Module 13: Apply it to your data 12

Import your data

data("mtcars")
mtcars <- as_tibble(mtcars)

Repeat the same operation over different columns of a data frame

Case of numeric variables

mtcars %>% map_dbl(.x = ., .f = ~mean(x = .x))

##        mpg        cyl       disp         hp       drat         wt       qsec 
##  20.090625   6.187500 230.721875 146.687500   3.596563   3.217250  17.848750 
##         vs         am       gear       carb 
##   0.437500   0.406250   3.687500   2.812500

mtcars %>% map_dbl(.f = ~mean(x = .x))

##        mpg        cyl       disp         hp       drat         wt       qsec 
##  20.090625   6.187500 230.721875 146.687500   3.596563   3.217250  17.848750 
##         vs         am       gear       carb 
##   0.437500   0.406250   3.687500   2.812500

mtcars %>% map_dbl(mean)

##        mpg        cyl       disp         hp       drat         wt       qsec 
##  20.090625   6.187500 230.721875 146.687500   3.596563   3.217250  17.848750 
##         vs         am       gear       carb 
##   0.437500   0.406250   3.687500   2.812500

# Adding an argument
mtcars %>% map_dbl(.x = ., .f = ~mean(x = .x, trim = 0.1))

##         mpg         cyl        disp          hp        drat          wt 
##  19.6961538   6.2307692 222.5230769 141.1923077   3.5792308   3.1526923 
##        qsec          vs          am        gear        carb 
##  17.8276923   0.4230769   0.3846154   3.6153846   2.6538462

mtcars %>% map_dbl(mean, trim = 0.1)

##         mpg         cyl        disp          hp        drat          wt 
##  19.6961538   6.2307692 222.5230769 141.1923077   3.5792308   3.1526923 
##        qsec          vs          am        gear        carb 
##  17.8276923   0.4230769   0.3846154   3.6153846   2.6538462

mtcars %>% select(.data = ., mpg)

## # A tibble: 32 × 1
##      mpg
##    <dbl>
##  1  21  
##  2  21  
##  3  22.8
##  4  21.4
##  5  18.7
##  6  18.1
##  7  14.3
##  8  24.4
##  9  22.8
## 10  19.2
## # ℹ 22 more rows

mtcars %>% select(mpg)

## # A tibble: 32 × 1
##      mpg
##    <dbl>
##  1  21  
##  2  21  
##  3  22.8
##  4  21.4
##  5  18.7
##  6  18.1
##  7  14.3
##  8  24.4
##  9  22.8
## 10  19.2
## # ℹ 22 more rows

Create your own function

# Double values in columns
double_by_factor <- function(x, factor) {x * factor}
10 %>% double_by_factor(factor = 2)

## [1] 20

mtcars %>% map_dfr(.x = ., .f = ~double_by_factor(x = .x, factor = 10))

## # A tibble: 32 × 11
##      mpg   cyl  disp    hp  drat    wt  qsec    vs    am  gear  carb
##    <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
##  1   210    60  1600  1100  39    26.2  165.     0    10    40    40
##  2   210    60  1600  1100  39    28.8  170.     0    10    40    40
##  3   228    40  1080   930  38.5  23.2  186.    10    10    40    10
##  4   214    60  2580  1100  30.8  32.2  194.    10     0    30    10
##  5   187    80  3600  1750  31.5  34.4  170.     0     0    30    20
##  6   181    60  2250  1050  27.6  34.6  202.    10     0    30    10
##  7   143    80  3600  2450  32.1  35.7  158.     0     0    30    40
##  8   244    40  1467   620  36.9  31.9  200     10     0    40    20
##  9   228    40  1408   950  39.2  31.5  229     10     0    40    20
## 10   192    60  1676  1230  39.2  34.4  183     10     0    40    40
## # ℹ 22 more rows

mtcars %>% map_dfr(double_by_factor, factor = 10)

## # A tibble: 32 × 11
##      mpg   cyl  disp    hp  drat    wt  qsec    vs    am  gear  carb
##    <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
##  1   210    60  1600  1100  39    26.2  165.     0    10    40    40
##  2   210    60  1600  1100  39    28.8  170.     0    10    40    40
##  3   228    40  1080   930  38.5  23.2  186.    10    10    40    10
##  4   214    60  2580  1100  30.8  32.2  194.    10     0    30    10
##  5   187    80  3600  1750  31.5  34.4  170.     0     0    30    20
##  6   181    60  2250  1050  27.6  34.6  202.    10     0    30    10
##  7   143    80  3600  2450  32.1  35.7  158.     0     0    30    40
##  8   244    40  1467   620  36.9  31.9  200     10     0    40    20
##  9   228    40  1408   950  39.2  31.5  229     10     0    40    20
## 10   192    60  1676  1230  39.2  34.4  183     10     0    40    40
## # ℹ 22 more rows

Repeat the same operation over different elements of a list

When you have a grouping variable (factor)

mtcars %>% lm(formula = mpg ~ wt, data = .)

