graebnerc/DataScienceExercises
Exercises for introductions to R

Package index
Search the graebnerc/DataScienceExercises package
Vignettes
Functions
11
Source code
17
Man pages
10
Home
/
GitHub
/
graebnerc/DataScienceExercises
/

In graebnerc/DataScienceExercises: Exercises for introductions to R 

library(learnr)
library(scales)
library(gradethis)
library(dplyr)
library(tidyr)
library(data.table)
knitr::opts_chunk$set(echo = FALSE)
gradethis_setup(
  pass.praise = TRUE, fail.hint = FALSE, 
  fail.encourage = TRUE, maybe_code_feedback = FALSE)

General remarks

This exercise session is meant to give you the opportunity to practice your skills in the context of data preparation. The focus will be on data wrangling, i.e. the transformation of wide and long data sets.

For the following exercises, assume that your project has the following directory structure with all data sets being located directly within the folder data, and you are working from within the script myscript.R:

Exercises
│   Exercises.Rproj    
│
└───data
│   │   education.csv
│   │   poverty_gdp_countries.csv
│   │   poverty_gdp_regions.csv
|   |   renewables_electricity.csv
└───R
    │   myscript.R

Attention: Due to the way these exercises were created you cannot use the function here(), as you would usually do. Thus, use relative paths from the project main directory, i.e. the paths you would normally pass to the function here().

Also, in the following exercises, please make sure that you return your final data set, otherwise your solution cannot be evaluated. This means the the following does not work:

my_solution <- data.frame("a"=1:2, "b"=3:4)

Instead, write:

my_solution <- data.frame("a"=1:2, "b"=3:4)
my_solution

Or:

data.frame("a"=1:2, "b"=3:4)

Finally, whenever your final solution contains a column with years, please make sure this column is called years, otherwise the automated feedback does not work.

Wide and long data I

Note: assume that your project has the following directory structure with all data sets being located directly within the folder data, and you are working from within the script myscript.R:

Exercises
│   Exercises.Rproj    
│
└───data
│   │   education.csv
│   │   poverty_gdp_countries.csv
│   │   poverty_gdp_regions.csv
|   |   renewables_electricity.csv
└───R
    │   myscript.R

Import the data set poverty_gdp_regions.csv and make it tidy. Make sure it is saved as a tibble.



data_raw <- data.table::____(____) 

data_tidy <- tibble::____(data_raw) %>% 
  ____(____
       ) %>% 
  ____(____)

data_tidy

data_raw <- data.table::____(
  file = ____, 
  ____ = ___) 

data_tidy <- tibble::____(data_raw) %>% 
  ____(____
       ) %>% 
  ____(____)

data_tidy

data_raw <- data.table::fread(
  file = ____, 
  ____ = ___) 

data_tidy <- tibble::____(data_raw) %>% 
  ____(____
       ) %>% 
  ____(____)

data_tidy

data_raw <- data.table::fread(
  file = "data/poverty_gdp_regions.csv", 
  ____ = ___) 

data_tidy <- tibble::____(data_raw) %>% 
  ____(____
       ) %>% 
  ____(____)

data_tidy

data_raw <- data.table::fread(
  file = "data/poverty_gdp_regions.csv", 
  ____ = TRUE) 

data_tidy <- tibble::____(data_raw) %>% 
  ____(____
       ) %>% 
  ____(____)

data_tidy

data_raw <- data.table::fread(
  file = "data/poverty_gdp_regions.csv", 
  header = TRUE) 

data_tidy <- tibble::____(data_raw) %>% 
  ____(____
       ) %>% 
  ____(____)

data_tidy

data_raw <- data.table::fread(
  file = "data/poverty_gdp_regions.csv", 
  header = TRUE) 

data_tidy <- tibble::as_tibble(data_raw) %>% 
  ____(____
       ) %>% 
  ____(____)

data_tidy

data_raw <- data.table::fread(
  file = "data/poverty_gdp_regions.csv", 
  header = TRUE) 

data_tidy <- tibble::as_tibble(data_raw) %>% 
  tidyr::____(____
       ) %>% 
  tidyr::____(____)

data_tidy

data_raw <- data.table::fread(
  file = "data/poverty_gdp_regions.csv", 
  header = TRUE) 

data_tidy <- tibble::as_tibble(data_raw) %>% 
  tidyr::pivot_longer(____
       ) %>% 
  tidyr::____(____)

data_tidy

data_raw <- data.table::fread(
  file = "data/poverty_gdp_regions.csv", 
  header = TRUE) 

data_tidy <- tibble::as_tibble(data_raw) %>% 
  tidyr::pivot_longer(____
       ) %>% 
  tidyr::pivot_wider(____)

