Reading and Writing Data

Code and text for Quiz 4.

1. Load the packages that we will use.

library(tidyverse)
library(here)
library(janitor)
library(skimr)

2. Download \(CO_2\) emissions per capita from Our World in Data into the directory for this post.

3. Assign the location of the file to file_csv. The data should be in the same directory as this file

Read the data into R and assign it to emissions

file_csv <- here("_posts",
                 "2022-02-17-reading-and-writing-data",
                 "co-emissions-per-capita.csv")

emissions <- read_csv(file_csv)

4. Show the first 10 rows (observations of) emissions

emissions

# A tibble: 23,949 × 4
   Entity      Code   Year `Share of global cumulative CO2 emissions`
   <chr>       <chr> <dbl>                                      <dbl>
 1 Afghanistan AFG    1949                                          0
 2 Afghanistan AFG    1950                                          0
 3 Afghanistan AFG    1951                                          0
 4 Afghanistan AFG    1952                                          0
 5 Afghanistan AFG    1953                                          0
 6 Afghanistan AFG    1954                                          0
 7 Afghanistan AFG    1955                                          0
 8 Afghanistan AFG    1956                                          0
 9 Afghanistan AFG    1957                                          0
10 Afghanistan AFG    1958                                          0
# … with 23,939 more rows

5. Start with emissions data THEN

• use clean_names from the janitor package to make the names easier to work with
• assign the output to tidy_emissions
• show the first 10 rows of tidy_emissions

tidy_emissions <- emissions %>% 
  clean_names()

tidy_emissions

# A tibble: 23,949 × 4
   entity      code   year share_of_global_cumulative_co2_emissions
   <chr>       <chr> <dbl>                                    <dbl>
 1 Afghanistan AFG    1949                                        0
 2 Afghanistan AFG    1950                                        0
 3 Afghanistan AFG    1951                                        0
 4 Afghanistan AFG    1952                                        0
 5 Afghanistan AFG    1953                                        0
 6 Afghanistan AFG    1954                                        0
 7 Afghanistan AFG    1955                                        0
 8 Afghanistan AFG    1956                                        0
 9 Afghanistan AFG    1957                                        0
10 Afghanistan AFG    1958                                        0
# … with 23,939 more rows

6. Start with the tidy_emissions THEN

• use filter to extract rows with year == 1997 THEN
• use skim to calculate the descriptive statistics

tidy_emissions %>% 
  filter(year == 1997) %>% 
  skim()

Table 1: Data summary

Name	Piped data
Number of rows	231
Number of columns	4
_______________________
Column type frequency:
character	2
numeric	2
________________________
Group variables	None

Variable type: character

skim_variable	n_missing	complete_rate	min	max	empty	n_unique	whitespace
entity	0	1.00	4	32	0	231	0
code	13	0.94	3	8	0	218	0

Variable type: numeric

skim_variable	n_missing	complete_rate	mean	sd	p0	p25	p50	p75	p100	hist
year	0	1	1997.0	0.00	1997	1997	1997.00	1997.0	1997	▁▁▇▁▁
share_of_global_cumulative_co2_emissions	0	1	1.7	8.21	0	0	0.02	0.2	100	▇▁▁▁▁

7. 13 observations have a missing code. How are these observations different?

• start with tidy emissions then extract rows with year == 1997 and are missing a code

tidy_emissions %>% 
  filter(year == 1997, is.na(code))

# A tibble: 13 × 4
   entity                     code   year share_of_global_cumulative_…
   <chr>                      <chr> <dbl>                        <dbl>
 1 Africa                     <NA>   1997                         2.17
 2 Asia                       <NA>   1997                        19.1 
 3 Asia (excl. China & India) <NA>   1997                        10.8 
 4 EU-27                      <NA>   1997                        21.9 
 5 EU-28                      <NA>   1997                        28.7 
 6 Europe                     <NA>   1997                        40.5 
 7 Europe (excl. EU-27)       <NA>   1997                        18.7 
 8 Europe (excl. EU-28)       <NA>   1997                        11.8 
 9 International transport    <NA>   1997                         1.94
10 North America              <NA>   1997                        33.0 
11 North America (excl. USA)  <NA>   1997                         3.49
12 Oceania                    <NA>   1997                         1.12
13 South America              <NA>   1997                         2.08

Entities that are not countries do not have country codes.

8. Start with tidy_emissions THEN

• use filter to extract rows with year == 1997 and without missing codes THEN
• use select to drop the year variable THEN
• use rename to change the variable entity to country
• assign the output to emissions_1997

emissions_1997 <- tidy_emissions %>% 
  filter(year == 1997, !is.na(code)) %>% 
  select(-year) %>% 
  rename(country = entity)

9. Which 15 countries have the highest share_of_global_cumulative_co2_emissions?

• start with emissions_1997 THEN
• use slice_max to extract the 15 rows with the share_of_global_cumulative_co2_emissions
• assign the output to max_15_emitters

max_15_emitters <- emissions_1997 %>%
  slice_max(share_of_global_cumulative_co2_emissions, n = 15)

10. Which 15 countries have the lowest share_of_global_cumulative_co2_emissions?

• start with emissions_1997 THEN
• use slice_max to extract the 15 rows with the lowest values
• assign the output to min_15_emitters

min_15_emitters <- emissions_1997 %>% 
  slice_min(share_of_global_cumulative_co2_emissions, n = 15)

11. Use bind_rows to bind together the max_15_emitters and min_15_emitters

• assign the output to max_min_15

max_min_15 <- bind_rows(max_15_emitters, min_15_emitters)

12. Export max_min_15 to 3 file formats

max_min_15 %>% write_csv("max_min_15.csv") # comma separated values
max_min_15 %>% write_tsv("max_min_15.tsv") # tab separated
max_min_15 %>% write_delim("max_min_15.psv", delim = "|") # pipe separated

13. Read the 3 file formats into R

max_min_15_csv <- read_csv("max_min_15.csv") # comma separated values
max_min_15_tsv <- read_tsv("max_min_15.tsv") # tab separated
max_min_15_psv <- read_delim("max_min_15.psv", delim = "|") # pipe separated

14. Use setdiff to check for any differences among max_min_15_csv, max_min_15_tsv and max_min_15_psv

setdiff(max_min_15_csv, max_min_15_tsv, max_min_15_psv)

# A tibble: 0 × 3
# … with 3 variables: country <chr>, code <chr>,
#   share_of_global_cumulative_co2_emissions <dbl>

Are there any differences?

15. Reorder country in max_min_15 for plotting and assign to max_min_15_plot_data

• start with emissions_1997 THEN
• use mutate to reorder country according to share_of_global_cumulative_co2_emissions

max_min_15_plot_data <- max_min_15 %>% 
  mutate(country = reorder(country, share_of_global_cumulative_co2_emissions))

16. Plot max_min_15_plot_data

ggplot(data = max_min_15_plot_data,
       mapping = aes(x = share_of_global_cumulative_co2_emissions, y = country))

 geom_col()

geom_col: width = NULL, na.rm = FALSE
stat_identity: na.rm = FALSE
position_stack 

 labs(title = "The top 15 and bottom 15 per capita CO2 emissions",
      subtitle = "for 1997",
      x = NULL,
      y = NULL)

$x
NULL

$y
NULL

$title
[1] "The top 15 and bottom 15 per capita CO2 emissions"

$subtitle
[1] "for 1997"

attr(,"class")
[1] "labels"

17. Save the plot directory with this post

ggsave(filename = "preview.png",
       path = here("_posts", "2022-02-17-reading-and-writing-data"))

18. Add preview.png to yaml chuck at the top of this file

preview: preview.png