Vila_Lacey_Homework_2
lacey vila
2024-01-23
R Markdown
This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.
When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:
summary(cars)## speed dist
## Min. : 4.0 Min. : 2.00
## 1st Qu.:12.0 1st Qu.: 26.00
## Median :15.0 Median : 36.00
## Mean :15.4 Mean : 42.98
## 3rd Qu.:19.0 3rd Qu.: 56.00
## Max. :25.0 Max. :120.00Including Plots
You can also embed plots, for example:
Note that the echo = FALSE parameter was added to the
code chunk to prevent printing of the R code that generated the
plot.
# 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"france_data <- read.fst("france_data.fst")table(france_data$ppltrst)##
## 0 1 2 3 4 5 6 7 8 9 10 77 88
## 1240 612 1575 2364 2294 5238 2096 2114 1109 231 148 3 14france_data$year <- NA
replacements <- c(2002, 2004, 2006, 2008, 2010, 2012, 2014, 2016, 2018, 2020)
for(i in 1:10){
france_data$year[france_data$essround == i] <- replacements[i]
}table(france_data$year)##
## 2002 2004 2006 2008 2010 2012 2014 2016 2018 2020
## 1503 1806 1986 2073 1728 1968 1917 2070 2010 1977trust_by_year <- france_data %>%
group_by(year) %>%
summarize(mean_trust = mean(ppltrst, na.rm = TRUE))
trust_by_year## # A tibble: 10 × 2
## year mean_trust
## <dbl> <dbl>
## 1 2002 4.75
## 2 2004 4.57
## 3 2006 4.47
## 4 2008 4.57
## 5 2010 4.38
## 6 2012 4.48
## 7 2014 4.71
## 8 2016 4.58
## 9 2018 4.69
## 10 2020 4.77ggplot(trust_by_year, aes(x = year, y = mean_trust)) +
geom_line(color = "lightpink", size = 1) + # Line to show the trend
geom_point(color = "skyblue", size = 3) + # Points to highlight each year's value
labs(title = "Trust in Others in France (2002-2020)",
x = "Survey Year",
y = "Average Trust (0-10 scale)") +
ylim(0, 10) + # Setting the y-axis limits from 0 to 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(trust_by_year, aes(x = year, y = mean_trust)) +
geom_line(aes(group = 1), color = "lightblue", size = 1, linetype = "longdash") + # Dashed line for the trend
# geom_point(aes(color = mean_trust), size = 3) + # if you want to try alternative + strive to keep improving
# scale_color_viridis(option = "D", end = 0.9, direction = -1) + # try the alternative, and try to keep improving
labs(title = "Trust in Others in France (2002-2020)",
x = "Survey Year",
y = "Average Trust (0-10 scale)") +
ylim(3.5, 5) + # change the numbers to truncate more or less or keep the full 0 to 10 scale
theme_minimal() + # Minimal theme for a clean look
theme(legend.position = "none") # Remove the legend
france_data <- france_data %>%
# Modify 'clsprty' column: set values of 2 to 0, and values in 7, 8, 9 to NA. Retain other values as is.
mutate(
clsprty = ifelse(clsprty == 2, 0, ifelse(clsprty %in% c(7, 8, 9), NA, clsprty))
