Code Along 7
Erin McEvoy
2024-10-22
data <- read_csv("../05_module7/WA_Fn-UseC_-HR-Employee-Attrition.csv")factors_vec <- data %>% select(Education, EnvironmentSatisfaction,JobInvolvement,JobSatisfaction,PerformanceRating,RelationshipSatisfaction,WorkLifeBalance, JobLevel, StockOptionLevel) %>% names()
data_clean <- data %>%
# mutate(Education = Education %>% as.factor)) %>%
# Address factors imported as numeric
mutate(across(all_of(factors_vec))) %>%
# Drop zero-variance variables
select(-c(Over18,EmployeeCount,StandardHours)) %>%
# Recode Attrition
mutate(Attrition = if_else(Attrition == "Yes", "Left", Attrition))Exlpore data
skimr::skim(data)| Name | data |
| Number of rows | 1470 |
| Number of columns | 35 |
| _______________________ | |
| Column type frequency: | |
| character | 9 |
| numeric | 26 |
| ________________________ | |
| Group variables | None |
Variable type: character
| skim_variable | n_missing | complete_rate | min | max | empty | n_unique | whitespace |
|---|---|---|---|---|---|---|---|
| Attrition | 0 | 1 | 2 | 3 | 0 | 2 | 0 |
| BusinessTravel | 0 | 1 | 10 | 17 | 0 | 3 | 0 |
| Department | 0 | 1 | 5 | 22 | 0 | 3 | 0 |
| EducationField | 0 | 1 | 5 | 16 | 0 | 6 | 0 |
| Gender | 0 | 1 | 4 | 6 | 0 | 2 | 0 |
| JobRole | 0 | 1 | 7 | 25 | 0 | 9 | 0 |
| MaritalStatus | 0 | 1 | 6 | 8 | 0 | 3 | 0 |
| Over18 | 0 | 1 | 1 | 1 | 0 | 1 | 0 |
| OverTime | 0 | 1 | 2 | 3 | 0 | 2 | 0 |
Variable type: numeric
| skim_variable | n_missing | complete_rate | mean | sd | p0 | p25 | p50 | p75 | p100 | hist |
|---|---|---|---|---|---|---|---|---|---|---|
| Age | 0 | 1 | 36.92 | 9.14 | 18 | 30.00 | 36.0 | 43.00 | 60 | ▂▇▇▃▂ |
| DailyRate | 0 | 1 | 802.49 | 403.51 | 102 | 465.00 | 802.0 | 1157.00 | 1499 | ▇▇▇▇▇ |
| DistanceFromHome | 0 | 1 | 9.19 | 8.11 | 1 | 2.00 | 7.0 | 14.00 | 29 | ▇▅▂▂▂ |
| Education | 0 | 1 | 2.91 | 1.02 | 1 | 2.00 | 3.0 | 4.00 | 5 | ▂▃▇▆▁ |
| EmployeeCount | 0 | 1 | 1.00 | 0.00 | 1 | 1.00 | 1.0 | 1.00 | 1 | ▁▁▇▁▁ |
| EmployeeNumber | 0 | 1 | 1024.87 | 602.02 | 1 | 491.25 | 1020.5 | 1555.75 | 2068 | ▇▇▇▇▇ |
| EnvironmentSatisfaction | 0 | 1 | 2.72 | 1.09 | 1 | 2.00 | 3.0 | 4.00 | 4 | ▅▅▁▇▇ |
| HourlyRate | 0 | 1 | 65.89 | 20.33 | 30 | 48.00 | 66.0 | 83.75 | 100 | ▇▇▇▇▇ |
| JobInvolvement | 0 | 1 | 2.73 | 0.71 | 1 | 2.00 | 3.0 | 3.00 | 4 | ▁▃▁▇▁ |
| JobLevel | 0 | 1 | 2.06 | 1.11 | 1 | 1.00 | 2.0 | 3.00 | 5 | ▇▇▃▂▁ |
| JobSatisfaction | 0 | 1 | 2.73 | 1.10 | 1 | 2.00 | 3.0 | 4.00 | 4 | ▅▅▁▇▇ |
| MonthlyIncome | 0 | 1 | 6502.93 | 4707.96 | 1009 | 2911.00 | 4919.0 | 8379.00 | 19999 | ▇▅▂▁▂ |
| MonthlyRate | 0 | 1 | 14313.10 | 7117.79 | 2094 | 8047.00 | 14235.5 | 20461.50 | 26999 | ▇▇▇▇▇ |
| NumCompaniesWorked | 0 | 1 | 2.69 | 2.50 | 0 | 1.00 | 2.0 | 4.00 | 9 | ▇▃▂▂▁ |
| PercentSalaryHike | 0 | 1 | 15.21 | 3.66 | 11 | 12.00 | 14.0 | 18.00 | 25 | ▇▅▃▂▁ |
| PerformanceRating | 0 | 1 | 3.15 | 0.36 | 3 | 3.00 | 3.0 | 3.00 | 4 | ▇▁▁▁▂ |
| RelationshipSatisfaction | 0 | 1 | 2.71 | 1.08 | 1 | 2.00 | 3.0 | 4.00 | 4 | ▅▅▁▇▇ |
| StandardHours | 0 | 1 | 80.00 | 0.00 | 80 | 80.00 | 80.0 | 80.00 | 80 | ▁▁▇▁▁ |
