codealong8
2026-03-25
Goal is to predict attrition # import data
library(tidyverse)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.6
## ✔ forcats 1.0.1 ✔ stringr 1.6.0
## ✔ ggplot2 4.0.2 ✔ tibble 3.3.1
## ✔ lubridate 1.9.4 ✔ tidyr 1.3.2
## ✔ purrr 1.2.1
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errorslibrary(correlationfunnel)## ══ correlationfunnel Tip #2 ════════════════════════════════════════════════════
## Clean your NA's prior to using `binarize()`.
## Missing values and cleaning data are critical to getting great correlations. :)data <- read_csv("../00_data/WA_Fn-UseC_-HR-Employee-Attrition.csv")## Rows: 1470 Columns: 35
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (9): Attrition, BusinessTravel, Department, EducationField, Gender, Job...
## dbl (26): Age, DailyRate, DistanceFromHome, Education, EmployeeCount, Employ...
##
## 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.clean 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 | ▇▂▅▁▁ |
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), as.factor)) %>%
#drop zero variance variables
select(-c(Over18,EmployeeCount,StandardHours)) %>%
#recode attrition
mutate(Attrition =if_else(Attrition == "Yes", "Left", Attrition))explore data
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
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 2L 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 No -0.246
## 4 OverTime Yes 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: The `size` argument of `element_line()` is deprecated as of ggplot2 3.4.0.
## ℹ Please use the `linewidth` argument instead.
## ℹ The deprecated feature was likely used in the correlationfunnel package.
## Please report the issue at
## <https://github.com/business-science/correlationfunnel/issues>.
## This warning is displayed once per session.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.## Warning: The `size` argument of `element_rect()` is deprecated as of ggplot2 3.4.0.
## ℹ Please use the `linewidth` argument instead.
## ℹ The deprecated feature was likely used in the correlationfunnel package.
## Please report the issue at
## <https://github.com/business-science/correlationfunnel/issues>.
## This warning is displayed once per session.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.## Warning: ggrepel: 73 unlabeled data points (too many overlaps). Consider
## increasing max.overlaps
model buidling
split data
library(tidymodels)## ── Attaching packages ────────────────────────────────────── tidymodels 1.4.1 ──## ✔ broom 1.0.12 ✔ rsample 1.3.2
## ✔ dials 1.4.2 ✔ tailor 0.1.0
## ✔ infer 1.1.0 ✔ tune 2.0.1
## ✔ modeldata 1.5.1 ✔ workflows 1.3.0
## ✔ parsnip 1.4.1 ✔ workflowsets 1.1.1
## ✔ recipes 1.3.1 ✔ yardstick 1.3.2## ── Conflicts ───────────────────────────────────────── tidymodels_conflicts() ──
## ✖ scales::discard() masks purrr::discard()
## ✖ dplyr::filter() masks stats::filter()
## ✖ recipes::fixed() masks stringr::fixed()
## ✖ dplyr::lag() masks stats::lag()
## ✖ yardstick::spec() masks readr::spec()
## ✖ recipes::step() masks stats::step()set.seed(1234)
data_clean <- data_clean %>% sample_n(200)
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 [133/16]> Fold01
## 2 <split [133/16]> Fold02
## 3 <split [134/15]> Fold03
## 4 <split [134/15]> Fold04
## 5 <split [134/15]> Fold05
## 6 <split [134/15]> Fold06
## 7 <split [134/15]> Fold07
## 8 <split [135/14]> Fold08
## 9 <split [135/14]> Fold09
## 10 <split [135/14]> Fold10preprocess data
library(themis)
