Loading [MathJax]/jax/output/CommonHTML/fonts/TeX/fontdata.js
+ - 0:00:00
Notes for current slide
Notes for next slide

Data Processing in R

With the {tidyverse}

Michael Jones

2021-08-25

1 / 35

A quick note
on Composition

2 / 35

f(g(x))=(f∘g)(x)

3 / 35
  • f(g(x)) = g(x) %>% f()
4 / 35
  • f(g(x)) = g(x) %>% f()
  • f(g(x)) = x %>% g() %>% f()
4 / 35
  • f(g(x)) = g(x) %>% f()
  • f(g(x)) = x %>% g() %>% f()
  • f(x, y) = x %>% f(y)
4 / 35
  • f(g(x)) = g(x) %>% f()
  • f(g(x)) = x %>% g() %>% f()
  • f(x, y) = x %>% f(y)
  • f(x, y) = x |> f(y)
4 / 35

Traditional Cake

sprinkle(
  sandwich(
    bake(
        mix(
          what = ingredients,
          in = "bowl"
        )
      in = "oven",
      at = 180
    )
  between = "jam",
  )
  with = "sugar"
)
5 / 35

Saving your intermediate steps

batter <- mix(what = ingredients, in = "bowl")
sponge <- bake(batter, in = "oven", at = 180)
assembled_cake <- sandwich(sponge, between = "jam")
decorated_cake <- sprinkle(assembled_cake, with = "sugar")
6 / 35

Piped Cake

mix(what = ingredients, in = "bowl") %>% 
  bake(in = "oven", at = 180) %>%
  sandwich(between = "jam") %>%
  sprinkle(with = "sugar")
7 / 35

{tidyverse}

8 / 35
library(tidyverse)
## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.1 ──
## ✓ ggplot2 3.3.5     ✓ purrr   0.3.4
## ✓ tibble  3.1.4     ✓ dplyr   1.0.7
## ✓ tidyr   1.1.3     ✓ stringr 1.4.0
## ✓ readr   2.0.1     ✓ forcats 0.5.1
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()
9 / 35

Other useful packages

library(readxl)
library(janitor)
## 
## Attaching package: 'janitor'
## The following objects are masked from 'package:stats':
## 
##     chisq.test, fisher.test
10 / 35

Reading in
a CSV

11 / 35

Old Fashioned

read.csv("my_data.csv")
##   id_column group        fruit rating    sampled
## 1         1     A        apple      4 2021-07-05
## 2         2     B      apricot      3 2021-07-13
## 3         3     A      avocado      5 2021-07-09
## 4         4     B       banana      1 2021-07-26
## 5         5     A  bell pepper      4 2021-07-22
## 6         6     B     bilberry      1 2021-07-31
## 7         7     A   blackberry      5 2021-07-01
## 8         8     B blackcurrant      1 2021-07-18
12 / 35

Tidyverse Way

read_csv("my_data.csv")
## Rows: 8 Columns: 5
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr  (2): group, fruit
## dbl  (2): id_column, rating
## date (1): sampled
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
## # A tibble: 8 × 5
##   id_column group fruit        rating sampled   
##       <dbl> <chr> <chr>         <dbl> <date>    
## 1         1 A     apple             4 2021-07-05
## 2         2 B     apricot           3 2021-07-13
## 3         3 A     avocado           5 2021-07-09
## 4         4 B     banana            1 2021-07-26
## 5         5 A     bell pepper       4 2021-07-22
## 6         6 B     bilberry          1 2021-07-31
## 7         7 A     blackberry        5 2021-07-01
## 8         8 B     blackcurrant      1 2021-07-18
13 / 35

Tell R what you expect

ratings <- read_csv("my_data.csv",
         col_types = cols(
           id_column = col_double(),
           group = col_character(),
           fruit = col_character(),
           rating = col_double(),
           sampled = col_date(format = "")
         ))
## # A tibble: 8 × 5
##   id_column group fruit        rating sampled   
##       <dbl> <chr> <chr>         <dbl> <date>    
## 1         1 A     apple             4 2021-07-05
## 2         2 B     apricot           3 2021-07-13
## 3         3 A     avocado           5 2021-07-09
## 4         4 B     banana            1 2021-07-26
## 5         5 A     bell pepper       4 2021-07-22
## 6         6 B     bilberry          1 2021-07-31
## 7         7 A     blackberry        5 2021-07-01
## 8         8 B     blackcurrant      1 2021-07-18
14 / 35

Tell R what you expect

ratings_bad <- read_csv("my_data.csv",
         col_types = cols(
           id_column = col_double(),
           group = col_character(),
           fruit = col_double(),
           rating = col_double(),
           sampled = col_date(format = "")
         ))
15 / 35

