Hassan_Aleena_Homework_1

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:

summary(cars)

##      speed           dist       
##  Min.   : 4.0   Min.   :  2.00  
##  1st Qu.:12.0   1st Qu.: 26.00  
##  Median :15.0   Median : 36.00  
##  Mean   :15.4   Mean   : 42.98  
##  3rd Qu.:19.0   3rd Qu.: 56.00  
##  Max.   :25.0   Max.   :120.00

Including Plots

You can also embed plots, for example:

Note that the echo = FALSE parameter was added to the code chunk to prevent printing of the R code that generated the plot.

###TASK 1: ###Prompt and question: calculate the average for the variable ‘happy’ for the country of Norway. On average, based on the ESS data, who reports higher levels of happiness: Norway or Belgium?

# 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"

getwd()

## [1] "C:/Users/hassa947/Desktop/222_Homework"

ess <- read_fst("All-ESS-Data.fst")

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"

###Calcution for Belgium

belgium_happy <- ess %>% 
  filter(cntry == "BE") %>% 
  select(happy)

belgium_happy$y <- belgium_happy$happy

table(belgium_happy$y)

## 
##    0    1    2    3    4    5    6    7    8    9   10   77   88   99 
##   50   27  104  194  234  830  999 3503 6521 3402 1565    3   16    3

# Recode values 77 through 99 to NA
belgium_happy$y[belgium_happy$y %in% 77:99] <- NA

# checking again
table(belgium_happy$y)

## 
##    0    1    2    3    4    5    6    7    8    9   10 
##   50   27  104  194  234  830  999 3503 6521 3402 1565

###Calculating Mean and Median

mean_y <- mean(belgium_happy$y, na.rm = TRUE)
cat("Mean of 'y' is:", mean_y, "\n")

## Mean of 'y' is: 7.737334

# Now, finding the median of 'y'.
median_y <- median(belgium_happy$y, na.rm = TRUE)
cat("Median of 'y' is:", median_y, "\n")

## Median of 'y' is: 8

belgium_happy %>%
  summarize(
    mean_y = mean(y, na.rm = TRUE),
    median_y = median(y, na.rm = TRUE)
  ) %>%
  print()

##     mean_y median_y
## 1 7.737334        8

###Finding the Mode and Standard Deviation

mode_y <- belgium_happy %>%
  filter(!is.na(y)) %>%
  count(y) %>%
  arrange(desc(n)) %>%
  slice(1) %>%
  pull(y)

cat("\nMode of Y:", mode_y, "\n")

## 
## Mode of Y: 8

sd_y <- sd(belgium_happy$y, na.rm = TRUE)
cat("Standard Deviation of 'y':", sd_y, "\n")

## Standard Deviation of 'y': 1.52045

belgium_happy2 <- ess %>%
  filter(cntry == "BE") %>%
  select(happy)

sd_happy2 <- sd(belgium_happy2$happy, na.rm = TRUE)
cat("Standard Deviation of 'happy not cleaned':", sd_happy2, "\n")

## Standard Deviation of 'happy not cleaned': 3.234511

###The Summary Function

summary(belgium_happy)

##      happy              y         
##  Min.   : 0.000   Min.   : 0.000  
##  1st Qu.: 7.000   1st Qu.: 7.000  
##  Median : 8.000   Median : 8.000  
##  Mean   : 7.839   Mean   : 7.737  
##  3rd Qu.: 9.000   3rd Qu.: 9.000  
##  Max.   :99.000   Max.   :10.000  
##                   NA's   :22

getwd()

## [1] "C:/Users/hassa947/Desktop/222_Homework"

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"

###Calculation for Norway

#calculating the average for the variable ‘happy’ for the country of Norway
norway_happy <- ess %>% 
  filter(cntry == "NO") %>% 
  select(happy)

norway_happy$y <- norway_happy$happy

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   10

# Recode values 77 through 99 to NA
norway_happy$y[norway_happy$y %in% 77:99] <- NA

# checking again
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 2344

###Calculating Mean and Median

mean_y <- mean(norway_happy$y, na.rm = TRUE)
cat("Mean of 'y' is:", mean_y, "\n")

## Mean of 'y' is: 7.975005

# Now, let's determine the median of 'y'.
median_y <- median(norway_happy$y, na.rm = TRUE)
cat("Median of 'y' is:", median_y, "\n")

## Median of 'y' is: 8

norway_happy %>%
  summarize(
    mean_y = mean(y, na.rm = TRUE),
    median_y = median(y, na.rm = TRUE)
  ) %>%
  print()

