Module 13: Apply it to your data 12

Chapter 21 Iteration

Import your data

data("mtcars")

Repeat the same operation over different columns of a data frame

Case of numeric variables

mtcars %>%
    
    # mutate(char_var = "A") %>%
    
    map(mean) # map(.x = ., .f = mean)

## $mpg
## [1] 20.09062
## 
## $cyl
## [1] 6.1875
## 
## $disp
## [1] 230.7219
## 
## $hp
## [1] 146.6875
## 
## $drat
## [1] 3.596563
## 
## $wt
## [1] 3.21725
## 
## $qsec
## [1] 17.84875
## 
## $vs
## [1] 0.4375
## 
## $am
## [1] 0.40625
## 
## $gear
## [1] 3.6875
## 
## $carb
## [1] 2.8125

Create your own function

muliply_by_factor <- function(x, factor) {x * factor}

10 %>% muliply_by_factor(factor = 2)

## [1] 20

mtcars %>% map(.x = ., .f = ~muliply_by_factor(x = .x, factor = 2))

## $mpg
##  [1] 42.0 42.0 45.6 42.8 37.4 36.2 28.6 48.8 45.6 38.4 35.6 32.8 34.6 30.4 20.8
## [16] 20.8 29.4 64.8 60.8 67.8 43.0 31.0 30.4 26.6 38.4 54.6 52.0 60.8 31.6 39.4
## [31] 30.0 42.8
## 
## $cyl
##  [1] 12 12  8 12 16 12 16  8  8 12 12 16 16 16 16 16 16  8  8  8  8 16 16 16 16
## [26]  8  8  8 16 12 16  8
## 
## $disp
##  [1] 320.0 320.0 216.0 516.0 720.0 450.0 720.0 293.4 281.6 335.2 335.2 551.6
## [13] 551.6 551.6 944.0 920.0 880.0 157.4 151.4 142.2 240.2 636.0 608.0 700.0
## [25] 800.0 158.0 240.6 190.2 702.0 290.0 602.0 242.0
## 
## $hp
##  [1] 220 220 186 220 350 210 490 124 190 246 246 360 360 360 410 430 460 132 104
## [20] 130 194 300 300 490 350 132 182 226 528 350 670 218
## 
## $drat
##  [1] 7.80 7.80 7.70 6.16 6.30 5.52 6.42 7.38 7.84 7.84 7.84 6.14 6.14 6.14 5.86
## [16] 6.00 6.46 8.16 9.86 8.44 7.40 5.52 6.30 7.46 6.16 8.16 8.86 7.54 8.44 7.24
## [31] 7.08 8.22
## 
## $wt
##  [1]  5.240  5.750  4.640  6.430  6.880  6.920  7.140  6.380  6.300  6.880
## [11]  6.880  8.140  7.460  7.560 10.500 10.848 10.690  4.400  3.230  3.670
## [21]  4.930  7.040  6.870  7.680  7.690  3.870  4.280  3.026  6.340  5.540
## [31]  7.140  5.560
## 
## $qsec
##  [1] 32.92 34.04 37.22 38.88 34.04 40.44 31.68 40.00 45.80 36.60 37.80 34.80
## [13] 35.20 36.00 35.96 35.64 34.84 38.94 37.04 39.80 40.02 33.74 34.60 30.82
## [25] 34.10 37.80 33.40 33.80 29.00 31.00 29.20 37.20
## 
## $vs
##  [1] 0 0 2 2 0 2 0 2 2 2 2 0 0 0 0 0 0 2 2 2 2 0 0 0 0 2 0 2 0 0 0 2
## 
## $am
##  [1] 2 2 2 0 0 0 0 0 0 0 0 0 0 0 0 0 0 2 2 2 0 0 0 0 0 2 2 2 2 2 2 2
## 
## $gear
##  [1]  8  8  8  6  6  6  6  8  8  8  8  6  6  6  6  6  6  8  8  8  6  6  6  6  6
## [26]  8 10 10 10 10 10  8
## 
## $carb
##  [1]  8  8  2  2  4  2  8  4  4  8  8  6  6  6  8  8  8  2  4  2  2  4  4  8  4
## [26]  2  4  4  8 12 16  4

mtcars %>% map_dfc(.x = ., .f = ~muliply_by_factor(x = .x, factor = 2))

