Module 13: Apply it to your data 12
Chapter 21 Iteration
Thomas Kaufield
Import your data
data("mtcars")
mtcars <- as_tibble(mtcars)
data <- read_excel("../00_data/NHLDATA.xlsx")
data## # A tibble: 8,474 × 9
## player_id first_name last_name birth_date birth_city birth_country
## <dbl> <chr> <chr> <dttm> <chr> <chr>
## 1 8467867 Bryan Adams 1977-03-20 00:00:00 Fort St. … CAN
## 2 8445176 Donald Audette 1969-09-23 00:00:00 Laval CAN
## 3 8460014 Eric Bertrand 1975-04-16 00:00:00 St-Ephrem CAN
## 4 8460510 Jason Botterill 1976-05-19 00:00:00 Edmonton CAN
## 5 8459596 Andrew Brunette 1973-08-24 00:00:00 Sudbury CAN
## 6 8445733 Kelly Buchberger 1966-12-02 00:00:00 Langenburg CAN
## 7 8460573 Hnat Domenichel… 1976-02-17 00:00:00 Edmonton CAN
## 8 8459450 Shean Donovan 1975-01-22 00:00:00 Timmins CAN
## 9 8446675 Nelson Emerson 1967-08-17 00:00:00 Hamilton CAN
## 10 8446823 Ray Ferraro 1964-08-23 00:00:00 Trail CAN
## # ℹ 8,464 more rows
## # ℹ 3 more variables: birth_state_province <chr>, birth_year <dbl>,
## # birth_month <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 2.812500mtcars %>% 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 2.812500mtcars %>% 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 2.6538462mtcars %>% 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 rowsmtcars %>% 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_vector <- function(x, factor) {x * factor}
10 %>% double_by_vector(factor = 2)## [1] 20mtcars %>% map_dfr(.x =., .f = ~double_by_vector(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 rowsmtcars %>% map_dfr(double_by_vector , 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)
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 = .)) %>%
# Extract coeffiecients 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
# Example: Multiply player goals by a factor for each numeric column
# First, select numeric columns
numeric_data <- data %>% select(where(is.numeric))
# Create a function to multiply values
multiply_by_factor <- function(x, factor) {
x * factor
}
# Apply function to all numeric columns using map_dfr
numeric_data_multiplied <- numeric_data %>% map_dfr(~multiply_by_factor(.x, factor = 2))
numeric_data_multiplied## # A tibble: 8,474 × 3
## player_id birth_year birth_month
## <dbl> <dbl> <dbl>
## 1 16935734 3954 6
## 2 16890352 3938 18
## 3 16920028 3950 8
## 4 16921020 3952 10
## 5 16919192 3946 16
## 6 16891466 3932 24
## 7 16921146 3952 4
## 8 16918900 3950 2
## 9 16893350 3934 16
## 10 16893646 3928 16
## # ℹ 8,464 more rows