| StockOptionLevel | 0 | 1 | 0.79 | 0.85 | 0 | 0.00 | 1.0 | 1.00 | 3 | ▇▇▁▂▁ |
| TotalWorkingYears | 0 | 1 | 11.28 | 7.78 | 0 | 6.00 | 10.0 | 15.00 | 40 | ▇▇▂▁▁ |
| TrainingTimesLastYear | 0 | 1 | 2.80 | 1.29 | 0 | 2.00 | 3.0 | 3.00 | 6 | ▂▇▇▂▃ |
| WorkLifeBalance | 0 | 1 | 2.76 | 0.71 | 1 | 2.00 | 3.0 | 3.00 | 4 | ▁▃▁▇▂ |
| YearsAtCompany | 0 | 1 | 7.01 | 6.13 | 0 | 3.00 | 5.0 | 9.00 | 40 | ▇▂▁▁▁ |
| YearsInCurrentRole | 0 | 1 | 4.23 | 3.62 | 0 | 2.00 | 3.0 | 7.00 | 18 | ▇▃▂▁▁ |
| YearsSinceLastPromotion | 0 | 1 | 2.19 | 3.22 | 0 | 0.00 | 1.0 | 3.00 | 15 | ▇▁▁▁▁ |
| YearsWithCurrManager | 0 | 1 | 4.12 | 3.57 | 0 | 2.00 | 3.0 | 7.00 | 17 | ▇▂▅▁▁ |
data_clean %>% count(Attrition)## # A tibble: 2 × 2
## Attrition n
## <chr> <int>
## 1 Left 237
## 2 No 1233data_clean %>%
ggplot(aes(Attrition)) +
geom_bar()
attrition vs. monthly income
data_clean %>%
ggplot(aes(Attrition, MonthlyIncome)) +
geom_boxplot()
correlation plot
# Step 1: binarize
data_binarized <- data_clean %>%
select(-EmployeeNumber) %>%
binarize()
data_binarized %>% glimpse()## Rows: 1,470
## Columns: 120
## $ `Age__-Inf_30` <dbl> 0, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, …
## $ Age__30_36 <dbl> 0, 0, 0, 1, 0, 1, 0, 0, 0, 1, 1, …
## $ Age__36_43 <dbl> 1, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, …
## $ Age__43_Inf <dbl> 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, …
## $ Attrition__Left <dbl> 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ Attrition__No <dbl> 0, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, …
## $ `BusinessTravel__Non-Travel` <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ BusinessTravel__Travel_Frequently <dbl> 0, 1, 0, 1, 0, 1, 0, 0, 1, 0, 0, …
## $ BusinessTravel__Travel_Rarely <dbl> 1, 0, 1, 0, 1, 0, 1, 1, 0, 1, 1, …
## $ `DailyRate__-Inf_465` <dbl> 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, …
## $ DailyRate__465_802 <dbl> 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, …
## $ DailyRate__802_1157 <dbl> 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, …
## $ DailyRate__1157_Inf <dbl> 0, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, …
## $ Department__Human_Resources <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ `Department__Research_&_Development` <dbl> 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, …
## $ Department__Sales <dbl> 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ `DistanceFromHome__-Inf_2` <dbl> 1, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, …
## $ DistanceFromHome__2_7 <dbl> 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, …
## $ DistanceFromHome__7_14 <dbl> 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ DistanceFromHome__14_Inf <dbl> 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, …
## $ Education__1 <dbl> 0, 1, 0, 0, 1, 0, 0, 1, 0, 0, 0, …
## $ Education__2 <dbl> 1, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, …
## $ Education__3 <dbl> 0, 0, 0, 0, 0, 0, 1, 0, 1, 1, 1, …
## $ Education__4 <dbl> 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, …
## $ Education__5 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ EducationField__Human_Resources <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ EducationField__Life_Sciences <dbl> 1, 1, 0, 1, 0, 1, 0, 1, 1, 0, 0, …
## $ EducationField__Marketing <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ EducationField__Medical <dbl> 0, 0, 0, 0, 1, 0, 1, 0, 0, 1, 1, …
## $ EducationField__Other <dbl> 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ EducationField__Technical_Degree <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ EnvironmentSatisfaction__1 <dbl> 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 1, …
## $ EnvironmentSatisfaction__2 <dbl> 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ EnvironmentSatisfaction__3 <dbl> 0, 1, 0, 0, 0, 0, 1, 0, 0, 1, 0, …
## $ EnvironmentSatisfaction__4 <dbl> 0, 0, 1, 1, 0, 1, 0, 1, 1, 0, 0, …
## $ Gender__Female <dbl> 1, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, …
## $ Gender__Male <dbl> 0, 1, 1, 0, 1, 1, 0, 1, 1, 1, 1, …
## $ `HourlyRate__-Inf_48` <dbl> 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, …
## $ HourlyRate__48_66 <dbl> 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, …
## $ HourlyRate__66_83.75 <dbl> 0, 0, 0, 0, 0, 1, 1, 1, 0, 0, 0, …
## $ HourlyRate__83.75_Inf <dbl> 1, 0, 1, 0, 0, 0, 0, 0, 0, 1, 1, …
## $ JobInvolvement__1 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ JobInvolvement__2 <dbl> 0, 1, 1, 0, 0, 0, 0, 0, 1, 0, 0, …
## $ JobInvolvement__3 <dbl> 1, 0, 0, 1, 1, 1, 0, 1, 0, 1, 0, …
## $ JobInvolvement__4 <dbl> 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, …
## $ JobLevel__1 <dbl> 0, 0, 1, 1, 1, 1, 1, 1, 0, 0, 1, …
## $ JobLevel__2 <dbl> 1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, …
## $ JobLevel__3 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, …
## $ JobLevel__4 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ JobLevel__5 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ JobRole__Healthcare_Representative <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, …
## $ JobRole__Human_Resources <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ JobRole__Laboratory_Technician <dbl> 0, 0, 1, 0, 1, 1, 1, 1, 0, 0, 1, …
## $ JobRole__Manager <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ JobRole__Manufacturing_Director <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, …
## $ JobRole__Research_Director <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ JobRole__Research_Scientist <dbl> 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, …
## $ JobRole__Sales_Executive <dbl> 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ JobRole__Sales_Representative <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ JobSatisfaction__1 <dbl> 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, …
## $ JobSatisfaction__2 <dbl> 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 1, …
## $ JobSatisfaction__3 <dbl> 0, 0, 1, 1, 0, 0, 0, 1, 1, 1, 0, …
## $ JobSatisfaction__4 <dbl> 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, …
## $ MaritalStatus__Divorced <dbl> 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, …
