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(.f = 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
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 value in column

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 %>% lm(formula = mpg ~ wt)
## 
## 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(.x = ., .f = ~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 coefficient
    filter(term == "wt")



# Demonstration: Same as above, but need pipe operator
    #map(~lm(formula = mpg ~ wt, data = .x))
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

# Import Data

data <- read_excel("../01_module4/data/myData.xlsx")

#Adding a categorical variable
data1 <- data%>%
    mutate(continent = countrycode (country, 
                                    origin = "country.name",
                                    destination = "continent"))


data1 %>% distinct(continent)
## # A tibble: 5 × 1
##   continent
##   <chr>    
## 1 Europe   
## 2 Oceania  
## 3 Asia     
## 4 Americas 
## 5 Africa
# Grouping variable - Continent - example 2

data1 %>% lm(formula = human_development_index_hdi ~ expected_years_of_schooling)
## 
## Call:
## lm(formula = human_development_index_hdi ~ expected_years_of_schooling, 
##     data = .)
## 
## Coefficients:
##                 (Intercept)  expected_years_of_schooling  
##                     0.14543                      0.04383
data1 %>% distinct(continent)
## # A tibble: 5 × 1
##   continent
##   <chr>    
## 1 Europe   
## 2 Oceania  
## 3 Asia     
## 4 Americas 
## 5 Africa
data1_reg_coeff_tbl <- data1 %>% 
    
    # Split it into a list of data frames
    split(.$continent) %>%

    # Repeat regression over each group
    map(.x = ., .f = ~lm(formula = human_development_index_hdi ~ expected_years_of_schooling, data = .x)) %>%
    
    
    #Extract coefficients from regression results
    map(broom::tidy, conf.int = TRUE) %>%

    # Convert to tibble 
    bind_rows(.id = "continent") %>%
    
    #Filter for wt coefficient
    filter(term == "expected_years_of_schooling")


data1_reg_coeff_tbl %>%
    mutate(estimate = -estimate,
           conf.low = -conf.low, 
           conf.high = -conf.high) %>%
    
    ggplot(aes(x = estimate, y = continent)) +
    geom_point() +
    geom_errorbar(aes(xmin = conf.low, xmax = conf.high))