Report1

# 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"

# Let's load our data for Spain
spain_data <- read.fst("spain_data.fst")

# Reviewing & Adding

# First, let's review how to calculate the average for a variable of interest and then visualize.

# We will be working with a political orientation variable -- leaning left or right.

# Before proceeding, we need to clean and transform our variable.

spain_data <- spain_data %>%
  mutate(
    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 
    )    
  ) 

# Always check your work. One quick way to do so:

table(spain_data$lrscale) # 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

## 
##  Left Right 
##  5610  2726

 #Next, let's recode the geographical location variable

spain_data <- spain_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 lrscale or geo

# Now, let's calculate conditional probabilities

cond_probabilities <- spain_data %>%
  count(lrscale, geo) %>%
  group_by(geo) %>%
  mutate(probability = n / sum(n))

# Visualization

plot <- ggplot(cond_probabilities, aes(x = lrscale, y = probability, 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 Spain", 
       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