library(tidyverse)
## Warning: package 'tidyverse' was built under R version 4.4.1
## Warning: package 'dplyr' was built under R version 4.4.1
## Warning: package 'lubridate' was built under R version 4.4.1
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 3.5.1 ✔ tibble 3.2.1
## ✔ lubridate 1.9.3 ✔ tidyr 1.3.1
## ✔ purrr 1.0.2
## ── 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 errors
attrition_raw_tbl <- 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.
attrition_raw_tbl %>% glimpse()
## Rows: 1,470
## Columns: 35
## $ Age <dbl> 41, 49, 37, 33, 27, 32, 59, 30, 38, 36, 35, 2…
## $ Attrition <chr> "Yes", "No", "Yes", "No", "No", "No", "No", "…
## $ BusinessTravel <chr> "Travel_Rarely", "Travel_Frequently", "Travel…
## $ DailyRate <dbl> 1102, 279, 1373, 1392, 591, 1005, 1324, 1358,…
## $ Department <chr> "Sales", "Research & Development", "Research …
## $ DistanceFromHome <dbl> 1, 8, 2, 3, 2, 2, 3, 24, 23, 27, 16, 15, 26, …
## $ Education <dbl> 2, 1, 2, 4, 1, 2, 3, 1, 3, 3, 3, 2, 1, 2, 3, …
## $ EducationField <chr> "Life Sciences", "Life Sciences", "Other", "L…
## $ EmployeeCount <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, …
## $ EmployeeNumber <dbl> 1, 2, 4, 5, 7, 8, 10, 11, 12, 13, 14, 15, 16,…
## $ EnvironmentSatisfaction <dbl> 2, 3, 4, 4, 1, 4, 3, 4, 4, 3, 1, 4, 1, 2, 3, …
## $ Gender <chr> "Female", "Male", "Male", "Female", "Male", "…
## $ HourlyRate <dbl> 94, 61, 92, 56, 40, 79, 81, 67, 44, 94, 84, 4…
## $ JobInvolvement <dbl> 3, 2, 2, 3, 3, 3, 4, 3, 2, 3, 4, 2, 3, 3, 2, …
## $ JobLevel <dbl> 2, 2, 1, 1, 1, 1, 1, 1, 3, 2, 1, 2, 1, 1, 1, …
## $ JobRole <chr> "Sales Executive", "Research Scientist", "Lab…
## $ JobSatisfaction <dbl> 4, 2, 3, 3, 2, 4, 1, 3, 3, 3, 2, 3, 3, 4, 3, …
## $ MaritalStatus <chr> "Single", "Married", "Single", "Married", "Ma…
## $ MonthlyIncome <dbl> 5993, 5130, 2090, 2909, 3468, 3068, 2670, 269…
## $ MonthlyRate <dbl> 19479, 24907, 2396, 23159, 16632, 11864, 9964…
## $ NumCompaniesWorked <dbl> 8, 1, 6, 1, 9, 0, 4, 1, 0, 6, 0, 0, 1, 0, 5, …
## $ Over18 <chr> "Y", "Y", "Y", "Y", "Y", "Y", "Y", "Y", "Y", …
## $ OverTime <chr> "Yes", "No", "Yes", "Yes", "No", "No", "Yes",…
## $ PercentSalaryHike <dbl> 11, 23, 15, 11, 12, 13, 20, 22, 21, 13, 13, 1…
## $ PerformanceRating <dbl> 3, 4, 3, 3, 3, 3, 4, 4, 4, 3, 3, 3, 3, 3, 3, …
## $ RelationshipSatisfaction <dbl> 1, 4, 2, 3, 4, 3, 1, 2, 2, 2, 3, 4, 4, 3, 2, …
## $ StandardHours <dbl> 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 8…
## $ StockOptionLevel <dbl> 0, 1, 0, 0, 1, 0, 3, 1, 0, 