## $ MaritalStatus__Married <dbl> 0, 1, 0, 1, 1, 0, 1, 0, 0, 1, 1, …
## $ MaritalStatus__Single <dbl> 1, 0, 1, 0, 0, 1, 0, 0, 1, 0, 0, …
## $ `MonthlyIncome__-Inf_2911` <dbl> 0, 0, 1, 1, 0, 0, 1, 1, 0, 0, 1, …
## $ MonthlyIncome__2911_4919 <dbl> 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, …
## $ MonthlyIncome__4919_8379 <dbl> 1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, …
## $ MonthlyIncome__8379_Inf <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, …
## $ `MonthlyRate__-Inf_8047` <dbl> 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ MonthlyRate__8047_14235.5 <dbl> 0, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, …
## $ MonthlyRate__14235.5_20461.5 <dbl> 1, 0, 0, 0, 1, 0, 0, 0, 0, 1, 1, …
## $ MonthlyRate__20461.5_Inf <dbl> 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, …
## $ `NumCompaniesWorked__-Inf_1` <dbl> 0, 1, 0, 1, 0, 1, 0, 1, 1, 0, 1, …
## $ NumCompaniesWorked__1_2 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ NumCompaniesWorked__2_4 <dbl> 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, …
## $ NumCompaniesWorked__4_Inf <dbl> 1, 0, 1, 0, 1, 0, 0, 0, 0, 1, 0, …
## $ OverTime__No <dbl> 0, 1, 0, 0, 1, 1, 0, 1, 1, 1, 1, …
## $ OverTime__Yes <dbl> 1, 0, 1, 1, 0, 0, 1, 0, 0, 0, 0, …
## $ `PercentSalaryHike__-Inf_12` <dbl> 1, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, …
## $ PercentSalaryHike__12_14 <dbl> 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1, …
## $ PercentSalaryHike__14_18 <dbl> 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ PercentSalaryHike__18_Inf <dbl> 0, 1, 0, 0, 0, 0, 1, 1, 1, 0, 0, …
## $ PerformanceRating__3 <dbl> 1, 0, 1, 1, 1, 1, 0, 0, 0, 1, 1, …
## $ PerformanceRating__4 <dbl> 0, 1, 0, 0, 0, 0, 1, 1, 1, 0, 0, …
## $ RelationshipSatisfaction__1 <dbl> 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, …
## $ RelationshipSatisfaction__2 <dbl> 0, 0, 1, 0, 0, 0, 0, 1, 1, 1, 0, …
## $ RelationshipSatisfaction__3 <dbl> 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 1, …
## $ RelationshipSatisfaction__4 <dbl> 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, …
## $ StockOptionLevel__0 <dbl> 1, 0, 1, 1, 0, 1, 0, 0, 1, 0, 0, …
## $ StockOptionLevel__1 <dbl> 0, 1, 0, 0, 1, 0, 0, 1, 0, 0, 1, …
## $ StockOptionLevel__2 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, …
## $ StockOptionLevel__3 <dbl> 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, …
## $ `TotalWorkingYears__-Inf_6` <dbl> 0, 0, 0, 0, 1, 0, 0, 1, 0, 0, 1, …
## $ TotalWorkingYears__6_10 <dbl> 1, 1, 1, 1, 0, 1, 0, 0, 1, 0, 0, …
## $ TotalWorkingYears__10_15 <dbl> 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, …
## $ TotalWorkingYears__15_Inf <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, …
## $ `TrainingTimesLastYear__-Inf_2` <dbl> 1, 0, 0, 0, 0, 1, 0, 1, 1, 0, 0, …
## $ TrainingTimesLastYear__2_3 <dbl> 0, 1, 1, 1, 1, 0, 1, 0, 0, 1, 0, …
## $ TrainingTimesLastYear__3_Inf <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, …
## $ WorkLifeBalance__1 <dbl> 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ WorkLifeBalance__2 <dbl> 0, 0, 0, 0, 0, 1, 1, 0, 0, 1, 0, …
## $ WorkLifeBalance__3 <dbl> 0, 1, 1, 1, 1, 0, 0, 1, 1, 0, 1, …
## $ WorkLifeBalance__4 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ `YearsAtCompany__-Inf_3` <dbl> 0, 0, 1, 0, 1, 0, 1, 1, 0, 0, 0, …
## $ YearsAtCompany__3_5 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, …
## $ YearsAtCompany__5_9 <dbl> 1, 0, 0, 1, 0, 1, 0, 0, 1, 1, 0, …
## $ YearsAtCompany__9_Inf <dbl> 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ `YearsInCurrentRole__-Inf_2` <dbl> 0, 0, 1, 0, 1, 0, 1, 1, 0, 0, 0, …
## $ YearsInCurrentRole__2_3 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ YearsInCurrentRole__3_7 <dbl> 1, 1, 0, 1, 0, 1, 0, 0, 1, 1, 1, …
## $ YearsInCurrentRole__7_Inf <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ `YearsSinceLastPromotion__-Inf_1` <dbl> 1, 1, 1, 0, 0, 0, 1, 1, 1, 0, 1, …
## $ YearsSinceLastPromotion__1_3 <dbl> 0, 0, 0, 1, 1, 1, 0, 0, 0, 0, 0, …
## $ YearsSinceLastPromotion__3_Inf <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, …
## $ `YearsWithCurrManager__-Inf_2` <dbl> 0, 0, 1, 1, 1, 0, 1, 1, 0, 0, 0, …
## $ YearsWithCurrManager__2_3 <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, …
## $ YearsWithCurrManager__3_7 <dbl> 1, 1, 0, 0, 0, 1, 0, 0, 0, 1, 0, …
## $ YearsWithCurrManager__7_Inf <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, …# Step 2: correlation
data_correlation <- data_binarized %>%
correlate(Attrition__Left)
data_correlation## # A tibble: 120 × 3
## feature bin correlation
## <fct> <chr> <dbl>
## 1 Attrition Left 1
## 2 Attrition No -1
## 3 OverTime Yes 0.246
## 4 OverTime No -0.246
## 5 JobLevel 1 0.213
## 6 MonthlyIncome -Inf_2911 0.207
## 7 StockOptionLevel 0 0.195
## 8 YearsAtCompany -Inf_3 0.183
## 9 MaritalStatus Single 0.175
## 10 TotalWorkingYears -Inf_6 0.169
## # ℹ 110 more rows# Step 3: plot
data_correlation %>%
correlationfunnel::plot_correlation_funnel()## Warning: ggrepel: 69 unlabeled data points (too many overlaps). Consider
## increasing max.overlaps
Model building
Split data
library(tidymodels)## Warning: package 'broom' was built under R version 4.3.3## Warning: package 'modeldata' was built under R version 4.3.3## Warning: package 'recipes' was built under R version 4.3.3set.seed(1234)
#data_clean <- data_clean %>% sample_n(100)
data_split <- initial_split(data_clean, strata = Attrition)
data_train <- training(data_split)
data_test <- testing(data_split)
data_cv <- rsample::vfold_cv(data_train, strata = Attrition)
data_cv## # 10-fold cross-validation using stratification
## # A tibble: 10 × 2
## splits id
## <list> <chr>
## 1 <split [990/111]> Fold01
## 2 <split [990/111]> Fold02
## 3 <split [990/111]> Fold03
## 4 <split [990/111]> Fold04
## 5 <split [991/110]> Fold05
## 6 <split [991/110]> Fold06
## 7 <split [991/110]> Fold07
## 8 <split [992/109]> Fold08
## 9 <split [992/109]> Fold09
## 10 <split [992/109]> Fold10Preprocess data
library(themis)
xgboost_rec <- recipes::recipe(Attrition ~ ., data = data_train) %>%
update_role(EmployeeNumber, new_role = "ID") %>%
