BASA_Luis_Homework_1
2024-01-16
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:
# List of packages
packages <- c("tidyverse", "fst", "modelsummary") # 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## [[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"ess <- read_fst("All-ESS-Data.fst")###PROMT 1###
unique(ess$cntry)## [1] "AT" "BE" "CH" "CZ" "DE" "DK" "ES" "FI" "FR" "GB" "GR" "HU" "IE" "IL" "IT"
## [16] "LU" "NL" "NO" "PL" "PT" "SE" "SI" "EE" "IS" "SK" "TR" "UA" "BG" "CY" "RU"
## [31] "HR" "LV" "RO" "LT" "AL" "XK" "ME" "RS" "MK"Norway_happy <- ess %>%
filter(cntry == "NO")%>%
select(happy)Norway_happy$y <- Norway_happy$happy
#pre-filter
table(Norway_happy$y)##
## 0 1 2 3 4 5 6 7 8 9 10 77 88
## 15 29 59 163 238 730 817 2617 5235 3796 2344 12 10Norway_happy$y[Norway_happy$y %in% 77:99] <- NA
#table post-filter
table(Norway_happy$y)##
## 0 1 2 3 4 5 6 7 8 9 10
## 15 29 59 163 238 730 817 2617 5235 3796 2344mean_y <- mean(Norway_happy$y, na.rm = TRUE)
cat("Mean of 'y' is:", mean_y)## Mean of 'y' is: 7.975005#THEREFORE, GIVEN THAT NORWAY HAS A MEAN OF 7.98, WE CAN CONCLUDE THAT ON AVERAGE, NORWAY REPORTS HIGHER LEVELS OF HAPPINESS THAN BELGIUM
###PROMT 2###
ireland_alcbnge <- ess %>%
filter(cntry == "IE") %>%
select(alcbnge)
ireland_alcbnge$y <- ireland_alcbnge$alcbnge
table (ireland_alcbnge$y)##
## 1 2 3 4 5 6 7 8
## 65 650 346 417 239 641 26 6mean_y <- mean(ireland_alcbnge$y, na.rm = TRUE)
median_y <- median(ireland_alcbnge$y, na.rm = TRUE)
cat("mean of 'y' is:", mean_y, "\n")## mean of 'y' is: 3.908787cat("median of 'y' is:", median_y)## median of 'y' is: 4df <- ireland_alcbnge %>%
mutate(
y_category = case_when(
y == 1 ~ "Daily or almost daily",
y == 2 ~ "Weekly",
y == 3 ~ "Monthly",
y == 4 ~ "Less than monthly",
y == 5 ~ "Never",
TRUE ~ NA_character_),
y_category = fct_relevel (factor(y_category),
"Daily or almost daily",
"Weekly",
"Monthly",
"Less than monthly",
"Never")
)
table(df$y_category)##
## Daily or almost daily Weekly Monthly
## 65 650 346
## Less than monthly Never
## 417 239get_mode <- function(v) {
tbl <- table(v)
mode_vals <- as.character(names(tbl)[tbl == max(tbl)])
return(mode_vals)
}
mode_values <- get_mode(df$y_category)
cat("Mode of y category:", paste(mode_values, collapse = ", "))## Mode of y category: Weekly#THEREFORE, THE MOST COMMON CATEGORY OF DRINKING WAS WEEKLY
ireland_alcbnge <- ess %>%
filter(cntry == "IE") %>%
select(alcbnge)
ireland_alcbnge$y <- ireland_alcbnge$alcbnge
mean_y <- mean(ireland_alcbnge$y, na.rm = TRUE)
median_y <- median(ireland_alcbnge$y, na.rm = TRUE)
cat("mean of 'y' is:", mean_y, "\n")## mean of 'y' is: 3.908787cat("median of 'y' is:", median_y)## median of 'y' is: 4df <- ireland_alcbnge %>%
mutate(
y_category = case_when(
y == 1 ~ "Daily or almost daily",
y == 2 ~ "Weekly",
y == 3 ~ "Monthly",