2, 1, 0, 1, 1, 0, …
## $ TotalWorkingYears <dbl> 8, 10, 7, 8, 6, 8, 12, 1, 10, 17, 6, 10, 5, 3…
## $ TrainingTimesLastYear <dbl> 0, 3, 3, 3, 3, 2, 3, 2, 2, 3, 5, 3, 1, 2, 4, …
## $ WorkLifeBalance <dbl> 1, 3, 3, 3, 3, 2, 2, 3, 3, 2, 3, 3, 2, 3, 3, …
## $ YearsAtCompany <dbl> 6, 10, 0, 8, 2, 7, 1, 1, 9, 7, 5, 9, 5, 2, 4,…
## $ YearsInCurrentRole <dbl> 4, 7, 0, 7, 2, 7, 0, 0, 7, 7, 4, 5, 2, 2, 2, …
## $ YearsSinceLastPromotion <dbl> 0, 1, 0, 3, 2, 3, 0, 0, 1, 7, 0, 0, 4, 1, 0, …
## $ YearsWithCurrManager <dbl> 5, 7, 0, 0, 2, 6, 0, 0, 8, 7, 3, 8, 3, 2, 3, …
# Load necessary libraries
library(tidyverse)
library(tidymodels)
## Warning: package 'tidymodels' was built under R version 4.4.1
## ── Attaching packages ────────────────────────────────────── tidymodels 1.2.0 ──
## ✔ broom 1.0.6 ✔ rsample 1.2.1
## ✔ dials 1.3.0 ✔ tune 1.2.1
## ✔ infer 1.0.7 ✔ workflows 1.1.4
## ✔ modeldata 1.4.0 ✔ workflowsets 1.1.0
## ✔ parsnip 1.2.1 ✔ yardstick 1.3.1
## ✔ recipes 1.0.10
## Warning: package 'dials' was built under R version 4.4.1
## Warning: package 'infer' was built under R version 4.4.1
## Warning: package 'modeldata' was built under R version 4.4.1
## Warning: package 'parsnip' was built under R version 4.4.1
## Warning: package 'tune' was built under R version 4.4.1
## Warning: package 'workflows' was built under R version 4.4.1
## Warning: package 'workflowsets' was built under R version 4.4.1
## Warning: package 'yardstick' was built under R version 4.4.1
## ── 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()
## • Dig deeper into tidy modeling with R at https://www.tmwr.org
library(h2o)
## Warning: package 'h2o' was built under R version 4.4.2
##
## ----------------------------------------------------------------------
##
## Your next step is to start H2O:
## > h2o.init()
##
## For H2O package documentation, ask for help:
## > ??h2o
##
## After starting H2O, you can use the Web UI at http://localhost:54321
## For more information visit https://docs.h2o.ai
##
## ----------------------------------------------------------------------
##
## Attaching package: 'h2o'
## The following objects are masked from 'package:lubridate':
##
## day, hour, month, week, year
## The following objects are masked from 'package:stats':
##
## cor, sd, var
## The following objects are masked from 'package:base':
##
## %*%, %in%, &&, ||, apply, as.factor, as.numeric, colnames,
## colnames<-, ifelse, is.character, is.factor, is.numeric, log,
## log10, log1p, log2, round, signif, trunc
# Initialize H2O cluster
h2o.init()