step_dummy(all_nominal_predictors()) %>%
step_normalize(all_numeric_predictors()) %>%
step_smote(Attrition)
xgboost_rec %>% prep() %>% juice() %>% glimpse()## Rows: 1,848
## Columns: 46
## $ Age <dbl> 0.008807237, -0.101383303, -0.542145…
## $ DailyRate <dbl> 1.42650782, 1.04705665, 0.81938595, …
## $ DistanceFromHome <dbl> -0.90560797, -0.04468277, 0.81624244…
## $ Education <dbl> -0.88220753, 1.05074867, -1.84868563…
## $ EmployeeNumber <dbl> 4, 27, 33, 45, 47, 55, 58, 64, 90, 1…
## $ EnvironmentSatisfaction <dbl> 1.1919528, 0.2780670, -0.6358188, -0…
## $ HourlyRate <dbl> 1.281526684, 0.789662751, 0.29779881…
## $ JobInvolvement <dbl> -1.0171141, -1.0171141, -2.4082230, …
## $ JobLevel <dbl> -0.96542632, -0.96542632, -0.9654263…
## $ JobSatisfaction <dbl> 0.2538533, -1.5610329, -1.5610329, 1…
## $ MonthlyIncome <dbl> -0.93899597, -0.66085114, -0.5527189…
## $ MonthlyRate <dbl> -1.6645786, -1.0194609, -1.3434252, …
## $ NumCompaniesWorked <dbl> 1.3192201, 1.7195678, -0.6825182, -0…
## $ PercentSalaryHike <dbl> -0.06569789, 2.10974214, 1.83781213,…
## $ PerformanceRating <dbl> -0.4360017, 2.2914860, 2.2914860, -0…
## $ RelationshipSatisfaction <dbl> -0.6470182, -0.6470182, -0.6470182, …
## $ StockOptionLevel <dbl> -0.9411004, -0.9411004, -0.9411004, …
## $ TotalWorkingYears <dbl> -0.5386623, -0.1543025, -0.1543025, …
## $ TrainingTimesLastYear <dbl> 0.1451189, 0.9245137, 1.7039084, -0.…
## $ WorkLifeBalance <dbl> 0.3580981, 0.3580981, 0.3580981, -1.…
## $ YearsAtCompany <dbl> -1.119612991, -0.323504813, 0.472603…
## $ YearsInCurrentRole <dbl> -1.15408286, -0.33886992, -0.6106075…
## $ YearsSinceLastPromotion <dbl> -0.67903619, -0.67903619, 1.21606861…
## $ YearsWithCurrManager <dbl> -1.12646331, -0.29520587, 0.81313739…
## $ Attrition <fct> Left, Left, Left, Left, Left, Left, …
## $ BusinessTravel_Travel_Frequently <dbl> -0.4781076, -0.4781076, 2.0896799, -…
## $ BusinessTravel_Travel_Rarely <dbl> 0.6327712, 0.6327712, -1.5789147, 0.…
## $ Department_Research...Development <dbl> 0.7300286, -1.3685653, 0.7300286, 0.…
## $ Department_Sales <dbl> -0.6595963, 1.5147018, -0.6595963, -…
## $ EducationField_Life.Sciences <dbl> -0.8420112, 1.1865540, 1.1865540, -0…
## $ EducationField_Marketing <dbl> -0.3463115, -0.3463115, -0.3463115, …
## $ EducationField_Medical <dbl> -0.6981366, -0.6981366, -0.6981366, …
## $ EducationField_Other <dbl> 4.1634411, -0.2399678, -0.2399678, -…
## $ EducationField_Technical.Degree <dbl> -0.2835453, -0.2835453, -0.2835453, …
## $ Gender_Male <dbl> 0.8078118, 0.8078118, -1.2367877, 0.…
## $ JobRole_Human.Resources <dbl> -0.1990579, -0.1990579, -0.1990579, …
## $ JobRole_Laboratory.Technician <dbl> 2.1411830, -0.4666074, -0.4666074, -…
## $ JobRole_Manager <dbl> -0.2663591, -0.2663591, -0.2663591, …
## $ JobRole_Manufacturing.Director <dbl> -0.3380364, -0.3380364, -0.3380364, …
## $ JobRole_Research.Director <dbl> -0.2524088, -0.2524088, -0.2524088, …
## $ JobRole_Research.Scientist <dbl> -0.4766741, -0.4766741, 2.0959640, 2…
## $ JobRole_Sales.Executive <dbl> -0.5319394, -0.5319394, -0.5319394, …
## $ JobRole_Sales.Representative <dbl> -0.2483152, 4.0234821, -0.2483152, -…
## $ MaritalStatus_Married <dbl> -0.9285259, -0.9285259, -0.9285259, …
## $ MaritalStatus_Single <dbl> 1.4765158, 1.4765158, 1.4765158, -0.…
## $ OverTime_Yes <dbl> 1.6002434, -0.6243374, 1.6002434, 1.…Specify model
xgboost_spec <-
