Module 13: Apply it to your data 12

Import your data

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

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

## # A tibble: 1,104 × 31
##    town11cd  town11nm population_2011 size_flag rgn11nm coastal coastal_detailed
##    <chr>     <chr>              <dbl> <chr>     <chr>   <chr>   <chr>           
##  1 E34000007 Carlton…            5456 Small To… East M… Non-co… Smaller non-coa…
##  2 E34000016 Dorches…           19060 Small To… South … Non-co… Smaller non-coa…
##  3 E34000020 Ely BUA            19090 Small To… East o… Non-co… Smaller non-coa…
##  4 E34000026 Market …            6429 Small To… Yorksh… Non-co… Smaller non-coa…
##  5 E34000027 Downham…           10884 Small To… East o… Non-co… Smaller non-coa…
##  6 E34000039 Penrith…           15181 Small To… North … Non-co… Smaller non-coa…
##  7 E34000048 Bolsove…           11754 Small To… East M… Non-co… Smaller non-coa…
##  8 E34000055 March B…           21051 Medium T… East o… Non-co… Large non-coast…
##  9 E34000056 Southam…            6567 Small To… West M… Non-co… Smaller non-coa…
## 10 E34000067 Royston…           15781 Small To… East o… Non-co… Smaller non-coa…
## # ℹ 1,094 more rows
## # ℹ 24 more variables: ttwa11cd <chr>, ttwa11nm <chr>,
## #   ttwa_classification <chr>, job_density_flag <chr>, income_flag <chr>,
## #   university_flag <chr>, level4qual_residents35_64_2011 <chr>,
## #   ks4_2012_2013_counts <dbl>,
## #   key_stage_2_attainment_school_year_2007_to_2008 <dbl>,
## #   key_stage_4_attainment_school_year_2012_to_2013 <dbl>, …

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) %>%
    
    # 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

my_coeff_tbl <- data %>% 
    filter(!is.na(education_score), !is.na(population_2011)) %>%
    
    # Split it into a list of data frames
    split(.$size_flag) %>%
    
    #Repeat regression over each group
    map(~lm(formula = education_score ~ population_2011, data = .x)) %>%
    
    # Extract coefficients from regression results
    map(broom::tidy, conf.int = TRUE) %>%
    
    # Convert to tibble
    bind_rows(.id = "size_flag") %>%
    
    # Filter for population_2011 coefficients
    filter(term == "population_2011")

my_coeff_tbl %>%
    ggplot(aes(x = estimate, y = size_flag)) +
    geom_point() +
    geom_errorbar(aes(xmin = conf.low, xmax = conf.high))

Module 13: Apply it to your data 12

Chapter 21 Iteration

Taylor Nelson

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