Module 13: Apply it to your data 12
Chapter 21 Iteration
Daniel Lee
Import your data
data("mtcars")
mtcars <- as_tibble(mtcars)library(readxl)
# excel file
mydata <- read_excel("../00_data/data/myData.xlsx")
mydata## # A tibble: 9,355 × 12
## work_year job_title job_category salary_currency salary salary_in_usd
## <dbl> <chr> <chr> <chr> <dbl> <dbl>
## 1 2023 AI Architect Machine Learning… USD 305100 305100
## 2 2023 AI Architect Machine Learning… USD 146900 146900
## 3 2023 AI Architect Machine Learning… USD 330000 330000
## 4 2023 AI Architect Machine Learning… USD 204000 204000
## 5 2023 AI Architect Machine Learning… USD 330000 330000
## 6 2023 AI Architect Machine Learning… USD 204000 204000
## 7 2023 AI Architect Machine Learning… EUR 200000 215936
## 8 2023 AI Architect Machine Learning… USD 330000 330000
## 9 2023 AI Architect Machine Learning… USD 204000 204000
## 10 2023 AI Architect Machine Learning… USD 200000 200000
## # ℹ 9,345 more rows
## # ℹ 6 more variables: employee_residence <chr>, experience_level <chr>,
## # employment_type <chr>, work_setting <chr>, company_location <chr>,
## # company_size <chr>Repeat the same operation over different columns of a data frame
Case of numeric variables
mtcars %>% map(.x = ., .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(.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)## # 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(.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 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 it into a list of data frames
split(.$cyl) %>%
# Repeat regression over each group
map(.x = ., .f = ~lm(formula = mpg ~ wt, data = .)) %>%
# 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
mydata %>% lm(formula = salary_in_usd ~ job_category, data = .)##
## Call:
## lm(formula = salary_in_usd ~ job_category, data = .)
##
## Coefficients:
## (Intercept)
## 135092
## job_categoryCloud and Database
## 19908
## job_categoryData Analysis
## -26586
## job_categoryData Architecture and Modeling
## 20910
## job_categoryData Engineering
## 11106
## job_categoryData Management and Strategy
## -31952
## job_categoryData Quality and Operations
## -34213
## job_categoryData Science and Research
## 28666
## job_categoryLeadership and Management
## 10384
## job_categoryMachine Learning and AI
## 43834mydata %>% distinct(job_category)## # A tibble: 10 × 1
## job_category
## <chr>
## 1 Machine Learning and AI
## 2 Data Science and Research
## 3 Leadership and Management
## 4 Data Architecture and Modeling
## 5 Data Engineering
## 6 BI and Visualization
## 7 Data Analysis
## 8 Cloud and Database
## 9 Data Management and Strategy
## 10 Data Quality and Operationsmydata %>% summarise(mean(salary_in_usd))%>% map_dbl(mean)## mean(salary_in_usd)
## 150299.5I don’t really know how to apply the functions to my data or if there is even a useful way to use it in my case.