## # 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  42      12  320    220  7.8   5.24  32.9     0     2     8     8
##  2  42      12  320    220  7.8   5.75  34.0     0     2     8     8
##  3  45.6     8  216    186  7.7   4.64  37.2     2     2     8     2
##  4  42.8    12  516    220  6.16  6.43  38.9     2     0     6     2
##  5  37.4    16  720    350  6.3   6.88  34.0     0     0     6     4
##  6  36.2    12  450    210  5.52  6.92  40.4     2     0     6     2
##  7  28.6    16  720    490  6.42  7.14  31.7     0     0     6     8
##  8  48.8     8  293.   124  7.38  6.38  40       2     0     8     4
##  9  45.6     8  282.   190  7.84  6.3   45.8     2     0     8     4
## 10  38.4    12  335.   246  7.84  6.88  36.6     2     0     8     8
## # … with 22 more rows

mtcars %>% map(muliply_by_factor, factor = 2)

## $mpg
##  [1] 42.0 42.0 45.6 42.8 37.4 36.2 28.6 48.8 45.6 38.4 35.6 32.8 34.6 30.4 20.8
## [16] 20.8 29.4 64.8 60.8 67.8 43.0 31.0 30.4 26.6 38.4 54.6 52.0 60.8 31.6 39.4
## [31] 30.0 42.8
## 
## $cyl
##  [1] 12 12  8 12 16 12 16  8  8 12 12 16 16 16 16 16 16  8  8  8  8 16 16 16 16
## [26]  8  8  8 16 12 16  8
## 
## $disp
##  [1] 320.0 320.0 216.0 516.0 720.0 450.0 720.0 293.4 281.6 335.2 335.2 551.6
## [13] 551.6 551.6 944.0 920.0 880.0 157.4 151.4 142.2 240.2 636.0 608.0 700.0
## [25] 800.0 158.0 240.6 190.2 702.0 290.0 602.0 242.0
## 
## $hp
##  [1] 220 220 186 220 350 210 490 124 190 246 246 360 360 360 410 430 460 132 104
## [20] 130 194 300 300 490 350 132 182 226 528 350 670 218
## 
## $drat
##  [1] 7.80 7.80 7.70 6.16 6.30 5.52 6.42 7.38 7.84 7.84 7.84 6.14 6.14 6.14 5.86
## [16] 6.00 6.46 8.16 9.86 8.44 7.40 5.52 6.30 7.46 6.16 8.16 8.86 7.54 8.44 7.24
## [31] 7.08 8.22
## 
## $wt
##  [1]  5.240  5.750  4.640  6.430  6.880  6.920  7.140  6.380  6.300  6.880
## [11]  6.880  8.140  7.460  7.560 10.500 10.848 10.690  4.400  3.230  3.670
## [21]  4.930  7.040  6.870  7.680  7.690  3.870  4.280  3.026  6.340  5.540
## [31]  7.140  5.560
## 
## $qsec
##  [1] 32.92 34.04 37.22 38.88 34.04 40.44 31.68 40.00 45.80 36.60 37.80 34.80
## [13] 35.20 36.00 35.96 35.64 34.84 38.94 37.04 39.80 40.02 33.74 34.60 30.82
## [25] 34.10 37.80 33.40 33.80 29.00 31.00 29.20 37.20
## 
## $vs
##  [1] 0 0 2 2 0 2 0 2 2 2 2 0 0 0 0 0 0 2 2 2 2 0 0 0 0 2 0 2 0 0 0 2
## 
## $am
##  [1] 2 2 2 0 0 0 0 0 0 0 0 0 0 0 0 0 0 2 2 2 0 0 0 0 0 2 2 2 2 2 2 2
## 
## $gear
##  [1]  8  8  8  6  6  6  6  8  8  8  8  6  6  6  6  6  6  8  8  8  6  6  6  6  6
## [26]  8 10 10 10 10 10  8
## 
## $carb
##  [1]  8  8  2  2  4  2  8  4  4  8  8  6  6  6  8  8  8  2  4  2  2  4  4  8  4
## [26]  2  4  4  8 12 16  4

