Module 13: Apply it to your data 12
Chapter 21 Iteration
Spencer Murrin
Import your data
data("mtcars")
mtcars <- as_tibble(mtcars)
# Apply Data
choc_data <- read_excel("../01_module4/data/MyData.xlsx")
choc_data## # A tibble: 2,657 × 10
## REF Compan…¹ Compa…² Revie…³ Count…⁴ Speci…⁵ Cocoa…⁶ Ingre…⁷ Most.…⁸ Rating
## <dbl> <chr> <chr> <dbl> <chr> <chr> <dbl> <chr> <chr> <dbl>
## 1 2454 5150 U.S.A. 2019 Tanzan… Kokoa … 0.76 3- B,S… rich c… 3.25
## 2 2458 5150 U.S.A. 2019 Domini… Zorzal… 0.76 3- B,S… cocoa,… 3.5
## 3 2454 5150 U.S.A. 2019 Madaga… Bejofo… 0.76 3- B,S… cocoa,… 3.75
## 4 2542 5150 U.S.A. 2021 Fiji Matasa… 0.68 3- B,S… chewy,… 3
## 5 2546 5150 U.S.A. 2021 Venezu… Sur de… 0.72 3- B,S… fatty,… 3
## 6 2546 5150 U.S.A. 2021 Uganda Semuli… 0.8 3- B,S… mildly… 3.25
## 7 2542 5150 U.S.A. 2021 India Anamal… 0.68 3- B,S… milk b… 3.5
## 8 2808 20N | 2… France 2022 Venezu… Chuao,… 0.78 2- B,S sandy,… 2.75
## 9 2808 20N | 2… France 2022 Venezu… Chuao,… 0.78 2- B,S sl. dr… 3
## 10 797 A. Morin France 2012 Bolivia Bolivia 0.7 4- B,S… vegeta… 3.5
## # … with 2,647 more rows, and abbreviated variable names ¹Company.Manufacturer,
## # ²Company.Location, ³Review.Date, ⁴Country.of.Bean.Origin,
## # ⁵Specific.Bean.Origin.or.Bar.Name, ⁶Cocoa.Percent, ⁷Ingredients,
## # ⁸Most.Memorable.CharacteristicsRepeat 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(.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)## # 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
## # … with 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
## # … with 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(.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
## # … 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)## # A tibble: 3 × 1
## cyl
## <dbl>
## 1 6
## 2 4
## 3 8reg_coeff_tbl <- mtcars %>%
# Split it into a list of data frames
split(.$cyl) %>%
#Repeat regression over each group
map(~lm(formula = mpg ~ wt, data = .x)) %>%
# Extract coefficients from regression results
map(broom::tidy, conf.int = TRUE) %>%
# Convert to tibble
bind_rows(.id = "cyl") %>%
# Filter for wt coefficients
filter(term == "wt")reg_coeff_tbl %>%
mutate(estimate = -estimate,
conf.low = -conf.low,
conf.high = -conf.high) %>%
ggplot(aes(x = estimate, y = cyl)) +
geom_point() +
geom_errorbar(aes(xmin = conf.low, xmax = conf.high))
Create your own
Choose either one of the two cases above and apply it to your data
choc_data %>% lm(formula = Review.Date ~ Cocoa.Percent, data = .)##
## Call:
## lm(formula = Review.Date ~ Cocoa.Percent, data = .)
##
## Coefficients:
## (Intercept) Cocoa.Percent
## 2014.378 0.519choc_data %>% distinct(Rating)## # A tibble: 12 × 1
## Rating
## <dbl>
## 1 3.25
## 2 3.5
## 3 3.75
## 4 3
## 5 2.75
## 6 4
## 7 2.5
## 8 1.75
## 9 2.25
## 10 1.5
## 11 2
## 12 1coeff_tbl <- choc_data %>%
# Split it into a list of data frames
split(.$Rating) %>%
#Repeat regression over each group
map(~lm(formula = Review.Date ~ Cocoa.Percent, data = .x)) %>%
# Extract coefficients from regression results
map(broom::tidy, conf.int = TRUE) %>%
# Convert to tibble
bind_rows(.id = "Rating") %>%
# Filter for wt coefficients
filter(term == "Cocoa.Percent")coeff_tbl %>%
mutate(estimate = -estimate,
conf.low = -conf.low,
conf.high = -conf.high) %>%
ggplot(aes(x = estimate, y = Rating)) +
geom_point() +
geom_errorbar(aes(xmin = conf.low, xmax = conf.high))