3 min read

Assignment A02: TIDYVERSE

Input the world-happiness-report.csv and world-happiness-report-2021.csv files

library(tidyverse)
## -- Attaching packages --------------------------------------- tidyverse 1.3.1 --
## v ggplot2 3.3.3     v purrr   0.3.4
## v tibble  3.1.1     v dplyr   1.0.6
## v tidyr   1.1.3     v stringr 1.4.0
## v readr   1.4.0     v forcats 0.5.1
## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()
happy <- read_csv("world-happiness-report.csv")
## 
## -- Column specification --------------------------------------------------------
## cols(
##   Country_name = col_character(),
##   year = col_double(),
##   Life_Ladder = col_double(),
##   Log_GDP_per_capita = col_double(),
##   Social_support = col_double(),
##   Healthy_life_expectancy_at_birth = col_double(),
##   Freedom_to_make_life_choices = col_double(),
##   Generosity = col_double(),
##   Perceptions_of_corruption = col_double(),
##   Positive_affect = col_double(),
##   Negative_affect = col_double()
## )
happy <- read_csv(file.choose())
## 
## -- Column specification --------------------------------------------------------
## cols(
##   Country_name = col_character(),
##   year = col_double(),
##   Life_Ladder = col_double(),
##   Log_GDP_per_capita = col_double(),
##   Social_support = col_double(),
##   Healthy_life_expectancy_at_birth = col_double(),
##   Freedom_to_make_life_choices = col_double(),
##   Generosity = col_double(),
##   Perceptions_of_corruption = col_double(),
##   Positive_affect = col_double(),
##   Negative_affect = col_double()
## )
happy21 <- read_csv("world-happiness-report-2021.csv")
## 
## -- Column specification --------------------------------------------------------
## cols(
##   .default = col_double(),
##   Country_name = col_character(),
##   Regional_indicator = col_character()
## )
## i Use `spec()` for the full column specifications.
happy21 <- read_csv(file.choose())
## 
## -- Column specification --------------------------------------------------------
## cols(
##   .default = col_double(),
##   Country_name = col_character(),
##   Regional_indicator = col_character()
## )
## i Use `spec()` for the full column specifications.
head(happy)
## # A tibble: 6 x 11
##   Country_name  year Life_Ladder Log_GDP_per_capita Social_support
##   <chr>        <dbl>       <dbl>              <dbl>          <dbl>
## 1 Afghanistan   2008        3.72               7.37          0.451
## 2 Afghanistan   2009        4.40               7.54          0.552
## 3 Afghanistan   2010        4.76               7.65          0.539
## 4 Afghanistan   2011        3.83               7.62          0.521
## 5 Afghanistan   2012        3.78               7.70          0.521
## 6 Afghanistan   2013        3.57               7.72          0.484
## # ... with 6 more variables: Healthy_life_expectancy_at_birth <dbl>,
## #   Freedom_to_make_life_choices <dbl>, Generosity <dbl>,
## #   Perceptions_of_corruption <dbl>, Positive_affect <dbl>,
## #   Negative_affect <dbl>
names(happy)
##  [1] "Country_name"                     "year"                            
##  [3] "Life_Ladder"                      "Log_GDP_per_capita"              
##  [5] "Social_support"                   "Healthy_life_expectancy_at_birth"
##  [7] "Freedom_to_make_life_choices"     "Generosity"                      
##  [9] "Perceptions_of_corruption"        "Positive_affect"                 
## [11] "Negative_affect"
head(happy21)
## # A tibble: 6 x 20
##   Country_name Regional_indicat~ Ladder_score Standard_error_of_la~ upperwhisker
##   <chr>        <chr>                    <dbl>                 <dbl>        <dbl>
## 1 Finland      Western Europe            7.84                 0.032         7.90
## 2 Denmark      Western Europe            7.62                 0.035         7.69
## 3 Switzerland  Western Europe            7.57                 0.036         7.64
## 4 Iceland      Western Europe            7.55                 0.059         7.67
## 5 Netherlands  Western Europe            7.46                 0.027         7.52
## 6 Norway       Western Europe            7.39                 0.035         7.46
## # ... with 15 more variables: lowerwhisker <dbl>, Logged_GDP_per_capita <dbl>,
## #   Social_support <dbl>, Healthy_life_expectancy <dbl>,
## #   Freedom_to_make_life_choices <dbl>, Generosity <dbl>,
## #   Perceptions_of_corruption <dbl>, Ladder_score_in_Dystopia <dbl>,
## #   Explained by_Log_GDP_per_capita <dbl>, Explained by_Social_support <dbl>,
## #   Explained by_Healthy_life_expectancy <dbl>,
## #   Explained_by_Freedom_to_make_life_choices <dbl>,
## #   Explained_by_Generosity <dbl>,
## #   Explained_by_Perceptions_of_corruption <dbl>, Dystopia_residual <dbl>
names(happy21)
##  [1] "Country_name"                             
##  [2] "Regional_indicator"                       
##  [3] "Ladder_score"                             
##  [4] "Standard_error_of_ladder_score"           
##  [5] "upperwhisker"                             
##  [6] "lowerwhisker"                             
##  [7] "Logged_GDP_per_capita"                    
##  [8] "Social_support"                           
##  [9] "Healthy_life_expectancy"                  
## [10] "Freedom_to_make_life_choices"             
## [11] "Generosity"                               
## [12] "Perceptions_of_corruption"                
## [13] "Ladder_score_in_Dystopia"                 
## [14] "Explained by_Log_GDP_per_capita"          
## [15] "Explained by_Social_support"              
## [16] "Explained by_Healthy_life_expectancy"     
## [17] "Explained_by_Freedom_to_make_life_choices"
## [18] "Explained_by_Generosity"                  
## [19] "Explained_by_Perceptions_of_corruption"   
## [20] "Dystopia_residual"

one table

happy21 %>%
  count(Healthy_life_expectancy > 70, sort = TRUE)
## # A tibble: 2 x 2
##   `Healthy_life_expectancy > 70`     n
##   <lgl>                          <int>
## 1 FALSE                            115
## 2 TRUE                              34