Module 13: Apply it to your data 12

Import your data

data("mtcars") 
mtcars <- as_tibble(mtcars)
data <- read_excel("../00_data/myData.xlsx")

## New names:
## • `` -> `...1`

data

## # A tibble: 4,810 × 24
##     ...1  rank position hand  player   years total…¹ status yr_st…² season   age
##    <dbl> <dbl> <chr>    <chr> <chr>    <chr>   <dbl> <chr>    <dbl> <chr>  <dbl>
##  1     1     1 C        Left  Wayne G… 1979…     894 Retir…    1979 1978-…    18
##  2     2     1 C        Left  Wayne G… 1979…     894 Retir…    1979 1978-…    18
##  3     3     1 C        Left  Wayne G… 1979…     894 Retir…    1979 1978-…    18
##  4     4     1 C        Left  Wayne G… 1979…     894 Retir…    1979 1979-…    19
##  5     5     1 C        Left  Wayne G… 1979…     894 Retir…    1979 1980-…    20
##  6     6     1 C        Left  Wayne G… 1979…     894 Retir…    1979 1981-…    21
##  7     7     1 C        Left  Wayne G… 1979…     894 Retir…    1979 1982-…    22
##  8     8     1 C        Left  Wayne G… 1979…     894 Retir…    1979 1983-…    23
##  9     9     1 C        Left  Wayne G… 1979…     894 Retir…    1979 1984-…    24
## 10    10     1 C        Left  Wayne G… 1979…     894 Retir…    1979 1985-…    25
## # … with 4,800 more rows, 13 more variables: team <chr>, league <chr>,
## #   season_games <dbl>, goals <dbl>, assists <dbl>, points <dbl>,
## #   plus_minus <chr>, penalty_min <dbl>, goals_even <chr>,
## #   goals_power_play <chr>, goals_short_handed <chr>, goals_game_winner <chr>,
## #   headshot <chr>, and abbreviated variable names ¹total_goals, ²yr_start

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
## # … with 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
## # … with 22 more rows

Create your own function

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

## [1] 20

mtcars %>% map_dfr(.x =., .f = ~double_by_vector(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
## # … with 22 more rows

mtcars %>% map_dfr(double_by_vector , 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
## # … with 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 = .)) %>%
    
    # Extract coeffiecients 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

 newdata <- data %>%
    filter(omit.na = TRUE)

newdata

## # A tibble: 4,810 × 24
##     ...1  rank position hand  player   years total…¹ status yr_st…² season   age
##    <dbl> <dbl> <chr>    <chr> <chr>    <chr>   <dbl> <chr>    <dbl> <chr>  <dbl>
##  1     1     1 C        Left  Wayne G… 1979…     894 Retir…    1979 1978-…    18
##  2     2     1 C        Left  Wayne G… 1979…     894 Retir…    1979 1978-…    18
##  3     3     1 C        Left  Wayne G… 1979…     894 Retir…    1979 1978-…    18
##  4     4     1 C        Left  Wayne G… 1979…     894 Retir…    1979 1979-…    19
##  5     5     1 C        Left  Wayne G… 1979…     894 Retir…    1979 1980-…    20
##  6     6     1 C        Left  Wayne G… 1979…     894 Retir…    1979 1981-…    21
##  7     7     1 C        Left  Wayne G… 1979…     894 Retir…    1979 1982-…    22
##  8     8     1 C        Left  Wayne G… 1979…     894 Retir…    1979 1983-…    23
##  9     9     1 C        Left  Wayne G… 1979…     894 Retir…    1979 1984-…    24
## 10    10     1 C        Left  Wayne G… 1979…     894 Retir…    1979 1985-…    25
## # … with 4,800 more rows, 13 more variables: team <chr>, league <chr>,
## #   season_games <dbl>, goals <dbl>, assists <dbl>, points <dbl>,
## #   plus_minus <chr>, penalty_min <dbl>, goals_even <chr>,
## #   goals_power_play <chr>, goals_short_handed <chr>, goals_game_winner <chr>,
## #   headshot <chr>, and abbreviated variable names ¹total_goals, ²yr_start

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

## 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

## 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

##               ...1               rank           position               hand 
##         2405.50000          120.89579                 NA                 NA 
##             player              years        total_goals             status 
##                 NA                 NA          392.29236                 NA 
##           yr_start             season                age               team 
##         1983.03222                 NA           28.18061                 NA 
##             league       season_games              goals            assists 
##                 NA           66.33940           21.79652           29.39293 
##             points         plus_minus        penalty_min         goals_even 
##           52.08784                 NA           41.29808                 NA 
##   goals_power_play goals_short_handed  goals_game_winner           headshot 
##                 NA                 NA                 NA                 NA

half_by_factor <- function(x, factor) {x / factor}

newdata %>% select("total_goals") %>% map_dfr(half_by_factor, factor = 2)

## # A tibble: 4,810 × 1
##    total_goals
##          <dbl>
##  1         447
##  2         447
##  3         447
##  4         447
##  5         447
##  6         447
##  7         447
##  8         447
##  9         447
## 10         447
## # … with 4,800 more rows

newdata %>% select("assists") %>% map_dfr(half_by_factor, factor = 2)

## # A tibble: 4,810 × 1
##    assists
##      <dbl>
##  1    32  
##  2     1.5
##  3    30.5
##  4    43  
##  5    54.5
##  6    60  
##  7    62.5
##  8    59  
##  9    67.5
## 10    81.5
## # … with 4,800 more rows

newdata %>% select("season_games") %>% map_dfr(half_by_factor, factor = 2)

## # A tibble: 4,810 × 1
##    season_games
##           <dbl>
##  1         40  
##  2          4  
##  3         36  
##  4         39.5
##  5         40  
##  6         40  
##  7         40  
##  8         37  
##  9         40  
## 10         40  
## # … with 4,800 more rows

Module 13: Apply it to your data 12

Chapter 21 Iteration

Daniel Lee

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