Taking a quick look at the data

ratings
## # A tibble: 8 × 5
##   id_column group fruit        rating sampled   
##       <dbl> <chr> <chr>         <dbl> <date>    
## 1         1 A     apple             4 2021-07-05
## 2         2 B     apricot           3 2021-07-13
## 3         3 A     avocado           5 2021-07-09
## 4         4 B     banana            1 2021-07-26
## 5         5 A     bell pepper       4 2021-07-22
## 6         6 B     bilberry          1 2021-07-31
## 7         7 A     blackberry        5 2021-07-01
## 8         8 B     blackcurrant      1 2021-07-18
16 / 35

Taking a quick look at the data

glimpse(ratings)
## Rows: 8
## Columns: 5
## $ id_column <dbl> 1, 2, 3, 4, 5, 6, 7, 8
## $ group     <chr> "A", "B", "A", "B", "A", "B", "A", "B"
## $ fruit     <chr> "apple", "apricot", "avocado", "banana", "bell pepper", "bil…
## $ rating    <dbl> 4, 3, 5, 1, 4, 1, 5, 1
## $ sampled   <date> 2021-07-05, 2021-07-13, 2021-07-09, 2021-07-26, 2021-07-22, …
17 / 35

Key idea of
the tidyverse

18 / 35

Functions accept a data frame

Functions return a data frame

19 / 35

Selecting Columns

select(<dataframe>, <columns>) → data frame

20 / 35

Selecting Columns

ratings %>%
  select(id_column)
## # A tibble: 8 × 1
##   id_column
##       <dbl>
## 1         1
## 2         2
## 3         3
## 4         4
## 5         5
## 6         6
## 7         7
## 8         8
20 / 35

Selecting Columns

ratings %>%
  select(id_column, group)
## # A tibble: 8 × 2
##   id_column group
##       <dbl> <chr>
## 1         1 A    
## 2         2 B    
## 3         3 A    
## 4         4 B    
## 5         5 A    
## 6         6 B    
## 7         7 A    
## 8         8 B
20 / 35

Selecting Columns

ratings %>%
  select(id_column:rating)
## # A tibble: 8 × 4
##   id_column group fruit        rating
##       <dbl> <chr> <chr>         <dbl>
## 1         1 A     apple             4
## 2         2 B     apricot           3
## 3         3 A     avocado           5
## 4         4 B     banana            1
## 5         5 A     bell pepper       4
## 6         6 B     bilberry          1
## 7         7 A     blackberry        5
## 8         8 B     blackcurrant      1
20 / 35

Selecting Columns

ratings %>%
  select(-id_column)
## # A tibble: 8 × 4
##   group fruit        rating sampled   
##   <chr> <chr>         <dbl> <date>    
## 1 A     apple             4 2021-07-05
## 2 B     apricot           3 2021-07-13
## 3 A     avocado           5 2021-07-09
## 4 B     banana            1 2021-07-26
## 5 A     bell pepper       4 2021-07-22
## 6 B     bilberry          1 2021-07-31
## 7 A     blackberry        5 2021-07-01
## 8 B     blackcurrant      1 2021-07-18
20 / 35
  • Yes: ratings %>% select(id_column)
  • No: ratings %>% select("id_column")
21 / 35

Filtering Columns

filter(<dataframe>, <predicates>) → data frame

22 / 35

Filtering Columns

ratings %>%
  filter(group == "A")
## # A tibble: 4 × 5
##   id_column group fruit       rating sampled   
##       <dbl> <chr> <chr>        <dbl> <date>    
## 1         1 A     apple            4 2021-07-05
## 2         3 A     avocado          5 2021-07-09
## 3         5 A     bell pepper      4 2021-07-22
## 4         7 A     blackberry       5 2021-07-01
22 / 35

Filtering Columns

ratings %>%
  filter(rating >= 3)
## # A tibble: 5 × 5
##   id_column group fruit       rating sampled   
##       <dbl> <chr> <chr>        <dbl> <date>    
## 1         1 A     apple            4 2021-07-05
## 2         2 B     apricot          3 2021-07-13
## 3         3 A     avocado          5 2021-07-09
## 4         5 A     bell pepper      4 2021-07-22
## 5         7 A     blackberry       5 2021-07-01
22 / 35

Filtering Columns

ratings %>%
  filter(sampled > as.Date("2021-07-15"))
## # A tibble: 4 × 5
##   id_column group fruit        rating sampled   
##       <dbl> <chr> <chr>         <dbl> <date>    
## 1         4 B     banana            1 2021-07-26
## 2         5 A     bell pepper       4 2021-07-22
## 3         6 B     bilberry          1 2021-07-31
## 4         8 B     blackcurrant      1 2021-07-18
22 / 35

Sorting Columns

arrange(<dataframe>, <columns>) → data frame

23 / 35

Sorting Columns

ratings %>%
  arrange(rating)
## # A tibble: 8 × 5
##   id_column group fruit        rating sampled   
##       <dbl> <chr> <chr>         <dbl> <date>    
## 1         4 B     banana            1 2021-07-26
## 2         6 B     bilberry          1 2021-07-31
## 3         8 B     blackcurrant      1 2021-07-18
## 4         2 B     apricot           3 2021-07-13
## 5         1 A     apple             4 2021-07-05
## 6         5 A     bell pepper       4 2021-07-22
## 7         3 A     avocado           5 2021-07-09
## 8         7 A     blackberry        5 2021-07-01
23 / 35

