummary" "fst"
## [6] "lubridate" "forcats" "stringr" "dplyr" "purrr"
## [11] "readr" "tidyr" "tibble" "ggplot2" "tidyverse"
## [16] "stats" "graphics" "grDevices" "utils" "datasets"
## [21] "methods" "base"
##
## [[6]]
## [1] "flextable" "kableExtra" "viridis" "viridisLite" "modelsummary"
## [6] "fst" "lubridate" "forcats" "stringr" "dplyr"
## [11] "purrr" "readr" "tidyr" "tibble" "ggplot2"
## [16] "tidyverse" "stats" "graphics" "grDevices" "utils"
## [21] "datasets" "methods" "base"
##
## [[7]]
## [1] "officer" "flextable" "kableExtra" "viridis" "viridisLite"
## [6] "modelsummary" "fst" "lubridate" "forcats" "stringr"
## [11] "dplyr" "purrr" "readr" "tidyr" "tibble"
## [16] "ggplot2" "tidyverse" "stats" "graphics" "grDevices"
## [21] "utils" "datasets" "methods" "base"gss <- load("gss2022.RData")
gss <- dfTask 1: Data Cleaning and Recoding
Objective: Clean and recode the variables to ensure they are ready for analysis.
Recode polviews into three categories: “Liberal”, “Moderate”, and “Conservative”. Clean sex, degree, and race but retain the relevant categories.
# Recode and clean variables
gss <- gss %>%
mutate(
polviews = case_when(
polviews %in% c("extremely liberal", "liberal", "slightly liberal") ~ "Liberal",
polviews %in% c("moderate") ~ "Moderate",
polviews %in% c("extremely conservative", "conservative", "slightly conservative") ~ "Conservative",
TRUE ~ NA_character_
),
sex = case_when(
sex %in% c("male", "female") ~ sex,
TRUE ~ NA_character_
),
degree = case_when(
degree %in% c("less than high school", "high school", "junior college", "bachelor", "graduate") ~ degree,
TRUE ~ NA_character_
),
race = case_when(
race %in% c("white", "black", "other") ~ race,
TRUE ~ NA_character_
)
)Task 2: Data Summary
Objective: Generate a summary table for selected variables using the datasummary_skim function from the modelsummary package.
Select the variables of interest: polviews, sex, degree, and race.
Generate a categorical summary table for these variables, clean the labels, and display it using the flextable package for styling.
# Create summary for selected categorical variables with flextable
categorical_summary_flextable <- datasummary_skim(
gss %>%
dplyr::select(polviews, sex, degree, race),
type = "categorical",
output = "flextable"
)## Warning: Inline histograms in `datasummary_skim()` are only supported for tables
## produced by the `tinytable` backend.# Customize the table appearance with flextable
categorical_summary_flextable <- categorical_summary_flextable %>%
set_header_labels(Variable = "Variable", Value = "Value", Freq = "Frequency") %>%
theme_box() %>%
bold(part = "header") %>%
bg(part = "header", bg = "#4CAF50") %>%
color(part = "header", color = "white") %>%
border_remove() %>%
border_inner_v(border = fp_border(color = "black", width = 1)) %>%
autofit()
print(categorical_summary_flextable)## a flextable object.
## col_keys: ` `, ` `, `N`, `%`
## header has 1 row(s)
## body has 14 row(s)
## original dataset sample:
## N %
## 1 polviews Conservative 21122 29.2
## 2 Liberal 17604 24.3
## 3 NA 33664 46.5
## 4 sex female 40301 55.7
## 5 male 31977 44.2Task 3: Visualization of Political Views by Gender
Objective: Create a bar chart showing the distribution of political views by gender.
Create a bar chart showing the distribution of political views by gender. Use a color palette that clearly differentiates the categories.
# Filter the data to remove NA values
gss_filtered <- gss %>%
filter(!is.na(polviews), !is.na(sex))
# Create a bar chart showing the distribution of political views by gender
ggplot(gss_filtered, aes(x = polviews, fill = sex)) +
geom_bar(position = "dodge") +
scale_fill_brewer(palette = "Set2") +
labs(title = "Distribution of Political Views by Gender",
x = "Political Views",
y = "Count",
fill = "Gender") +
theme_minimal() +
theme(legend.position = "bottom")
Task 4: Trends Over Time
Objective: Visualize trends in religious attendance over time.
Select the year and attend variables from the GSS data.
Create a line plot showing the proportion of each category of religious attendance over time.
# Select the year and attend variables, and filter out NA values
gss_filtered <- gss %>%
select(year, attend) %>%
filter(!is.na(year), !is.na(attend))
# Summarize the data by year and attendance
gss_yearly <- gss_filtered %>%
group_by(year, attend) %>%
summarize(count = n(), .groups = 'drop') %>%
group_by(year) %>%
mutate(total = sum(count),
proportion = count / total)
# Create a line plot to visualize the trends in religious attendance over time
ggplot(gss_yearly, aes(x = year, y = proportion, color = attend, group = attend)) +
geom_line(size = 1.2) + # Create lines for each attendance category with increased line size
scale_color_brewer(palette = "Set3") + # Use a color palette for better differentiation
labs(title = "Trends in Religious Attendance Over Time", # Add plot title
x = "Year", # Label x-axis
y = "Proportion", # Label y-axis
color = "Religious Attendance") + # Label the legend
theme_minimal() + # Apply a minimal theme to the plot
theme(legend.position = "bottom") # Position the legend at the bottom## Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
## ℹ Please use `linewidth` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
Task 5: Comparison Trends
Objective: Create a stacked bar chart showing the distribution of fejobaff (preferential hiring) across different age groups.
Create an age group variable by categorizing age into “18-29”, “30-44”, “45-59”, “60+”. Create a stacked bar chart showing the distribution of the fejobaff response categories for each age group.
# Create age groups based on age variable
gss <- gss %>%
mutate(age_group = case_when(
age >= 18 & age <= 29 ~ "18-29",
age >= 30 & age <= 44 ~ "30-44",
age >= 45 & age <= 59 ~ "45-59",
age >= 60 ~ "60+",
TRUE ~ NA_character_
))
# Filter out rows with NA values in fejobaff
gss_filtered <- gss %>%
filter(!is.na(fejobaff), !is.na(age_group))
# Create a stacked bar chart showing distribution of fejobaff across age groups
ggplot(gss_filtered, aes(x = age_group, fill = fejobaff)) +
geom_bar(position = "stack") +
labs(title = "Distribution of Preferential Hiring Responses by Age Group",
x = "Age Group",
y = "Count",
fill = "Preferential Hiring Response") +
theme_minimal() +
theme(axis.text.x = element_text(angle = 45, hjust = 1)) +
scale_fill_brewer(palette = "Set2") # Choose a suitable color palette
## End