) %>%
# Modify 'yrbrn' column: set specific values (7777, 8888, 9999) to NA.
mutate(
yrbrn = ifelse(yrbrn %in% c(7777, 8888, 9999), NA, yrbrn)
)# Start with the 'france_data' dataframe
clsprty_proportions <- france_data %>%
# Filter data to:
# 1. Exclude missing values in 'yrbrn'
# 2. Only include rows where 'yrbrn' is 1920 or later
# 3. Exclude missing values in 'clsprty'
filter(!is.na(yrbrn) & yrbrn >= 1920 & !is.na(clsprty)) %>%
# Group the data by 'yrbrn' (year of birth) and '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
# This is done by dividing the count of each 'clsprty' by the total count for that 'yrbrn'
mutate(proportion = n / sum(n)) %>%
# Remove the grouping to allow further manipulations on the dataframe if needed
ungroup()clsprtyplot <- ggplot(clsprty_proportions, aes(x = yrbrn, y = proportion, color = as.factor(clsprty))) + # Initialize the ggplot, setting 'yrbrn' as x-axis, 'proportion' as y-axis, and coloring by 'clsprty' (converted to a factor)
geom_point() + # Add points to the plot for each data point, representing each cohort's proportion
geom_smooth(method = 'loess', se = FALSE) + # Add a LOESS smoothed line to visualize the trend without standard error bands
labs(
title = "Proportions of Feeling Close to a Party by Cohort in France", # Title of the plot, specifically mentioning it's for France
x = "Cohort", # Label for the x-axis, representing the birth cohort
y = "Proportion" # Label for the y-axis, representing the proportion of respondents
) +
theme_minimal() + # Use a minimal theme for a cleaner look
theme(
panel.grid.major = element_blank(), # Remove major grid lines for a cleaner plot
panel.grid.minor = element_blank() # Remove minor grid lines as well
) +
scale_color_discrete(name = "Close to Party", labels = c("No", "Yes")) # Set the color scale as discrete with a legend titled "Close to Party" and labels as "No" and "Yes"
clsprtyplot # Display the plot## `geom_smooth()` using formula = 'y ~ x'
clsprty_proportions## # A tibble: 172 × 4
## yrbrn clsprty n proportion
## <dbl> <dbl> <int> <dbl>
## 1 1920 0 17 0.425
## 2 1920 1 23 0.575
## 3 1921 0 12 0.308
## 4 1921 1 27 0.692
## 5 1922 0 33 0.5
## 6 1922 1 33 0.5
## 7 1923 0 20 0.377
## 8 1923 1 33 0.623
## 9 1924 0 27 0.435
## 10 1924 1 35 0.565
## # ℹ 162 more rowsitaly_data <- read.fst("italy_data.fst")
norway_data <- read.fst("norway_data.fst")# Combine data from three countries (France, Norway, Italy) into a single dataset
combined_countries_data <- bind_rows(
france_data %>% mutate(cntry = "France"), # Add a new column 'cntry' with the value 'France' to france_data
norway_data %>% mutate(cntry = "Norway"), # Do the same for norway_data with 'Norway'
italy_data %>% mutate(cntry = "Italy") # And for italy_data with 'Italy'
) %>%
filter(!yrbrn %in% c(7777, 8888)) %>% # Remove rows where 'yrbrn' (year born) is either 7777 or 8888 (likely missing data codes)
mutate(
yrbrn = ifelse(yrbrn > 2005, NA, yrbrn), # Replace 'yrbrn' values greater than 2005 with NA (as they are invalid)
clsprty = ifelse(clsprty %in% c(7, 8, 9), NA, clsprty), # Replace 'clsprty' values of 7, 8, 9 with NA (considered as invalid or missing)
clsprty = ifelse(clsprty == 2, 0, clsprty) # Convert 'clsprty' value of 2 to 0 (recoding for analysis purposes)
)
# Compute proportions for 'clsprty' by 'yrbrn' for each country
clsprty_proportions_compare <- combined_countries_data %>%
filter(!is.na(yrbrn) & yrbrn >= 1920 & !is.na(clsprty)) %>% # Filter out rows with NA in 'yrbrn' and 'clsprty', and where 'yrbrn' is earlier than 1920
group_by(yrbrn, cntry) %>% # Group the data by 'yrbrn' (year born) and 'cntry' (country)
summarise(yes_count = sum(clsprty), total_count = n(), .groups = 'drop') %>% # Summarise data to get count of 'clsprty' and total count per group
mutate(proportion = yes_count / total_count) # Calculate the proportion of 'clsprty' in each groupclsprty_proportions_compare## # A tibble: 258 × 5
