Module 13: Apply it to your data 12
Chapter 21 Iteration
Camden Dezotell
Import your data
data("mtcars")
mtcars <- as_tibble(mtcars)
data <- read_csv("../00_data/myData.csv")## Rows: 882 Columns: 69
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (22): EXPID, PEAKID, SEASON_FACTOR, HOST_FACTOR, ROUTE1, ROUTE2, NATION...
## dbl (17): YEAR, SEASON, HOST, SMTDAYS, TOTDAYS, TERMREASON, HIGHPOINT, CAMP...
## lgl (27): ROUTE3, ROUTE4, SUCCESS1, SUCCESS2, SUCCESS3, SUCCESS4, ASCENT3, ...
## date (3): BCDATE, SMTDATE, TERMDATE
##
## 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: 882 × 69
## EXPID PEAKID YEAR SEASON SEASON_FACTOR HOST HOST_FACTOR ROUTE1 ROUTE2
## <chr> <chr> <dbl> <dbl> <chr> <dbl> <chr> <chr> <chr>
## 1 EVER20101 EVER 2020 1 Spring 2 China N Col-N… <NA>
## 2 EVER20102 EVER 2020 1 Spring 2 China N Col-N… <NA>
## 3 EVER20103 EVER 2020 1 Spring 2 China N Col-N… <NA>
## 4 AMAD20301 AMAD 2020 3 Autumn 1 Nepal SW Ridge <NA>
## 5 AMAD20302 AMAD 2020 3 Autumn 1 Nepal SW Ridge <NA>
## 6 AMAD20303 AMAD 2020 3 Autumn 1 Nepal SW Ridge <NA>
## 7 AMAD20304 AMAD 2020 3 Autumn 1 Nepal SW Ridge <NA>
## 8 AMAD20305 AMAD 2020 3 Autumn 1 Nepal SW Ridge <NA>
## 9 AMAD20306 AMAD 2020 3 Autumn 1 Nepal SW Ridge <NA>
## 10 AMAD20307 AMAD 2020 3 Autumn 1 Nepal SW Ridge <NA>
## # ℹ 872 more rows
## # ℹ 60 more variables: ROUTE3 <lgl>, ROUTE4 <lgl>, NATION <chr>, LEADERS <chr>,
## # SPONSOR <chr>, SUCCESS1 <lgl>, SUCCESS2 <lgl>, SUCCESS3 <lgl>,
## # SUCCESS4 <lgl>, ASCENT1 <chr>, ASCENT2 <chr>, ASCENT3 <lgl>, ASCENT4 <lgl>,
## # CLAIMED <lgl>, DISPUTED <lgl>, COUNTRIES <chr>, APPROACH <chr>,
## # BCDATE <date>, SMTDATE <date>, SMTTIME <chr>, SMTDAYS <dbl>, TOTDAYS <dbl>,
## # TERMDATE <date>, TERMREASON <dbl>, TERMREASON_FACTOR <chr>, …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(.f = 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 2.812500mtcars %>% 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
## # 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_vector <- function(x, factor) {x * factor}
10 %>% double_by_vector(factor = 2)## [1] 20mtcars %>% map_dfr(.x = ., .f = ~double_by_vector(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_vector, 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 it into a list of dataf rames
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 or 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 %>%
mutate(SUCCESS1, SUCCESS1,
NATION = NATION) %>%
ggplot(aes(x = ROUTE1, y = NATION)) +
geom_point() +
geom_errorbar(aes(xmin = NATION, xmax = ROUTE1))