xgboost_rec <- recipes::recipe(Attrition ~., data = data_train) %>%
update_role(EmployeeNumber, new_role = "ID") %>%
step_dummy(all_nominal_predictors()) %>%
#step_YeoJohnson(DistanceFromHome, MonthlyIncome, NumCompaniesWorked, PercentSalaryHike, TotalWorkingYears, YearsAtCompany, starts_with("Years")) %>%
step_normalize(all_numeric_predictors()) %>%
#step_pca(all_numeric_predictors(), threshold = .99) %>%
step_smote(Attrition)
xgboost_rec %>% prep() %>% juice() %>% glimpse()## Rows: 264
## Columns: 64
## $ Age <dbl> -0.22049222, -1.24715914, -0.5627145…
## $ DailyRate <dbl> -0.6386971, 0.7080382, 0.9984601, -1…
## $ DistanceFromHome <dbl> 0.73157007, -0.05075486, -0.83307980…
## $ EmployeeNumber <dbl> 1010, 796, 1692, 161, 1761, 840, 787…
## $ HourlyRate <dbl> -1.23160528, -1.27983371, 1.46918695…
## $ MonthlyIncome <dbl> -0.5149021, -0.1531987, -1.0518591, …
## $ MonthlyRate <dbl> -0.45520934, -1.40777095, 1.55291555…
## $ NumCompaniesWorked <dbl> -0.66382843, 1.24563945, -0.66382843…
## $ PercentSalaryHike <dbl> 2.3701781, 0.3909181, -1.0228391, 0.…
## $ TotalWorkingYears <dbl> -0.86889956, -0.71747730, -1.4745886…
## $ TrainingTimesLastYear <dbl> -0.6317776, -0.6317776, -0.6317776, …
## $ YearsAtCompany <dbl> -0.64046153, -0.64046153, -1.2259141…
## $ YearsInCurrentRole <dbl> -0.71496441, -0.39791174, -1.3490697…
## $ YearsSinceLastPromotion <dbl> -0.71450951, -0.36315005, -0.7145095…
## $ YearsWithCurrManager <dbl> -0.7096256, -0.7096256, -1.2858338, …
## $ Attrition <fct> Left, Left, Left, Left, Left, Left, …
## $ BusinessTravel_Travel_Frequently <dbl> -0.5934357, -0.5934357, -0.5934357, …
## $ BusinessTravel_Travel_Rarely <dbl> 0.7844788, 0.7844788, 0.7844788, 0.7…
## $ Department_Research...Development <dbl> 0.7623513, -1.3029277, 0.7623513, 0.…
## $ Department_Sales <dbl> -0.6660365, 1.4913426, -0.6660365, -…
## $ Education_X2 <dbl> -0.4582177, -0.4582177, -0.4582177, …
## $ Education_X3 <dbl> -0.8530191, 1.1644388, -0.8530191, -…
## $ Education_X4 <dbl> 1.5647913, -0.6347738, 1.5647913, 1.…
## $ Education_X5 <dbl> -0.08192319, -0.08192319, -0.0819231…
## $ EducationField_Life.Sciences <dbl> -0.7844788, -0.7844788, 1.2661764, 1…
## $ EducationField_Marketing <dbl> -0.3456781, -0.3456781, -0.3456781, …
## $ EducationField_Medical <dbl> -0.7514028, -0.7514028, -0.7514028, …
## $ EducationField_Other <dbl> 4.4888271, -0.2212802, -0.2212802, -…
## $ EducationField_Technical.Degree <dbl> -0.2949634, 3.3674983, -0.2949634, -…
## $ EnvironmentSatisfaction_X2 <dbl> -0.5212185, -0.5212185, -0.5212185, …
## $ EnvironmentSatisfaction_X3 <dbl> 1.5151239, -0.6555824, -0.6555824, -…
## $ EnvironmentSatisfaction_X4 <dbl> -0.7082802, 1.4023949, 1.4023949, -0…
## $ Gender_Male <dbl> 0.8767076, 0.8767076, 0.8767076, -1.…
## $ JobInvolvement_X2 <dbl> 1.5647913, 1.5647913, -0.6347738, -0…
## $ JobInvolvement_X3 <dbl> -1.1329759, -1.1329759, 0.8767076, 0…
## $ JobInvolvement_X4 <dbl> -0.3810157, -0.3810157, -0.3810157, …
## $ JobLevel_X2 <dbl> -0.7297154, 1.3611999, -0.7297154, -…
## $ JobLevel_X3 <dbl> -0.4148081, -0.4148081, -0.4148081, …
## $ JobLevel_X4 <dbl> -0.1857126, -0.1857126, -0.1857126, …
## $ JobLevel_X5 <dbl> -0.2212802, -0.2212802, -0.2212802, …
## $ JobRole_Human.Resources <dbl> -0.2373959, -0.2373959, -0.2373959, …
## $ JobRole_Laboratory.Technician <dbl> 2.0273529, -0.4899436, 2.0273529, -0…
## $ JobRole_Manager <dbl> -0.2212802, -0.2212802, -0.2212802, …
## $ JobRole_Manufacturing.Director <dbl> -0.3081342, -0.3081342, -0.3081342, …
## $ JobRole_Research.Director <dbl> -0.252694, -0.252694, -0.252694, -0.