Basa_Luis_Homework_2
2024-01-28
# List of packages
packages <- c("tidyverse", "fst", "modelsummary", "viridis") # 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 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 3.4.4 ✔ 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## [[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"spain_data <- read.fst("spain_data.fst")spain_data <- spain_data %>%
mutate(
trstplt = ifelse(trstplt %in% c(77, 88, 99), NA, trstplt)
)table(spain_data$trstplt)##
## 0 1 2 3 4 5 6 7 8 9 10
## 5165 1830 2329 2441 2085 2890 1154 639 355 80 71spain_data$year <- NA
replacements <- c(2002, 2004, 2006, 2008, 2010, 2012, 2014, 2016, 2018, 2020)
for (i in 1:10) {
spain_data$year[spain_data$essround == i] <- replacements[i]
}table(spain_data$year)##
## 2002 2004 2006 2008 2010 2012 2014 2016 2018 2020
## 1729 1663 1876 2576 1885 1889 1925 1958 1668 2283trust_by_year <- spain_data %>%
group_by(year) %>%
summarize(mean_trust = mean(trstplt, na.rm = TRUE))
trust_by_year## # A tibble: 10 × 2
## year mean_trust
## <dbl> <dbl>
## 1 2002 3.41
## 2 2004 3.66
## 3 2006 3.49
## 4 2008 3.32
## 5 2010 2.72
## 6 2012 1.91
## 7 2014 2.23
## 8 2016 2.40
## 9 2018 2.55
## 10 2020 1.94ggplot(trust_by_year, aes(x = year, y = mean_trust)) +
geom_line(color = "black", size = 1) +
geom_point(color = "red", size = 2) +
labs(title = "Spain Trust in Parliament 2002-2020",
x = "Survey Year",
y = "Average Trust (0-10) scale") +
ylim(0, 7.5) + theme_minimal()## 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.
Therefore, based on the visual we can observe a slight gradual decline
in parliament trust as the years progress
#PROMT 2
Unlike France and Italy, Norway is shown to have a gradual increase in trust in parliament as the years progress. Further, Italy seems to have experienced a steeper decline in trust from 2002 to ~2010 as well as
#PROMPT 3
italy_data <- read.fst("italy_data.fst")italy_data <- italy_data %>%
mutate(clsprty = ifelse(clsprty == 2, 0, ifelse(clsprty %in% c(7, 8, 9), NA, clsprty))
)
italy_data <- italy_data %>%
mutate(
gndr = case_when(
gndr == 1 ~ "Male",
gndr == 2 ~ "Female",
TRUE ~ NA_character_
))clsprty_percentages <- italy_data %>%
filter(!is.na(clsprty), !is.na(gndr))%>%
group_by(gndr, clsprty) %>%
summarize(count = n(), .groups = 'drop') %>%
mutate(percentage = count / sum(count) *100)
clsprty_percentages## # A tibble: 4 × 4
## gndr clsprty count percentage
## <chr> <dbl> <int> <dbl>
## 1 Female 0 3228 34.2
## 2 Female 1 1686 17.9
## 3 Male 0 2593 27.5
## 4 Male 1 1936 20.5Therefore, we can see that the marginal percentage of Men who feel close to a particular political party is 20.5%
#PROMT 4
sweden_data <- read.fst("sweden_data.fst")sweden_data <- sweden_data %>%
mutate(
gndr = case_when(
gndr == 1 ~ "Male",
gndr == 2 ~ "Female",
TRUE ~ NA_character_
),
lrscale = case_when(
lrscale %in% 0:3 ~ "Left",
lrscale %in% 7:10 ~ "Right",
TRUE ~ NA_character_
)
)lrscale_percentages <- sweden_data %>%
filter(!is.na(lrscale), !is.na(gndr)) %>%
group_by(gndr, lrscale) %>%
summarise(count = n(), .groups = 'drop') %>%
mutate(percentage = count / sum(count)*100)
lrscale_percentages## # A tibble: 4 × 4
## gndr lrscale count percentage
## <chr> <chr> <int> <dbl>
## 1 Female Left 2296 23.0
## 2 Female Right 2530 25.3
## 3 Male Left 2062 20.6
## 4 Male Right 3107 31.1lrscale_plot_v2 <- ggplot(lrscale_percentages, aes(x = percentage, y = reorder(gndr, -percentage), fill = gndr))+
geom_col() +
coord_flip() +
guides(fill = "none") +
facet_wrap(~ lrscale, nrow = 1) +
labs(x= "Percentage of Respondents",
y = NULL,
title = "Political Orientation by Gender",
subtitle = "Comparing the percentage distribution of Left vs. Right for Sweden") +
theme(plot.title = element_text(size = 16, face = "bold"),
plot.subtitle = element_text(size = 12),
axis.title.y = element_blank(),
legend.position = "bottom"
)
lrscale_plot_v2
#PROMPT 5
hungary_data <- read.fst("hungary_data.fst")hungary_data <- hungary_data %>%
mutate(clsprty = ifelse(clsprty == 2, 0, ifelse(clsprty %in% c(7, 8, 9), NA, clsprty))
)hungary_data <- hungary_data %>%
mutate(
geo = recode(as.character(domicil),
'1' = "Urban",
'2' = "Urban",
'3' = "Rural",
'4' = "Rural",
'5' = "Rural",
'7' = NA_character_,
'8' = NA_character_,
'9' = NA_character_)
) %>%
filter(!is.na(clsprty), !is.na(geo))cond <- hungary_data %>%
count(clsprty, geo) %>%
group_by(geo) %>%
mutate(prob = n / sum(n))
cond## # A tibble: 4 × 4
## # Groups: geo [2]
## clsprty geo n prob
## <dbl> <chr> <int> <dbl>
## 1 0 Rural 6275 0.554
## 2 0 Urban 2395 0.512
## 3 1 Rural 5055 0.446
## 4 1 Urban 2283 0.488Therefore, the conditional probability of NOT feeling close to any particular party given that the person lives in a rural area is 55.38%