Module 13: Apply it to your data 12
Chapter 21 Iteration
Jackson Chicklis
Import your data
data("mtcars")
mtcars <- as_tibble(mtcars)
my_data <- read_excel("../00_data/newmyData.xlsx")
my_data## # A tibble: 20,755 × 4
## Entity Code Year LifeExpectancy
## <chr> <chr> <dbl> <dbl>
## 1 Afghanistan AFG 1950 27.7
## 2 Afghanistan AFG 1951 28.0
## 3 Afghanistan AFG 1952 28.4
## 4 Afghanistan AFG 1953 28.9
## 5 Afghanistan AFG 1954 29.2
## 6 Afghanistan AFG 1955 29.9
## 7 Afghanistan AFG 1956 30.4
## 8 Afghanistan AFG 1957 30.9
## 9 Afghanistan AFG 1958 31.5
## 10 Afghanistan AFG 1959 32.0
## # ℹ 20,745 more rowsRepeat 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_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 rowsmtcars %>% 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 into a list of data frames
split(.$cyl) %>%
#repeat regression over each group
map(~lm(formula = mpg ~ wt, data =.)) %>%
map(broom::tidy, conf.int = TRUE) %>%
#convert to tibble
bind_rows(.id = "cyl") %>%
#filter to 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 %>% map_dbl(mean)## Warning in mean.default(.x[[i]], ...): argument is not numeric or logical:
## returning NA
## Warning in mean.default(.x[[i]], ...): argument is not numeric or logical:
## returning NA## Entity Code Year LifeExpectancy
## NA NA 1975.73023 61.61799my_data %>% map_dbl(mean, trim=0.1)## Warning in mean.default(.x[[i]], ...): argument is not numeric or logical:
## returning NA
## Warning in mean.default(.x[[i]], ...): argument is not numeric or logical:
## returning NA## Entity Code Year LifeExpectancy
## NA NA 1981.09509 62.47794my_data2 <- select(my_data, LifeExpectancy)
adjust_life_expectancy_by_factor <- function(x,factor) {x*factor}
10 %>% double_by_factor(factor = 2)## [1] 20my_data2 %>% map_dfr(adjust_life_expectancy_by_factor, factor = 2)## # A tibble: 20,755 × 1
## LifeExpectancy
## <dbl>
## 1 55.5
## 2 55.9
## 3 56.9
## 4 57.9
## 5 58.5
## 6 59.8
## 7 60.8
## 8 61.9
## 9 63.0
## 10 64.1
## # ℹ 20,745 more rows