Homework_6_Adam_Chmelauskas
AC
2023-10-30
Mission 1 & Setup
# List of packages
packages <- c("tidyverse", "modelsummary", "forcats", "RColorBrewer",
"fst", "viridis", "knitr", "rmarkdown", "ggridges", "viridis", "questionr", "flextable", "infer") # 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)## ── 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"setwd("C:/Users/2expl/Desktop/UToronto/Year 2/SOC202")
# read data
ess <- read_fst("All-ESS-Data.fst")Mission 2
# Subsetting Great Britan from ESS
GB_data <- ess %>%
filter(cntry == "GB")
# Saving Great Britan subset to the project folder
write_fst(GB_data, "C:/Users/2expl/Desktop/UToronto/Year 2/SOC202/Chmelauskas_Adam_Project_202/GB_data.fst") Mission 3
#Clearing enviroment and loading chosen subset for easier manipulation
rm(list=ls()); gc()## used (Mb) gc trigger (Mb) max used (Mb)
## Ncells 1258520 67.3 2273074 121.4 2273074 121.4
## Vcells 2128076 16.3 1256984332 9590.1 1361139193 10384.7GB_df <- read_fst("C:/Users/2expl/Desktop/UToronto/Year 2/SOC202/Chmelauskas_Adam_Project_202/GB_data.fst")Mission 4
#Subsetting the three Variables of interest and removing any non-answer values from the dataset.
GB_data_subset <- GB_df %>%
filter(cntry == "GB") %>%
mutate(
cgtsmke = ifelse(cgtsmke %in% c(7, 8, 9), NA, cgtsmke),
health = ifelse(health %in% c(7, 8, 9), NA, health),
edulvla = ifelse(edulvla %in% c(55, 77, 88, 99), NA, edulvla)
)
#renaming variables for easier understanding in output tables
GB_data_v2 <- GB_data_subset %>%
select(cgtsmke, health, edulvla) %>%
rename(
`How Often Does the Respondent Smoke` = cgtsmke,
`General Health` = health,
`Highest Education Level` = edulvla
)
#Creating summary table (via flexTable) using updated variables
summary_table_v2 <- datasummary_skim(GB_data_v2, 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.#saving to project folder in .Docx format
flextable::save_as_docx(summary_table_v2, path = "C:/Users/2expl/Desktop/UToronto/Year 2/SOC202/Chmelauskas_Adam_Project_202/Homework5_summary_table_GB.docx", # change name to whatever you would like
width = 5.0, height = 5.0)
summary_table_v2
| Unique (#) | Missing (%) | Mean | SD | Min | Median | Max |
|---|---|---|---|---|---|---|---|
How Often Does the Respondent Smoke | 6 | 89 | 3.6 | 1.5 | 1.0 | 4.0 | 5.0 |
General Health | 6 | 0 | 2.1 | 1.0 | 1.0 | 2.0 | 5.0 |
Highest Education Level | 5 | 59 | 2.9 | 1.7 | 1.0 | 2.0 | 5.0 |
Mission 9
#set working directory to open ESS
setwd("C:/Users/2expl/Desktop/UToronto/Year 2/SOC202")
# read data
ess <- read_fst("All-ESS-Data.fst")
# Filter the data for Millennial and Boomers
millennials_data <- ess %>%
filter(cntry == "GB", yrbrn > 1980 & yrbrn < 1997)
boomers_data <- ess %>%
filter(cntry == "GB", yrbrn > 1945 & yrbrn < 1965)
# Cleaning the variables (millennial)
millennials_data_cleaned <- millennials_data %>%
mutate(
cgtsmke = ifelse(cgtsmke %in% c(7, 8, 9), NA, cgtsmke)
) %>%
group_by(yrbrn) %>%
summarise(
avg_cgtsmke.M = mean(cgtsmke, na.rm = TRUE)
)
#leaning the variables (Boomers)
boomers_data_cleaned <- boomers_data %>%
mutate(
cgtsmke = ifelse(cgtsmke %in% c(7, 8, 9), NA, cgtsmke)
) %>%
group_by(yrbrn) %>%
summarise(
avg_cgtsmke.B = mean(cgtsmke, na.rm = TRUE),
)
ggplot() +
geom_point(data = millennials_data_cleaned, aes(x = yrbrn, y = avg_cgtsmke.M), color = "blue", alpha = 0.6) +
geom_point(data = boomers_data_cleaned, aes(x = yrbrn, y = avg_cgtsmke.B), color = "red", alpha = 0.6) +
geom_smooth(data = millennials_data_cleaned, aes(x = yrbrn, y = avg_cgtsmke.M), method = "lm", formula = y ~ poly(x, 1), color = "blue") +
geom_smooth(data = boomers_data_cleaned, aes(x = yrbrn, y = avg_cgtsmke.B), method = "lm", formula = y ~ poly(x, 1), color = "red") +
labs(
title = "Average Smoking Habits by Birth Year in the United Kingdom (Millennials vs. Boomers)",
x = "Year of Birth",
y = "Average Frequancy of Smoking"
) +
scale_color_manual(values = c("black", "black"))