data_tidy

data_raw <- data.table::fread(
  file = "data/poverty_gdp_regions.csv", 
  header = TRUE) 

data_tidy <- tibble::as_tibble(data_raw) %>% 
  tidyr::pivot_longer(
    cols = ____,
    names_to = ____,
    values_to = ____
    ) %>% 
  tidyr::pivot_wider(____)

data_tidy

data_raw <- data.table::fread(
  file = "data/poverty_gdp_regions.csv", 
  header = TRUE) 

data_tidy <- tibble::as_tibble(data_raw) %>% 
  tidyr::pivot_longer(
    cols = -c("country", "Indicator"), 
    names_to = ____,
    values_to = ____
    ) %>% 
  tidyr::pivot_wider(____)

data_tidy

data_raw <- data.table::fread(
  file = "data/poverty_gdp_regions.csv", 
  header = TRUE) 

data_tidy <- tibble::as_tibble(data_raw) %>% 
  tidyr::pivot_longer(
    cols = -c("country", "Indicator"), 
    names_to = "year", 
    values_to = "value"
    ) %>% 
  tidyr::pivot_wider(____)

data_tidy

data_raw <- data.table::fread(
  file = "data/poverty_gdp_regions.csv", 
  header = TRUE) 

data_tidy <- tibble::as_tibble(data_raw) %>% 
  tidyr::pivot_longer(
    cols = -c("country", "Indicator"), 
    names_to = "year", 
    values_to = "value"
    ) %>% 
  tidyr::pivot_wider(
    names_from = ____, 
    values_from = ____)

data_tidy

data_raw <- data.table::fread(
  file = "data/poverty_gdp_regions.csv", 
  header = TRUE) 

data_tidy <- tibble::as_tibble(data_raw) %>% 
  tidyr::pivot_longer(
    cols = -c("country", "Indicator"), 
    names_to = "year", 
    values_to = "value"
    ) %>% 
  tidyr::pivot_wider(
    names_from = "Indicator", 
    values_from = ____)

data_tidy

data_raw <- data.table::fread(
  file = "data/poverty_gdp_regions.csv",
  header = TRUE) 

data_tidy <- tibble::as_tibble(data_raw) %>% 
  tidyr::pivot_longer(
    cols = -c("country", "Indicator"), 
    names_to = "year", 
    values_to = "value"
    ) %>% 
  tidyr::pivot_wider(
    names_from = "Indicator", 
    values_from = "value")

data_tidy

wrang_2_1_sol <- data.table::fread(
  file = "data/poverty_gdp_regions.csv",
  header = TRUE) %>% 
  tibble::as_tibble() %>% 
  tidyr::pivot_longer(
    cols = -c("country", "Indicator"), 
    names_to = "year", 
    values_to = "value"
    ) %>% 
  tidyr::pivot_wider(
    names_from = "Indicator", 
    values_from = "value")

grader <- grade_this({

  if ( stringr::str_detect(.user_code, "here\\(")){
    fail(message = paste0(
      "Your code should not use the function `here::here()`, although ",
      "you should usually use this function. But for the sake of this ",
      "exercise simply use the relative paths you would usually have ",
      "passed to `here::here()`.")
      )
  }

  if ( !stringr::str_detect(.user_code, "fread") ){
   fail(message = paste0(
      "You need to use the function `fread()` from the package ",
      "`data.table` to import the data!")
    )
  }

  if ( !stringr::str_detect(.user_code, "header") ){
      fail(message = paste0(
        "Have a look at the raw data. For data as this you need to ",
        "use the argument `header` in `data.table::fread()`!")
        )
    }

  if ( !stringr::str_detect(.user_code, "pivot_longer") ){
      fail(message = paste0(
        "When making this data tidy, at some point you need to make ",
        "it longer using the respective function from the package ",
        "`tidyr`!")
        )
    }

  if ( !stringr::str_detect(.user_code, "pivot_wider")){
    fail(message = paste0(
      "When making this data tidy, at some point you need to make ",
      "it wider using the respective function from the package ",
      "`tidyr`!")
      )
  }

  if ( !tibble::is_tibble(.result)){
    fail(message = paste0(
      "Your solution is not a tibble. Did you forget to return it? Or ",
      "did you forget to transform the imported data into a `tibble`? ",
      "The package `tibble` contains a function with which you can ",
      "transform data frames into a `tibble`!")
    )
  }

  if (identical(.result, wrang_2_1_sol)){
    pass()
  }

  fail()
})

Wide and long data II

Note: assume that your project has the following directory structure with all data sets being located directly within the folder data, and you are working from within the script myscript.R:

