1.Load the R packages we will use.
Download \(CO_2\) emission per capita from Our World in Data into the directory for this post.
Assign the location of the file to ‘file_CSV’. the data should be in the same directory as this file.
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 (observation 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- 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’
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- Start with the ‘tidy_emissions’. THEN use ‘filter’ to extract rows with ‘year == 1984’. THEN use ‘skim’ to calculate the descriptive statistics.
| Name | Piped data |
| Number of rows | 209 |
| 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 | 209 | 0 |
| code | 12 | 0.94 | 3 | 8 | 0 | 197 | 0 |
Variable type: numeric
| skim_variable | n_missing | complete_rate | mean | sd | p0 | p25 | p50 | p75 | p100 | hist |
|---|---|---|---|---|---|---|---|---|---|---|
| year | 0 | 1 | 1984.00 | 0.0 | 1984.00 | 1984.00 | 1984.0 | 1984.00 | 1984.0 | ▁▁▇▁▁ |
| per_capita_co2_emissions | 0 | 1 | 5.31 | 8.3 | 0.04 | 0.51 | 2.4 | 7.55 | 75.6 | ▇▁▁▁▁ |
- 13 observations have a missing code. How are these observations different? Start with ‘tidy_emissions’. then extract rows with ‘year == 1984’ and are missing a code.
# A tibble: 12 x 4
entity code year per_capita_co2_emissions
<chr> <chr> <dbl> <dbl>
1 Africa <NA> 1984 1.23
2 Asia <NA> 1984 1.74
3 Asia (excl. China & India) <NA> 1984 2.71
4 EU-27 <NA> 1984 9.08
5 EU-28 <NA> 1984 9.11
6 Europe <NA> 1984 10.5
7 Europe (excl. EU-27) <NA> 1984 12.5
8 Europe (excl. EU-28) <NA> 1984 13.2
9 North America <NA> 1984 13.3
10 North America (excl. USA) <NA> 1984 5.04
11 Oceania <NA> 1984 10.7
12 South America <NA> 1984 1.87- Start with ’tidy_emissions. Then
- Use ‘filter’ to extract rows with year == 1984 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_1984’
- which 15 countries have the highest ‘per_capita_co2-emissions’?
- Start with ‘emissions_1984’
- use ‘slice_min’ to extract the 15 rows with the ‘per_capita_co2-emissions’
- assign the output to (per_capita_co2-emissions, n=15)
max_15_emitters <- emissions_1984 %>%
slice_max(per_capita_co2_emissions, n = 15)
- which 15 countries have the lowest ‘per_capita_co2-emissions’?
- Start with ‘emissions_1984’
- use ‘slice_min’ to extract the 15 rows with the ‘per_capita_co2-emissions’
- assign the output to (per_capita_co2-emissions, n=15)
min_15_emitters <- emissions_1984 %>%
slice_min(per_capita_co2_emissions, n = 15)
- 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)
- 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
- 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
- Use ‘setdiff’ to chack 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>Are there any differences?
- Reorder ‘country in ’max_min_15’ for plotting and assign to max_min_15_plot_data
- Start with ‘emissions_1984’. Then
- Use ‘mutate’ to reorder ‘country’ according to ‘per_capita_co2_emissions’
max_min_15_plot_data <- max_min_15 %>%
mutate(country = reorder(country, per_capita_co2_emissions))
- Plot’ max_min_15_plot_data
ggplot(data = max_min_15_plot_data,
mapping = aes(x= per_capita_co2_emissions, y = country)) +
geom_col() +
labs(title = "The top 15 and bottom 15 per capita CO2 emissions",
subtitle = "for 1984",
x = NULL,
y = NULL)
- Save the plot directory with this post.
ggsave(filename = "preview.png",
path = here("_posts", "2021-03-02-reading-and-writing-data"))
- Add Picture to the top of file.
preview: preview.png