Module 13: Apply it to your data 12
Chapter 21 Iteration
Laurence Bouchard
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# . alone represent the data set mtcars = aussi .x
# .f represent the function we want to use
# This is quite long, we usually omit the first part, instead we can write:
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# We can further abbreviate like this:
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# And like this
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## Only if the expression is not too complicate
# 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## How to abbreviate this one:
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 2.6538462mtcars %>% 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# This also do the same thing
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 rowsCreate your own function
# Double values in columns
double_by_factor <- function(x, factor) {x * factor}
10 %>% double_by_factor(factor = 2)## [1] 20mtcars %>% 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# simplified:
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 rowsRepeat 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 -5.344mtcars %>% distinct(cyl)## # A tibble: 3 × 1
## cyl
## <dbl>
## 1 6
## 2 4
## 3 8reg_coeff_tbl <- mtcars %>%
# Split it into a list of data frames
split(.$cyl) %>%
# . = mtcars, $ is a way to access the cyl column
# 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 data
NCAA <- read_excel("../00_data/myData_charts.xls")## New names:
## • `` -> `...1`NCAA## # A tibble: 16,383 × 29
## ...1 year unitid institution_name city_txt state_cd zip_text
## <dbl> <dbl> <dbl> <chr> <chr> <chr> <dbl>
## 1 1 2015 100654 Alabama A & M University Normal AL 35762
## 2 2 2015 100654 Alabama A & M University Normal AL 35762
## 3 3 2015 100654 Alabama A & M University Normal AL 35762
## 4 4 2015 100654 Alabama A & M University Normal AL 35762
## 5 5 2015 100654 Alabama A & M University Normal AL 35762
## 6 6 2015 100654 Alabama A & M University Normal AL 35762
## 7 7 2015 100654 Alabama A & M University Normal AL 35762
## 8 8 2015 100654 Alabama A & M University Normal AL 35762
## 9 9 2015 100654 Alabama A & M University Normal AL 35762
## 10 10 2015 100654 Alabama A & M University Normal AL 35762
## # ℹ 16,373 more rows
## # ℹ 22 more variables: classification_code <dbl>, classification_name <chr>,
## # classification_other <chr>, ef_male_count <dbl>, ef_female_count <dbl>,
## # ef_total_count <dbl>, sector_cd <dbl>, sector_name <chr>, sportscode <dbl>,
## # partic_men <chr>, partic_women <chr>, partic_coed_men <chr>,
## # partic_coed_women <chr>, sum_partic_men <dbl>, sum_partic_women <dbl>,
## # rev_men <chr>, rev_women <chr>, total_rev_menwomen <chr>, exp_men <chr>, …NCAA_small <- NCAA %>%
select(institution_name, sports, rev_women, sum_partic_men, sum_partic_women) %>%
filter(institution_name %in% c("University of Denver"))
NCAA_small## # A tibble: 10 × 5
## institution_name sports rev_women sum_partic_men sum_partic_women
## <chr> <chr> <chr> <dbl> <dbl>
## 1 University of Denver Basketball 1729128 17 18
## 2 University of Denver Golf 617182 7 7
## 3 University of Denver Gymnastics 1388115 0 14
## 4 University of Denver Ice Hockey NA 27 0
## 5 University of Denver Lacrosse 1271011 51 32
## 6 University of Denver Skiing 812527 9 14
## 7 University of Denver Soccer 1356455 25 24
## 8 University of Denver Swimming and … 1122277 28 27
## 9 University of Denver Tennis 796467 10 8
## 10 University of Denver Volleyball 1349643 0 15NCAA_small %>%
select(sum_partic_women, sum_partic_men) %>%
map_dbl(~ mean(.x, na.rm = TRUE))## sum_partic_women sum_partic_men
## 15.9 17.4NCAA_small %>%
select(where(is.numeric)) %>%
map_dbl(~ mean(.x, na.rm = TRUE))## sum_partic_men sum_partic_women
## 17.4 15.9