homework 6
Huang_helen
2023-11-04
#Mission 1
packages <- c("tidyverse", "modelsummary", "forcats", "RColorBrewer",
"fst", "viridis", "knitr", "kableExtra", "rmarkdown", "ggridges", "viridis", "questionr")setwd("C:\\Users\\helen\\OneDrive\\Desktop\\soc202")
library(fst)
ess <- read_fst("All-ESS-Data.fst")
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
## Loading required package: viridisLite
##
##
## Attaching package: 'kableExtra'
##
##
## The following object is masked from 'package:dplyr':
##
## group_rows## [[1]]
## [1] "lubridate" "forcats" "stringr" "dplyr" "purrr" "readr"
## [7] "tidyr" "tibble" "ggplot2" "tidyverse" "fstcore" "fst"
## [13] "stats" "graphics" "grDevices" "utils" "datasets" "methods"
## [19] "base"
##
## [[2]]
## [1] "modelsummary" "lubridate" "forcats" "stringr" "dplyr"
## [6] "purrr" "readr" "tidyr" "tibble" "ggplot2"
## [11] "tidyverse" "fstcore" "fst" "stats" "graphics"
## [16] "grDevices" "utils" "datasets" "methods" "base"
##
## [[3]]
## [1] "modelsummary" "lubridate" "forcats" "stringr" "dplyr"
## [6] "purrr" "readr" "tidyr" "tibble" "ggplot2"
## [11] "tidyverse" "fstcore" "fst" "stats" "graphics"
## [16] "grDevices" "utils" "datasets" "methods" "base"
##
## [[4]]
## [1] "RColorBrewer" "modelsummary" "lubridate" "forcats" "stringr"
## [6] "dplyr" "purrr" "readr" "tidyr" "tibble"
## [11] "ggplot2" "tidyverse" "fstcore" "fst" "stats"
## [16] "graphics" "grDevices" "utils" "datasets" "methods"
## [21] "base"
##
## [[5]]
## [1] "RColorBrewer" "modelsummary" "lubridate" "forcats" "stringr"
## [6] "dplyr" "purrr" "readr" "tidyr" "tibble"
## [11] "ggplot2" "tidyverse" "fstcore" "fst" "stats"
## [16] "graphics" "grDevices" "utils" "datasets" "methods"
## [21] "base"
##
## [[6]]
## [1] "viridis" "viridisLite" "RColorBrewer" "modelsummary" "lubridate"
## [6] "forcats" "stringr" "dplyr" "purrr" "readr"
## [11] "tidyr" "tibble" "ggplot2" "tidyverse" "fstcore"
## [16] "fst" "stats" "graphics" "grDevices" "utils"
## [21] "datasets" "methods" "base"
##
## [[7]]
## [1] "knitr" "viridis" "viridisLite" "RColorBrewer" "modelsummary"
## [6] "lubridate" "forcats" "stringr" "dplyr" "purrr"
## [11] "readr" "tidyr" "tibble" "ggplot2" "tidyverse"
## [16] "fstcore" "fst" "stats" "graphics" "grDevices"
## [21] "utils" "datasets" "methods" "base"
##
## [[8]]
## [1] "kableExtra" "knitr" "viridis" "viridisLite" "RColorBrewer"
## [6] "modelsummary" "lubridate" "forcats" "stringr" "dplyr"
## [11] "purrr" "readr" "tidyr" "tibble" "ggplot2"
## [16] "tidyverse" "fstcore" "fst" "stats" "graphics"
## [21] "grDevices" "utils" "datasets" "methods" "base"
##
## [[9]]
## [1] "rmarkdown" "kableExtra" "knitr" "viridis" "viridisLite"
## [6] "RColorBrewer" "modelsummary" "lubridate" "forcats" "stringr"
## [11] "dplyr" "purrr" "readr" "tidyr" "tibble"
## [16] "ggplot2" "tidyverse" "fstcore" "fst" "stats"
## [21] "graphics" "grDevices" "utils" "datasets" "methods"
## [26] "base"
##
## [[10]]
## [1] "ggridges" "rmarkdown" "kableExtra" "knitr" "viridis"
## [6] "viridisLite" "RColorBrewer" "modelsummary" "lubridate" "forcats"
## [11] "stringr" "dplyr" "purrr" "readr" "tidyr"