Exercises
│   Exercises.Rproj    
│
└───data
│   │   education.csv
│   │   poverty_gdp_countries.csv
│   │   poverty_gdp_regions.csv
|   |   renewables_electricity.csv
└───R
    │   myscript.R

Import the data set poverty_gdp_countries.csv. Make the data set tidy and consider only the observations after 2000 and countries from Latin America and the Caribbean. Make sure it is saved as a tibble and does not contain columns that only have one unique value.



data_raw <- ____(____) 

data_tidy <- ____(data_raw) %>% 
  ____(____) %>% 
  ____(____) %>% 
  ____(____) %>% 
  ____(____)

data_tidy

data_raw <- data.table::fread(____) 

data_tidy <- ____(data_raw) %>% 
  ____(____) %>% 
  ____(____) %>% 
  ____(____) %>% 
  ____(____)

data_tidy

data_raw <- data.table::fread(
  file = ,
   = TRUE) 

data_tidy <- ____(data_raw) %>% 
  ____(____) %>% 
  ____(____) %>% 
  ____(____) %>% 
  ____(____)

data_tidy

data_raw <- data.table::fread(
  file = "data/poverty_gdp_countries.csv",
  header = TRUE) 

data_tidy <- ____(data_raw) %>% 
  ____(____) %>% 
  ____(____) %>% 
  ____(____) %>% 
  ____(____)

data_tidy

data_raw <- data.table::fread(
  file = "data/poverty_gdp_countries.csv",
  header = TRUE) 

data_tidy <- tibble::as_tibble(data_raw) %>% 
  ____(____) %>% 
  ____(____) %>% 
  ____(____) %>% 
  ____(____)

data_tidy

data_raw <- data.table::fread(
  file = "data/poverty_gdp_countries.csv",
  header = TRUE) 

data_tidy <- tibble::as_tibble(data_raw) %>% 
  tidyr::____(____) %>% 
  dplyr::____(____) %>% 
  tidyr::____(____) %>% 
  dplyr::____(____)

data_tidy

data_raw <- data.table::fread(
  file = "data/poverty_gdp_countries.csv",
  header = TRUE) 

data_tidy <- tibble::as_tibble(data_raw) %>% 
  tidyr::pivot_longer(____) %>% 
  dplyr::____(____) %>% 
  tidyr::____(____) %>% 
  dplyr::____(____)

data_tidy

data_raw <- data.table::fread(
  file = "data/poverty_gdp_countries.csv",
  header = TRUE) 

data_tidy <- tibble::as_tibble(data_raw) %>% 
  tidyr::pivot_longer(____) %>% 
  dplyr::____(____) %>% 
  tidyr::____(____) %>% 
  dplyr::____(____)

data_tidy

data_raw <- data.table::fread(
  file = "data/poverty_gdp_countries.csv",
  header = TRUE) 

data_tidy <- tibble::as_tibble(data_raw) %>% 
  tidyr::pivot_longer(
    cols = ____, 
    names_to = ____, 
    values_to = ____
  ) %>% 
  dplyr::____(____) %>% 
  tidyr::____(____) %>% 
  dplyr::____(____)

data_tidy

data_raw <- data.table::fread(
  file = "data/poverty_gdp_countries.csv",
  header = TRUE) 

data_tidy <- tibble::as_tibble(data_raw) %>% 
  tidyr::pivot_longer(
    cols = -c("country", "region", "Indicator"), 
    names_to = "year", 
    values_to = "value"
  ) %>% 
  dplyr::____(____) %>% 
  tidyr::____(____) %>% 
  dplyr::____(____)

data_tidy

data_raw <- data.table::fread(
  file = "data/poverty_gdp_countries.csv",
  header = TRUE) 

data_tidy <- tibble::as_tibble(data_raw) %>% 
  tidyr::pivot_longer(
    cols = -c("country", "region", "Indicator"), 
    names_to = "year", 
    values_to = "value"
  ) %>% 
  dplyr::filter(____) %>% 
  tidyr::____(____) %>% 
  dplyr::____(____)

data_tidy

data_raw <- data.table::fread(
  file = "data/poverty_gdp_countries.csv",
  header = TRUE) 

data_tidy <- tibble::as_tibble(data_raw) %>% 
  tidyr::pivot_longer(
    cols = -c("country", "region", "Indicator"), 
    names_to = "year", 
    values_to = "value"
  ) %>% 
  dplyr::filter(
    year>=2000,
    region == "Latin America & Caribbean"
    ) %>% 
  tidyr::____(____) %>% 
  dplyr::____(____)

data_tidy

data_raw <- data.table::fread(
  file = "data/poverty_gdp_countries.csv",
  header = TRUE) 