##
## H2O is not running yet, starting it now...
##
## Note: In case of errors look at the following log files:
## C:\Users\Surplus\AppData\Local\Temp\RtmpgDN8Gc\file4e48167c1f51/h2o_Surplus_started_from_r.out
## C:\Users\Surplus\AppData\Local\Temp\RtmpgDN8Gc\file4e4854f27d21/h2o_Surplus_started_from_r.err
##
##
## Starting H2O JVM and connecting: Connection successful!
##
## R is connected to the H2O cluster:
## H2O cluster uptime: 6 seconds 157 milliseconds
## H2O cluster timezone: America/New_York
## H2O data parsing timezone: UTC
## H2O cluster version: 3.44.0.3
## H2O cluster version age: 11 months and 27 days
## H2O cluster name: H2O_started_from_R_Surplus_qyz143
## H2O cluster total nodes: 1
## H2O cluster total memory: 1.75 GB
## H2O cluster total cores: 4
## H2O cluster allowed cores: 4
## H2O cluster healthy: TRUE
## H2O Connection ip: localhost
## H2O Connection port: 54321
## H2O Connection proxy: NA
## H2O Internal Security: FALSE
## R Version: R version 4.4.0 (2024-04-24 ucrt)
## Warning in h2o.clusterInfo():
## Your H2O cluster version is (11 months and 27 days) old. There may be a newer version available.
## Please download and install the latest version from: https://h2o-release.s3.amazonaws.com/h2o/latest_stable.html
# Preprocessing the dataset
attrition_raw_tbl <- attrition_raw_tbl %>%
mutate(
Attrition = as.factor(Attrition),
BusinessTravel = as.factor(BusinessTravel),
Department = as.factor(Department),
EducationField = as.factor(EducationField),
Gender = as.factor(Gender),
MaritalStatus = as.factor(MaritalStatus),
OverTime = as.factor(OverTime)
)
# Split the data into training and testing sets
set.seed(123) # For reproducibility
data_split <- initial_split(attrition_raw_tbl, prop = 0.8, strata = Attrition)
train_data <- training(data_split)
test_data <- testing(data_split)
# Data preprocessing using recipe
attrition_recipe <- recipe(Attrition ~ ., data = train_data) %>%
step_rm(EmployeeCount, Over18, StandardHours, EmployeeNumber) %>% # Remove irrelevant columns
step_dummy(all_nominal_predictors(), -all_outcomes()) %>% # One-hot encode categorical variables
step_normalize(all_numeric_predictors()) # Normalize numeric predictors
# Prepare the processed data
attrition_prep <- attrition_recipe %>% prep()
train_processed <- bake(attrition_prep, new_data = NULL)
test_processed <- bake(attrition_prep, new_data = test_data)
# Convert processed data to H2O frame
train_h2o <- as.h2o(train_processed)
## | | | 0% | |======================================================================| 100%
test_h2o <- as.h2o(test_processed)
## | | | 0% | |======================================================================| 100%
# Train an H2O logistic regression model
h2o_model <- h2o.glm(
x = setdiff(names(train_processed), "Attrition"),
y = "Attrition",
training_frame = train_h2o,
family = "binomial"
)
## | | | 0% | |======================================================================| 100%
# Summarize the H2O model
h2o.performance(h2o_model, train_h2o)
## H2OBinomialMetrics: glm
##
## MSE: 0.08694483
## RMSE: 0.2948641
## LogLoss: 0.2985547
## Mean Per-Class Error: 0.2371723
## AUC: 0.861967
## AUCPR: 0.6711617
## Gini: 0.723934
## R^2: 0.3558592
## Residual Deviance: 701.6034
## AIC: 791.6034
##
## Confusion Matrix (vertical: actual; across: predicted) for F1-optimal threshold:
## No Yes Error Rate
## No 920 66 0.066937 =66/986
## Yes 77 112 0.407407 =77/189
## Totals 997 178 0.121702 =143/1175
##
## Maximum Metrics: Maximum metrics at their respective thresholds
## metric threshold value idx
## 1 max f1 0.357925 0.610354 134
## 2 max f2 0.190545 0.672192 211
## 3 max f0point5 0.537526 0.694200 78
## 4 max accuracy 0.493309 0.893617 87
## 5 max precision 0.979064 1.000000 0
## 6 max recall 0.004499 1.000000 391
## 7 max specificity 0.979064 1.000000 0
## 8 max absolute_mcc 0.451954 0.552022 100
## 9 max min_per_class_accuracy 0.174629 0.788360 222
## 10 max mean_per_class_accuracy 0.214204 0.793511 198
## 11 max tns 0.979064 986.000000 0
## 12 max fns 0.979064 188.000000 0
## 13 max fps 0.000211 986.000000 399
## 14 max tps 0.004499 189.000000 391
## 15 max tnr 0.979064 1.000000 0
## 16 max fnr 0.979064 0.994709 0
## 17 max fpr 0.000211 1.000000 399
## 18 max tpr 0.004499 1.000000 391
##
## Gains/Lift Table: Extract with `h2o.gainsLift(<model>, <data>)` or `h2o.gainsLift(<model>, valid=<T/F>, xval=<T/F>)`
# Make predictions on the test set
predictions <- h2o.predict(h2o_model, newdata = test_h2o)
## | | | 0% | |======================================================================| 100%
# Add predictions back to the test set
test_results <- test_data %>%
mutate(
predicted_prob = as.vector(predictions$Yes),
predicted_class = ifelse(predicted_prob > 0.5, "Yes", "No")
)
# Ensure predicted_class is a factor with levels matching Attrition
test_results <- test_results %>%
mutate(
predicted_class = factor(predicted_class, levels = levels(Attrition))
)
# Evaluate model performance
metrics <- test_results %>%
metrics(truth = Attrition, estimate = predicted_class)
# Compute confusion matrix
conf_matrix <- test_results %>%
conf_mat(truth = Attrition, estimate = predicted_class)
# Print evaluation metrics
metrics %>%
as_tibble() %>%
arrange(desc(.metric)) %>%
print()
## # A tibble: 2 × 3
## .metric .estimator .estimate
## <chr> <chr> <dbl>
## 1 kap binary 0.473
## 2 accuracy binary 0.875
# Plot confusion matrix
autoplot(conf_matrix)
# Shut down H2O
h2o.shutdown(prompt = FALSE)