Sorting Columns

ratings %>%
  arrange(desc(rating))
## # A tibble: 8 × 5
##   id_column group fruit        rating sampled   
##       <dbl> <chr> <chr>         <dbl> <date>    
## 1         3 A     avocado           5 2021-07-09
## 2         7 A     blackberry        5 2021-07-01
## 3         1 A     apple             4 2021-07-05
## 4         5 A     bell pepper       4 2021-07-22
## 5         2 B     apricot           3 2021-07-13
## 6         4 B     banana            1 2021-07-26
## 7         6 B     bilberry          1 2021-07-31
## 8         8 B     blackcurrant      1 2021-07-18
23 / 35

Sorting Columns

ratings %>%
  arrange(group, sampled)
## # A tibble: 8 × 5
##   id_column group fruit        rating sampled   
##       <dbl> <chr> <chr>         <dbl> <date>    
## 1         7 A     blackberry        5 2021-07-01
## 2         1 A     apple             4 2021-07-05
## 3         3 A     avocado           5 2021-07-09
## 4         5 A     bell pepper       4 2021-07-22
## 5         2 B     apricot           3 2021-07-13
## 6         8 B     blackcurrant      1 2021-07-18
## 7         4 B     banana            1 2021-07-26
## 8         6 B     bilberry          1 2021-07-31
23 / 35

Changing Columns

mutate(<dataframe>, <new_column> = <function>) → data frame

24 / 35

Changing Columns

ratings %>%
  mutate(rating = rating * 20)
## # A tibble: 8 × 5
##   id_column group fruit        rating sampled   
##       <dbl> <chr> <chr>         <dbl> <date>    
## 1         1 A     apple            80 2021-07-05
## 2         2 B     apricot          60 2021-07-13
## 3         3 A     avocado         100 2021-07-09
## 4         4 B     banana           20 2021-07-26
## 5         5 A     bell pepper      80 2021-07-22
## 6         6 B     bilberry         20 2021-07-31
## 7         7 A     blackberry      100 2021-07-01
## 8         8 B     blackcurrant     20 2021-07-18
24 / 35

Changing Columns

ratings %>%
  mutate(fruit = str_to_upper(fruit))
## # A tibble: 8 × 5
##   id_column group fruit        rating sampled   
##       <dbl> <chr> <chr>         <dbl> <date>    
## 1         1 A     APPLE             4 2021-07-05
## 2         2 B     APRICOT           3 2021-07-13
## 3         3 A     AVOCADO           5 2021-07-09
## 4         4 B     BANANA            1 2021-07-26
## 5         5 A     BELL PEPPER       4 2021-07-22
## 6         6 B     BILBERRY          1 2021-07-31
## 7         7 A     BLACKBERRY        5 2021-07-01
## 8         8 B     BLACKCURRANT      1 2021-07-18
24 / 35

Changing Columns

ratings %>%
  mutate(sampled = format(sampled, "%b %d"), rating = rating * 20)
## # A tibble: 8 × 5
##   id_column group fruit        rating sampled
##       <dbl> <chr> <chr>         <dbl> <chr>  
## 1         1 A     apple            80 Jul 05 
## 2         2 B     apricot          60 Jul 13 
## 3         3 A     avocado         100 Jul 09 
## 4         4 B     banana           20 Jul 26 
## 5         5 A     bell pepper      80 Jul 22 
## 6         6 B     bilberry         20 Jul 31 
## 7         7 A     blackberry      100 Jul 01 
## 8         8 B     blackcurrant     20 Jul 18
24 / 35

Changing Columns

ratings %>%
  mutate(new_col = 1:8)
## # A tibble: 8 × 6
##   id_column group fruit        rating sampled    new_col
##       <dbl> <chr> <chr>         <dbl> <date>       <int>
## 1         1 A     apple             4 2021-07-05       1
## 2         2 B     apricot           3 2021-07-13       2
## 3         3 A     avocado           5 2021-07-09       3
## 4         4 B     banana            1 2021-07-26       4
## 5         5 A     bell pepper       4 2021-07-22       5
## 6         6 B     bilberry          1 2021-07-31       6
## 7         7 A     blackberry        5 2021-07-01       7
## 8         8 B     blackcurrant      1 2021-07-18       8
24 / 35

Chaining Functions Together

ratings
## # A tibble: 8 × 5
##   id_column group fruit        rating sampled   
##       <dbl> <chr> <chr>         <dbl> <date>    
## 1         1 A     apple             4 2021-07-05
## 2         2 B     apricot           3 2021-07-13
## 3         3 A     avocado           5 2021-07-09
## 4         4 B     banana            1 2021-07-26
## 5         5 A     bell pepper       4 2021-07-22
## 6         6 B     bilberry          1 2021-07-31
## 7         7 A     blackberry        5 2021-07-01
## 8         8 B     blackcurrant      1 2021-07-18
24 / 35