data_tidy <- tibble::as_tibble(data_raw) %>% 
  tidyr::pivot_longer(
    cols = -c("country", "region", "Indicator"), 
    names_to = "year", 
    values_to = "value"
  ) %>% 
  dplyr::filter(
    year>=2000,
    region == "Latin America & Caribbean"
    ) %>% 
  tidyr::pivot_wider(____) %>% 
  dplyr::____(____)

data_tidy

data_raw <- data.table::fread(
  file = "data/poverty_gdp_countries.csv",
  header = TRUE) 

data_tidy <- tibble::as_tibble(data_raw) %>% 
  tidyr::pivot_longer(
    cols = -c("country", "region", "Indicator"), 
    names_to = "year", 
    values_to = "value"
  ) %>% 
  dplyr::filter(
    year>=2000,
    region == "Latin America & Caribbean"
    ) %>% 
  tidyr::pivot_wider(
    names_from = ____, 
    values_from = ____
  ) %>% 
  dplyr::____(____)

data_tidy

data_raw <- data.table::fread(
  file = "data/poverty_gdp_countries.csv",
  header = TRUE) 

data_tidy <- tibble::as_tibble(data_raw) %>% 
  tidyr::pivot_longer(
    cols = -c("country", "region", "Indicator"), 
    names_to = "year", 
    values_to = "value"
  ) %>% 
  dplyr::filter(
    year>=2000,
    region == "Latin America & Caribbean"
    ) %>% 
  tidyr::pivot_wider(
    names_from = "Indicator", 
    values_from = "value"
  ) %>% 
  dplyr::____(____)

data_tidy

data_raw <- data.table::fread(
  file = "data/poverty_gdp_countries.csv",
  header = TRUE) 

data_tidy <- tibble::as_tibble(data_raw) %>% 
  tidyr::pivot_longer(
    cols = -c("country", "region", "Indicator"), 
    names_to = "year", 
    values_to = "value"
  ) %>% 
  dplyr::filter(
    year>=2000,
    region == "Latin America & Caribbean"
    ) %>% 
  tidyr::pivot_wider(
    names_from = "Indicator", 
    values_from = "value"
  ) %>% 
  dplyr::select(____)

data_tidy

data_raw <- data.table::fread(
  file = "data/poverty_gdp_countries.csv",
  header = TRUE) 

data_tidy <- tibble::as_tibble(data_raw) %>% 
  tidyr::pivot_longer(
    cols = -c("country", "region", "Indicator"), 
    names_to = "year", 
    values_to = "value"
    ) %>% 
  dplyr::filter(
    year>=2000,
    region == "Latin America & Caribbean"
    ) %>% 
  tidyr::pivot_wider(
    names_from = "Indicator", 
    values_from = "value"
    ) %>% 
  dplyr::select(-region)

data_tidy

wrang_2_2_sol <- data.table::fread(
  file = "data/poverty_gdp_countries.csv",
  header = TRUE) %>% 
  tibble::as_tibble(.) %>% 
  tidyr::pivot_longer(
    cols = -c("country", "region", "Indicator"), 
    names_to = "year", 
    values_to = "value"
    ) %>% 
  dplyr::filter(
    year>=2000,
    region == "Latin America & Caribbean"
    ) %>% 
  tidyr::pivot_wider(
    names_from = "Indicator", 
    values_from = "value") %>% 
  dplyr::select(-region)

grader <- grade_this({

  if ( stringr::str_detect(.user_code, "here\\(")){
    fail(message = paste0(
      "Your code should not use the function `here::here()`, although ",
      "you should usually use this function. But for the sake of this ",
      "exercise simply use the relative paths you would usually have ",
      "passed to `here::here()`.")
      )
  }

  if ( !stringr::str_detect(.user_code, "fread") ){
   fail(message = paste0(
      "You need to use the function `fread()` from the package ",
      "`data.table` to import the data!")
    )
  }

  if ( !stringr::str_detect(.user_code, "header") ){
      fail(message = paste0(
        "Have a look at the raw data. For data as this you need to ",
        "use the argument `header` in `data.table::fread()`!")
        )
    }

  if ( !stringr::str_detect(.user_code, "pivot_longer") ){
      fail(message = paste0(
        "When making this data tidy, at some point you need to make ",
        "it longer using the respective function from the package ",
        "`tidyr`!")
        )
    }

  if ( !stringr::str_detect(.user_code, "pivot_wider")){
    fail(message = paste0(
      "When making this data tidy, at some point you need to make ",
      "it wider using the respective function from the package ",
      "`tidyr`!")
      )
  }

