Module 13: Apply it to your data 12
Chapter 21 Iteration
Eli Pockette
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 2.812500mtcars %>% 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(.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(.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(.x = ., .f = ~lm(formula = mpg ~ wt, data = .x)) %>%
# Extract coefficients 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
data <- read_csv("C:/Users/ejp14/OneDrive/Desktop/PSU_DAT3000_IntroToDA/01_module4/Data/myData.csv")## Rows: 81525 Columns: 24
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (3): name, team, position
## dbl (21): game_year, game_week, rush_att, rush_yds, rush_avg, rush_tds, rush...
##
## 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## # A tibble: 81,525 × 24
## name team game_year game_week rush_att rush_yds rush_avg rush_tds
## <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 Duce Staley PHI 2000 1 26 201 7.7 1
## 2 Lamar Smith MIA 2000 1 27 145 5.4 1
## 3 Tiki Barber NYG 2000 1 13 144 11.1 2
## 4 Stephen Davis WAS 2000 1 23 133 5.8 1
## 5 Edgerrin James IND 2000 1 28 124 4.4 1
## 6 Priest Holmes BAL 2000 1 27 119 4.4 0
## 7 Curtis Martin NYJ 2000 1 30 110 3.7 1
## 8 Robert Smith MIN 2000 1 14 109 7.8 0
## 9 Tim Biakabutuka CAR 2000 1 15 88 5.9 0
## 10 Cade McNown CHI 2000 1 10 87 8.7 1
## # ℹ 81,515 more rows
## # ℹ 16 more variables: rush_fumbles <dbl>, rec <dbl>, rec_yds <dbl>,
## # rec_avg <dbl>, rec_tds <dbl>, rec_fumbles <dbl>, pass_att <dbl>,
## # pass_yds <dbl>, pass_tds <dbl>, int <dbl>, sck <dbl>, pass_fumbles <dbl>,
## # rate <dbl>, position <chr>, total_yards <dbl>, `total tds` <dbl>reg_coeff_tbl_mydata <- data %>%
# Split into list of data frames by team
split(.$team) %>%
# Run regression on each subset
map(~lm(rush_yds ~ rush_att, data = .x)) %>%
# Extract coefficients
map(broom::tidy, conf.int = TRUE) %>%
# Combine into one tibble
bind_rows(.id = "team") %>%
# Keep only rush_att coefficient
filter(term == "rush_att")reg_coeff_tbl_mydata %>%
mutate(
estimate = -estimate,
conf.low = -conf.low,
conf.high = -conf.high
) %>%
ggplot(aes(x = estimate, y = team)) +
geom_point() +
geom_errorbar(aes(xmin = conf.low, xmax = conf.high))