Chaining Functions Together

ratings %>%
  filter(group == "A")
## # A tibble: 4 × 5
##   id_column group fruit       rating sampled   
##       <dbl> <chr> <chr>        <dbl> <date>    
## 1         1 A     apple            4 2021-07-05
## 2         3 A     avocado          5 2021-07-09
## 3         5 A     bell pepper      4 2021-07-22
## 4         7 A     blackberry       5 2021-07-01
24 / 35

Chaining Functions Together

ratings %>%
  filter(group == "A") %>%
  select(fruit, sampled)
## # A tibble: 4 × 2
##   fruit       sampled   
##   <chr>       <date>    
## 1 apple       2021-07-05
## 2 avocado     2021-07-09
## 3 bell pepper 2021-07-22
## 4 blackberry  2021-07-01
24 / 35

Chaining Functions Together

ratings %>%
  filter(group == "A") %>%
  select(fruit, sampled) %>%
  mutate(month_name = format(sampled, "%b"))
## # A tibble: 4 × 3
##   fruit       sampled    month_name
##   <chr>       <date>     <chr>     
## 1 apple       2021-07-05 Jul       
## 2 avocado     2021-07-09 Jul       
## 3 bell pepper 2021-07-22 Jul       
## 4 blackberry  2021-07-01 Jul
24 / 35

Chaining Functions Together

ratings %>%
  filter(group == "A") %>%
  select(fruit, sampled) %>%
  mutate(month_name = format(sampled, "%b")) %>%
  arrange(desc(fruit))
## # A tibble: 4 × 3
##   fruit       sampled    month_name
##   <chr>       <date>     <chr>     
## 1 blackberry  2021-07-01 Jul       
## 2 bell pepper 2021-07-22 Jul       
## 3 avocado     2021-07-09 Jul       
## 4 apple       2021-07-05 Jul
24 / 35

Grouping and Summarising

25 / 35

Grouping and Summarising

group_by(<dataframe>, <columns>) → data frame

summarise(<dataframe>, <new column> = <function>) → data frame

26 / 35

Grouping and Summarising

ratings %>% head(n = 2)
## # A tibble: 2 × 5
##   id_column group fruit   rating sampled   
##       <dbl> <chr> <chr>    <dbl> <date>    
## 1         1 A     apple        4 2021-07-05
## 2         2 B     apricot      3 2021-07-13
ratings %>% group_by(group) %>% head(n = 2)
## # A tibble: 2 × 5
## # Groups:   group [2]
##   id_column group fruit   rating sampled   
##       <dbl> <chr> <chr>    <dbl> <date>    
## 1         1 A     apple        4 2021-07-05
## 2         2 B     apricot      3 2021-07-13
27 / 35

Grouping and Summarising

ratings %>% summarise(mean = mean(rating))
## # A tibble: 1 × 1
##    mean
##   <dbl>
## 1     3
ratings %>% group_by(group) %>% summarise(mean = mean(rating))
## # A tibble: 2 × 2
##   group  mean
##   <chr> <dbl>
## 1 A       4.5
## 2 B       1.5
28 / 35

Counting

ratings %>% group_by(group) %>% summarise(count = n())
## # A tibble: 2 × 2
##   group count
##   <chr> <int>
## 1 A         4
## 2 B         4
ratings %>% count(group, name = "count")
## # A tibble: 2 × 2
##   group count
##   <chr> <int>
## 1 A         4
## 2 B         4
29 / 35

tibbles within tibbles

30 / 35

Nesting Data

ratings
## # A tibble: 8 × 5
##   id_column group fruit        rating sampled   
##       <dbl> <chr> <chr>         <dbl> <date>    
## 1         1 A     apple             4 2021-07-05
## 2         2 B     apricot           3 2021-07-13
## 3         3 A     avocado           5 2021-07-09
## 4         4 B     banana            1 2021-07-26
## 5         5 A     bell pepper       4 2021-07-22
## 6         6 B     bilberry          1 2021-07-31
## 7         7 A     blackberry        5 2021-07-01
## 8         8 B     blackcurrant      1 2021-07-18
30 / 35

Nesting Data

ratings %>%
  group_by(group)
## # A tibble: 8 × 5
## # Groups:   group [2]
##   id_column group fruit        rating sampled   
##       <dbl> <chr> <chr>         <dbl> <date>    
## 1         1 A     apple             4 2021-07-05
## 2         2 B     apricot           3 2021-07-13
## 3         3 A     avocado           5 2021-07-09
## 4         4 B     banana            1 2021-07-26
## 5         5 A     bell pepper       4 2021-07-22
## 6         6 B     bilberry          1 2021-07-31
## 7         7 A     blackberry        5 2021-07-01
## 8         8 B     blackcurrant      1 2021-07-18
30 / 35

