Data Wrangling - dplyr

Code - R

~/code/R/

Introduction

• dplyr 1.0.0. html

• Data Wrangling Cheatsheet. pdf

gapminder %>%
  tbl_df() %>%
  glimpse() %>%
  head(10) %>%
  {if (is_html_output()) print_table(.) else .}

## Warning: `tbl_df()` is deprecated as of dplyr 1.0.0.
## Please use `tibble::as_tibble()` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_warnings()` to see where this warning was generated.

## Rows: 1,704
## Columns: 6
## $ country   <fct> Afghanistan, Afghanistan, Afghanistan, Afghanistan, Afghani…
## $ continent <fct> Asia, Asia, Asia, Asia, Asia, Asia, Asia, Asia, Asia, Asia,…
## $ year      <int> 1952, 1957, 1962, 1967, 1972, 1977, 1982, 1987, 1992, 1997,…
## $ lifeExp   <dbl> 28.801, 30.332, 31.997, 34.020, 36.088, 38.438, 39.854, 40.…
## $ pop       <int> 8425333, 9240934, 10267083, 11537966, 13079460, 14880372, 1…
## $ gdpPercap <dbl> 779.4453, 820.8530, 853.1007, 836.1971, 739.9811, 786.1134,…

country	continent	year	lifeExp	pop	gdpPercap
Afghanistan	Asia	1952	28.801	8425333	779.4453
Afghanistan	Asia	1957	30.332	9240934	820.8530
Afghanistan	Asia	1962	31.997	10267083	853.1007
Afghanistan	Asia	1967	34.020	11537966	836.1971
Afghanistan	Asia	1972	36.088	13079460	739.9811
Afghanistan	Asia	1977	38.438	14880372	786.1134
Afghanistan	Asia	1982	39.854	12881816	978.0114
Afghanistan	Asia	1987	40.822	13867957	852.3959
Afghanistan	Asia	1992	41.674	16317921	649.3414
Afghanistan	Asia	1997	41.763	22227415	635.3414

Review: grouping and summarizing

gapminder %>%
  group_by(continent) %>%
  summarize(avg_lifeExp = mean(lifeExp)) %>%
  {if (is_html_output()) print_table(.) else .}

## `summarise()` ungrouping output (override with `.groups` argument)

continent	avg_lifeExp
Africa	48.86533
Americas	64.65874
Asia	60.06490
Europe	71.90369
Oceania	74.32621

Review: writing our own function

qdiff <- function(x, probs = c(0, 1), na.rm = TRUE) {
  the_quantiles <- quantile(x = x, probs = probs, na.rm = na.rm)
  return(max(the_quantiles) - min(the_quantiles))
}
qdiff(gapminder$lifeExp) %>%
  {if (is_html_output()) print_table(.) else .}

x
59.004

gapminder %>%
  summarize(qdiff = qdiff(lifeExp)) %>%
  {if (is_html_output()) print_table(.) else .}

qdiff
59.004

gapminder %>%
  group_by(continent) %>%
  summarize(qdiff = qdiff(lifeExp)) %>%
  {if (is_html_output()) print_table(.) else .}

## `summarise()` ungrouping output (override with `.groups` argument)

continent	qdiff
Africa	52.843
Americas	43.074
Asia	53.802
Europe	38.172
Oceania	12.115

gapminder %>%
  group_by(continent) %>%
  summarize(qdiff = qdiff(lifeExp, probs = c(0.2, 0.8))) %>%
  {if (is_html_output()) print_table(.) else .}

## `summarise()` ungrouping output (override with `.groups` argument)

continent	qdiff
Africa	15.1406
Americas	15.7914
Asia	22.3130
Europe	7.3460
Oceania	7.0360

Meet “do”

gapminder %>%
  filter(year == 2007) %>% 
  group_by(continent) %>%
  do(head(., 2)) %>%
  {if (is_html_output()) print_table(.) else .}

country	continent	year	lifeExp	pop	gdpPercap
Algeria	Africa	2007	72.301	33333216	6223.3675
Angola	Africa	2007	42.731	12420476	4797.2313
Argentina	Americas	2007	75.320	40301927	12779.3796
Bolivia	Americas	2007	65.554	9119152	3822.1371
Afghanistan	Asia	2007	43.828	31889923	974.5803
Bahrain	Asia	2007	75.635	708573	29796.0483
Albania	Europe	2007	76.423	3600523	5937.0295
Austria	Europe	2007	79.829	8199783	36126.4927
Australia	Oceania	2007	81.235	20434176	34435.3674
New Zealand	Oceania	2007	80.204	4115771	25185.0091

gapminder %>% 
  filter(year == 2002) %>% 
  group_by(continent) %>% 
  arrange(desc(pop)) %>% 
  do(slice(., 10)) %>%
  {if (is_html_output()) print_table(.) else .}

country	continent	year	lifeExp	pop	gdpPercap
Morocco	Africa	2002	69.615	31167783	3258.496
Ecuador	Americas	2002	74.173	12921234	5773.045
Thailand	Asia	2002	68.564	62806748	5913.188
Greece	Europe	2002	78.256	10603863	22514.255

gapminder %>% 
  filter(year == 2002) %>% 
  group_by(continent) %>% 
  filter(min_rank(desc(pop)) == 10) %>%
  {if (is_html_output()) print_table(.) else .}

country	continent	year	lifeExp	pop	gdpPercap
Ecuador	Americas	2002	74.173	12921234	5773.045
Greece	Europe	2002	78.256	10603863	22514.255
Morocco	Africa	2002	69.615	31167783	3258.496
Thailand	Asia	2002	68.564	62806748	5913.188

gapminder %>%
  group_by(continent) %>%
  do(range = range(.$lifeExp)) %>% str

## tibble [5 × 2] (S3: rowwise_df/tbl_df/tbl/data.frame)
##  $ continent: Factor w/ 5 levels "Africa","Americas",..: 1 2 3 4 5
##  $ range    :List of 5
##   ..$ : num [1:2] 23.6 76.4
##   ..$ : num [1:2] 37.6 80.7
##   ..$ : num [1:2] 28.8 82.6
##   ..$ : num [1:2] 43.6 81.8
##   ..$ : num [1:2] 69.1 81.2
##  - attr(*, "groups")= tibble [5 × 1] (S3: tbl_df/tbl/data.frame)
##   ..$ .rows: list<int> [1:5] 
##   .. ..$ : int 1
##   .. ..$ : int 2
##   .. ..$ : int 3
##   .. ..$ : int 4
##   .. ..$ : int 5
##   .. ..@ ptype: int(0)