Reading and Writing data

A short description of the post.

Load the R packages we will use

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

Download emissions per capita from Our World in Data
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", "2021-02-27-reading-and-writing-data", "co-emissions-per-capita.csv")
emissions <- read_csv(file_csv)

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

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

Start with the tidy_emissions THEN

use filter to extract rows with year == 2005 THEN
use skim to calculate the descriptive statistics

tidy_emissions %>%
  filter(year == 2005) %>%
skim()

Table 1: Data summary
Name	Piped data
Number of rows	220
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	220	0
code	12	0.95	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	2005.00	0.00	2005.00	2005.00	2005.00	2005.00	2005.0	▁▁▇▁▁
per_capita_co2_emissions	0	1	5.34	6.83	0.02	0.85	3.16	8.44	58.6	▇▁▁▁▁

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

start with tidy_emissions then extract rows with year == 2005 and are missing a code

tidy_emissions %>%
  filter(year == 2005, is.na(code))

# A tibble: 12 x 4
   entity                     code   year per_capita_co2_emissions
   <chr>                      <chr> <dbl>                    <dbl>
 1 Africa                     <NA>   2005                     1.16
 2 Asia                       <NA>   2005                     3.11
 3 Asia (excl. China & India) <NA>   2005                     3.61
 4 EU-27                      <NA>   2005                     8.63
 5 EU-28                      <NA>   2005                     8.73
 6 Europe                     <NA>   2005                     8.80
 7 Europe (excl. EU-27)       <NA>   2005                     9.00
 8 Europe (excl. EU-28)       <NA>   2005                     8.89
 9 North America              <NA>   2005                    14.3 
10 North America (excl. USA)  <NA>   2005                     5.48
11 Oceania                    <NA>   2005                    13.0 
12 South America              <NA>   2005                     2.37

Entities that are not countries do not have country codes.

Start with tidy_emissions THEN

use filter to extract rows with year == 2005 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_2005

emissions_2005 <- tidy_emissions %>%
  filter(year == 2005, !is.na(code)) %>%
  select(-year) %>%
  rename(country = entity)

Which 15 countries have the highest per_capita_co2_emissions?

start with emissions_2005 THEN
use slice_max to extract the 15 rows with the per_capita_co2_emissions
assign the output to max_15_emitters

max_15_emitters <- emissions_2005 %>%
  slice_max(per_capita_co2_emissions, n = 15)

Which 15 countries have the lowest per_capita_co2_emissions?

start with emissions_2005 THEN
use slice_min to extract the 15 rows with the lowest values
assign the output to min_15_emitters

min_15_emitters <- emissions_2005%>%
  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_15to 3 file formats

max_min_15 %>% write_csv("max_min_15.csv") # comma-separataed 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 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>

Are there any differences?

Recorder country in max_min_15 for plotting and assign to max_min_15_plot_data

start with emissions_2005 THEN
use mutate to reorder country according to per_capital_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 C02 emissions",
          subtitle = "for 2005",
          x = NULL,
          y = NULL)

Save the plot directory with this post

ggsave(filename = "preview.png",
       path = here("_posts", "2021-02-27-reading-and-writing-data"))

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

preview: preview.png

Reading and Writing data

Authors

Affiliations

Published

DOI

Footnotes