## [16] "tibble" "ggplot2" "tidyverse" "fstcore" "fst"
## [21] "stats" "graphics" "grDevices" "utils" "datasets"
## [26] "methods" "base"
##
## [[11]]
## [1] "ggridges" "rmarkdown" "kableExtra" "knitr" "viridis"
## [6] "viridisLite" "RColorBrewer" "modelsummary" "lubridate" "forcats"
## [11] "stringr" "dplyr" "purrr" "readr" "tidyr"
## [16] "tibble" "ggplot2" "tidyverse" "fstcore" "fst"
## [21] "stats" "graphics" "grDevices" "utils" "datasets"
## [26] "methods" "base"
##
## [[12]]
## [1] "questionr" "ggridges" "rmarkdown" "kableExtra" "knitr"
## [6] "viridis" "viridisLite" "RColorBrewer" "modelsummary" "lubridate"
## [11] "forcats" "stringr" "dplyr" "purrr" "readr"
## [16] "tidyr" "tibble" "ggplot2" "tidyverse" "fstcore"
## [21] "fst" "stats" "graphics" "grDevices" "utils"
## [26] "datasets" "methods" "base"#Mission 2
france_data <- ess %>%
filter(cntry == "FR") write_fst(france_data, "./france_data.fst") #Mission 3
rm(list=ls()); gc()## used (Mb) gc trigger (Mb) max used (Mb)
## Ncells 1259907 67.3 1954354 104.4 1954354 104.4
## Vcells 2135657 16.3 1506453632 11493.4 1357095510 10353.9dgb <- read_fst( "./france_data.fst")#Mission 4
dgb$year <- NA
replacements <- c(2002, 2004, 2006, 2008, 2010, 2012, 2014, 2016, 2018, 2020)
for(i in 1:10){
dgb$year[dgb$essround == i] <- replacements[i]
}
france_data <- dgb
france_data_table_subset <- france_data %>%
mutate(
happy = ifelse(happy %in% c(77, 88, 99), NA, happy),
health = ifelse(health %in% c(7, 8, 9), NA, health),
impsafe = ifelse(impsafe %in% c(7, 8, 9), NA, impsafe)
)
summary_table <- datasummary_skim(france_data_table_subset %>% select(happy, health, impsafe), 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 |
|---|---|---|---|---|---|---|---|
happy | 12 | 0 | 7.2 | 1.8 | 0.0 | 8.0 | 10.0 |
health | 6 | 0 | 2.3 | 0.9 | 1.0 | 2.0 | 5.0 |
impsafe | 7 | 2 | 2.7 | 1.4 | 1.0 | 2.0 | 6.0 |
france_data_v2 <- france_data_table_subset %>%
rename(
`How happy are you` = happy,
`How good is your general health` = health,
`importance of living somewhere safe` = impsafe
)
summary_table_v2 <- datasummary_skim(france_data_v2 %>% select(`How happy are you`,`How good is your general health`, `importance of living somewhere safe`), 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.#France_summary_table_v2 <- add_header_lines(France_summary_table_v2, values = "Table1 :Descriptive Statistics for socio-demographic variables")#Mission 5
avg_happy_by_year <- aggregate(happy ~ year + imprich, data=france_data_table_subset, mean)
p1 <- ggplot(avg_happy_by_year, aes(x=year, y=happy, color=as.factor(imprich))) +
geom_line(aes(group=imprich)) +
labs(title="Mean of Happiness by year in relation to",
subtitle = "the importance of being rich in the France",
x="Survey Year",
y="Happiness 0 = extremely unhappy - 10 = extremely happy") +
scale_color_discrete(name="How happy are you", labels=c("Very much like me", "Like me", "Somewhat like me", "A little like me", "Not like me", "Not like me at all")) +
theme_minimal()
p1
ggsave(filename = "plot1.pdf", plot = p1, device = "pdf", width = 8, height = 6)