## yrbrn cntry yes_count total_count proportion
## <dbl> <chr> <dbl> <int> <dbl>
## 1 1920 France 23 40 0.575
## 2 1920 Italy 1 2 0.5
## 3 1920 Norway 21 25 0.84
## 4 1921 France 27 39 0.692
## 5 1921 Italy 4 7 0.571
## 6 1921 Norway 28 36 0.778
## 7 1922 France 33 66 0.5
## 8 1922 Italy 8 13 0.615
## 9 1922 Norway 28 35 0.8
## 10 1923 France 33 53 0.623
## # ℹ 248 more rowsfrance_data <- france_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", # 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_percentages <- france_data %>% # Begin with the dataset 'france_data'
filter(!is.na(lrscale), !is.na(gndr)) %>% # Filter out rows where 'lrscale' or 'gender' is NA (missing data)
group_by(gndr, lrscale) %>% # Group the data by 'gender' and 'lrscale' categories
summarise(count = n(), .groups = 'drop') %>% # Summarise each group to get counts, and then drop groupings
mutate(percentage = count / sum(count) * 100) # Calculate percentage for each group by dividing count by total count and multiplying by 100
lrscale_percentages # The resulting dataframe## # A tibble: 4 × 4
## gndr lrscale count percentage
## <chr> <chr> <int> <dbl>
## 1 Female Left 2507 27.8
## 2 Female Right 2211 24.5
## 3 Male Left 2202 24.4
## 4 Male Right 2091 23.2lrscale_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") + # Fixed scales for y-axis across facets
scale_fill_brewer(palette = "Set1") + # Distinct colors for Left and Right
labs(
title = "Political Orientation (Left vs. Right) by Gender in France",
x = "Political Orientation",
y = "Percentage of Respondents",
fill = "Orientation"
) +
theme_minimal() + # Minimal theme for clarity
theme(legend.position = "bottom") # Legend at the bottom
# Display the ggplot object
lrscale_plot
# Create a ggplot object for horizontal bar chart with the specified style
lrscale_plot_v2 <- ggplot(lrscale_percentages,
aes(x = percentage, # Use percentage directly
y = reorder(gndr, -percentage), # Order bars within each gender
fill = gndr)) + # Fill color based on Gender
# Create horizontal bar chart
geom_col() + # Draws the bars using the provided data
coord_flip() + # Flip coordinates to make bars horizontal
# Remove fill color legend
guides(fill = "none") + # Removes legend for the fill aesthetic
# Split the plot based on Political Orientation
facet_wrap(~ lrscale, nrow = 1) + # Separate plots for Left/Right
# Labels and titles for the plot
labs(x = "Percentage of Respondents", # X-axis label
y = NULL, # Remove Y-axis label
title = "Political Orientation by Gender", # Main title
subtitle = "Comparing the percentage distribution of left vs. right for France (2002-2020)") + # Subtitle
# Adjust visual properties of the plot
theme(plot.title = element_text(size = 16, face = "bold"), # Format title
plot.subtitle = element_text(size = 12), # Format subtitle
axis.title.y = element_blank(), # Remove Y-axis title
legend.position = "bottom") # Position the legend at the bottom
# Display the ggplot object
lrscale_plot_v2
# Recode clsprty and geo variables, removing NAs
france_data <- france_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(lrscale), !is.na(geo)) # Removing rows with NA in clsprty or geo# Calculate conditional probabilities, excluding NAs
cond <- france_data %>%
count(lrscale, geo) %>%
group_by(geo) %>%
mutate(prob = n / sum(n))
cond## # A tibble: 4 × 4
## # Groups: geo [2]
## lrscale geo n prob
## <chr> <chr> <int> <dbl>
## 1 Left Rural 3004 0.496
## 2 Left Urban 1704 0.577
## 3 Right Rural 3055 0.504
## 4 Right Urban 1247 0.423# Plot conditional probabilities
plot <- ggplot(cond, aes(x = lrscale, y = prob, fill = lrscale)) +
geom_bar(stat = "identity", position = "dodge") +
scale_fill_viridis_d(name = "Political Orientation") +
labs(y = "Conditional Probability",
x = "Feels Close to a Party",