Repeat the same operation over different elements of a list

When you have a grouping variable (factor)

Create your own

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

Import Data

results <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2021/2021-09-07/results.csv')

## Warning: One or more parsing issues, see `problems()` for details

## Rows: 25220 Columns: 18
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr  (8): position, positionText, time, milliseconds, fastestLap, rank, fast...
## dbl (10): resultId, raceId, driverId, constructorId, number, grid, positionO...
## 
## 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.

skimr::skim(results)

Data summary

Name	results
Number of rows	25220
Number of columns	18
_______________________
Column type frequency:
character	8
numeric	10
________________________
Group variables	None

Variable type: character

skim_variable	n_missing	complete_rate	min	max	empty	n_unique	whitespace
position	0	1	1	2	0	34	0
positionText	0	1	1	2	0	39	0
time	0	1	2	11	0	6488	0
milliseconds	0	1	2	8	0	6687	0
fastestLap	0	1	1	2	0	80	0
rank	0	1	1	2	0	26	0
fastestLapTime	0	1	2	8	0	6266	0
fastestLapSpeed	0	1	2	7	0	6395	0

Variable type: numeric

skim_variable	n_missing	complete_rate	mean	sd	p0	p25	p50	p75	p100	hist
resultId	0	1	12611.23	7281.58	1	6305.75	12610.5	18915.25	25225	▇▇▇▇▇
raceId	0	1	517.95	290.34	1	287.00	503.0	762.00	1064	▆▇▇▆▆
driverId	0	1	250.84	258.25	1	56.00	158.0	347.00	854	▇▃▂▁▂
constructorId	0	1	47.48	58.39	1	6.00	25.0	57.00	214	▇▂▁▁▁
number	6	1	17.59	14.80	0	7.00	15.0	23.00	208	▇▁▁▁▁
grid	0	1	11.21	7.27	0	5.00	11.0	17.00	34	▇▇▇▃▁
positionOrder	0	1	12.93	7.74	1	6.00	12.0	19.00	39	▇▇▆▂▁
points	0	1	1.80	4.03	0	0.00	0.0	2.00	50	▇▁▁▁▁
laps	0	1	45.79	30.04	0	21.00	52.0	66.00	200	▅▇▁▁▁
statusId	0	1	17.72	26.10	1	1.00	11.0	14.00	139	▇▁▁▁▁

Columns Operation

mean_results <- results %>% 
    
    map(mean)

## Warning in mean.default(.x[[i]], ...): argument is not numeric or logical:
## returning NA

## Warning in mean.default(.x[[i]], ...): argument is not numeric or logical:
## returning NA

## Warning in mean.default(.x[[i]], ...): argument is not numeric or logical:
## returning NA

## Warning in mean.default(.x[[i]], ...): argument is not numeric or logical:
## returning NA

## Warning in mean.default(.x[[i]], ...): argument is not numeric or logical:
## returning NA

## Warning in mean.default(.x[[i]], ...): argument is not numeric or logical:
## returning NA

## Warning in mean.default(.x[[i]], ...): argument is not numeric or logical:
## returning NA

## Warning in mean.default(.x[[i]], ...): argument is not numeric or logical:
## returning NA

Function

mean_laps <- function(.data, laps) {
    
    mean_results <- .data %>% 
        
        mean(laps) %>% 
        
        return(mean_laps)
}