##     mean_y median_y
## 1 7.975005        8

###Finding the Mode and Standard Deviation

mode_y <- norway_happy %>%
  filter(!is.na(y)) %>%
  count(y) %>%
  arrange(desc(n)) %>%
  slice(1) %>%
  pull(y)

cat("\nMode of Y:", mode_y, "\n")

## 
## Mode of Y: 8

sd_y <- sd(norway_happy$y, na.rm = TRUE)
cat("Standard Deviation of 'y':", sd_y, "\n")

## Standard Deviation of 'y': 1.539186

norway_happy2 <- ess %>%
  filter(cntry == "NO") %>%
  select(happy)

sd_happy2 <- sd(norway_happy2$happy, na.rm = TRUE)
cat("Standard Deviation of 'happy not cleaned':", sd_happy2, "\n")

## Standard Deviation of 'happy not cleaned': 3.146621

###The summary function

summary(norway_happy)

##      happy              y         
##  Min.   : 0.000   Min.   : 0.000  
##  1st Qu.: 7.000   1st Qu.: 7.000  
##  Median : 8.000   Median : 8.000  
##  Mean   : 8.076   Mean   : 7.975  
##  3rd Qu.: 9.000   3rd Qu.: 9.000  
##  Max.   :88.000   Max.   :10.000  
##                   NA's   :22

###Answer: The mean for the variable ‘happy’ for Belgium is 7.839 and the mean for the variable ‘happy’ for Norway is 8.076, therefore Norway reports higher levels of happiness.

###TASK 2: ###Prompt and question: what is the most common category selected, for Irish respondents, for frequency of binge drinking? The variable of interest is: alcbnge.

# 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)

## [[1]]
##  [1] "fstcore"      "modelsummary" "fst"          "lubridate"    "forcats"     
##  [6] "stringr"      "dplyr"        "purrr"        "readr"        "tidyr"       
## [11] "tibble"       "ggplot2"      "tidyverse"    "stats"        "graphics"    
## [16] "grDevices"    "utils"        "datasets"     "methods"      "base"        
## 
## [[2]]
##  [1] "fstcore"      "modelsummary" "fst"          "lubridate"    "forcats"     
##  [6] "stringr"      "dplyr"        "purrr"        "readr"        "tidyr"       
## [11] "tibble"       "ggplot2"      "tidyverse"    "stats"        "graphics"    
## [16] "grDevices"    "utils"        "datasets"     "methods"      "base"        
## 
## [[3]]
##  [1] "fstcore"      "modelsummary" "fst"          "lubridate"    "forcats"     
##  [6] "stringr"      "dplyr"        "purrr"        "readr"        "tidyr"       
## [11] "tibble"       "ggplot2"      "tidyverse"    "stats"        "graphics"    
## [16] "grDevices"    "utils"        "datasets"     "methods"      "base"

getwd()

## [1] "C:/Users/hassa947/Desktop/222_Homework"

ess <- read_fst("All-ESS-Data.fst")

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"

###Counting categorical variables

ireland_bdfrequency <- ess %>%
  filter(cntry == "IE") %>%
  select(alcbnge)

ireland_bdfrequency$y <- ireland_bdfrequency$alcbnge

table(ireland_bdfrequency$y)

## 
##   1   2   3   4   5   6   7   8 
##  65 650 346 417 239 641  26   6

# Recode values 6 through 8 to NA
ireland_bdfrequency$y[ireland_bdfrequency$y %in% 6:8] <- NA

# Compute mean and median
mean_y <- mean(ireland_bdfrequency$y, na.rm = TRUE)
median_y <- median(ireland_bdfrequency$y, na.rm = TRUE)

cat("Mean of 'y':", mean_y, "\n")

## Mean of 'y': 3.066977

cat("Median of 'y':", median_y, "\n")

## Median of 'y': 3

# Converting to categories to get mode as a category instead of a number
df <- ireland_bdfrequency %>%
  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),  ### here you would put the categories in order you want them to appear or else it will appear alphabetically
                             "Daily or almost daily",
                             "Weekly", 
                             "Monthly", 
                             "Less than monthly", 
                             "Never")
  )

# To confirm the conversion:
table(df$y_category)

## 
## Daily or almost daily                Weekly               Monthly 
##                    65                   650                   346 
##     Less than monthly                 Never 
##                   417                   239

#determining the mode of the newly created category:
get_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 = ", "), "\n")

## Mode of y category: Weekly

###Answer: The most common category selected for Irish respondents for frequency of binge drinking is “weekly.”

###TASK 3: ###Prompt and question: when you use the summary() function for the variable plnftr (about planning for future or taking every each day as it comes from 0-10) for both the countries of Portugal and Serbia, what do you notice? What stands out as different when you compare the two countries (note: look up the variable information on the ESS website to help with interpretation)? Explain while referring to the output generated.

