Petsche_Lauren_Homework_2
2024-01-23
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)## ── 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"hungary_data <- read.fst("hungary_data.fst")sweden_data <- read.fst("sweden_data.fst")italy_data <- read.fst("italy_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), )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]
}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 1.94ggplot(trust_by_year, aes(x = year, y = mean_trust)) +
geom_line(aes(group = 1), color = "blue", size = 1, linetype = "longdash") +
geom_point(aes(color = mean_trust), size = 4) +
labs(title = "Trust in Parliament in Spain (2002-2020)",
x = "Survey Year",
y = "Average Trust (0-5 scale)") +
ylim(0, 5) +
theme_minimal() +
theme(legend.position = "none")## 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.
Using the Trust in parliament value, the measured is from 0-10, where 0 represents “No trust at all” and 10 is “Complete trust”.
As visualized on the chart, overall the range of trust is relatively low with all the values being below 5. The highest value occurs at 2004 with 3.65 indicating the most amount of trust in parliament throughout the years in Spain. After this point there was a gradual decrease in trust reaching the lowest value of 1.91 in the year 2012 indicating the least overall average trust in parliament within Spain. There was then a slight raise in trust until 2018, then another drop reaching its second lowest point in 2020 at 1.93.
The main takeaway based on the outputted values is that overall there has been a decrease in the trust of parliament with slight fluctuation throughout the years.
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.
On task2_plot, all three countries have shown a gradual decline in the response of feeling close to a party by cohort. While France, Italy, and Norway have all decreased, they have maintained the same position with Norway having the highest value, France in the middle, and Italy with the lowest value throughout 1920 to 2000 cohorts.
Additionally, in relation to Norway and Italy, France started off at the 1920 cohort with a relatively equal distance between the two countries. However after reaching the 2000 cohort, the gap between Norway and France is much greater as Norway has a value above 0.50 while Italy and France are much closer in value with both being around the 0.25 value.
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 <- italy_data %>%
mutate(
gndr = case_when(
gndr == 1 ~ "Male",
TRUE ~ NA_character_
),
lrscale = case_when(
lrscale %in% 0:3 ~ "Left",
lrscale %in% 7:10 ~ "Right",
lrscale %in% 4:6 ~ "Moderate",
TRUE ~ NA_character_
)
) lrscale_percentages <- italy_data %>%
filter(!is.na(lrscale), !is.na(gndr)) %>%
group_by(gndr, lrscale) %>%
summarise(count = n(), .groups = 'drop') %>%
mutate(percentage = count / sum(count) * 100)
lrscale_percentages ## # A tibble: 3 × 4
## gndr lrscale count percentage
## <chr> <chr> <int> <dbl>
## 1 Male Left 924 25.4
## 2 Male Moderate 1632 44.8
## 3 Male Right 1084 29.8The Marginal Percentages in Survey Data:
Male and Left: out of the Italian male respondents, 25.4% are closer to the politically left.
Male and Right: out of the Italian male respondents, 29.8% are closer to the politically right.
Male and Moderate: out of the Italian male respondents, 44.8% don’t lean close to a particular political party
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 <- 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_percentagesxx <- 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_plot_v2 <- ggplot(lrscale_percentagesxx,
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 <- hungary_data %>%
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)
)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 geohungary_data <- hungary_data %>%
mutate(
clsprty = case_when(
clsprty == 1 ~ "Yes",
clsprty == 2 ~ "No",
TRUE ~ NA_character_
)
) cond <- hungary_data %>%
count(clsprty, geo) %>%
group_by(geo) %>%
mutate(prob = n / sum(n))
cond## # A tibble: 4 × 4
## # Groups: geo [2]
## clsprty geo n prob
## <chr> <chr> <int> <dbl>
## 1 Yes Rural 5055 0.446
## 2 Yes Urban 2283 0.488
## 3 <NA> Rural 6275 0.554
## 4 <NA> Urban 2395 0.512Given that someone lives in a rural area in Hungary, there is a 55.4% probability of not feeling close to any particular party.