Nesting Data

ratings %>%
  group_by(group) %>%
  nest()
## # A tibble: 2 × 2
## # Groups:   group [2]
##   group data            
##   <chr> <list>          
## 1 A     <tibble [4 × 4]>
## 2 B     <tibble [4 × 4]>
30 / 35

Nesting Data

(subset <- ratings %>%
   filter(group == "A"))
## # A tibble: 4 × 5
##   id_column group fruit       rating sampled   
##       <dbl> <chr> <chr>        <dbl> <date>    
## 1         1 A     apple            4 2021-07-05
## 2         3 A     avocado          5 2021-07-09
## 3         5 A     bell pepper      4 2021-07-22
## 4         7 A     blackberry       5 2021-07-01
30 / 35

Nesting Data

(subset <- ratings %>%
   filter(group == "A"))
my_func <- function(df) {
  f <- df %>%
    filter(rating == max(rating)) %>%
    slice(1) %>%
    pull(fruit)
  paste("The highest rated fruit is", f)
}
## # A tibble: 4 × 5
##   id_column group fruit       rating sampled   
##       <dbl> <chr> <chr>        <dbl> <date>    
## 1         1 A     apple            4 2021-07-05
## 2         3 A     avocado          5 2021-07-09
## 3         5 A     bell pepper      4 2021-07-22
## 4         7 A     blackberry       5 2021-07-01
30 / 35

Nesting Data

(subset <- ratings %>%
   filter(group == "A"))
my_func <- function(df) {
  f <- df %>%
    filter(rating == max(rating)) %>%
    slice(1) %>%
    pull(fruit)
  paste("The highest rated fruit is", f)
}
my_func(subset)
## # A tibble: 4 × 5
##   id_column group fruit       rating sampled   
##       <dbl> <chr> <chr>        <dbl> <date>    
## 1         1 A     apple            4 2021-07-05
## 2         3 A     avocado          5 2021-07-09
## 3         5 A     bell pepper      4 2021-07-22
## 4         7 A     blackberry       5 2021-07-01
## [1] "The highest rated fruit is avocado"
30 / 35

Nesting Data

my_func <- function(df) {
  f <- df %>%
    filter(rating == max(rating)) %>%
    slice(1) %>%
    pull(fruit)
  paste("The highest rated fruit is", f)
}
30 / 35

Nesting Data

my_func <- function(df) {
  f <- df %>%
    filter(rating == max(rating)) %>%
    slice(1) %>%
    pull(fruit)
  paste("The highest rated fruit is", f)
}
ratings %>%
  group_by(group) %>%
  nest()
## # A tibble: 2 × 2
## # Groups:   group [2]
##   group data            
##   <chr> <list>          
## 1 A     <tibble [4 × 4]>
## 2 B     <tibble [4 × 4]>
30 / 35

Nesting Data

my_func <- function(df) {
  f <- df %>%
    filter(rating == max(rating)) %>%
    slice(1) %>%
    pull(fruit)
  paste("The highest rated fruit is", f)
}
ratings %>%
  group_by(group) %>%
  nest() %>%
  mutate(description = map(data, my_func))
## # A tibble: 2 × 3
## # Groups:   group [2]
##   group data             description
##   <chr> <list>           <list>     
## 1 A     <tibble [4 × 4]> <chr [1]>  
## 2 B     <tibble [4 × 4]> <chr [1]>
30 / 35

Nesting Data

my_func <- function(df) {
  f <- df %>%
    filter(rating == max(rating)) %>%
    slice(1) %>%
    pull(fruit)
  paste("The highest rated fruit is", f)
}
ratings %>%
  group_by(group) %>%
  nest() %>%
  mutate(description = map(data, my_func)) %>%
  unnest(description)
## # A tibble: 2 × 3
## # Groups:   group [2]
##   group data             description                       
##   <chr> <list>           <chr>                             
## 1 A     <tibble [4 × 4]> The highest rated fruit is avocado
## 2 B     <tibble [4 × 4]> The highest rated fruit is apricot
30 / 35

More involved nesting

library(gapminder)
30 / 35

More involved nesting

library(gapminder)
lm_fit <- function(df) {
  lm(lifeExp ~ year, data = df)
}
30 / 35

More involved nesting

library(gapminder)
lm_fit <- function(df) {
  lm(lifeExp ~ year, data = df)
}
plot_graph <- function(df) {
  ggplot(df, aes(x = year, y = lifeExp)) +
    geom_point() +
    geom_smooth(method = "lm")
}
30 / 35

