Reading and writing data

A short description of the post.

1. Load the R packages we will use.

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

2. Download \(C_2\) 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",
                  "2021-03-02-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: 22,383 x 4
   Entity      Code   Year `Per capita CO2 emissions`
   <chr>       <chr> <dbl>                      <dbl>
 1 Afghanistan AFG    1949                    0.00191
 2 Afghanistan AFG    1950                    0.0109 
 3 Afghanistan AFG    1951                    0.0117 
 4 Afghanistan AFG    1952                    0.0115 
 5 Afghanistan AFG    1953                    0.0132 
 6 Afghanistan AFG    1954                    0.0130 
 7 Afghanistan AFG    1955                    0.0186 
 8 Afghanistan AFG    1956                    0.0218 
 9 Afghanistan AFG    1957                    0.0343 
10 Afghanistan AFG    1958                    0.0380 
# ... with 22,373 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: 22,383 x 4
   entity      code   year per_capita_co2_emissions
   <chr>       <chr> <dbl>                    <dbl>
 1 Afghanistan AFG    1949                  0.00191
 2 Afghanistan AFG    1950                  0.0109 
 3 Afghanistan AFG    1951                  0.0117 
 4 Afghanistan AFG    1952                  0.0115 
 5 Afghanistan AFG    1953                  0.0132 
 6 Afghanistan AFG    1954                  0.0130 
 7 Afghanistan AFG    1955                  0.0186 
 8 Afghanistan AFG    1956                  0.0218 
 9 Afghanistan AFG    1957                  0.0343 
10 Afghanistan AFG    1958                  0.0380 
# ... with 22,373 more rows

6. Start with the tidy_emissions THEN

• use filter to extract rows with year == 2019 THEN
• use skim to calculate the descriptive statistics

tidy_emissions %>% 
  filter(year == 2019) %>% 
  skim

Table 1: Data summary

Name	Piped data
Number of rows	221
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	221	0
code	13	0.94	3	8	0	208	0

Variable type: numeric

skim_variable	n_missing	complete_rate	mean	sd	p0	p25	p50	p75	p100	hist
year	0	1	2019	0.00	2019.00	2019.00	2019.00	2019.00	2019.00	▁▁▇▁▁
per_capita_co2_emissions	0	1	5	5.71	0.03	1.12	3.53	6.56	38.61	▇▂▁▁▁

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

• start with tidy_emissions then extract rows with year == 2019 and are missing a code

tidy_emissions %>% 
  filter(year == 2019, is.na(code))

# A tibble: 13 x 4
   entity                     code   year per_capita_co2_emissions
   <chr>                      <chr> <dbl>                    <dbl>
 1 Africa                     <NA>   2019                     1.12
 2 Asia                       <NA>   2019                     4.40
 3 Asia (excl. China & India) <NA>   2019                     4.14
 4 EU-27                      <NA>   2019                     6.56
 5 EU-28                      <NA>   2019                     6.41
 6 Europe                     <NA>   2019                     7.28
 7 Europe (excl. EU-27)       <NA>   2019                     8.33
 8 Europe (excl. EU-28)       <NA>   2019                     9.14
 9 International transport    <NA>   2019                     4.58
10 North America              <NA>   2019                    11.0 
11 North America (excl. USA)  <NA>   2019                     4.63
12 Oceania                    <NA>   2019                    11.2 
13 South America              <NA>   2019                     2.54

8. Start with tidy_emissions THEN

• use filter to extract rows with year == 2019 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_2019

emissions_2019  <- tidy_emissions %>% 
  filter(year == 2019, !is.na(code)) %>% 
  select(-year) %>% 
  rename(country = entity)

9. Which 15 countries have the highest per_capita_co2_emissions?

• start with emissions_2019 THEN
• use slice_max to extract the 15 rows with the per_capita_co2_emissions
• assign the output to max_15_emissions

max_15_emitters  <- emissions_2019 %>% 
  slice_max(per_capita_co2_emissions, n = 15)

10. Which 15 countries have the lowest per_capita_co2_emissions?

• start with emissions_2019 THEN
• use slice_min to extract the 15 rows with the lowest values
• assign the output to min_15_emitters

min_15_emitters  <- emissions_2019 %>% 
  slice_min(per_capita_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") 
max_min_15 %>% write_tsv("max_min_15.tsv") 
max_min_15 %>% write_delim("max_min_15.psv", delim = "|") 

13. Read the 3 formats into R

max_min_15_csv <-  read_csv("max_min_15.csv") 
max_min_15_tsv <-  read_tsv("max_min_15.tsv") 
max_min_15_psv <-  read_delim("max_min_15.psv", delim = "|") 

14. Use setdif 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 x 3
# ... with 3 variables: country <chr>, code <chr>,
#   per_capita_co2_emissions <dbl>

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

• start with emissions_2019 THEN
• use mutate to reorder country accordint to per_capita_co2_emissions

max_min_15_plot_data  <- max_min_15 %>% 
  mutate(country = reorder(country, per_capita_co2_emissions))

16. Plot max_min_15_plot_data

ggplot(data = max_min_15_plot_data,
       mapping = aes(per_capita_co2_emissions, country)) +
  geom_col() +
  labs(title = "The top 15 and bottom 15 per capita CO2 emissions",
       subtitle = "for 2019",
       x = NULL,
       y = NULL)

17. Save the plot directory with this post

ggsave(filename = "preview.png",
       path = here("_posts", "2021-03-02-reading-and-writing-data"))

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

preview: preview.png