y == 4 ~ "Less than monthly",
y == 5 ~ "Never",
TRUE ~ NA_character_),
y_category = fct_relevel (factor(y_category),
"Daily or almost daily",
"Weekly",
"Monthly",
"Less than monthly",
"Never")
)
table(df$y_category)##
## Daily or almost daily Weekly Monthly
## 65 650 346
## Less than monthly Never
## 417 239get_mode <- function(v) {
tbl <- table(v)
mode_vals <- as.character(names(tbl)[tbl == max(tbl)])
return(mode_vals)
}
mode_values <- get_mode(df$y_category)
cat("Mode of y category:", paste(mode_values, collapse = ", "))## Mode of y category: Weekly###PROMT 3###
unique(ess$cntry)## [1] "AT" "BE" "CH" "CZ" "DE" "DK" "ES" "FI" "FR" "GB" "GR" "HU" "IE" "IL" "IT"
## [16] "LU" "NL" "NO" "PL" "PT" "SE" "SI" "EE" "IS" "SK" "TR" "UA" "BG" "CY" "RU"
## [31] "HR" "LV" "RO" "LT" "AL" "XK" "ME" "RS" "MK"portugal_plnftr <- ess %>%
filter(cntry == "PT") %>%
select(plnftr)table(portugal_plnftr)## plnftr
## 0 1 2 3 4 5 6 7 8 9 10 88
## 114 184 313 356 264 481 262 382 345 166 370 40#NOTE: FILTERING 88 AS “NA” JUST IN CASE AND IN THE EVENT THAT SOME CODING MISTAKE THAT I’M NOT AWARE ABOUT HAPPENS
portugal_plnftr$y <- portugal_plnftr$plnftr
portugal_plnftr$y [portugal_plnftr$y %in% 88] <- NA
table(portugal_plnftr)## y
## plnftr 0 1 2 3 4 5 6 7 8 9 10
## 0 114 0 0 0 0 0 0 0 0 0 0
## 1 0 184 0 0 0 0 0 0 0 0 0
## 2 0 0 313 0 0 0 0 0 0 0 0
## 3 0 0 0 356 0 0 0 0 0 0 0
## 4 0 0 0 0 264 0 0 0 0 0 0
## 5 0 0 0 0 0 481 0 0 0 0 0
## 6 0 0 0 0 0 0 262 0 0 0 0
## 7 0 0 0 0 0 0 0 382 0 0 0
## 8 0 0 0 0 0 0 0 0 345 0 0
## 9 0 0 0 0 0 0 0 0 0 166 0
## 10 0 0 0 0 0 0 0 0 0 0 370
## 88 0 0 0 0 0 0 0 0 0 0 0mean_y <-mean(portugal_plnftr$plnftr, na.rm = TRUE)
cat("Mean of 'y' is:", mean_y, "\n")## Mean of 'y' is: 6.426305median_y <- median(portugal_plnftr$y, na.rm = TRUE)
cat("Median of 'y' is:", median_y, "\n")## Median of 'y' is: 5unique(ess$cntry)## [1] "AT" "BE" "CH" "CZ" "DE" "DK" "ES" "FI" "FR" "GB" "GR" "HU" "IE" "IL" "IT"
## [16] "LU" "NL" "NO" "PL" "PT" "SE" "SI" "EE" "IS" "SK" "TR" "UA" "BG" "CY" "RU"
## [31] "HR" "LV" "RO" "LT" "AL" "XK" "ME" "RS" "MK"serbia_plnftr <- ess %>%
filter(cntry =="RS") %>%
select(plnftr)table(serbia_plnftr)## plnftr
## 0 1 2 3 4 5 6 7 8 9 10 77 88
## 587 133 152 138 95 246 70 87 103 47 364 4 17serbia_plnftr$y <- serbia_plnftr$plnftr
serbia_plnftr$y [serbia_plnftr$y %in% 77:88] <- NA
table(serbia_plnftr)## y
## plnftr 0 1 2 3 4 5 6 7 8 9 10
## 0 587 0 0 0 0 0 0 0 0 0 0
## 1 0 133 0 0 0 0 0 0 0 0 0
## 2 0 0 152 0 0 0 0 0 0 0 0
## 3 0 0 0 138 0 0 0 0 0 0 0
## 4 0 0 0 0 95 0 0 0 0 0 0
## 5 0 0 0 0 0 246 0 0 0 0 0
## 6 0 0 0 0 0 0 70 0 0 0 0
## 7 0 0 0 0 0 0 0 87 0 0 0
## 8 0 0 0 0 0 0 0 0 103 0 0
## 9 0 0 0 0 0 0 0 0 0 47 0
## 10 0 0 0 0 0 0 0 0 0 0 364
## 77 0 0 0 0 0 0 0 0 0 0 0
## 88 0 0 0 0 0 0 0 0 0 0 0mean_y <- mean(serbia_plnftr$plnftr, na.rm = TRUE)
cat("Mean of 'y' is:", mean_y, "\n")## Mean of 'y' is: 4.983358median_y <- median(serbia_plnftr$plnftr, na.rm = TRUE)