# 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)

## [[1]]
##  [1] "fstcore"      "modelsummary" "fst"          "lubridate"    "forcats"     
##  [6] "stringr"      "dplyr"        "purrr"        "readr"        "tidyr"       
## [11] "tibble"       "ggplot2"      "tidyverse"    "stats"        "graphics"    
## [16] "grDevices"    "utils"        "datasets"     "methods"      "base"        
## 
## [[2]]
##  [1] "fstcore"      "modelsummary" "fst"          "lubridate"    "forcats"     
##  [6] "stringr"      "dplyr"        "purrr"        "readr"        "tidyr"       
## [11] "tibble"       "ggplot2"      "tidyverse"    "stats"        "graphics"    
## [16] "grDevices"    "utils"        "datasets"     "methods"      "base"        
## 
## [[3]]
##  [1] "fstcore"      "modelsummary" "fst"          "lubridate"    "forcats"     
##  [6] "stringr"      "dplyr"        "purrr"        "readr"        "tidyr"       
## [11] "tibble"       "ggplot2"      "tidyverse"    "stats"        "graphics"    
## [16] "grDevices"    "utils"        "datasets"     "methods"      "base"

getwd()

## [1] "C:/Users/hassa947/Desktop/222_Homework"

ess <- read_fst("All-ESS-Data.fst")

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"

###Comparing means by groupby

result <- ess %>%
  # Step 1: Filter for the countries of interest
  filter(cntry %in% c("PT", "RS")) %>%
  
  # Step 2: Recode 77, 88, 99 to NA for 'plnftr'
  mutate(plnftr = recode(plnftr, `77` = NA_real_, `88` = NA_real_, `99` = NA_real_)) %>%
  
  # Step 3: Compute mean by country
  group_by(cntry) %>%
  summarize(mean_plnftr = mean(plnftr, na.rm = TRUE))

print(result)

## # A tibble: 2 × 2
##   cntry mean_plnftr
##   <chr>       <dbl>
## 1 PT           5.42
## 2 RS           4.14

#Filter country of interest
portugal_data <- filter(ess, cntry == "PT")
serbia_data <- filter(ess, cntry == "RS")

#Use summary function to find summary of each
summary_portugal <- summary(portugal_data$plnftr)
summary_serbia <- summary(serbia_data$plnftr)

#Print summary function for portugal
print(summary(portugal_data$plnftr))

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##   0.000   3.000   5.000   6.426   8.000  88.000   14604

#Print summary function for Serbia
print(summary(serbia_data$plnftr))

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##   0.000   0.000   4.000   4.983   8.000  88.000    1505

###Answer: When I use the summary() function for plnftr for Portugal and Serbia I notice that the mean and median differs between the two countries. The median for Portugal is 5.000 and it is 4.000 for Serbia. Similarily the mean is higher for Portugal as well with it being 6.426 while it is only 4.983 for Serbia. This can also be seen on the ESS website where a large amount of people in Portugal are seen taking each day as it comes while very few plan it out. In contrast, though, Serbia does quite the opposite.

###TASK 4: ###Prompt and question: using the variables stfdem and gndr, answer the following: on average, who is more dissastified with democracy in Italy, men or women? Explain while referring to the output generated.

# 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)

## [[1]]
##  [1] "fstcore"      "modelsummary" "fst"          "lubridate"    "forcats"     
##  [6] "stringr"      "dplyr"        "purrr"        "readr"        "tidyr"       
## [11] "tibble"       "ggplot2"      "tidyverse"    "stats"        "graphics"    
## [16] "grDevices"    "utils"        "datasets"     "methods"      "base"        
## 
## [[2]]
##  [1] "fstcore"      "modelsummary" "fst"          "lubridate"    "forcats"     
##  [6] "stringr"      "dplyr"        "purrr"        "readr"        "tidyr"       
## [11] "tibble"       "ggplot2"      "tidyverse"    "stats"        "graphics"    
## [16] "grDevices"    "utils"        "datasets"     "methods"      "base"        
## 
## [[3]]
##  [1] "fstcore"      "modelsummary" "fst"          "lubridate"    "forcats"     
##  [6] "stringr"      "dplyr"        "purrr"        "readr"        "tidyr"       
## [11] "tibble"       "ggplot2"      "tidyverse"    "stats"        "graphics"    
## [16] "grDevices"    "utils"        "datasets"     "methods"      "base"

getwd()

## [1] "C:/Users/hassa947/Desktop/222_Homework"

ess <- read_fst("All-ESS-Data.fst")