  if ( !stringr::str_detect(.user_code, "filter") ){
      fail(message = paste0(
        "You need to filter the data with the right function from the ",
        "package `dplyr`!")
        )
  }

  if ( !stringr::str_detect(.user_code, "select") ){
      fail(message = paste0(
        "You need to remove columns that only contain a single unique ",
        "value. You can use the function `unique` to search these ",
        "columns, and remove them using `dplyr::select()`!")
        )
  }

  if ( "region" %in%  names(.result) ){
      fail(message = paste0(
        "Your result contains the colums `region`, but you were asked to ",
        "keep only countries from the region 'Latin America & Caribbean. ",
        "Thus, this column becomes superflouus. ",
        "You can remove it using `dplyr::select()`!")
        )
  }

  if ( !tibble::is_tibble(.result)){
    fail(message = paste0(
      "Your solution is not a tibble. Did you forget to return it? Or ",
      "did you forget to transform the imported data into a `tibble`? ",
      "The package `tibble` contains a function with which you can ",
      "transform data frames into a `tibble`!")
    )
  }

  if (identical(.result, wrang_2_2_sol)){
    pass()
  }

  fail()
})

Wide and long data III

Note: assume that your project has the following directory structure with all data sets being located directly within the folder data, and you are working from within the script myscript.R:

Exercises
│   Exercises.Rproj    
│
└───data
│   │   education.csv
│   │   poverty_gdp_countries.csv
│   │   poverty_gdp_regions.csv
|   |   renewables_electricity.csv
└───R
    │   myscript.R

Import the data set renewables_electricity.csv. It contains information about the share of electricity created from renewable sources. Make it tidy, filter out any missing values, only keep countries from the region 'Europe & Central Asia', and remove all columns that contain only one unique value. Also, information about the share of renawable electricity should be in a column called 'RenewableElectricity'. Finally, make sure the data is saved as a tibble .



data_raw <- ____(____)

data_tidy <- ____(____) %>% 
  ____(____) %>% 
  ____(____) %>% 
  ____(____)

data_tidy

data_raw <- data.table::fread(____)

data_tidy <- ____(____) %>% 
  ____(____) %>% 
  ____(____) %>% 
  ____(____)

data_tidy

data_raw <- data.table::fread(
  file = "data/renewables_electricity.csv")

data_tidy <- ____(____) %>% 
  ____(____) %>% 
  ____(____) %>% 
  ____(____)

data_tidy

data_raw <- data.table::fread(
  file = "data/renewables_electricity.csv")

data_tidy <- tibble::____(____) %>% 
  ____(____) %>% 
  ____(____) %>% 
  ____(____)

data_tidy

data_raw <- data.table::fread(
  file = "data/renewables_electricity.csv")

data_tidy <- tibble::as_tibble(data_raw) %>% 
  ____(____) %>% 
  ____(____) %>% 
  ____(____)

data_tidy

data_raw <- data.table::fread(
  file = "data/renewables_electricity.csv")

data_tidy <- tibble::as_tibble(data_raw) %>% 
  tidyr::____(____) %>% 
  ____(____) %>% 
  ____(____)

data_tidy

data_raw <- data.table::fread(
  file = "data/renewables_electricity.csv")

data_tidy <- tibble::as_tibble(data_raw) %>% 
  tidyr::pivot_longer(____) %>% 
  ____(____) %>% 
  ____(____)

data_tidy

data_raw <- data.table::fread(
  file = "data/renewables_electricity.csv")

data_tidy <- tibble::as_tibble(data_raw) %>% 
  tidyr::pivot_longer(
    ____ = ____, 
    ____ = ____, 
    ____ = ____
  ) %>% 
  ____(____) %>% 
  ____(____)

data_tidy

data_raw <- data.table::fread(
  file = "data/renewables_electricity.csv")

data_tidy <- tibble::as_tibble(data_raw) %>% 
  tidyr::pivot_longer(
    cols = ____, 
    names_to = ____, 
    values_to = ____
  ) %>% 
  ____(____) %>% 
  ____(____)

data_tidy

data_raw <- data.table::fread(
  file = "data/renewables_electricity.csv")

data_tidy <- tibble::as_tibble(data_raw) %>% 
  tidyr::pivot_longer(
    cols = -c("country", "year"), 
    names_to = ____, 
    values_to = ____
  ) %>% 
  ____(____) %>% 
  ____(____)

data_tidy

data_raw <- data.table::fread(
  file = "data/renewables_electricity.csv")

data_tidy <- tibble::as_tibble(data_raw) %>% 
  tidyr::pivot_longer(
    cols = -c("country", "year"), 
    names_to = "region", 
    values_to = ____
  ) %>% 
  ____(____) %>% 
  ____(____)

