Sohn_Jio_Homework2
Jio Sohn
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")italy_data <- read.fst("italy_data.fst")sweden_data <- read.fst("sweden_data.fst")hungary_data <- read.fst("hungary_data.fst")Task 1
Provide code and answer.
Prompt: in the tutorial, we calculated the average trust in others for France and visualized it. Using instead the variable ‘Trust in Parliament’ (trstplt) and the country of Spain (country file provided on course website), visualize the average trust by survey year. You can truncate the y-axis if you wish. Provide appropriate titles and labels given the changes. What are your main takeaways based on the visual (e.g., signs of increase, decrease, or stall)?
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 = "purple", size = 1) +
geom_point(color = "green", size = 3) +
labs(title = "Trust in Politicians in Spain (2002-2020)",
x = "Survey Year",
y = "Average Trust (0-10 scale)") +
ylim(0, 10) +
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.
A: The trust in politicians seem to be in a general decrease during the surveyed years. There is steeper decline from 2004 to 2012, and slight incline from 2012 to 2018.
Task 2
Provide answer only.
Prompt and question: Based on the figure we produced above called task2_plot, tell us: what are your main takeaways regarding France relative to Italy and Norway? Make sure to be concrete and highlight at least two important comparative trends visualized in the graph.
A: France has a higher proportion of individuals that feel close to a political party than Italy, but a lower proportion than Norway. All three countries are experiencing a decline trend, with France having the steepest decline. France’s proportion is approaching Italy’s.
Task 3
Provide code and answer.
Question: What is the marginal percentage of Italian men who feel close to a particular political party?
italy_data <- italy_data %>%
mutate(
gndr = case_when(
gndr == 1 ~ "Male",
gndr == 2 ~ "Female",
TRUE ~ NA_character_
),
clsprty = case_when(
clsprty %in% 1 ~ "Yes",
clsprty %in% 2 ~ "No",
TRUE ~ NA_character_
)
) clsprty_percentages <- italy_data %>%
filter(!is.na(clsprty), !is.na(gndr)) %>%
group_by(gndr, clsprty) %>%
summarise(count = n(), .groups = 'drop') %>%
mutate(percentage = count / sum(count) * 100)
clsprty_percentages## # A tibble: 4 × 4
## gndr clsprty count percentage
## <chr> <chr> <int> <dbl>
## 1 Female No 3228 34.2
## 2 Female Yes 1686 17.9
## 3 Male No 2593 27.5
## 4 Male Yes 1936 20.5A: The marginal percentage of Italian men who feel close to a political party is 20.5%
Task 4
Provide code and output only.
Prompt: In the tutorial, we calculated then visualized the percentage distribution for left vs. right by gender for France. Your task is to replicate the second version of the visualization but for the country of Sweden instead.
sweden_data <- sweden_data %>%
mutate(
gndr = case_when(
gndr == 1 ~ "Male",
gndr == 2 ~ "Female",
TRUE ~ NA_character_ # Set anything that is not 1 or 2 to NA
),
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 <- ggplot(lrscale_percentages, aes(x = lrscale, y = percentage, fill = lrscale)) +
geom_bar(stat = "identity", position = position_dodge()) + # Dodged bar chart
facet_wrap(~ gndr, scales = "fixed") +
scale_fill_brewer(palette = "Set3") +
labs(
title = "Political Orientation (Left vs. Right) by Gender in Sweden",
x = "Political Orientation",
y = "Percentage of Respondents",
fill = "Orientation"
) +
theme_minimal() +
theme(legend.position = "bottom")
lrscale_plot
Task 5
Provide code and answer: In Hungary, what is the conditional probability of NOT feeling close to any particular party given that the person lives in a rural area?
hungary_data <- hungary_data %>%
mutate(
clsprty = case_when(
clsprty %in% 1 ~ "Yes",
clsprty %in% 2 ~ "No",
TRUE ~ NA_character_
)
) 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))condprob <- hungary_data %>%
count(clsprty, geo) %>%
group_by(geo) %>%
mutate(prob = n / sum(n))
condprob## # A tibble: 4 × 4
## # Groups: geo [2]
## clsprty geo n prob
## <chr> <chr> <int> <dbl>
## 1 No Rural 6275 0.554
## 2 No Urban 2395 0.512
## 3 Yes Rural 5055 0.446
## 4 Yes Urban 2283 0.488A: The conditional probability of someone who lives in a rural area and does not feel close to a political party is 55.38%