master_data_science/bonus_tidy_gapminder.R at master · joseramoncajide/master_data_science · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
##########################################################################
# Jose Cajide - @jrcajide
# Master Data Science: Tidyr
##########################################################################

library(tidyverse)
library(readr)
library(tidyr)


gapminder <- read_csv("data/gapminder.csv")

gap_wide <- read_csv("https://docs.google.com/spreadsheets/d/1NTXQNoY8V0H_EZ_peFmnH1ZcGlxCPhwl2VmJNpiACMU/pub?output=csv")
# gap_wide <- read.csv('data/gapminder_wide.csv')
head(gap_wide)

gap_long <- gap_wide %>%
  gather(key   = obstype_year,
         value = obs_values)
head(gap_long)
tail(gap_long)

# Debemos indicar las columnas a transformar
gap_long <- gap_wide %>%
  gather(key   = obstype_year,
         value = obs_values,
         3:38)  # ó -1:-2
head(gap_long)
tail(gap_long)

# Alternativa
gap_long <- gap_wide %>%
  gather(key   = obstype_year,
         value = obs_values,
         dplyr::starts_with('pop'),
         dplyr::starts_with('lifeExp'),
         dplyr::starts_with('gdpPercap'))
head(gap_long)
tail(gap_long)

# ¿Que ocurre con la variable 'obstype_year'?

gap_long <- gap_wide %>%
  gather(key   = obstype_year,
         value = obs_values,
         -continent, -country) %>%
  separate(obstype_year,
           into = c('obs_type','year'),
           sep="_")
head(gap_long)
tail(gap_long)

# spread()
gap_normal <- gap_long %>%
  spread(obs_type, obs_values)

head(gap_normal)
head(gapminder)