## 
## Call:
## lm(formula = mpg ~ wt, data = .)
## 
## Coefficients:
## (Intercept)           wt  
##      37.285       -5.344

mtcars %>% distinct(cyl)

## # A tibble: 3 × 1
##     cyl
##   <dbl>
## 1     6
## 2     4
## 3     8

reg_coeff_tbl <- mtcars %>%
    # Split it into a list of data frames
    split(.$cyl) %>%
    
    # Repeat regression over each group 
    map(~lm(formula = mpg ~ wt, data = .x)) %>%
   
    # Extract coefficients from regression results
     map(broom::tidy, conf.int = TRUE) %>%
    
    # Convert to tibble
    bind_rows(.id = "cyl") %>%
    
    # Filter for wt coefficients
    filter(term == "wt")

reg_coeff_tbl %>%
    mutate(estimate = -estimate,
           conf.low = -conf.low,
           conf.high = -conf.high) %>%
    ggplot(aes(x = estimate, y = cyl)) +
    geom_point() +
    geom_errorbar(aes(xmin = conf.low, xmax = conf.high))

Create your own

Choose either one of the two cases above and apply it to your data

taylor_album_songs <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2023/2023-10-17/taylor_album_songs.csv')

## Rows: 194 Columns: 29
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr   (7): album_name, track_name, artist, featuring, key_name, mode_name, k...
## dbl  (14): track_number, danceability, energy, key, loudness, mode, speechin...
## lgl   (4): ep, bonus_track, explicit, lyrics
## date  (4): album_release, promotional_release, single_release, track_release
## 
## 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.

Taylor_numeric <- taylor_album_songs %>%
    select(track_number, key, mode, tempo, liveness, loudness)

Taylor_numeric %>% map_dbl(.x = ., .f = ~mean(x = .x, na.rm = TRUE))

## track_number          key         mode        tempo     liveness     loudness 
##   10.7061856    4.6858639    0.9109948  125.9914241    0.1408131   -7.5180576

Taylor_numeric %>% map_dbl(.f = ~mean(x = .x, na.rm = TRUE))

## track_number          key         mode        tempo     liveness     loudness 
##   10.7061856    4.6858639    0.9109948  125.9914241    0.1408131   -7.5180576

Taylor_numeric %>% map_dbl(mean, na.rm = TRUE)

## track_number          key         mode        tempo     liveness     loudness 
##   10.7061856    4.6858639    0.9109948  125.9914241    0.1408131   -7.5180576

# Adding an argument
Taylor_numeric %>% map_dbl(.x = ., .f = ~mean(x = .x, na.rm = TRUE, trim = 0.1))

## track_number          key         mode        tempo     liveness     loudness 
##   10.2115385    4.5947712    1.0000000  124.8144837    0.1250176   -7.3463203

Taylor_numeric %>% map_dbl(mean, na.rm = TRUE, trim = 0.1)

## track_number          key         mode        tempo     liveness     loudness 
##   10.2115385    4.5947712    1.0000000  124.8144837    0.1250176   -7.3463203

# Double values in columns
Taylor_numeric %>% map_dfr(.x = ., .f = ~double_by_factor(x = .x, factor = 20))

## # A tibble: 194 × 6
##    track_number   key  mode tempo liveness loudness
##           <dbl> <dbl> <dbl> <dbl>    <dbl>    <dbl>
##  1           20     0    20 1520.     2.42   -129. 
##  2           40   140    20 2112.     1.92    -42.0
##  3           60   200    20 1999.     2.38   -139. 
##  4           80   180    20 2301.     6.4     -57.6
##  5          100   100    20 3511.     2.46   -115. 
##  6          120   100    20 2260.     4.8     -81.1
##  7          140    40    20 2923.     1.68    -99.3
##  8          160   160    20 2632.     2.74    -98.4
##  9          180    80     0 3359.     3.92    -75.4
## 10          200    40    20 1498      3.64   -106. 
## # ℹ 184 more rows

Taylor_numeric %>% map_dfr(double_by_factor, factor = 20)

## # A tibble: 194 × 6
##    track_number   key  mode tempo liveness loudness
##           <dbl> <dbl> <dbl> <dbl>    <dbl>    <dbl>
##  1           20     0    20 1520.     2.42   -129. 
##  2           40   140    20 2112.     1.92    -42.0
##  3           60   200    20 1999.     2.38   -139. 
##  4           80   180    20 2301.     6.4     -57.6
##  5          100   100    20 3511.     2.46   -115. 
##  6          120   100    20 2260.     4.8     -81.1
##  7          140    40    20 2923.     1.68    -99.3
##  8          160   160    20 2632.     2.74    -98.4
##  9          180    80     0 3359.     3.92    -75.4
## 10          200    40    20 1498      3.64   -106. 
## # ℹ 184 more rows

Module 13: Apply it to your data 12

Chapter 21 Iteration

Alyssa D’Alessio

Import your data

Repeat the same operation over different columns of a data frame

Repeat the same operation over different elements of a list

Create your own