data_tidy

data_raw <- data.table::fread(
  file = "data/renewables_electricity.csv")

data_tidy <- tibble::as_tibble(data_raw) %>% 
  tidyr::pivot_longer(
    cols = -c("country", "year"), 
    names_to = "region", 
    values_to = "RenewableElectricity"
  ) %>% 
  ____(____) %>% 
  ____(____)

data_tidy

data_raw <- data.table::fread(
  file = "data/renewables_electricity.csv")

data_tidy <- tibble::as_tibble(data_raw) %>% 
  tidyr::pivot_longer(
    cols = -c("country", "year"), 
    names_to = "region", 
    values_to = "RenewableElectricity"
  ) %>% 
  dplyr::filter(____) %>% 
  ____(____)

data_tidy

data_raw <- data.table::fread(
  file = "data/renewables_electricity.csv")

data_tidy <- tibble::as_tibble(data_raw) %>% 
  tidyr::pivot_longer(
    cols = -c("country", "year"), 
    names_to = "region", 
    values_to = "RenewableElectricity"
  ) %>% 
  dplyr::filter(
    region == ____,
    !____(____)
  ) %>% 
  ____(____)

data_tidy

data_raw <- data.table::fread(
  file = "data/renewables_electricity.csv")

data_tidy <- tibble::as_tibble(data_raw) %>% 
  tidyr::pivot_longer(
    cols = -c("country", "year"), 
    names_to = "region", 
    values_to = "RenewableElectricity"
  ) %>% 
  dplyr::filter(
    region == "Europe & Central Asia",
    !is.na(RenewableElectricity)
  ) %>% 
  ____(____)

data_tidy

data_raw <- data.table::fread(
  file = "data/renewables_electricity.csv")

data_tidy <- tibble::as_tibble(data_raw) %>% 
  tidyr::pivot_longer(
    cols = -c("country", "year"), 
    names_to = "region", 
    values_to = "RenewableElectricity"
  ) %>% 
  dplyr::filter(
    region == "Europe & Central Asia",
    !is.na(RenewableElectricity)
  ) %>% 
  dplyr::select(____)

data_tidy

data_raw <- data.table::fread(
  file = "data/renewables_electricity.csv")

data_tidy <- tibble::as_tibble(data_raw) %>% 
  tidyr::pivot_longer(
    cols = -c("country", "year"), 
    names_to = "region", 
    values_to = "RenewableElectricity"
    ) %>% 
  dplyr::filter(
    region == "Europe & Central Asia",
    !is.na(RenewableElectricity)
    ) %>% 
  dplyr::select(-region)

data_tidy

wrang_2_3_sol <- data.table::fread(
  file = "data/renewables_electricity.csv") %>% 
  tibble::as_tibble(.) %>% 
  tidyr::pivot_longer(
    cols = -c("country", "year"), 
    names_to = "region", 
    values_to = "RenewableElectricity"
    ) %>% 
  dplyr::filter(
    region == "Europe & Central Asia",
    !is.na(RenewableElectricity)
    ) %>% 
  dplyr::select(-region)

grader <- grade_this({

  if ( stringr::str_detect(.user_code, "here\\(")){
    fail(message = paste0(
      "Your code should not use the function `here::here()`, although ",
      "you should usually use this function. But for the sake of this ",
      "exercise simply use the relative paths you would usually have ",
      "passed to `here::here()`.")
      )
  }

  if ( !stringr::str_detect(.user_code, "fread") ){
   fail(message = paste0(
      "You need to use the function `fread()` from the package ",
      "`data.table` to import the data!")
    )
  }

  if ( !stringr::str_detect(.user_code, "pivot_longer") ){
      fail(message = paste0(
        "When making this data tidy, at some point you need to make ",
        "it longer using the respective function from the package ",
        "`tidyr`!")
        )
    }

  if ( !stringr::str_detect(.user_code, "filter") ){
      fail(message = paste0(
        "You need to filter the data with the right function from the ",
        "package `dplyr`!")
        )
  }

  if ( !stringr::str_detect(.user_code, "select") ){
      fail(message = paste0(
        "You need to remove columns that only contain a single unique ",
        "value. You can use the function `unique` to search these ",
        "columns, and remove them using `dplyr::select()`!")
        )
  }

  if ( !"RenewableElectricity" %in%  names(.result) ){
      fail(message = paste0(
        "You were asked to save the information about the share of electricity ",
        "in a column called `RenewableElectricity`. You might use ",
        "dplyr::rename() or set the right name when using tidyr::pivot_longer()!")
        )
  }