More involved nesting

library(gapminder)
lm_fit <- function(df) {
  lm(lifeExp ~ year, data = df)
}
plot_graph <- function(df) {
  ggplot(df, aes(x = year, y = lifeExp)) +
    geom_point() +
    geom_smooth(method = "lm")
}
gapminder
## # A tibble: 1,704 × 6
##    country     continent  year lifeExp      pop gdpPercap
##    <fct>       <fct>     <int>   <dbl>    <int>     <dbl>
##  1 Afghanistan Asia       1952    28.8  8425333      779.
##  2 Afghanistan Asia       1957    30.3  9240934      821.
##  3 Afghanistan Asia       1962    32.0 10267083      853.
##  4 Afghanistan Asia       1967    34.0 11537966      836.
##  5 Afghanistan Asia       1972    36.1 13079460      740.
##  6 Afghanistan Asia       1977    38.4 14880372      786.
##  7 Afghanistan Asia       1982    39.9 12881816      978.
##  8 Afghanistan Asia       1987    40.8 13867957      852.
##  9 Afghanistan Asia       1992    41.7 16317921      649.
## 10 Afghanistan Asia       1997    41.8 22227415      635.
## # … with 1,694 more rows
30 / 35

More involved nesting

library(gapminder)
lm_fit <- function(df) {
  lm(lifeExp ~ year, data = df)
}
plot_graph <- function(df) {
  ggplot(df, aes(x = year, y = lifeExp)) +
    geom_point() +
    geom_smooth(method = "lm")
}
gapminder %>%
  group_by(country) %>%
  nest()
## # A tibble: 142 × 2
## # Groups:   country [142]
##    country     data             
##    <fct>       <list>           
##  1 Afghanistan <tibble [12 × 5]>
##  2 Albania     <tibble [12 × 5]>
##  3 Algeria     <tibble [12 × 5]>
##  4 Angola      <tibble [12 × 5]>
##  5 Argentina   <tibble [12 × 5]>
##  6 Australia   <tibble [12 × 5]>
##  7 Austria     <tibble [12 × 5]>
##  8 Bahrain     <tibble [12 × 5]>
##  9 Bangladesh  <tibble [12 × 5]>
## 10 Belgium     <tibble [12 × 5]>
## # … with 132 more rows
30 / 35

More involved nesting

library(gapminder)
lm_fit <- function(df) {
  lm(lifeExp ~ year, data = df)
}
plot_graph <- function(df) {
  ggplot(df, aes(x = year, y = lifeExp)) +
    geom_point() +
    geom_smooth(method = "lm")
}
gapminder %>%
  group_by(country) %>%
  nest() %>%
  mutate(model = map(data, lm_fit),
         plot = map(data, plot_graph))
## # A tibble: 142 × 4
## # Groups:   country [142]
##    country     data              model  plot  
##    <fct>       <list>            <list> <list>
##  1 Afghanistan <tibble [12 × 5]> <lm>   <gg>  
##  2 Albania     <tibble [12 × 5]> <lm>   <gg>  
##  3 Algeria     <tibble [12 × 5]> <lm>   <gg>  
##  4 Angola      <tibble [12 × 5]> <lm>   <gg>  
##  5 Argentina   <tibble [12 × 5]> <lm>   <gg>  
##  6 Australia   <tibble [12 × 5]> <lm>   <gg>  
##  7 Austria     <tibble [12 × 5]> <lm>   <gg>  
##  8 Bahrain     <tibble [12 × 5]> <lm>   <gg>  
##  9 Bangladesh  <tibble [12 × 5]> <lm>   <gg>  
## 10 Belgium     <tibble [12 × 5]> <lm>   <gg>  
## # … with 132 more rows
30 / 35

More involved nesting

gapminder_modified %>%
  filter(country == "United Kingdom") %>%
  pull(model)
## [[1]]
## 
## Call:
## lm(formula = lifeExp ~ year, data = df)
## 
## Coefficients:
## (Intercept)         year  
##    -294.197        0.186
30 / 35

More involved nesting

gapminder_modified %>%
  filter(country == "United Kingdom") %>%
  pull(plot)
## [[1]]
## `geom_smooth()` using formula 'y ~ x'

30 / 35

Reshape your data

31 / 35

Pivoting Longer

gapminder %>%
  select(-c(continent))
## # A tibble: 1,704 × 5
##    country      year lifeExp      pop gdpPercap
##    <fct>       <int>   <dbl>    <int>     <dbl>
##  1 Afghanistan  1952    28.8  8425333      779.
##  2 Afghanistan  1957    30.3  9240934      821.
##  3 Afghanistan  1962    32.0 10267083      853.
##  4 Afghanistan  1967    34.0 11537966      836.
##  5 Afghanistan  1972    36.1 13079460      740.
##  6 Afghanistan  1977    38.4 14880372      786.
##  7 Afghanistan  1982    39.9 12881816      978.
##  8 Afghanistan  1987    40.8 13867957      852.
##  9 Afghanistan  1992    41.7 16317921      649.
## 10 Afghanistan  1997    41.8 22227415      635.
## # … with 1,694 more rows
31 / 35

