data("mtcars")
mtcars <- as_tibble(mtcars)
winners <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2023/2023-04-25/winners.csv')
## Rows: 163 Columns: 5
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (3): Category, Athlete, Nationality
## dbl (1): Year
## time (1): Time
##
## 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.
london_marathon <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2023/2023-04-25/london_marathon.csv')
## Rows: 42 Columns: 8
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (1): Official charity
## dbl (6): Year, Applicants, Accepted, Starters, Finishers, Raised
## 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.
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)
## # 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 rows
Create your own function
# Double values in columns
double_by_factor <- function(x, factor) {x * factor}
10 %>% double_by_factor(factor = 2)
## [1] 20
mtcars %>% 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
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 rows
When you have a grouping variable (factor)
mtcars %>% lm(formula = mpg ~ wt, data = .)
##
## Call:
## lm(formula = mpg ~ wt, data = .)
##
## Coefficients:
## (Intercept) wt
## 37.285 -5.344
mtcars %>% distinct(cyl)
## # A tibble: 3 × 1
## cyl
## <dbl>
## 1 6
## 2 4
## 3 8
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 = .x)) %>%
# Extract coefficients from regression resuls
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))
Choose either one of the two cases above and apply it to your data
london_marathon %>%
select(Applicants:Finishers) %>%
na.omit(data) %>%
map_dbl(mean)
## Applicants Accepted Starters Finishers
## 133354.33 39269.45 28886.42 28144.72
# Adding an argument
london_marathon %>%
select(Applicants:Finishers) %>%
na.omit(data) %>%
map_dbl(mean, trim = 0.1)
## Applicants Accepted Starters Finishers
## 112692.62 40865.50 29752.25 28977.69
london_marathon %>% select(.data = ., Applicants)
## # A tibble: 42 × 1
## Applicants
## <dbl>
## 1 20000
## 2 90000
## 3 60000
## 4 70000
## 5 83000
## 6 80000
## 7 80000
## 8 73000
## 9 72000
## 10 73000
## # ℹ 32 more rows
london_marathon %>% select(Applicants)
## # A tibble: 42 × 1
## Applicants
## <dbl>
## 1 20000
## 2 90000
## 3 60000
## 4 70000
## 5 83000
## 6 80000
## 7 80000
## 8 73000
## 9 72000
## 10 73000
## # ℹ 32 more rows
Create your own function
# Double values in columns
divide_by_factor <- function(x, factor) {x / factor}
10 %>% divide_by_factor(factor = 2)
## [1] 5
london_marathon %>%
select(Applicants:Finishers) %>%
na.omit(data) %>%
map_dfr(divide_by_factor, factor = 10)
## # A tibble: 40 × 4
## Applicants Accepted Starters Finishers
## <dbl> <dbl> <dbl> <dbl>
## 1 2000 775. 706. 626.
## 2 9000 1806. 1635 1512.
## 3 6000 1974. 1650 1579.
## 4 7000 2114. 1699. 1568.
## 5 8300 2227. 1750 1587.
## 6 8000 2557. 1926. 1807.
## 7 8000 2836. 2148. 1959.
## 8 7300 2998. 2247. 2093.
## 9 7200 3177. 2445. 2270.
## 10 7300 3488. 2650 2501.
## # ℹ 30 more rows