title = "Conditional Probability of Political Orientation in France",
subtitle = "by Geographical Area: Urban vs. Rural") +
facet_wrap(~ geo, nrow = 1) +
theme(legend.position = "bottom",
legend.title = element_blank(),
plot.title = element_text(size = 16, face = "bold"),
plot.subtitle = element_text(size = 12),
axis.text.x = element_text(angle = 45, hjust = 1))
# Display the plot
plot
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")
# Load the required libraries
packages <- c("tidyverse", "fst", "modelsummary", "viridis")
new_packages <- packages[!(packages %in% installed.packages()[,"Package"])]
if(length(new_packages)) install.packages(new_packages)
lapply(packages, library, character.only = TRUE)## [[1]]
## [1] "fstcore" "viridis" "viridisLite" "modelsummary" "fst"
## [6] "lubridate" "forcats" "stringr" "dplyr" "purrr"
## [11] "readr" "tidyr" "tibble" "ggplot2" "tidyverse"
## [16] "stats" "graphics" "grDevices" "utils" "datasets"
## [21] "methods" "base"
##
## [[2]]
## [1] "fstcore" "viridis" "viridisLite" "modelsummary" "fst"
## [6] "lubridate" "forcats" "stringr" "dplyr" "purrr"
## [11] "readr" "tidyr" "tibble" "ggplot2" "tidyverse"
## [16] "stats" "graphics" "grDevices" "utils" "datasets"
## [21] "methods" "base"
##
## [[3]]
## [1] "fstcore" "viridis" "viridisLite" "modelsummary" "fst"
## [6] "lubridate" "forcats" "stringr" "dplyr" "purrr"
## [11] "readr" "tidyr" "tibble" "ggplot2" "tidyverse"
## [16] "stats" "graphics" "grDevices" "utils" "datasets"
## [21] "methods" "base"
##
## [[4]]
## [1] "fstcore" "viridis" "viridisLite" "modelsummary" "fst"
## [6] "lubridate" "forcats" "stringr" "dplyr" "purrr"
## [11] "readr" "tidyr" "tibble" "ggplot2" "tidyverse"
## [16] "stats" "graphics" "grDevices" "utils" "datasets"
## [21] "methods" "base"# Loading Spain data
spain_data <- read.fst("spain_data.fst")
# Cleaning 'trstplt' variable
spain_data <- spain_data %>%
mutate(
trstplt = ifelse(trstplt %in% c(77, 88, 99), NA, trstplt)
)
# Check for unexpected values
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 71# Create 'year' variable
spain_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$essround == i] <- replacements[i]
}
# Check that 'year' variable creation worked
table(spain_data$year)##
## 2002 2004 2006 2008 2010 2012 2014 2016 2018 2020
## 1729 1663 1876 2576 1885 1889 1925 1958 1668 2283# Calculate average trust by year
trustplt_by_year <- spain_data %>%
group_by(year) %>%
summarize(mean_trustplt = mean(trstplt, na.rm = TRUE))
# Visualize the data
ggplot(trustplt_by_year, aes(x = year, y = mean_trustplt)) +
geom_line(color = "lightpink", size = 1) +
geom_point(color = "lightblue", 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()
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.
ANSWER: In task2_plot there are clear trends being indicated. One trend found was that there is a continuous decline with proportion in each country (France, Italy, Norway). Even though eaach country is declining France has a steeper downwords slope starting in 1960, whereas Italy’s decline starts in the 1980’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 <- read.fst("italy_data.fst")
italy_data <- italy_data %>%
mutate(
gndr = case_when(
gndr == 1 ~ "Male",
gndr == 2 ~ "Female",
TRUE ~ NA_character_ # Set anything that is not 1 or 2 to NA
),
clsprty = case_when(
clsprty == 1 ~ "Left", # Left-wing (0 to 3)
clsprty == 2 ~ "Right", # Right-wing (7 to 10)
TRUE ~ NA_character_ # Moderate (4, 5, 6) and special codes (77, 88, 99) set to NA
)
)
clsprty <- italy_data %>%
filter(!is.na(clsprty), !is.na(gndr)) %>% # Filter out rows where 'lrscale' or 'gender' is NA (missing data)
group_by(gndr, clsprty) %>%
summarise(count = n(), .groups = 'drop') %>%
mutate(percentage = count / sum(count) * 100)
clsprty ## # A tibble: 4 × 4