Pivoting Longer

gapminder %>%
  select(-c(continent)) %>%
  pivot_longer(cols = -c(country, year),
               names_to = "stat",
               values_to = "value")
## # A tibble: 5,112 × 4
##    country      year stat           value
##    <fct>       <int> <chr>          <dbl>
##  1 Afghanistan  1952 lifeExp         28.8
##  2 Afghanistan  1952 pop        8425333  
##  3 Afghanistan  1952 gdpPercap      779. 
##  4 Afghanistan  1957 lifeExp         30.3
##  5 Afghanistan  1957 pop        9240934  
##  6 Afghanistan  1957 gdpPercap      821. 
##  7 Afghanistan  1962 lifeExp         32.0
##  8 Afghanistan  1962 pop       10267083  
##  9 Afghanistan  1962 gdpPercap      853. 
## 10 Afghanistan  1967 lifeExp         34.0
## # … with 5,102 more rows
31 / 35

Pivoting Wider

gapminder %>%
  select(country, year, pop)
## # A tibble: 1,704 × 3
##    country      year      pop
##    <fct>       <int>    <int>
##  1 Afghanistan  1952  8425333
##  2 Afghanistan  1957  9240934
##  3 Afghanistan  1962 10267083
##  4 Afghanistan  1967 11537966
##  5 Afghanistan  1972 13079460
##  6 Afghanistan  1977 14880372
##  7 Afghanistan  1982 12881816
##  8 Afghanistan  1987 13867957
##  9 Afghanistan  1992 16317921
## 10 Afghanistan  1997 22227415
## # … with 1,694 more rows
31 / 35

Pivoting Wider

gapminder %>%
  select(country, year, pop) %>%
  pivot_wider(names_from = "year",
              values_from = "pop")
## # A tibble: 142 × 13
##    country `1952` `1957` `1962` `1967` `1972` `1977` `1982` `1987` `1992` `1997`
##    <fct>    <int>  <int>  <int>  <int>  <int>  <int>  <int>  <int>  <int>  <int>
##  1 Afghan… 8.43e6 9.24e6 1.03e7 1.15e7 1.31e7 1.49e7 1.29e7 1.39e7 1.63e7 2.22e7
##  2 Albania 1.28e6 1.48e6 1.73e6 1.98e6 2.26e6 2.51e6 2.78e6 3.08e6 3.33e6 3.43e6
##  3 Algeria 9.28e6 1.03e7 1.10e7 1.28e7 1.48e7 1.72e7 2.00e7 2.33e7 2.63e7 2.91e7
##  4 Angola  4.23e6 4.56e6 4.83e6 5.25e6 5.89e6 6.16e6 7.02e6 7.87e6 8.74e6 9.88e6
##  5 Argent… 1.79e7 1.96e7 2.13e7 2.29e7 2.48e7 2.70e7 2.93e7 3.16e7 3.40e7 3.62e7
##  6 Austra… 8.69e6 9.71e6 1.08e7 1.19e7 1.32e7 1.41e7 1.52e7 1.63e7 1.75e7 1.86e7
##  7 Austria 6.93e6 6.97e6 7.13e6 7.38e6 7.54e6 7.57e6 7.57e6 7.58e6 7.91e6 8.07e6
##  8 Bahrain 1.20e5 1.39e5 1.72e5 2.02e5 2.31e5 2.97e5 3.78e5 4.55e5 5.29e5 5.99e5
##  9 Bangla… 4.69e7 5.14e7 5.68e7 6.28e7 7.08e7 8.04e7 9.31e7 1.04e8 1.14e8 1.23e8
## 10 Belgium 8.73e6 8.99e6 9.22e6 9.56e6 9.71e6 9.82e6 9.86e6 9.87e6 1.00e7 1.02e7
## # … with 132 more rows, and 2 more variables: 2002 <int>, 2007 <int>
31 / 35

Combining Data

32 / 35

New data

group_details
## # A tibble: 4 × 2
##   group time     
##   <chr> <chr>    
## 1 A     morning  
## 2 B     lunchtime
## 3 C     afternoon
## 4 D     evening

More groups than in ratings

fruit_details
## # A tibble: 3 × 2
##   fruit      price
##   <chr>      <dbl>
## 1 apple          2
## 2 banana         4
## 3 blackberry     6

Fewer fruits than in ratings

33 / 35

Left Join

ratings
## # A tibble: 8 × 5
##   id_column group fruit        rating sampled   
##       <dbl> <chr> <chr>         <dbl> <date>    
## 1         1 A     apple             4 2021-07-05
## 2         2 B     apricot           3 2021-07-13
## 3         3 A     avocado           5 2021-07-09
## 4         4 B     banana            1 2021-07-26
## 5         5 A     bell pepper       4 2021-07-22
## 6         6 B     bilberry          1 2021-07-31
## 7         7 A     blackberry        5 2021-07-01
## 8         8 B     blackcurrant      1 2021-07-18
33 / 35

Left Join

ratings %>%
  left_join(group_details, by = "group")
## # A tibble: 8 × 6
##   id_column group fruit        rating sampled    time     
##       <dbl> <chr> <chr>         <dbl> <date>     <chr>    
## 1         1 A     apple             4 2021-07-05 morning  
## 2         2 B     apricot           3 2021-07-13 lunchtime
## 3         3 A     avocado           5 2021-07-09 morning  
## 4         4 B     banana            1 2021-07-26 lunchtime
## 5         5 A     bell pepper       4 2021-07-22 morning  
## 6         6 B     bilberry          1 2021-07-31 lunchtime
## 7         7 A     blackberry        5 2021-07-01 morning  
## 8         8 B     blackcurrant      1 2021-07-18 lunchtime
33 / 35