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"

###Average of Y by X

italy_data <- ess %>% 
  filter(cntry == "IT")

# Convert gender and stfdem
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)  # Convert stfdem values
  )

# Compute mean for male
mean_male_stfdem <- italy_data %>%
  filter(gndr == "Male") %>%
  summarize(mean_stfdem_men = mean(stfdem, na.rm = TRUE))

print(mean_male_stfdem)

##   mean_stfdem_men
## 1        4.782646

# Compute mean for female
mean_female_stfdem <- italy_data %>%
  filter(gndr == "Female") %>%
  summarize(mean_stfdem_women = mean(stfdem, na.rm = TRUE))

print(mean_female_stfdem)

##   mean_stfdem_women
## 1          4.694652

# Compute average of stfdem by gender
means_by_gender <- italy_data %>%
  group_by(gndr) %>% # here I am "grouping by" my second variable
  summarize(stfdem = mean(stfdem, na.rm = TRUE)) # here I am summarizing my variable of interest

print(means_by_gender)

## # A tibble: 3 × 2
##   gndr   stfdem
##   <chr>   <dbl>
## 1 9        3.25
## 2 Female   4.69
## 3 Male     4.78

###Answer: By referring to the output generated we can see that the mean of men that are satisfied with democracy is 4.782646 and the mean of women satisfied with democracy is 4.694652. Therefore, this tells us that women on average are more dissatisifed with democracy in Italy.

###TASK 5: ###Prompt: Interpret the boxplot graph of stfedu and stfhlth that we generated already: according to ESS data, would we say that the median French person is more satisfied with the education system or health services? Explain.

###Change the boxplot graph: provide the code to change some of the key labels: (1) Change the title to: Boxplot of satisfaction with the state of education vs. health services; (2) Remove the x-axis label; (3) Change the y-axis label to: Satisfaction (0-10).

# 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)

## [[1]]
##  [1] "fstcore"      "modelsummary" "fst"          "lubridate"    "forcats"     
##  [6] "stringr"      "dplyr"        "purrr"        "readr"        "tidyr"       
## [11] "tibble"       "ggplot2"      "tidyverse"    "stats"        "graphics"    
## [16] "grDevices"    "utils"        "datasets"     "methods"      "base"        
## 
## [[2]]
##  [1] "fstcore"      "modelsummary" "fst"          "lubridate"    "forcats"     
##  [6] "stringr"      "dplyr"        "purrr"        "readr"        "tidyr"       
## [11] "tibble"       "ggplot2"      "tidyverse"    "stats"        "graphics"    
## [16] "grDevices"    "utils"        "datasets"     "methods"      "base"        
## 
## [[3]]
##  [1] "fstcore"      "modelsummary" "fst"          "lubridate"    "forcats"     
##  [6] "stringr"      "dplyr"        "purrr"        "readr"        "tidyr"       
## [11] "tibble"       "ggplot2"      "tidyverse"    "stats"        "graphics"    
## [16] "grDevices"    "utils"        "datasets"     "methods"      "base"

getwd()

## [1] "C:/Users/hassa947/Desktop/222_Homework"

ess <- read_fst("All-ESS-Data.fst")

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"

france_data <- ess %>%
  filter(cntry == "FR")

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 = "Y-axis", x = "X-axis", title = "Boxplot of stfedu vs. stfhlth") +
  theme_minimal()

## Warning: Removed 364 rows containing non-finite values (`stat_boxplot()`).

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 and changing the title
  ggplot(aes(x = variable, y = value)) +
  geom_boxplot() +
  labs(y = "Y-axis", x = "X-axis", title = "Boxplot of satisfaction with the state of education vs. health services") +
  theme_minimal()

## Warning: Removed 364 rows containing non-finite values (`stat_boxplot()`).

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 and removing the x-axis label
  ggplot(aes(y = value)) +
  geom_boxplot() +
  labs(y = "Y-axis", title = "Boxplot of satisfaction with the state of education vs. health services") +
  theme_minimal()

## Warning: Removed 364 rows containing non-finite values (`stat_boxplot()`).

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 and changing the y-axis label
  ggplot(aes(y =  value)) +
  geom_boxplot() +
  labs(y = " Satisfaction (0-10)", title = "Boxplot of satisfaction with the state of education vs. health services") +
  theme_minimal()

## Warning: Removed 364 rows containing non-finite values (`stat_boxplot()`).

###Answer: According to ESS data the median French person is more satisfied with the health care system than the education system since the median line is higher on the satisfaction scale for the health care system.The satisfaction level is approximately at 7.0 for healh care and 5.0 for the education system.