## gndr clsprty count percentage
## <chr> <chr> <int> <dbl>
## 1 Female Left 1686 17.9
## 2 Female Right 3228 34.2
## 3 Male Left 1936 20.5
## 4 Male Right 2593 27.5Task 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.fst <- read.fst("sweden_data.fst")sweden_data <- read.fst("sweden_data.fst")
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", # 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_percentages <- sweden_data %>% # Begin with the dataset 'sweden_data'
filter(!is.na(lrscale), !is.na(gndr)) %>% # Filter out rows where 'lrscale' or 'gender' is NA (missing data)
group_by(gndr, lrscale) %>% # Group the data by 'gender' and 'lrscale' categories
summarise(count = n(), .groups = 'drop') %>% # Summarise each group to get counts, and then drop groupings
mutate(percentage = count / sum(count) * 100) # Calculate percentage for each group by dividing count by total count and multiplying by 100
lrscale_percentages # The resulting dataframe## # 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 31.1# Create a ggplot object for horizontal bar chart with the specified style
lrscale_plot_v2 <- ggplot(lrscale_percentages,
aes(x = percentage, # Use percentage directly
y = reorder(gndr, -percentage), # Order bars within each gender
fill = gndr)) + # Fill color based on Gender
# Create horizontal bar chart
geom_col() + # Draws the bars using the provided data
coord_flip() + # Flip coordinates to make bars horizontal
# Remove fill color legend
guides(fill = "none") + # Removes legend for the fill aesthetic
# Split the plot based on Political Orientation
facet_wrap(~ lrscale, nrow = 1) + # Separate plots for Left/Right
# Labels and titles for the plot
labs(x = "Percentage of Respondents", # X-axis label
y = NULL, # Remove Y-axis label
title = "Political Orientation by Gender", # Main title
subtitle = "Comparing the percentage distribution of left vs. right for sweden (2002-2020)") + # Subtitle
# Adjust visual properties of the plot
theme(plot.title = element_text(size = 16, face = "bold"), # Format title
plot.subtitle = element_text(size = 12), # Format subtitle
axis.title.y = element_blank(), # Remove Y-axis title
legend.position = "bottom") # Position the legend at the bottom
# Display the ggplot object
lrscale_plot_v2
## 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.fst <- read.fst("hungary_data.fst")hungary_data <- read.fst("hungary_data.fst")
hungary_data <- hungary_data %>%
mutate(
gndr = case_when(
gndr == 1 ~ "Male",
gndr == 2 ~ "Female",
TRUE ~ NA_character_ # Set anything that is not 1 or 2 to NA
),
clsprty = case_when(
clsprty == 1 ~ "Left", # Left-wing (0 to 3)
clsprty == 2 ~ "Right", # Right-wing (7 to 10)
TRUE ~ NA_character_ # Moderate (4, 5, 6) and special codes (77, 88, 99) set to NA
)
)
clsprty <- hungary_data %>%
filter(!is.na(clsprty), !is.na(gndr)) %>% # Filter out rows where 'lrscale' or 'gender' is NA (missing data)
group_by(gndr, clsprty) %>%
summarise(count = n(), .groups = 'drop') %>%
mutate(percentage = count / sum(count) * 100)
clsprty ## # A tibble: 4 × 4
## gndr clsprty count percentage
## <chr> <chr> <int> <dbl>
## 1 Female Left 4008 25.0
## 2 Female Right 5071 31.7
## 3 Male Left 3334 20.8
## 4 Male Right 3608 22.5hungary_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(lrscale), !is.na(geo))
plot <- ggplot(cond, aes(x = lrscale, y = prob, fill = lrscale)) +
geom_bar(stat = "identity", position = "dodge") +
scale_fill_viridis_d(name = "Political Orientation") +
labs(y = "Conditional Probability",
x = "Feels Close to a Party",
title = "Conditional Probability of Political Orientation in France",
subtitle = "by Geographical Area: Urban vs. Rural") +
facet_wrap(~ geo, nrow = 1) +
theme(legend.position = "bottom",
legend.title = element_blank(),
plot.title = element_text(size = 16, face = "bold"),
plot.subtitle = element_text(size = 12),
axis.text.x = element_text(angle = 45, hjust = 1))
# Display the plot
plot