cat("median of 'y' is:", median_y, "\n")## median of 'y' is: 4summary(portugal_plnftr)## plnftr y
## Min. : 0.000 Min. : 0.000
## 1st Qu.: 3.000 1st Qu.: 3.000
## Median : 5.000 Median : 5.000
## Mean : 6.426 Mean : 5.418
## 3rd Qu.: 8.000 3rd Qu.: 8.000
## Max. :88.000 Max. :10.000
## NA's :14604 NA's :14644summary(serbia_plnftr)## plnftr y
## Min. : 0.000 Min. : 0.000
## 1st Qu.: 0.000 1st Qu.: 0.000
## Median : 4.000 Median : 4.000
## Mean : 4.983 Mean : 4.143
## 3rd Qu.: 8.000 3rd Qu.: 8.000
## Max. :88.000 Max. :10.000
## NA's :1505 NA's :1526Conclusion:
Therefore, we see that Serbians tend to plan for their future more than the French given that Serbia has a lower mean average as a result of more individuals scoring lower as a result of future planning. We also see that there is more variance of scores in the middle of the distribution for the French, and at the extremes for Serbia
PROMPT 4
italy_data <- ess %>%
filter(cntry == "IT")
italy_data <- italy_data %>%
mutate(
gndr = case_when(
gndr == 1 ~ "Male",
gndr == 2 ~ "Female",
TRUE ~ as.character(gndr)
),
stfdem = ifelse(stfdem %in% c(77:88), NA, stfdem)
) mean_male_stfdem <- italy_data %>%
filter(gndr == "Male") %>%
summarize(mean_male_stfdem = mean(stfdem, na.rm = TRUE))
means_by_gender <- italy_data %>%
group_by(gndr) %>%
summarize(stfdem = mean(stfdem, na.rm = TRUE))
print (means_by_gender)## # A tibble: 3 × 2
## gndr stfdem
## <chr> <dbl>
## 1 9 3.25
## 2 Female 4.69
## 3 Male 4.78THEREFORE, MEN ON AVERAGE TEND TO BE MORE SATISFIED WITH DEMOCRACY THAN WOMEN IN ITALY
PROMPT 5
france_data <- ess %>%
filter(cntry == "FR")ggplot(france_data %>%
mutate(clsprty = ifelse(clsprty %in% c(7, 8), NA, clsprty)),
aes(x = clsprty)) +
geom_bar(na.rm = TRUE) +
labs(title = "Boxplot of satisfaciton with the state of education vs health services",
x = "X-axis", # note: you would want to label these appropriately but showcasing what happens when you just put 'X-axis'
y = "Y-axis") # as well as 'Y-axis'
france_data %>%
# Setting values to NA
mutate(stfedu = ifelse(stfedu %in% c(77, 88, 99), NA, stfedu),
stfhlth = ifelse(stfhlth %in% c(77, 88, 99), NA, stfhlth)) %>%
# Reshaping the data
select(stfedu, stfhlth) %>%
gather(variable, value, c(stfedu, stfhlth)) %>%
# Creating the boxplot
ggplot(aes(x = variable, y = value)) +
geom_boxplot() +
labs(y = "Satisfaction (0-10)", x = "", title = "Boxplot of satisfaction with the state of education vs. health services") +
theme_minimal()## Warning: Removed 364 rows containing non-finite values (`stat_boxplot()`).
We would say that the median French person is more satisfied with the health services as indicative of a higher bolded median line in the box of the box plot (stfhlth)