Module 13: Apply it to your data 12

Import your data

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

setwd("~/Desktop/PSU_DAT3000_IntroToDA/05_module8/data/")
data <- read_excel("My_Data.xlsx")
data

## # A tibble: 1,302 × 9
##    Language   Endonym `World Region` Country `Global Speakers` `Language Family`
##    <chr>      <chr>   <chr>          <chr>               <dbl> <chr>            
##  1 Abakuá     Abakuá  Caribbean      "Cuba"                 NA <NA>             
##  2 Abaza      Абаза   Western Asia   "Turke…             49800 Abkhaz-Adyge     
##  3 Abruzzese… Abruzz… Southern Euro… "Italy"                NA Indo-European    
##  4 Abruzzese… Abruzz… Southern Euro… "Italy"                NA Indo-European    
##  5 Acehnese   Bahsa … Southeastern … "Indon…           3500000 Austronesian     
##  6 Acehnese   Bahsa … Southeastern … "Indon…           3500000 Austronesian     
##  7 Adjoukrou  <NA>    Western Africa "Ivory…            140000 Atlantic-Congo   
##  8 Adyghe     <NA>    Western Asia   "Turke…            117500 Abkhaz-Adyge     
##  9 Afenmai    Afenmai Western Africa "Niger…            270000 Atlantic-Congo   
## 10 African-A… Black … Northern Amer… "Unite…          45109521 Indo-European    
## # ℹ 1,292 more rows
## # ℹ 3 more variables: Location <chr>, Size <chr>, Status <chr>

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 regressgion 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

ex.2) Repeat the same operation over different elements of a list When you have a grouping variable (factor)

data %>% lm(formula = as.numeric(factor(Status)) ~ Size, data = .)

## 
## Call:
## lm(formula = as.numeric(factor(Status)) ~ Size, data = .)
## 
## Coefficients:
##  (Intercept)   SizeLargest    SizeMedium     SizeSmall  SizeSmallest  
##      3.73118       0.13132      -0.07513      -0.28409      -0.46345

data %>% distinct(Country)

## # A tibble: 354 × 1
##    Country                    
##    <chr>                      
##  1 "Cuba"                     
##  2 "Turkey,\r\nRussia"        
##  3 "Italy"                    
##  4 "Indonesia"                
##  5 "Ivory Coast"              
##  6 "Nigeria"                  
##  7 "United States"            
##  8 "South Africa,\r\nZimbabwe"
##  9 "Ghana"                    
## 10 "Philippines"              
## # ℹ 344 more rows

reg_coeff_tbl <- data %>%
    mutate(Size = factor(Size, levels = c("Smallest", "Small", "Medium", "Large")), 
           Size = as.numeric(Size), 
           `Global Speakers` = as.numeric(`Global Speakers`)) %>%
    
    # Filtering
    filter(!is.na(Size), !is.na(`Global Speakers`)) %>%
    
    
    # Split it into a list of data frames
    split(.$Location) %>%

    # Repeat regression over each group
    map(~lm(formula = Size ~ `Global Speakers`, data = .x)) %>%
    
    # Extract coefficients from regression results
    map(broom::tidy, conf.int = TRUE) %>%
    
    # Convert to tibble
    bind_rows(.id = "Status") %>%
    
    # Filter for wt coefficients
    filter(term == "`Global Speakers`")

reg_coeff_tbl %>%
    slice_sample(n = 30) %>%
    
    mutate(estimate = -estimate,
           conf.low = -conf.low,
           conf.high = -conf.high) %>%
    slice_sample(n = 30) %>%
    
    ggplot(aes(x = estimate, y = Status)) +
    geom_point() + 
    geom_errorbar(aes(xmin = conf.low, xmax = conf.high))

Module 13: Apply it to your data 12

Chapter 21 Iteration

Alex Lenfest

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