  if ( "region" %in%  names(.result) ){
      fail(message = paste0(
        "Your result contains the colums `region`, but you were asked to ",
        "keep only countries from the region 'Latin America & Caribbean. ",
        "Thus, this column becomes superflouus. ",
        "You can remove it using `dplyr::select()`!")
        )
  }

  if ( sum(is.na(.result))>0 ){
      fail(message = paste0(
        "You still need to filter out missing values. Use `is.na()` ",
        "within `dplyr::filter()` to do so!")
        )
  }
  if ( !tibble::is_tibble(.result)){
    fail(message = paste0(
      "Your solution is not a tibble. Did you forget to return it? Or ",
      "did you forget to transform the imported data into a `tibble`? ",
      "The package `tibble` contains a function with which you can ",
      "transform data frames into a `tibble`!")
    )
  }

  if (identical(.result, wrang_2_3_sol)){
    pass()
  }

  fail()
})

Wide and long data IV

Note: assume that your project has the following directory structure with all data sets being located directly within the folder data, and you are working from within the script myscript.R:

Exercises
│   Exercises.Rproj    
│
└───data
│   │   education.csv
│   │   poverty_gdp_countries.csv
│   │   poverty_gdp_regions.csv
|   |   renewables_electricity.csv
└───R
    │   myscript.R

Import the data set education.csv and compute average values for the period after 2000 for the different regions. Then make sure the resulting data set is saved as a tibble and each region has its own column.

Note: This means you are not asked to return a tidy data set!



data_raw <- ____(____)

data_final <- ____(____) %>% 
  ____(____) %>% 
  ____(____) %>% 
  ____(____)

data_final

data_raw <- data.table::fread(____)

data_final <- ____(____) %>% 
  ____(____) %>% 
  ____(____) %>% 
  ____(____)

data_final

data_raw <- data.table::fread(
  file = "data/education.csv")

data_final <- ____(____) %>% 
  ____(____) %>% 
  ____(____) %>% 
  ____(____)

data_final

data_raw <- data.table::fread(
  file = "data/education.csv")

data_final <- tibble::____(data_raw) %>% 
  ____(____) %>% 
  ____(____) %>% 
  ____(____)

data_final

data_raw <- data.table::fread(
  file = "data/education.csv")

data_final <- tibble::as_tibble(data_raw) %>% 
  ____(____) %>% 
  ____(____) %>% 
  ____(____)

data_final

data_raw <- data.table::fread(
  file = "data/education.csv")

data_final <- tibble::as_tibble(data_raw) %>% 
  dplyr::____(____) %>% 
  dplyr::____(____) %>% 
  tidyr::____(____)

data_final

data_raw <- data.table::fread(
  file = "data/education.csv")

data_final <- tibble::as_tibble(data_raw) %>% 
  dplyr::filter(____) %>% 
  dplyr::____(____) %>% 
  tidyr::____(____)

data_final

data_raw <- data.table::fread(
  file = "data/education.csv")

data_final <- tibble::as_tibble(data_raw) %>% 
  dplyr::filter(year>=2000) %>% 
  dplyr::____(____) %>% 
  tidyr::____(____)

data_final

data_raw <- data.table::fread(
  file = "data/education.csv")

data_final <- tibble::as_tibble(data_raw) %>% 
  dplyr::filter(year>=2000) %>% 
  dplyr::summarise(____) %>% 
  tidyr::____(____)

data_final

data_raw <- data.table::fread(
  file = "data/education.csv")

data_final <- tibble::as_tibble(data_raw) %>% 
  dplyr::filter(year>=2000) %>% 
  dplyr::summarise(
    Value=____(____), 
    ____ = c("region", "Indicator")
  ) %>% 
  tidyr::____(____)

data_final

data_raw <- data.table::fread(
  file = "data/education.csv")

data_final <- tibble::as_tibble(data_raw) %>% 
  dplyr::filter(year>=2000) %>% 
  dplyr::summarise(
    Value=mean(Value), 
    ____ = c("region", "Indicator")
  ) %>% 
  tidyr::____(____)

data_final

data_raw <- data.table::fread(
  file = "data/education.csv")

data_final <- tibble::as_tibble(data_raw) %>% 
  dplyr::filter(year>=2000) %>% 
  dplyr::summarise(
    Value=mean(Value), 
    .by = c("region", "Indicator")
  ) %>% 
  tidyr::____(____)

data_final

data_raw <- data.table::fread(
  file = "data/education.csv")

data_final <- tibble::as_tibble(data_raw) %>% 
  dplyr::filter(year>=2000) %>% 
  dplyr::summarise(
    Value=mean(Value), 
    .by = c("region", "Indicator")
  ) %>% 
  tidyr::pivot_wider(____)

