Module 13: Apply it to your data 12
Chapter 21 Iteration
lilli warnock
Import your data
penguins <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/main/data/2025/2025-04-15/penguins.csv') ## Rows: 344 Columns: 8
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (3): species, island, sex
## dbl (5): bill_len, bill_dep, flipper_len, body_mass, year
##
## 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.data("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_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)## mpg
## Mazda RX4 21.0
## Mazda RX4 Wag 21.0
## Datsun 710 22.8
## Hornet 4 Drive 21.4
## Hornet Sportabout 18.7
## Valiant 18.1
## Duster 360 14.3
## Merc 240D 24.4
## Merc 230 22.8
## Merc 280 19.2
## Merc 280C 17.8
## Merc 450SE 16.4
## Merc 450SL 17.3
## Merc 450SLC 15.2
## Cadillac Fleetwood 10.4
## Lincoln Continental 10.4
## Chrysler Imperial 14.7
## Fiat 128 32.4
## Honda Civic 30.4
## Toyota Corolla 33.9
## Toyota Corona 21.5
## Dodge Challenger 15.5
## AMC Javelin 15.2
## Camaro Z28 13.3
## Pontiac Firebird 19.2
## Fiat X1-9 27.3
## Porsche 914-2 26.0
## Lotus Europa 30.4
## Ford Pantera L 15.8
## Ferrari Dino 19.7
## Maserati Bora 15.0
## Volvo 142E 21.4 mtcars %>% select(mpg)## mpg
## Mazda RX4 21.0
## Mazda RX4 Wag 21.0
## Datsun 710 22.8
## Hornet 4 Drive 21.4
## Hornet Sportabout 18.7
## Valiant 18.1
## Duster 360 14.3
## Merc 240D 24.4
## Merc 230 22.8
## Merc 280 19.2
## Merc 280C 17.8
## Merc 450SE 16.4
## Merc 450SL 17.3
## Merc 450SLC 15.2
## Cadillac Fleetwood 10.4
## Lincoln Continental 10.4
## Chrysler Imperial 14.7
## Fiat 128 32.4
## Honda Civic 30.4
## Toyota Corolla 33.9
## Toyota Corona 21.5
## Dodge Challenger 15.5
## AMC Javelin 15.2
## Camaro Z28 13.3
## Pontiac Firebird 19.2
## Fiat X1-9 27.3
## Porsche 914-2 26.0
## Lotus Europa 30.4
## Ford Pantera L 15.8
## Ferrari Dino 19.7
## Maserati Bora 15.0
## Volvo 142E 21.4Create your own function
# Double value in column
double_by_factor <- function(x, factor)
10 %>% double_by_factor(factor = 2)
# mtcars %>% map(.x = ., .f = ~double_by_factor(x = .x, factor = 10))
# mtcars %>% map_dfr(double_by_factor, factor = 10)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 -5.344mtcars %>% distinct(cyl)## cyl
## Mazda RX4 6
## Datsun 710 4
## Hornet Sportabout 8reg_coeff_tbl <- mtcars %>%
#split it into a list of data frams
split(.$cyl) %>%
# repeat regression over each data group
map(~lm(formula = mpg ~wt, data = .x)) %>%
# extract coefficients fron 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
penguins %>% map_dbl(.x = ., .f = ~mean(x = .x))## Warning in mean.default(x = .x): argument is not numeric or logical: returning
## NA
## Warning in mean.default(x = .x): argument is not numeric or logical: returning
## NA
## Warning in mean.default(x = .x): argument is not numeric or logical: returning
## NA## species island bill_len bill_dep flipper_len body_mass
## NA NA NA NA NA NA
## sex year
## NA 2008.029penguins %>% map_dbl(.f = ~mean(x = .x))## Warning in mean.default(x = .x): argument is not numeric or logical: returning
## NA
## Warning in mean.default(x = .x): argument is not numeric or logical: returning
## NA
## Warning in mean.default(x = .x): argument is not numeric or logical: returning
## NA## species island bill_len bill_dep flipper_len body_mass
## NA NA NA NA NA NA
## sex year
## NA 2008.029penguins %>% 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
## Warning in mean.default(.x[[i]], ...): argument is not numeric or logical:
## returning NA## species island bill_len bill_dep flipper_len body_mass
## NA NA NA NA NA NA
## sex year
## NA 2008.029# Adding an argument
penguins %>% map_dbl(.x = ., .f = ~mean(x = .x, trim = 0.1))## Warning in mean.default(x = .x, trim = 0.1): argument is not numeric or
## logical: returning NA## Warning in mean.default(x = .x, trim = 0.1): argument is not numeric or
## logical: returning NA
## Warning in mean.default(x = .x, trim = 0.1): argument is not numeric or
## logical: returning NA## species island bill_len bill_dep flipper_len body_mass
## NA NA NA NA NA NA
## sex year
## NA 2008.036penguins %>% 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
## Warning in mean.default(.x[[i]], ...): argument is not numeric or logical:
## returning NA## species island bill_len bill_dep flipper_len body_mass
## NA NA NA NA NA NA
## sex year
## NA 2008.036penguins %>% select(.data = ., species)## # A tibble: 344 × 1
## species
## <chr>
## 1 Adelie
## 2 Adelie
## 3 Adelie
## 4 Adelie
## 5 Adelie
## 6 Adelie
## 7 Adelie
## 8 Adelie
## 9 Adelie
## 10 Adelie
## # ℹ 334 more rowspenguins %>% select(species)## # A tibble: 344 × 1
## species
## <chr>
## 1 Adelie
## 2 Adelie
## 3 Adelie
## 4 Adelie
## 5 Adelie
## 6 Adelie
## 7 Adelie
## 8 Adelie
## 9 Adelie
## 10 Adelie
## # ℹ 334 more rows# Double value in column
double_by_factor <- function(x, factor)
10 %>% double_by_factor(factor = 2)
# penguins %>% map_dfr(double_by_factor, factor = 10)