boost_tree(trees = tune(), tree_depth = tune()) %>%
set_mode("classification") %>%
set_engine("xgboost")
xgboost_workflow <-
workflow() %>%
add_recipe(xgboost_rec) %>%
add_model(xgboost_spec) Tune hyperparameters
tree_grid <- grid_regular(cost_complexity(),
tree_depth(),
levels = 5)
doParallel::registerDoParallel()
set.seed(65743)
xgboost_tune <-
tune_grid(xgboost_workflow,
resamples = data_cv,
grid = 5,
control = control_grid(save_pred = TRUE))## Warning: package 'xgboost' was built under R version 4.3.3Model Evaluation
Identify Optimal Values for Hyperparameters
collect_metrics(xgboost_tune)## # A tibble: 15 × 8
## trees tree_depth .metric .estimator mean n std_err .config
## <int> <int> <chr> <chr> <dbl> <int> <dbl> <chr>
## 1 1741 3 accuracy binary 0.877 10 0.00880 Preprocessor1_Mo…
## 2 1741 3 brier_class binary 0.105 10 0.00641 Preprocessor1_Mo…
## 3 1741 3 roc_auc binary 0.817 10 0.0160 Preprocessor1_Mo…
## 4 885 5 accuracy binary 0.880 10 0.00587 Preprocessor1_Mo…
## 5 885 5 brier_class binary 0.102 10 0.00626 Preprocessor1_Mo…
## 6 885 5 roc_auc binary 0.816 10 0.0150 Preprocessor1_Mo…
## 7 325 7 accuracy binary 0.878 10 0.00798 Preprocessor1_Mo…
## 8 325 7 brier_class binary 0.103 10 0.00722 Preprocessor1_Mo…
## 9 325 7 roc_auc binary 0.824 10 0.0194 Preprocessor1_Mo…
## 10 1312 12 accuracy binary 0.878 10 0.00876 Preprocessor1_Mo…
## 11 1312 12 brier_class binary 0.103 10 0.00627 Preprocessor1_Mo…
## 12 1312 12 roc_auc binary 0.822 10 0.0172 Preprocessor1_Mo…
## 13 555 15 accuracy binary 0.880 10 0.00794 Preprocessor1_Mo…
## 14 555 15 brier_class binary 0.101 10 0.00633 Preprocessor1_Mo…
## 15 555 15 roc_auc binary 0.829 10 0.0167 Preprocessor1_Mo…collect_predictions(xgboost_tune) %>%
group_by(id) %>%
roc_curve(Attrition, .pred_Left) %>%
autoplot()
Fit the Model for the Last Time
xgboost_last <- xgboost_workflow %>%
finalize_workflow(select_best(xgboost_tune, metric = "accuracy")) %>%
last_fit(data_split)
collect_metrics(xgboost_last)## # A tibble: 3 × 4
## .metric .estimator .estimate .config
## <chr> <chr> <dbl> <chr>
## 1 accuracy binary 0.843 Preprocessor1_Model1
## 2 roc_auc binary 0.771 Preprocessor1_Model1
## 3 brier_class binary 0.132 Preprocessor1_Model1collect_predictions(xgboost_last) %>%
yardstick::conf_mat(Attrition, .pred_class)## Truth
## Prediction Left No
## Left 21 19
## No 39 290Variable Importance
library(vip)
xgboost_last %>%
workflows::extract_fit_engine() %>%
vip()
Conclusion
The previous model had accuracy of 0.864 and AUC of 0.810 * Feature transformation: normalize numeric data. It resulted in slight improvement with accuracy of 0.875, but a small decline in AUC of 0.807 * Feature transformation: YeoJohnson transformation. There was no improvement * Feature selection: PCA did not make any improvements