Nasrawi_Simona_Homework_2
2024-01-23
#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 2.1.4
## ✔ 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"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 <- read.fst("spain_data.fst")spain_data <- spain_data %>%
mutate(
trstplt = ifelse(trstplt %in% c(77, 88, 99), NA, trstplt), # set values 77, 88, and 99 to NA.
)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 2283ptrust_by_year <- spain_data %>%
group_by(year) %>%
summarize(mean_trust = mean(trstplt, na.rm = TRUE))
ptrust_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(ptrust_by_year, aes(x = year, y = mean_trust)) +
geom_line(color = "blue", size = 1) +
geom_point(color = "red", size = 3) +
labs(title = "Trust in Parliament 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.
ggplot(ptrust_by_year, aes(x = year, y = mean_trust)) +
geom_line(aes(group = 1), color = "blue", size = 1, linetype = "longdash") +
labs(title = "Trust in Parliament in Spain (2002-2020)",
x = "Survey Year",
y = "Average Trust (0-10 scale)") +
ylim(0, 10) +
theme_minimal() +
theme(legend.position = "none") 
Trust in Parliament, in Spain, has slowly decreased overtime.
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.
Based on the figure produced above called task2_plot, the proportion of people in France that feel close to a political party is in-between the other countries of Italy and Norway. Notably, Norway has the largest proportion of people that feel close to a political party, while Italy has the smallest proportion. The proportion of individuals that feel close to a political party is declining over time in France and Italy. Conversely, in Norway, while the proportion of individuals that feel close to a political party is also declining over time, this trend is becoming more steady and stable in the recent years.
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 <- read.fst("italy_data.fst")italy_data <- italy_data %>%
# Modify 'clsprty' column: set values of 2 to 0, and values in 7, 8, 9 to NA.
mutate(
clsprty = ifelse(clsprty == 2, 0, ifelse(clsprty %in% c(7, 8, 9), NA, clsprty))
) %>%
mutate(
yrbrn = ifelse(yrbrn %in% c(7777, 8888, 9999), NA, yrbrn)
)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) %>%
summarise(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 20.5The marginal percentage of Italian men who feel close to a particular political party is 20.50196%.
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 <- read.fst("sweden_data.fst")sweden_data <- sweden_data %>%
mutate(
gndr = case_when(
gndr == 1 ~ "Male",
gndr == 2 ~ "Female",
TRUE ~ NA_character_ # Setting anything that is not 1 or 2 to NA
),
lrscale = case_when(
lrscale %in% 0:3 ~ "Left", # Left-wing (0 to 3)
lrscale %in% 7:10 ~ "Right", # Right-wing (7 to 10)
TRUE ~ NA_character_ # Moderate (4, 5, 6) and special codes (77, 88, 99) set to NA
)
) lrscale_spercentages <- 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_spercentages ## # 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_splot <- ggplot(lrscale_spercentages, aes(x = lrscale, y = percentage, fill = lrscale)) +
geom_bar(stat = "identity", position = position_dodge()) +
facet_wrap(~ gndr, scales = "fixed") +
scale_fill_brewer(palette = "Set1") +
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")
# Display the ggplot object
lrscale_splot
lrscale_plot_sv2 <- ggplot(lrscale_spercentages,
aes(x = percentage,
y = reorder(gndr, -percentage),
fill = gndr)) +
# Create horizontal bar chart
geom_col() +
coord_flip() +
# Remove fill color legend
guides(fill = "none") +
# Split the plot based on Political Orientation
facet_wrap(~ lrscale, nrow = 1) +
# Labels and titles for the plot
labs(x = "Percentage of Respondents",
y = NULL,
title = "Political Orientation by Gender",
subtitle = "Comparing the percentage distribution of left vs. right for Sweden (2002-2020)") +
# Adjust visual properties of the plot
theme(plot.title = element_text(size = 16, face = "bold"),
plot.subtitle = element_text(size = 12),
axis.title.y = element_blank(),
legend.position = "bottom")
# Display the ggplot object
lrscale_plot_sv2
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 <- read.fst("hungary_data.fst")hungary_data <- hungary_data %>%
# Modify 'clsprty' column: set values of 2 to 0, and values in 7, 8, 9 to NA.
mutate(
clsprty = ifelse(clsprty == 2, 0, ifelse(clsprty %in% c(7, 8, 9), NA, clsprty))
) %>%
mutate(
yrbrn = ifelse(yrbrn %in% c(7777, 8888, 9999), NA, yrbrn)
)clsprty_hproportions <- hungary_data %>%
filter(!is.na(yrbrn) & yrbrn >= 1920 & !is.na(clsprty)) %>%
group_by(yrbrn, clsprty) %>%
# Count the number of rows (i.e., occurrences) for each combination of 'yrbrn' and 'clsprty'
tally() %>%
# Calculate the proportion of each 'clsprty' value within each 'yrbrn' group
mutate(proportion = n / sum(n)) %>%
ungroup()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)) # Removing rows with NA in clsprty or geocondp <- hungary_data %>%
count(clsprty, geo) %>%
group_by(geo) %>%
mutate(prob = n / sum(n))
condp## # 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 0.488In Hungary, the conditional probability of not feeling close to any particular party given that the person lives in a rural area is 0.5538394.