data_final

data_raw <- data.table::fread(
  file = "data/education.csv")

data_final <- tibble::as_tibble(data_raw) %>% 
  dplyr::filter(year>=2000) %>% 
  dplyr::summarise(
    Value=mean(Value), 
    .by = c("region", "Indicator")
  ) %>% 
  tidyr::pivot_wider(
    names_from = ____, 
    values_from = ____)

data_final

data_raw <- data.table::fread(
  file = "data/education.csv")

data_final <- tibble::as_tibble(data_raw) %>% 
  dplyr::filter(year>=2000) %>% 
  dplyr::summarise(
    Value=mean(Value), 
    .by = c("region", "Indicator")
  ) %>% 
  tidyr::pivot_wider(
    names_from = "region", 
    values_from = ____)

data_final

data_raw <- data.table::fread(
  file = "data/education.csv")

data_final <- tibble::as_tibble(data_raw) %>% 
  dplyr::filter(year>=2000) %>% 
  dplyr::summarise(
    Value=mean(Value), 
    .by = c("region", "Indicator")
    ) %>% 
  tidyr::pivot_wider(
    names_from = "region", 
    values_from = "Value")

data_final

wrang_2_4_sol <- data.table::fread(
  file = "data/education.csv") %>% 
  tibble::as_tibble(.) %>% 
  dplyr::filter(year>=2000) %>% 
  dplyr::summarise(
    Value=mean(Value), 
    .by = c("region", "Indicator")
    ) %>% 
  tidyr::pivot_wider(
    names_from = "region", 
    values_from = "Value")

wrang_2_4_sol_alt <- data.table::fread(
  file = "data/education.csv") %>% 
  tibble::as_tibble(.) %>% 
  dplyr::filter(year>=2000) %>% 
  dplyr::group_by(region, Indicator) %>% 
  dplyr::summarise(
    Value=mean(Value), .groups = "drop"
    ) %>% 
  tidyr::pivot_wider(
    names_from = "region", 
    values_from = "Value")


grader <- grade_this({

  if ( stringr::str_detect(.user_code, "here\\(")){
    fail(message = paste0(
      "Your code should not use the function `here::here()`, although ",
      "you should usually use this function. But for the sake of this ",
      "exercise simply use the relative paths you would usually have ",
      "passed to `here::here()`.")
      )
  }

  if ( !stringr::str_detect(.user_code, "fread") ){
   fail(message = paste0(
      "You need to use the function `fread()` from the package ",
      "`data.table` to import the data!")
    )
  }

  if ( !stringr::str_detect(.user_code, "filter") ){
      fail(message = paste0(
        "You need to filter the data with the right function from the ",
        "package `dplyr`!")
        )
  }

  if ( !stringr::str_detect(.user_code, "summari") ){
      fail(message = paste0(
        "You need to summarize the data with the right function from the ",
        "package `dplyr`!")
        )
  }

  if ( !(stringr::str_detect(.user_code, "\\.by") | stringr::str_detect(.user_code, "group_by")) ){
      fail(message = paste0(
        "You need to group the data when summarizing it. You can use ",
        "`dplyr::group_by()` or the `.by` argument in `dplyr::summarize()`.")
        )
  }

  if ( !stringr::str_detect(.user_code, "pivot_wider")){
    fail(message = paste0(
      "When making this data tidy, at some point you need to make ",
      "it wider using the respective function from the package ",
      "`tidyr`!")
      )
  }

  if (dplyr::is_grouped_df(.result) ){
    fail(message = paste0(
      "Your final data is still grouped. You need to ungroup it!")
      )
  }

  if ( !tibble::is_tibble(.result)){
    fail(message = paste0(
      "Your solution is not a tibble. Did you forget to return it? Or ",
      "did you forget to transform the imported data into a `tibble`? ",
      "The package `tibble` contains a function with which you can ",
      "transform data frames into a `tibble`!")
    )
  }

  if ( identical(.result, wrang_2_4_sol) | identical(.result, wrang_2_4_sol_alt) ){
    pass()
  }

  fail()
})


graebnerc/DataScienceExercises documentation built on April 11, 2025, 7:57 p.m.

R Package Documentation

rdrr.io home R language documentation Run R code online

Browse R Packages

CRAN packages Bioconductor packages R-Forge packages GitHub packages

We want your feedback!

Note that we can't provide technical support on individual packages. You should contact the package authors for that.
GitHub issue tracker
ian@mutexlabs.com
Personal blog

 
Embedding an R snippet on your website

Add the following code to your website.

For more information on customizing the embed code, read Embedding Snippets.

Close