Left Join

ratings
## # A tibble: 8 × 5
##   id_column group fruit        rating sampled   
##       <dbl> <chr> <chr>         <dbl> <date>    
## 1         1 A     apple             4 2021-07-05
## 2         2 B     apricot           3 2021-07-13
## 3         3 A     avocado           5 2021-07-09
## 4         4 B     banana            1 2021-07-26
## 5         5 A     bell pepper       4 2021-07-22
## 6         6 B     bilberry          1 2021-07-31
## 7         7 A     blackberry        5 2021-07-01
## 8         8 B     blackcurrant      1 2021-07-18
33 / 35

Left Join

ratings %>%
  left_join(fruit_details, by = "fruit")
## # A tibble: 8 × 6
##   id_column group fruit        rating sampled    price
##       <dbl> <chr> <chr>         <dbl> <date>     <dbl>
## 1         1 A     apple             4 2021-07-05     2
## 2         2 B     apricot           3 2021-07-13    NA
## 3         3 A     avocado           5 2021-07-09    NA
## 4         4 B     banana            1 2021-07-26     4
## 5         5 A     bell pepper       4 2021-07-22    NA
## 6         6 B     bilberry          1 2021-07-31    NA
## 7         7 A     blackberry        5 2021-07-01     6
## 8         8 B     blackcurrant      1 2021-07-18    NA
33 / 35

Inner Join

ratings
## # A tibble: 8 × 5
##   id_column group fruit        rating sampled   
##       <dbl> <chr> <chr>         <dbl> <date>    
## 1         1 A     apple             4 2021-07-05
## 2         2 B     apricot           3 2021-07-13
## 3         3 A     avocado           5 2021-07-09
## 4         4 B     banana            1 2021-07-26
## 5         5 A     bell pepper       4 2021-07-22
## 6         6 B     bilberry          1 2021-07-31
## 7         7 A     blackberry        5 2021-07-01
## 8         8 B     blackcurrant      1 2021-07-18
33 / 35

Inner Join

ratings %>%
  inner_join(fruit_details, by = "fruit")
## # A tibble: 3 × 6
##   id_column group fruit      rating sampled    price
##       <dbl> <chr> <chr>       <dbl> <date>     <dbl>
## 1         1 A     apple           4 2021-07-05     2
## 2         4 B     banana          1 2021-07-26     4
## 3         7 A     blackberry      5 2021-07-01     6
33 / 35

Full Join

ratings
## # A tibble: 8 × 5
##   id_column group fruit        rating sampled   
##       <dbl> <chr> <chr>         <dbl> <date>    
## 1         1 A     apple             4 2021-07-05
## 2         2 B     apricot           3 2021-07-13
## 3         3 A     avocado           5 2021-07-09
## 4         4 B     banana            1 2021-07-26
## 5         5 A     bell pepper       4 2021-07-22
## 6         6 B     bilberry          1 2021-07-31
## 7         7 A     blackberry        5 2021-07-01
## 8         8 B     blackcurrant      1 2021-07-18
33 / 35

Full Join

ratings %>%
  full_join(group_details, by = "group")
## # A tibble: 10 × 6
##    id_column group fruit        rating sampled    time     
##        <dbl> <chr> <chr>         <dbl> <date>     <chr>    
##  1         1 A     apple             4 2021-07-05 morning  
##  2         2 B     apricot           3 2021-07-13 lunchtime
##  3         3 A     avocado           5 2021-07-09 morning  
##  4         4 B     banana            1 2021-07-26 lunchtime
##  5         5 A     bell pepper       4 2021-07-22 morning  
##  6         6 B     bilberry          1 2021-07-31 lunchtime
##  7         7 A     blackberry        5 2021-07-01 morning  
##  8         8 B     blackcurrant      1 2021-07-18 lunchtime
##  9        NA C     <NA>             NA NA         afternoon
## 10        NA D     <NA>             NA NA         evening
33 / 35

Key Takeaways

34 / 35
  • The tidyverse is big
  • Composition is a key part
  • Grouping and nesting is powerful
  • Writing tidyverse style functions is a little more involved
35 / 35

A quick note
on Composition

2 / 35
Paused

Help

Keyboard shortcuts

↑, ←, Pg Up, k Go to previous slide
↓, →, Pg Dn, Space, j Go to next slide
Home Go to first slide
End Go to last slide
Number + Return Go to specific slide
b / m / f Toggle blackout / mirrored / fullscreen mode
c Clone slideshow
p Toggle presenter mode
t Restart the presentation timer
?, h Toggle this help
oTile View: Overview of Slides
Esc Back to slideshow