R Markdown
library(tidyverse)
## ── 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("~/Desktop/PSU_DAT3100_IntermediateDataAnalytics/PSU_DAT3100/00_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.
# If data is not sensitive:
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, …
# If data is sensitive:
attrition_raw_tbl %>%
slice(0) %>%
glimpse()
## Rows: 0
## Columns: 35
## $ Age <dbl>
## $ Attrition <chr>
## $ BusinessTravel <chr>
## $ DailyRate <dbl>
## $ Department <chr>
## $ DistanceFromHome <dbl>
## $ Education <dbl>
## $ EducationField <chr>
## $ EmployeeCount <dbl>
## $ EmployeeNumber <dbl>
## $ EnvironmentSatisfaction <dbl>
## $ Gender <chr>
## $ HourlyRate <dbl>
## $ JobInvolvement <dbl>
## $ JobLevel <dbl>
## $ JobRole <chr>
## $ JobSatisfaction <dbl>
## $ MaritalStatus <chr>
## $ MonthlyIncome <dbl>
## $ MonthlyRate <dbl>
## $ NumCompaniesWorked <dbl>
## $ Over18 <chr>
## $ OverTime <chr>
## $ PercentSalaryHike <dbl>
## $ PerformanceRating <dbl>
## $ RelationshipSatisfaction <dbl>
## $ StandardHours <dbl>
## $ StockOptionLevel <dbl>
## $ TotalWorkingYears <dbl>
## $ TrainingTimesLastYear <dbl>
## $ WorkLifeBalance <dbl>
## $ YearsAtCompany <dbl>
## $ YearsInCurrentRole <dbl>
## $ YearsSinceLastPromotion <dbl>
## $ YearsWithCurrManager <dbl>
# Load necessary libraries
library(tidymodels)
## ── 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
## ── 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()
## • Use suppressPackageStartupMessages() to eliminate package startup messages
library(h2o)
##
## ----------------------------------------------------------------------
##
## 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
h2o.init()
##
## H2O is not running yet, starting it now...
##
## Note: In case of errors look at the following log files:
## /var/folders/9c/6s3xfkv91613gfg8pxfdlmjh0000gn/T//Rtmp23HJwx/filea50d1d56b1ba/h2o_julius_mondschein_started_from_r.out
## /var/folders/9c/6s3xfkv91613gfg8pxfdlmjh0000gn/T//Rtmp23HJwx/filea50d26ae3962/h2o_julius_mondschein_started_from_r.err
##
##
## Starting H2O JVM and connecting: ..... Connection successful!
##
## R is connected to the H2O cluster:
## H2O cluster uptime: 8 seconds 639 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 13 days
## H2O cluster name: H2O_started_from_R_julius.mondschein_rdu492
## H2O cluster total nodes: 1
## H2O cluster total memory: 1.77 GB
## H2O cluster total cores: 8
## H2O cluster allowed cores: 8
## 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)
## Warning in h2o.clusterInfo():
## Your H2O cluster version is (11 months and 13 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
# Data preprocessing
# Convert all character columns to factor and exclude columns with only one unique value
attrition_raw_tbl <- attrition_raw_tbl %>%
mutate(across(where(is.character), as.factor)) %>%
select_if(~ n_distinct(.) > 1)
# Set up recipe
recipe <- recipe(Attrition ~ ., data = attrition_raw_tbl) %>%
step_dummy(all_nominal(), -all_outcomes(), one_hot = TRUE) %>%
step_zv(all_predictors()) %>%
prep()
# Prepare data
data_processed <- bake(recipe, new_data = NULL)
set.seed(123)
data_split <- initial_split(data_processed, prop = 0.8)
train_data <- training(data_split)
test_data <- testing(data_split)
# Convert to H2O frames
train_data_h2o <- as.h2o(train_data)
## | | | 0% | |======================================================================| 100%
test_data_h2o <- as.h2o(test_data)
## | | | 0% | |======================================================================| 100%
# Define and train the H2O model
attrition_model <- h2o.glm(
x = setdiff(names(train_data_h2o), "Attrition"),
y = "Attrition",
training_frame = train_data_h2o,
family = "binomial",
lambda_search = TRUE
)
## | | | 0% | |==== | 6% | |============================================== | 66% | |======================================================================| 100%
# Predict on the test data
predictions <- h2o.predict(attrition_model, newdata = test_data_h2o)
## | | | 0% | |======================================================================| 100%
predicted_probabilities <- as.data.frame(predictions)$p1
# Convert probabilities to binary predictions
binary_predictions <- ifelse(predicted_probabilities > 0.5, 1, 0)
# Extract actual outcomes from the test data
test_actual <- as.vector(test_data$Attrition)
# Check length consistency and calculate accuracy
if (length(binary_predictions) == length(test_actual)) {
conf_mat <- table(Predicted = binary_predictions, Actual = test_actual)
accuracy <- sum(diag(conf_mat)) / sum(conf_mat)
print(paste("Accuracy:", accuracy))
# More detailed performance metrics
performance <- h2o.performance(attrition_model, newdata = test_data_h2o)
print(paste("AUC:", h2o.auc(performance)))
} else {
print("Error: Mismatch in the length of predicted and actual outcome vectors.")
}
## [1] "Error: Mismatch in the length of predicted and actual outcome vectors."
# Clean up
h2o.shutdown(prompt = FALSE)