…
## $ JobRole_Research.Scientist <dbl> -0.4688562, -0.4688562, -0.4688562, …
## $ JobRole_Sales.Executive <dbl> -0.5522291, 1.7986892, -0.5522291, -…
## $ JobRole_Sales.Representative <dbl> -0.252694, -0.252694, -0.252694, -0.…
## $ JobSatisfaction_X2 <dbl> 1.9849546, -0.5004087, 1.9849546, 1.…
## $ JobSatisfaction_X3 <dbl> -0.7844788, -0.7844788, -0.7844788, …
## $ JobSatisfaction_X4 <dbl> -0.6140698, -0.6140698, -0.6140698, …
## $ MaritalStatus_Married <dbl> -1.0169113, -1.0169113, -1.0169113, …
## $ MaritalStatus_Single <dbl> -0.6244109, 1.5907611, 1.5907611, -0…
## $ OverTime_Yes <dbl> 1.7657357, -0.5625353, -0.5625353, 1…
## $ PerformanceRating_X4 <dbl> 2.1677221, -0.4582177, -0.4582177, -…
## $ RelationshipSatisfaction_X2 <dbl> -0.4899436, -0.4899436, -0.4899436, …
## $ RelationshipSatisfaction_X3 <dbl> -0.6555824, 1.5151239, -0.6555824, -…
## $ RelationshipSatisfaction_X4 <dbl> 1.4913426, -0.6660365, -0.6660365, -…
## $ StockOptionLevel_X1 <dbl> 1.1025727, -0.9008826, -0.9008826, -…
## $ StockOptionLevel_X2 <dbl> -0.3334502, -0.3334502, -0.3334502, …
## $ StockOptionLevel_X3 <dbl> -0.2673193, -0.2673193, -0.2673193, …
## $ WorkLifeBalance_X2 <dbl> -0.6037463, 1.6452086, -0.6037463, -…
## $ WorkLifeBalance_X3 <dbl> -1.058772, -1.058772, 0.938152, 0.93…
## $ WorkLifeBalance_X4 <dbl> -0.4258105, -0.4258105, -0.4258105, …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(31899)
xgboost_tune <-
tune_grid(xgboost_workflow,
resamples = data_cv,
grid = 5,
control = control_grid(save_pred = TRUE))## → A | warning: ! The following column has zero variance so scaling cannot be used:
## Education_X5.
## ℹ Consider using ?step_zv (`?recipes::step_zv()`) to remove those columns
## before normalizing.## There were issues with some computations A: x1There were issues with some computations A: x1Model evaluation
identify optimal values
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 1 4 accuracy binary 0.751 10 0.0141 pre0_mod1_post0
## 2 1 4 brier_class binary 0.204 10 0.00344 pre0_mod1_post0
## 3 1 4 roc_auc binary 0.522 10 0.0593 pre0_mod1_post0
## 4 500 11 accuracy binary 0.847 10 0.0165 pre0_mod2_post0
## 5 500 11 brier_class binary 0.139 10 0.0107 pre0_mod2_post0
## 6 500 11 roc_auc binary 0.391 10 0.0584 pre0_mod2_post0
## 7 1000 1 accuracy binary 0.772 10 0.0283 pre0_mod3_post0
## 8 1000 1 brier_class binary 0.199 10 0.0243 pre0_mod3_post0
## 9 1000 1 roc_auc binary 0.357 10 0.0648 pre0_mod3_post0
## 10 1500 15 accuracy binary 0.847 10 0.0165 pre0_mod4_post0
## 11 1500 15 brier_class binary 0.139 10 0.0112 pre0_mod4_post0
## 12 1500 15 roc_auc binary 0.383 10 0.0559 pre0_mod4_post0
## 13 2000 8 accuracy binary 0.847 10 0.0165 pre0_mod5_post0
## 14 2000 8 brier_class binary 0.142 10 0.0117 pre0_mod5_post0
## 15 2000 8 roc_auc binary 0.382 10 0.0559 pre0_mod5_post0collect_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 0.863 pre0_mod0_post0
## 2 roc_auc binary 0.667 pre0_mod0_post0
## 3 brier_class binary 0.116 pre0_mod0_post0collect_predictions(xgboost_last) %>%
yardstick::conf_mat(Attrition, .pred_class) %>%
autoplot()
variable importance
library(vip)## Warning: package 'vip' was built under R version 4.5.3##
## Attaching package: 'vip'## The following object is masked from 'package:utils':
##
## vixgboost_last %>%
workflows::extract_fit_engine() %>%
vip()