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     1.3.1
## ✔ 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")
france_data <- france_data %>%
  mutate(
    ppltrst = ifelse(ppltrst %in% c(77, 88, 99), NA, ppltrst), # set values 77, 88, and 99 to NA.
  )
table(france_data$ppltrst)
## 
##    0    1    2    3    4    5    6    7    8    9   10 
## 1240  612 1575 2364 2294 5238 2096 2114 1109  231  148
france_data$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 1977
trust_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       4.47
##  2  2004       4.52
##  3  2006       4.43
##  4  2008       4.45
##  5  2010       4.33
##  6  2012       4.44
##  7  2014       4.67
##  8  2016       4.58
##  9  2018       4.62
## 10  2020       4.69
ggplot(trust_by_year, aes(x = year, y = mean_trust)) +
  geom_line(color = "blue", size = 1) +  # Line to show the trend
  geom_point(color = "red", 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 = "blue", 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

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$year)
## < table of extent 0 >
  spain_data$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]
}

table(spain_data$year)
## 
## 2002 2004 2006 2008 2010 2012 2014 2016 2018 2020 
## 1729 1663 1876 2576 1885 1889 1925 1958 1668 2283
trust_by_year <- spain_data %>%
  group_by(year) %>%
  summarize(mean_trust = mean(trstplt, na.rm = TRUE))
    trust_by_year
## # A tibble: 10 × 2
##     year mean_trust
##    <dbl>      <dbl>
##  1  2002       3.41
##  2  2004       3.66
##  3  2006       3.49
##  4  2008       3.32
##  5  2010       2.72
##  6  2012       1.91
##  7  2014       2.23
##  8  2016       2.40
##  9  2018       2.55
## 10  2020       1.94
    table(spain_data$year)
## 
## 2002 2004 2006 2008 2010 2012 2014 2016 2018 2020 
## 1729 1663 1876 2576 1885 1889 1925 1958 1668 2283

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)?

ggplot(trust_by_year, aes(x = year, y = mean_trust)) +
  geom_line(color = "blue", size = 1) +  # Line to show the trend
  geom_point(color = "red", size = 3) +  # Points to highlight each year's value
  labs(title = "Trust in Parliament (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()

Trust in parliament reached its lowest point in the early 2010’s, confidence consistently increasing until taking a hit in 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.

  1. Italy has the lowest proportion of individuals feeling close to a party by cohort

  2. France has had a steadily decreasing rate since 1940

Task 3

Provide code and answer.

italy_data <- read.fst("italy_data.fst")
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 ~ "Yes",
      clsprty == 2 ~ "No",
      TRUE ~ NA_character_  # Set anything that is not 1 or 2 to NA
    ),
    
      clsprty = ifelse(clsprty %in% c(7, 8, 9), NA, clsprty),
    
    
  )

clsprty_percentages <- italy_data %>%  # Begin with the dataset 'france_data'
  filter(!is.na(clsprty), !is.na(gndr)) %>%  # Filter out rows where 'lrscale' or 'gender' is NA (missing data)
  group_by(gndr, clsprty) %>%  # 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

clsprty_percentages  # The resulting dataframe
## # 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       20.5
table(italy_data$clsprty)
## 
##   No  Yes 
## 5828 3626

Question: What is the marginal percentage of Italian men who feel close to a particular political party?

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. 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?