library(tidyverse)
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 errorsattrition_raw_tbl <- 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.# 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>Please write R code to create a predictive model that predicts the probability of attrition.
# Load necessary libraries
library(tidyverse)
library(caret)## Loading required package: lattice##
## Attaching package: 'caret'## The following object is masked from 'package:purrr':
##
## lift# 1. Clean and preprocess the data
attrition_clean_tbl <- attrition_raw_tbl %>%
select(-EmployeeCount, -Over18, -StandardHours, -EmployeeNumber) %>% # Remove constant or ID columns
mutate(Attrition = as.factor(Attrition)) %>%
mutate_if(is.character, as.factor) # Convert character columns to factors
# 2. Split the data into training and testing sets
set.seed(123)
split <- createDataPartition(attrition_clean_tbl$Attrition, p = 0.8, list = FALSE)
train_tbl <- attrition_clean_tbl[split, ]
test_tbl <- attrition_clean_tbl[-split, ]
# 3. Train a logistic regression model
model_logit <- train(
Attrition ~ .,
data = train_tbl,
method = "glm",
family = "binomial",
trControl = trainControl(method = "cv", number = 5)
)
# 4. Evaluate model performance
pred_prob <- predict(model_logit, newdata = test_tbl, type = "prob")
pred_class <- predict(model_logit, newdata = test_tbl)
conf_matrix <- confusionMatrix(pred_class, test_tbl$Attrition)
print(conf_matrix)## Confusion Matrix and Statistics
##
## Reference
## Prediction No Yes
## No 236 30
## Yes 10 17
##
## Accuracy : 0.8635
## 95% CI : (0.8188, 0.9006)
## No Information Rate : 0.8396
## P-Value [Acc > NIR] : 0.149962
##
## Kappa : 0.3878
##
## Mcnemar's Test P-Value : 0.002663
##
## Sensitivity : 0.9593
## Specificity : 0.3617
## Pos Pred Value : 0.8872
## Neg Pred Value : 0.6296
## Prevalence : 0.8396
## Detection Rate : 0.8055
## Detection Prevalence : 0.9078
## Balanced Accuracy : 0.6605
##
## 'Positive' Class : No
## # 5. Add predicted probabilities to the test set
results <- test_tbl %>%
mutate(Predicted_Attrition_Prob = pred_prob$Yes)
# View top predictions
head(results %>% select(Attrition, Predicted_Attrition_Prob))## # A tibble: 6 × 2
## Attrition Predicted_Attrition_Prob
## <fct> <dbl>
## 1 No 0.0356
## 2 No 0.0688
## 3 No 0.0726
## 4 No 0.0384
## 5 No 0.0860
## 6 No 0.000366Please update the code to use tidymodels instead of caret and to use the h2o model instead of glmnet.
# Load libraries
library(tidymodels)## ── Attaching packages ────────────────────────────────────── tidymodels 1.2.0 ──## ✔ broom 1.0.8 ✔ 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 1.3.2
## ✔ recipes 1.1.0## ── Conflicts ───────────────────────────────────────── tidymodels_conflicts() ──
## ✖ scales::discard() masks purrr::discard()
## ✖ dplyr::filter() masks stats::filter()
## ✖ recipes::fixed() masks stringr::fixed()
## ✖ dplyr::lag() masks stats::lag()
## ✖ caret::lift() masks purrr::lift()
## ✖ yardstick::precision() masks caret::precision()
## ✖ yardstick::recall() masks caret::recall()
## ✖ yardstick::sensitivity() masks caret::sensitivity()
## ✖ yardstick::spec() masks readr::spec()
## ✖ yardstick::specificity() masks caret::specificity()
## ✖ recipes::step() masks stats::step()
## • Search for functions across packages at https://www.tidymodels.org/find/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, trunclibrary(dplyr)
# Initialize H2O
h2o.init()## Connection successful!
##
## R is connected to the H2O cluster:
## H2O cluster uptime: 13 days 23 hours
## H2O cluster timezone: America/New_York
## H2O data parsing timezone: UTC
## H2O cluster version: 3.44.0.3
## H2O cluster version age: 1 year, 4 months and 15 days
## H2O cluster name: H2O_started_from_R_katiegoy_fyb567
## H2O cluster total nodes: 1
## H2O cluster total memory: 1.30 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 4.4.1 (2024-06-14)## Warning in h2o.clusterInfo():
## Your H2O cluster version is (1 year, 4 months and 15 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 ---
# Remove unnecessary columns and convert types
attrition_clean_tbl <- attrition_raw_tbl %>%
select(-EmployeeCount, -Over18, -StandardHours, -EmployeeNumber) %>%
mutate(Attrition = as.factor(Attrition)) %>%
mutate(across(where(is.character), as.factor))
# Split data
set.seed(123)
data_split <- initial_split(attrition_clean_tbl, prop = 0.8, strata = Attrition)
train_data <- training(data_split)
test_data <- testing(data_split)
# Ensure Attrition is a factor (important for classification)
train_data <- train_data %>% mutate(Attrition = as.factor(Attrition))
test_data <- test_data %>% mutate(Attrition = as.factor(Attrition))
# Convert to H2O frames
train_h2o <- as.h2o(train_data)## | | | 0% | |======================================================================| 100%test_h2o <- as.h2o(test_data)## | | | 0% | |======================================================================| 100%# Define response and predictors
y <- "Attrition"
x <- setdiff(names(train_data), y)
# Fit H2O GLM model (logistic regression)
h2o_model <- h2o.glm(
x = x,
y = y,
training_frame = train_h2o,
family = "binomial",
seed = 123
)## | | | 0% | |======================================================================| 100%# Predict on test set
predictions <- h2o.predict(h2o_model, test_h2o)## | | | 0% | |======================================================================| 100%print(predictions) # Check output columns## predict No Yes
## 1 No 0.9743353 0.0256647194
## 2 No 0.9278288 0.0721712366
## 3 No 0.9325557 0.0674442703
## 4 No 0.9549825 0.0450175293
## 5 No 0.9225257 0.0774742801
## 6 No 0.9994963 0.0005037438
##
## [295 rows x 3 columns]# Convert predictions to tibble and merge with actual Attrition
pred_df <- as_tibble(predictions) %>%
bind_cols(test_data %>% select(Attrition)) %>%
rename(prob_attrition = Yes)
# Evaluate
conf_mat <- conf_mat(pred_df, truth = Attrition, estimate = predict)
print(conf_mat)## Truth
## Prediction No Yes
## No 225 20
## Yes 22 28# View sample predictions
pred_df %>% select(Attrition, predict, prob_attrition) %>% head()## # A tibble: 6 × 3
## Attrition predict prob_attrition
## <fct> <fct> <dbl>
## 1 No No 0.0257
## 2 No No 0.0722
## 3 No No 0.0674
## 4 No No 0.0450
## 5 No No 0.0775
## 6 No No 0.000504