Week 14: Apply it to your data 13

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(mean)

## $mpg
## [1] 20.09062
## 
## $cyl
## [1] 6.1875
## 
## $disp
## [1] 230.7219
## 
## $hp
## [1] 146.6875
## 
## $drat
## [1] 3.596563
## 
## $wt
## [1] 3.21725
## 
## $qsec
## [1] 17.84875
## 
## $vs
## [1] 0.4375
## 
## $am
## [1] 0.40625
## 
## $gear
## [1] 3.6875
## 
## $carb
## [1] 2.8125

# 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_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
## # … with 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
## # … 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 = .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

Import data

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

## # A tibble: 21,560 × 12
##     year gnis_id geometry   metad…¹ numbe…² parkn…³ region state unit_…⁴ unit_…⁵
##    <dbl>   <dbl> <chr>      <chr>     <dbl> <chr>   <chr>  <chr> <chr>   <chr>  
##  1  1904 1163670 POLYGON    NA            1 Crater… PW     OR    CRLA    Crater…
##  2  1941 1531834 MULTIPOLY… NA            1 Lake R… PW     WA    LARO    Lake R…
##  3  1961 2055170 MULTIPOLY… NA            1 Lewis … PW     WA    LEWI    Lewis …
##  4  1935 1530459 MULTIPOLY… NA            1 Olympic PW     WA    OLYM    Olympi…
##  5  1982  277263 POLYGON    NA            1 Santa … PW     CA    SAMO    Santa …
##  6  1919  578853 MULTIPOLY… NA            1 NA      NE     ME    ACAD    Acadia…
##  7  1969 1329499 MULTIPOLY… NA            1 NA      IM     TX    AMIS    Amista…
##  8  1967  589056 POLYGON    NA            1 NA      NE     MD    ASIS    Assate…
##  9  1944 1377082 POLYGON    NA            1 NA      IM     TX    BIBE    Big Be…
## 10  1989  302659 POLYGON    NA            1 NA      SE     FL    BICY    Big Cy…
## # … with 21,550 more rows, 2 more variables: unit_type <chr>, visitors <dbl>,
## #   and abbreviated variable names ¹metadata, ²number_of_records, ³parkname,
## #   ⁴unit_code, ⁵unit_name

data %>% lm(formula = year ~ visitors, data = .)

## 
## Call:
## lm(formula = year ~ visitors, data = .)
## 
## Coefficients:
## (Intercept)     visitors  
##   1.980e+03    2.179e-06

data %>% distinct(geometry)

## # A tibble: 2 × 1
##   geometry    
##   <chr>       
## 1 POLYGON     
## 2 MULTIPOLYGON

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

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

Week 14: Apply it to your data 13

Chapter 21 Iteration

Maddie Westbrook

2022-12-05

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

Import data