code along 12: chat gpt

load data

attrition_raw_tbl <- read_csv("/Users/owner/Desktop/PSU_Data3100/00_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>

Initialize H2O

h2o.init()

##  Connection successful!
## 
## R is connected to the H2O cluster: 
##     H2O cluster uptime:         6 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 10 days 
##     H2O cluster name:           H2O_started_from_R_owner_dit581 
##     H2O cluster total nodes:    1 
##     H2O cluster total memory:   1.29 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 4.3.1 (2023-06-16)

## Warning in h2o.clusterInfo(): 
## Your H2O cluster version is (1 year, 4 months and 10 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

Clean dataset

attrition_tbl <- attrition_raw_tbl %>%
  select(-EmployeeCount, -StandardHours, -Over18, -EmployeeNumber) %>%
  mutate(Attrition = as.factor(Attrition)) %>%
  mutate_if(is.character, as.factor)

Split data

set.seed(123)
attrition_split <- initial_split(attrition_tbl, prop = 0.8, strata = Attrition)
train_tbl <- training(attrition_split)
test_tbl  <- testing(attrition_split)

Step 1: Recipe for preprocessing

attrition_recipe <- recipe(Attrition ~ ., data = train_tbl) %>%
  step_dummy(all_nominal_predictors()) %>%
  step_zv(all_predictors()) %>%
  step_normalize(all_numeric_predictors()) %>%
  prep()

train_preprocessed <- bake(attrition_recipe, new_data = train_tbl)
test_preprocessed  <- bake(attrition_recipe, new_data = test_tbl)

Step 2: Convert to H2O frames

train_h2o <- as.h2o(train_preprocessed)

## 
  |                                                                            
  |                                                                      |   0%
  |                                                                            
  |======================================================================| 100%

test_h2o  <- as.h2o(test_preprocessed)

## 
  |                                                                            
  |                                                                      |   0%
  |                                                                            
  |======================================================================| 100%

Step 3: Train H2O GBM model

h2o_model <- h2o.gbm(
  x = setdiff(names(train_h2o), "Attrition"),
  y = "Attrition",
  training_frame = train_h2o,
  model_id = "h2o_gbm_model",
  seed = 1234
)

## 
  |                                                                            
  |                                                                      |   0%
  |                                                                            
  |======================================================================| 100%

Step 4: Performance Evaluation using h2o.performance()

perf <- h2o.performance(h2o_model, newdata = test_h2o)

Print metrics

print(perf)

## H2OBinomialMetrics: gbm
## 
## MSE:  0.0962407
## RMSE:  0.3102269
## LogLoss:  0.3111299
## Mean Per-Class Error:  0.168944
## AUC:  0.8718792
## AUCPR:  0.5822296
## Gini:  0.7437584
## R^2:  0.2935773
## 
## Confusion Matrix (vertical: actual; across: predicted) for F1-optimal threshold:
##         No Yes    Error     Rate
## No     215  32 0.129555  =32/247
## Yes     10  38 0.208333   =10/48
## Totals 225  70 0.142373  =42/295
## 
## Maximum Metrics: Maximum metrics at their respective thresholds
##                         metric threshold      value idx
## 1                       max f1  0.217794   0.644068  69
## 2                       max f2  0.217794   0.725191  69
## 3                 max f0point5  0.370974   0.611702  34
## 4                 max accuracy  0.370974   0.874576  34
## 5                max precision  0.963428   1.000000   0
## 6                   max recall  0.028507   1.000000 244
## 7              max specificity  0.963428   1.000000   0
## 8             max absolute_mcc  0.217794   0.574461  69
## 9   max min_per_class_accuracy  0.156380   0.801619  87
## 10 max mean_per_class_accuracy  0.217794   0.831056  69
## 11                     max tns  0.963428 247.000000   0
## 12                     max fns  0.963428  47.000000   0
## 13                     max fps  0.006412 247.000000 294
## 14                     max tps  0.028507  48.000000 244
## 15                     max tnr  0.963428   1.000000   0
## 16                     max fnr  0.963428   0.979167   0
## 17                     max fpr  0.006412   1.000000 294
## 18                     max tpr  0.028507   1.000000 244
## 
## Gains/Lift Table: Extract with `h2o.gainsLift(<model>, <data>)` or `h2o.gainsLift(<model>, valid=<T/F>, xval=<T/F>)`

AUC

h2o.auc(perf)

## [1] 0.8718792

Confusion matrix

h2o.confusionMatrix(perf)

## Confusion Matrix (vertical: actual; across: predicted)  for max f1 @ threshold = 0.217794387292298:
##         No Yes    Error     Rate
## No     215  32 0.129555  =32/247
## Yes     10  38 0.208333   =10/48
## Totals 225  70 0.142373  =42/295

ROC Curve (plot)

plot(perf, type = "roc")

Step 5: Predict Probabilities

predictions <- h2o.predict(h2o_model, test_h2o)

## 
  |                                                                            
  |                                                                      |   0%
  |                                                                            
  |======================================================================| 100%

head(predictions)

##   predict        No        Yes
## 1      No 0.9382303 0.06176966
## 2      No 0.9573292 0.04267083
## 3      No 0.9389149 0.06108513
## 4      No 0.9736064 0.02639359
## 5     Yes 0.6792807 0.32071926
## 6      No 0.9769874 0.02301263