Import your data

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

mydata <- read_excel("../00_data/mydata.xlsx") %>%
    janitor::clean_names()
mydata 
## # A tibble: 54 × 9
##     year winner        score runner_up     third_place  fourth_place    location
##    <dbl> <chr>         <dbl> <chr>         <chr>        <chr>           <chr>   
##  1  2024 UConn          75.6 Purdue        *Alabama     *NCState        Phoenix 
##  2  2023 UConn          76.6 SanDiegoSt.   *Miami(FL)   *FloridaAtlant… Houston 
##  3  2022 Kansas         72.7 NorthCarolina *Villanova   *Duke           NewOrle…
##  4  2021 Baylor         86.7 Gonzaga       *Houston     *UCLA           Indiana…
##  5  2019 Virginia       85.8 TexasTech     *Auburn      *MichiganSt.    Minneap…
##  6  2018 Villanova      79.6 Michigan      *Kansas      *LoyolaChicago  SanAnto…
##  7  2017 NorthCarolina  71.6 Gonzaga       *Oregon      *SouthCarolina  Phoenix 
##  8  2016 Villanova      77.7 NorthCarolina *Oklahoma    *Syracuse       Houston 
##  9  2015 Duke           68.6 Wisconsin     *MichiganSt. *Kentucky       Indiana…
## 10  2014 UConn          60.5 Kentucky      *Florida     *Wisconsin      Arlingt…
## # ℹ 44 more rows
## # ℹ 2 more variables: most_outstanding_player <chr>, winning_coach <chr>
data_clean <- mydata %>% 
    select(winner, year, runner_up, score) %>% 
    slice(1:24)
data_clean <- as_tibble(data_clean)

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) %>%

    # Covert 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

data_clean %>% map(.x = ., .f = ~mean(x = .x))
## Warning in mean.default(x = .x): argument is not numeric or logical: returning
## NA
## Warning in mean.default(x = .x): argument is not numeric or logical: returning
## NA
## $winner
## [1] NA
## 
## $year
## [1] 2011.667
## 
## $runner_up
## [1] NA
## 
## $score
## [1] 75.90875
data_clean %>% map(.f = ~mean(x = .x))
## Warning in mean.default(x = .x): argument is not numeric or logical: returning
## NA
## Warning in mean.default(x = .x): argument is not numeric or logical: returning
## NA
## $winner
## [1] NA
## 
## $year
## [1] 2011.667
## 
## $runner_up
## [1] NA
## 
## $score
## [1] 75.90875
data_clean %>% 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
## $winner
## [1] NA
## 
## $year
## [1] 2011.667
## 
## $runner_up
## [1] NA
## 
## $score
## [1] 75.90875
# Adding an argument 
data_clean %>% map_dbl(.x = ., .f = ~mean(x = .x, trim = 0.1))
## Warning in mean.default(x = .x, trim = 0.1): argument is not numeric or
## logical: returning NA
## Warning in mean.default(x = .x, trim = 0.1): argument is not numeric or
## logical: returning NA
##    winner      year runner_up     score 
##        NA  2011.600        NA    76.419
data_clean %>% 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
##    winner      year runner_up     score 
##        NA  2011.600        NA    76.419
data_clean %>% select(.data = ., score)
## # A tibble: 24 × 1
##    score
##    <dbl>
##  1  75.6
##  2  76.6
##  3  72.7
##  4  86.7
##  5  85.8
##  6  79.6
##  7  71.6
##  8  77.7
##  9  68.6
## 10  60.5
## # ℹ 14 more rows
data_clean %>% select(score)
## # A tibble: 24 × 1
##    score
##    <dbl>
##  1  75.6
##  2  76.6
##  3  72.7
##  4  86.7
##  5  85.8
##  6  79.6
##  7  71.6
##  8  77.7
##  9  68.6
## 10  60.5
## # ℹ 14 more rows