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

3. Assign the locations 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",
                 "2021-03-03-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 == 1988 THEN -use skim to calculate the descriptive statistics

tidy_emissions %>%
  filter(year == 1988) %>%
  skim()

Table 1: Data summary

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	1988.00	0.00	1988.00	1988.00	1988.00	1988.00	1988.00	▁▁▇▁▁
per_capita_co2_emissions	0	1	5.07	5.86	0.01	0.54	2.82	8.11	29.56	▇▃▁▁▁

7. 12 observations have a missing code. How are these observations different? -start with tidy_emissions then extract rows with year == 1988 and are missing a code

tidy_emissions %>%
  filter(year ==1988, is.na(code))

# A tibble: 12 x 4
   entity                     code   year per_capita_co2_emissions
   <chr>                      <chr> <dbl>                    <dbl>
 1 Africa                     <NA>   1988                     1.23
 2 Asia                       <NA>   1988                     1.98
 3 Asia (excl. China & India) <NA>   1988                     2.94
 4 EU-27                      <NA>   1988                     9.07
 5 EU-28                      <NA>   1988                     9.18
 6 Europe                     <NA>   1988                    10.9 
 7 Europe (excl. EU-27)       <NA>   1988                    13.4 
 8 Europe (excl. EU-28)       <NA>   1988                    14.2 
 9 North America              <NA>   1988                    13.8 
10 North America (excl. USA)  <NA>   1988                     5.06
11 Oceania                    <NA>   1988                    11.2 
12 South America              <NA>   1988                     2.04

8.Start with tidy_emissions THEN

-use filter to extract rows with year == 1988 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_1988

emissions_1988 <- tidy_emissions %>%
  filter(year == 1988, !is.na(code)) %>%
  select(-year) %>% 
  rename(country=entity)

9.Which 15 countries have the highest per_capita_co2_emissions?

-start with emissions_1988 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_1988 %>%
  slice_max(per_capita_co2_emissions, n =15)

10.Which 15 countries have the lowest per_capita_co2_emissions?

-start with emissions_1988 THEN -use slice_min to extract the 15 rows with the lowest values -assign the output to min_15_emitters

min_15_emitters <- emissions_1988 %>%
  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") #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