Module 13: Apply it to your data 12
Chapter 21 Iteration
Reed Wilson
Import your data
data("mtcars")
# excel file
airlines <- read_excel("../00_data/MyData.xlsx") %>%
mutate(n_events = as.numeric(n_events)) %>%
mutate(avail_seat_km_per_week = as.numeric(avail_seat_km_per_week))
airlines## # A tibble: 336 × 6
## Ref airline avail_seat_km_per_week year_range type_…¹ n_eve…²
## <dbl> <chr> <dbl> <chr> <chr> <dbl>
## 1 NA Aer Lingus 320906734 85_99 incide… 2
## 2 2 Aeroflot* 1197672318 85_99 incide… 76
## 3 3 Aerolineas Argentinas 385803648 85_99 incide… 6
## 4 4 Aeromexico* 596871813 85_99 incide… 3
## 5 5 Air Canada 1865253802 85_99 incide… 2
## 6 6 Air France 3004002661 85_99 incide… 14
## 7 7 Air India* 869253552 85_99 incide… 2
## 8 8 Air New Zealand* 710174817 85_99 incide… 3
## 9 9 Alaska Airlines* 965346773 85_99 incide… 5
## 10 10 Alitalia 698012498 85_99 incide… 7
## # … with 326 more rows, and abbreviated variable names ¹type_of_event,
## # ²n_eventsairlines## # A tibble: 336 × 6
## Ref airline avail_seat_km_per_week year_range type_…¹ n_eve…²
## <dbl> <chr> <dbl> <chr> <chr> <dbl>
## 1 NA Aer Lingus 320906734 85_99 incide… 2
## 2 2 Aeroflot* 1197672318 85_99 incide… 76
## 3 3 Aerolineas Argentinas 385803648 85_99 incide… 6
## 4 4 Aeromexico* 596871813 85_99 incide… 3
## 5 5 Air Canada 1865253802 85_99 incide… 2
## 6 6 Air France 3004002661 85_99 incide… 14
## 7 7 Air India* 869253552 85_99 incide… 2
## 8 8 Air New Zealand* 710174817 85_99 incide… 3
## 9 9 Alaska Airlines* 965346773 85_99 incide… 5
## 10 10 Alitalia 698012498 85_99 incide… 7
## # … with 326 more rows, and abbreviated variable names ¹type_of_event,
## # ²n_eventsRepeat 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(.f = ~mean(x = .x))## $mpg
## [1] 20.09062
##
## $cyl
## [1] 6.1875
##
## $disp
## [1] 230.7219
##
## $hp
## [1] 146.6875
##
## $drat
## [1] 3.596563
##
## $wt
## [1] 3.21725
##
## $qsec
## [1] 17.84875
##
## $vs
## [1] 0.4375
##
## $am
## [1] 0.40625
##
## $gear
## [1] 3.6875
##
## $carb
## [1] 2.8125mtcars %>% 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)## 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 21.4mtcars %>% 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 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(factor = 10, x = .x))## # 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
## # … with 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
## # … with 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)## cyl
## Mazda RX4 6
## Datsun 710 4
## Hornet Sportabout 8regression_coefficient_tibble <- mtcars %>%
# Split to a list of data frames
split(.$cyl)%>%
# Repeat regression over each group
map(~lm(formula = mpg ~ wt, data = .)) %>%
# Extract coefficient from regression results
map(broom::tidy, conf.int = TRUE) %>%
# Convert to tibble
bind_rows(.id = "cyl") %>%
# Filter wt coefficients
filter(term == "wt")
regression_coefficient_tibble%>%
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
airlines %>% lm(formula = n_events ~ type_of_event)##
## Call:
## lm(formula = n_events ~ type_of_event, data = .)
##
## Coefficients:
## (Intercept) type_of_eventfatalities type_of_eventincidents
## 1.420 82.545 4.232airlines %>% distinct(airline)## # A tibble: 56 × 1
## airline
## <chr>
## 1 Aer Lingus
## 2 Aeroflot*
## 3 Aerolineas Argentinas
## 4 Aeromexico*
## 5 Air Canada
## 6 Air France
## 7 Air India*
## 8 Air New Zealand*
## 9 Alaska Airlines*
## 10 Alitalia
## # … with 46 more rowsregression_coefficient_tibble <- airlines %>%
# Split to a list of data frames
split(.$airline)%>%
# Repeat regression over each group
map(~lm(formula = n_events ~ type_of_event, data = .)) %>%
# Extract coefficient from regression results
map(broom::tidy, conf.int = TRUE) %>%
# Convert to tibble
bind_rows(.id = "airline") %>%
# Filter wt coefficients
filter(term == "type_of_eventfatalities")## Warning in summary.lm(x): essentially perfect fit: summary may be unreliable## Warning in summary.lm(object, ...): essentially perfect fit: summary may be
## unreliable## Warning in summary.lm(x): essentially perfect fit: summary may be unreliable## Warning in summary.lm(object, ...): essentially perfect fit: summary may be
## unreliableregression_coefficient_tibble## # A tibble: 56 × 8
## airline term estimate std.er…¹ statistic p.value conf.low conf.h…²
## <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 Aer Lingus type… 2.07e-16 8.16e- 1 2.54e-16 1 -2.60e+ 0 2.60e+ 0
## 2 Aeroflot* type… 1.01e+ 2 3.33e+ 1 3.01e+ 0 0.0570 -5.60e+ 0 2.07e+ 2
## 3 Aerolineas Arg… type… -2.52e-16 2.04e+ 0 -1.23e-16 1 -6.50e+ 0 6.50e+ 0
## 4 Aeromexico* type… 3.15e+ 1 2.61e+ 1 1.20e+ 0 0.315 -5.17e+ 1 1.15e+ 2
## 5 Air Canada type… 0 1.28e-17 0 1 -4.07e-17 4.07e-17
## 6 Air France type… 2.05e+ 2 1.05e+ 2 1.95e+ 0 0.147 -1.30e+ 2 5.40e+ 2
## 7 Air India* type… 2.42e+ 2 6.98e+ 1 3.47e+ 0 0.0402 2.03e+ 1 4.65e+ 2
## 8 Air New Zealan… type… 3 e+ 0 3 e+ 0 1 e+ 0 0.391 -6.55e+ 0 1.25e+ 1
## 9 Alaska Airline… type… 4.35e+ 1 3.59e+ 1 1.21e+ 0 0.313 -7.08e+ 1 1.58e+ 2
## 10 Alitalia type… 2.4 e+ 1 2.05e+ 1 1.17e+ 0 0.326 -4.11e+ 1 8.91e+ 1
## # … with 46 more rows, and abbreviated variable names ¹std.error, ²conf.highregression_coefficient_tibble <- regression_coefficient_tibble %>%
mutate(estimate = -estimate,
conf.low = -conf.low,
conf.high = -conf.high) %>%
ggplot(aes(x = estimate, y = term)) +
geom_point() +
geom_errorbar(aes(xmin = conf.low, xmax = conf.high))