Module 13: Apply it to your data 12
Chapter 21 Iteration
Joshua Rockefeller
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 # this is quite long , we usally 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 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 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 rowsCreate your own function
# double values in collums
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#simplify
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) %>%
#repeat regression over each group
map(~lm(formula = mpg ~ wt , data = .x)) %>%
#extract coefficents from regression result
map(broom::tidy, conf.int=TRUE) %>%
#convet to tibble
bind_rows(.id="cyl")%>%
#filter for wt coefficents
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
Gas_Prices <-read_csv("../00_data/Gas_Prices.csv")## Rows: 22360 Columns: 5
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (3): fuel, grade, formulation
## dbl (1): price
## date (1): date
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.Gas_Prices## # A tibble: 22,360 × 5
## date fuel grade formulation price
## <date> <chr> <chr> <chr> <dbl>
## 1 1990-08-20 gasoline regular all 1.19
## 2 1990-08-20 gasoline regular conventional 1.19
## 3 1990-08-27 gasoline regular all 1.25
## 4 1990-08-27 gasoline regular conventional 1.25
## 5 1990-09-03 gasoline regular all 1.24
## 6 1990-09-03 gasoline regular conventional 1.24
## 7 1990-09-10 gasoline regular all 1.25
## 8 1990-09-10 gasoline regular conventional 1.25
## 9 1990-09-17 gasoline regular all 1.27
## 10 1990-09-17 gasoline regular conventional 1.27
## # ℹ 22,350 more rowsGas_Prices_fuel <- Gas_Prices %>%
group_by(date, grade, fuel) %>%
summarise(price = mean(price, na.rm = TRUE), .groups = "drop") %>%
pivot_wider(names_from = fuel, values_from = price)
Gas_Prices_fuel## # A tibble: 7,743 × 4
## date grade gasoline diesel
## <date> <chr> <dbl> <dbl>
## 1 1990-08-20 regular 1.19 NA
## 2 1990-08-27 regular 1.25 NA
## 3 1990-09-03 regular 1.24 NA
## 4 1990-09-10 regular 1.25 NA
## 5 1990-09-17 regular 1.27 NA
## 6 1990-09-24 regular 1.27 NA
## 7 1990-10-01 regular 1.32 NA
## 8 1990-10-08 regular 1.33 NA
## 9 1990-10-15 regular 1.34 NA
## 10 1990-10-22 regular 1.34 NA
## # ℹ 7,733 more rowsGas_Prices_fuel %>%
select(gasoline, diesel) %>%
map_dbl(~mean( .x, na.rm= TRUE))## gasoline diesel
## 2.510127 2.902305