Tutorial 3: Visualizing the 3 P’s
First things first: setting up your environment
Remember: you always need to do this step first and include all the packages you need
# 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"Loading Data into R
Let’s load our data. We will first work with France.
france_data <- read.fst("france_data.fst")italy_data <- read.fst("italy_data.fst")hungary_data <- read.fst("hungary_data.fst")sweden_data <- read.fst("sweden_data.fst")spain_data <- read.fst("spain_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), # set values 77, 88, and 99 to NA.
)Always check your work. One quick way to do so:
table(spain_data$trstplt) # if there are values that are not supposed to be there (e.g., 77, 88, 99 in this case), then we need to deal with it##
## 0 1 2 3 4 5 6 7 8 9 10
## 5165 1830 2329 2441 2085 2890 1154 639 355 80 71Next, let’s create a ‘year’ variable from the essround variable. We will use it to visualize.
spain_data$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]
}Let’s check that it worked
table(spain_data$year)##
## 2002 2004 2006 2008 2010 2012 2014 2016 2018 2020
## 1729 1663 1876 2576 1885 1889 1925 1958 1668 2283Now, we will calculate the average by year to then visualize:
trust_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 1.94library(ggplot2)
ggplot(trust_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.
The average trust in Parliament has been gradually dropping, with big drops in 2012 and 2020
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.
France is in the middle in comparison to Italy and Norway.Italy and France are quite close to one another while Norway has higher numbers of people feeling close to a party. All three countries though are seeing a decline in people who feel close to a party.
##Task 3 Provide code and answer.
Question: What is the marginal percentage of Italian men who feel close to a particular political party?
library(dplyr)
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 %in% 0:3 ~ "Left", # Left-wing (0 to 3)
clsprty %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
)
)
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 Left 4914 48.3
## 2 Female Right 415 4.08
## 3 Male Left 4529 44.6
## 4 Male Right 307 3.02The marginal percentage is 44.55%
##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")library("dplyr")
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)
library(ggplot2)
lrscale_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 (2002-2020)") +
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
## 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")library(dplyr)
hungary_data <- hungary_data %>%
mutate(
clsprty = ifelse(clsprty == 2, 0, ifelse(clsprty %in% c(7, 8, 9), NA, clsprty))
) %>%
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) %>%
mutate(prob = n / sum(n))
cond## clsprty geo n prob
## 1 0 Rural 6275 0.3919915
## 2 0 Urban 2395 0.1496127
## 3 1 Rural 5055 0.3157796
## 4 1 Urban 2283 0.1426162the conditional probability is 39.2%