Untitled
Javony Deleon
2026-03-04
Goal is to predict attrition, employees who are likely to leave the company.
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)## ══ Using correlationfunnel? ════════════════════════════════════════════════════
## You might also be interested in applied data science training for business.
## </> Learn more at - www.business-science.io </>library(recipes)##
## Attaching package: 'recipes'
##
## The following object is masked from 'package:stringr':
##
## fixed
##
## The following object is masked from 'package:stats':
##
## steplibrary(tidymodels)## ── Attaching packages ────────────────────────────────────── tidymodels 1.4.1 ──
## ✔ broom 1.0.12 ✔ tailor 0.1.0
## ✔ dials 1.4.2 ✔ tune 2.0.1
## ✔ infer 1.1.0 ✔ workflows 1.3.0
## ✔ modeldata 1.5.1 ✔ workflowsets 1.1.1
## ✔ parsnip 1.4.1 ✔ yardstick 1.3.2
## ✔ rsample 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()library(themis)
data <- read_csv("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.Issues with data
- Missing values
- Factors or numeric variables
- Education, EnvironmentSatisfaction, JobInvolvement, JobSatisfaction, PerformanceRating, RelationshipSatisfaction, WorkLifeBalance
- Zero variance variables
- Over18, EmployCount, StandardHours
- Character variables
- Unbalanced target variable
- ID variable
factors_vec <- data %>% select(Education, EnvironmentSatisfaction, JobInvolvement, JobSatisfaction,
PerformanceRating, RelationshipSatisfaction, WorkLifeBalance) %>% names()
data_clean <- data %>%
# Address factors imported as numeric
mutate(across(factors_vec, as.factor)) %>%
# Drop zero-variance variables
select(-c(Over18,EmployeeCount,StandardHours))## Warning: There was 1 warning in `mutate()`.
## ℹ In argument: `across(factors_vec, as.factor)`.
## Caused by warning:
## ! Using an external vector in selections was deprecated in tidyselect 1.1.0.
## ℹ Please use `all_of()` or `any_of()` instead.
## # Was:
## data %>% select(factors_vec)
##
## # Now:
## data %>% select(all_of(factors_vec))
##
## See <https://tidyselect.r-lib.org/reference/faq-external-vector.html>.Explore data
data_clean %>% count(Attrition)## # A tibble: 2 × 2
## Attrition n
## <chr> <int>
## 1 No 1233
## 2 Yes 237data_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__No <dbl> 0, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, …
## $ Attrition__Yes <dbl> 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ `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__Yes)
# 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 building
Split data
library(tidymodels)
set.seed(1234)
#data <- data %>% sample_n(100)
data_split <- initial_split(data, 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
xgboost_recipes <- recipes::recipe(Attrition ~ ., data = data_train) %>%
update_role(EmployeeNumber, new_role = "ID") %>%
step_rm(Over18) %>%
step_dummy(all_nominal_predictors()) %>%
step_smote(Attrition)
xgboost_recipes %>% prep() %>% juice() %>% glimpse()## Rows: 1,848
## Columns: 48
## $ Age <dbl> 49, 33, 27, 32, 30, 38, 36, 29, 31, …
## $ DailyRate <dbl> 279, 1392, 591, 1005, 1358, 216, 129…
## $ DistanceFromHome <dbl> 8, 3, 2, 2, 24, 23, 27, 15, 26, 21, …
## $ Education <dbl> 1, 4, 1, 2, 1, 3, 3, 2, 1, 4, 2, 3, …
## $ EmployeeCount <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, …
## $ EmployeeNumber <dbl> 2, 5, 7, 8, 11, 12, 13, 15, 16, 20, …
## $ EnvironmentSatisfaction <dbl> 3, 4, 1, 4, 4, 4, 3, 4, 1, 2, 1, 4, …
## $ HourlyRate <dbl> 61, 56, 40, 79, 67, 44, 94, 49, 31, …
## $ JobInvolvement <dbl> 2, 3, 3, 3, 3, 2, 3, 2, 3, 4, 4, 3, …
## $ JobLevel <dbl> 2, 1, 1, 1, 1, 3, 2, 2, 1, 3, 1, 1, …
## $ JobSatisfaction <dbl> 2, 3, 2, 4, 3, 3, 3, 3, 3, 1, 2, 4, …
## $ MonthlyIncome <dbl> 5130, 2909, 3468, 3068, 2693, 9526, …
## $ MonthlyRate <dbl> 24907, 23159, 16632, 11864, 13335, 8…
## $ NumCompaniesWorked <dbl> 1, 1, 9, 0, 1, 0, 6, 0, 1, 1, 0, 5, …
## $ PercentSalaryHike <dbl> 23, 11, 12, 13, 22, 21, 13, 12, 17, …
## $ PerformanceRating <dbl> 4, 3, 3, 3, 4, 4, 3, 3, 3, 3, 3, 3, …
## $ RelationshipSatisfaction <dbl> 4, 3, 4, 3, 2, 2, 2, 4, 4, 3, 4, 3, …
## $ StandardHours <dbl> 80, 80, 80, 80, 80, 80, 80, 80, 80, …
## $ StockOptionLevel <dbl> 1, 0, 1, 0, 1, 0, 2, 0, 1, 1, 2, 0, …
## $ TotalWorkingYears <dbl> 10, 8, 6, 8, 1, 10, 17, 10, 5, 10, 7…
## $ TrainingTimesLastYear <dbl> 3, 3, 3, 2, 2, 2, 3, 3, 1, 1, 5, 3, …
## $ WorkLifeBalance <dbl> 3, 3, 3, 2, 3, 3, 2, 3, 2, 3, 2, 3, …
## $ YearsAtCompany <dbl> 10, 8, 2, 7, 1, 9, 7, 9, 5, 10, 6, 3…
## $ YearsInCurrentRole <dbl> 7, 7, 2, 7, 0, 7, 7, 5, 2, 9, 2, 2, …
## $ YearsSinceLastPromotion <dbl> 1, 3, 2, 3, 0, 1, 7, 0, 4, 8, 0, 1, …
## $ YearsWithCurrManager <dbl> 7, 0, 2, 6, 0, 8, 7, 8, 3, 8, 5, 2, …
## $ Attrition <fct> No, No, No, No, No, No, No, No, No, …
## $ BusinessTravel_Travel_Frequently <dbl> 1, 1, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, …
## $ BusinessTravel_Travel_Rarely <dbl> 0, 0, 1, 0, 1, 0, 1, 1, 1, 1, 1, 1, …
## $ Department_Research...Development <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, …
## $ Department_Sales <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ EducationField_Life.Sciences <dbl> 1, 1, 0, 1, 1, 1, 0, 1, 1, 1, 1, 1, …
## $ EducationField_Marketing <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ EducationField_Medical <dbl> 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, …
## $ EducationField_Other <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ EducationField_Technical.Degree <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ Gender_Male <dbl> 1, 0, 1, 1, 1, 1, 1, 0, 1, 0, 1, 1, …
## $ JobRole_Human.Resources <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ JobRole_Laboratory.Technician <dbl> 0, 0, 1, 1, 1, 0, 0, 1, 0, 0, 0, 0, …
## $ JobRole_Manager <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ JobRole_Manufacturing.Director <dbl> 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, …
## $ JobRole_Research.Director <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ JobRole_Research.Scientist <dbl> 1, 1, 0, 0, 0, 0, 0, 0, 1, 0, 1, 1, …
## $ JobRole_Sales.Executive <dbl> 0, 0, 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, 0, …
## $ MaritalStatus_Married <dbl> 1, 1, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, …
## $ MaritalStatus_Single <dbl> 0, 0, 0, 1, 0, 1, 0, 1, 0, 0, 0, 1, …
## $ OverTime_Yes <dbl> 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 1, 1, …Specify model
library(usemodels)
usemodels::use_xgboost(Attrition ~ ., data = data_train)## xgboost_recipe <-
## recipe(formula = Attrition ~ ., data = data_train) %>%
## step_zv(all_predictors())
##
## xgboost_spec <-
## boost_tree(trees = tune(), min_n = tune(), tree_depth = tune(), learn_rate = tune(),
## loss_reduction = tune(), sample_size = tune()) %>%
## set_mode("classification") %>%
## set_engine("xgboost")
##
## xgboost_workflow <-
## workflow() %>%
## add_recipe(xgboost_recipe) %>%
## add_model(xgboost_spec)
##
## set.seed(27584)
## xgboost_tune <-
## tune_grid(xgboost_workflow, resamples = stop("add your rsample object"), grid = stop("add number of candidate points"))xgboost_spec <-
boost_tree(trees = tune(), min_n = tune(), tree_depth = tune(), learn_rate = tune(),
loss_reduction = tune(), sample_size = tune()) %>%
set_mode("classification") %>%
set_engine("xgboost")
xgboost_workflow <-
workflow() %>%
add_recipe(xgboost_recipes) %>%
add_model(xgboost_spec)Tune hyperparameters
doParallel::registerDoParallel()
set.seed(65743)
xgboost_tune <-
tune_grid(xgboost_workflow,
resamples = data_cv,
grid = 5)