Goal is to automate building and tuning a classification model to predict employee attrition, using the h2o::h2o.automl.
Import the cleaned data from Module 7.
library(h2o)## Warning: package 'h2o' was built under R version 4.5.3##
## ----------------------------------------------------------------------
##
## 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: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(tidyverse)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.0 ✔ stringr 1.5.2
## ✔ ggplot2 4.0.0 ✔ tibble 3.3.0
## ✔ lubridate 1.9.4 ✔ tidyr 1.3.1
## ✔ purrr 1.1.0## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ lubridate::day() masks h2o::day()
## ✖ dplyr::filter() masks stats::filter()
## ✖ lubridate::hour() masks h2o::hour()
## ✖ dplyr::lag() masks stats::lag()
## ✖ lubridate::month() masks h2o::month()
## ✖ lubridate::week() masks h2o::week()
## ✖ lubridate::year() masks h2o::year()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errorslibrary(tidymodels)## Warning: package 'tidymodels' was built under R version 4.5.2## ── Attaching packages ────────────────────────────────────── tidymodels 1.4.1 ──
## ✔ broom 1.0.10 ✔ rsample 1.3.1
## ✔ dials 1.4.2 ✔ tailor 0.1.0
## ✔ infer 1.1.0 ✔ tune 2.0.1
## ✔ modeldata 1.5.1 ✔ workflows 1.3.0
## ✔ parsnip 1.4.1 ✔ workflowsets 1.1.1
## ✔ recipes 1.3.1 ✔ yardstick 1.3.2## Warning: package 'dials' was built under R version 4.5.2## Warning: package 'infer' was built under R version 4.5.2## Warning: package 'modeldata' was built under R version 4.5.2## Warning: package 'parsnip' was built under R version 4.5.2## Warning: package 'tailor' was built under R version 4.5.2## Warning: package 'tune' was built under R version 4.5.2## Warning: package 'workflows' was built under R version 4.5.2## Warning: package 'workflowsets' was built under R version 4.5.2## Warning: package 'yardstick' was built under R version 4.5.2## ── 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(tidyquant)## Registered S3 method overwritten by 'quantmod':
## method from
## as.zoo.data.frame zoo
## ── Attaching core tidyquant packages ─────────────────────── tidyquant 1.0.11 ──
## ✔ PerformanceAnalytics 2.0.8 ✔ TTR 0.24.4
## ✔ quantmod 0.4.28 ✔ xts 0.14.1── Conflicts ────────────────────────────────────────── tidyquant_conflicts() ──
## ✖ zoo::as.Date() masks base::as.Date()
## ✖ zoo::as.Date.numeric() masks base::as.Date.numeric()
## ✖ scales::col_factor() masks readr::col_factor()
## ✖ lubridate::day() masks h2o::day()
## ✖ scales::discard() masks purrr::discard()
## ✖ dplyr::filter() masks stats::filter()
## ✖ xts::first() masks dplyr::first()
## ✖ recipes::fixed() masks stringr::fixed()
## ✖ lubridate::hour() masks h2o::hour()
## ✖ dplyr::lag() masks stats::lag()
## ✖ xts::last() masks dplyr::last()
## ✖ PerformanceAnalytics::legend() masks graphics::legend()
## ✖ TTR::momentum() masks dials::momentum()
## ✖ lubridate::month() masks h2o::month()
## ✖ yardstick::spec() masks readr::spec()
## ✖ quantmod::summary() masks h2o::summary(), base::summary()
## ✖ lubridate::week() masks h2o::week()
## ✖ lubridate::year() masks h2o::year()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errorsdata <- read_csv("../00_data/data_wrangled/data_clean.csv") %>%
# h2o requires all variables to be either numeric or factors
mutate(across(where(is.character), factor))## Rows: 1470 Columns: 32
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (8): Attrition, BusinessTravel, Department, EducationField, Gender, Job...
## dbl (24): Age, DailyRate, DistanceFromHome, Education, EmployeeNumber, Envir...
##
## 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.set.seed(1234)
data_split <- initial_split(data, strata = "Attrition")
train_tbl <- training(data_split)
test_tbl <- testing(data_split)recipe_obj <- recipe(Attrition ~ ., data = train_tbl) %>%
# Remove zero variance variables
step_zv(all_predictors()) h2o.init()## Connection successful!
##
## R is connected to the H2O cluster:
## H2O cluster uptime: 23 minutes 21 seconds
## H2O cluster timezone: America/New_York
## H2O data parsing timezone: UTC
## H2O cluster version: 3.44.0.3
## H2O cluster version age: 2 years, 4 months and 5 days
## H2O cluster name: H2O_started_from_R_conno_nlb794
## H2O cluster total nodes: 1
## H2O cluster total memory: 7.80 GB
## H2O cluster total cores: 16
## H2O cluster allowed cores: 16
## H2O cluster healthy: TRUE
## H2O Connection ip: localhost
## H2O Connection port: 54321
## H2O Connection proxy: NA
## H2O Internal Security: FALSE
## R Version: R version 4.5.1 (2025-06-13 ucrt)## Warning in h2o.clusterInfo():
## Your H2O cluster version is (2 years, 4 months and 5 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# Recreate the H2O data frames (Required for the knit to work)
train_h2o <- as.h2o(train_tbl)## | | | 0% | |======================================================================| 100%test_h2o <- as.h2o(test_tbl)## | | | 0% | |======================================================================| 100%# Load the model HERE so it is available for the rest of the document
best_model <- h2o.loadModel("h2o_models/GLM_1_AutoML_1_20260426_150130")examine the output of h2o.automl
# This chunk was crashing because models_h2o does not exist.
# We will inspect best_model instead.
typeof(best_model)## [1] "S4"slotNames(best_model)## [1] "model_id" "algorithm" "parameters" "allparameters"
## [5] "params" "have_pojo" "have_mojo" "model"# Since we don't have the full leaderboard in this session,
# we can just print the best_model details.
print(best_model)## Model Details:
## ==============
##
## H2OBinomialModel: glm
## Model ID: GLM_1_AutoML_1_20260426_150130
## GLM Model: summary
## family link regularization
## 1 binomial logit Ridge ( lambda = 0.02062 )
## lambda_search
## 1 nlambda = 30, lambda.max = 6.2664, lambda.min = 0.02062, lambda.1se = -1.0
## number_of_predictors_total number_of_active_predictors number_of_iterations
## 1 52 52 26
## training_frame
## 1 AutoML_1_20260426_150130_training_train_tbl_sid_bb68_1
##
## Coefficients: glm coefficients
## names coefficients standardized_coefficients
## 1 Intercept 4.178306 -1.710400
## 2 JobRole.Healthcare Representative -0.143863 -0.143863
## 3 JobRole.Human Resources -0.009489 -0.009489
## 4 JobRole.Laboratory Technician 0.214816 0.214816
## 5 JobRole.Manager -0.044525 -0.044525
##
## ---
## names coefficients standardized_coefficients
## 48 TrainingTimesLastYear -0.149741 -0.195723
## 49 WorkLifeBalance -0.324669 -0.234313
## 50 YearsAtCompany 0.028538 0.178531
## 51 YearsInCurrentRole -0.079875 -0.286338
## 52 YearsSinceLastPromotion 0.090227 0.289193
## 53 YearsWithCurrManager -0.060290 -0.215217
##
## H2OBinomialMetrics: glm
## ** Reported on training data. **
##
## MSE: 0.09078449
## RMSE: 0.3013046
## LogLoss: 0.3125029
## Mean Per-Class Error: 0.225214
## AUC: 0.8636697
## AUCPR: 0.6985762
## Gini: 0.7273394
## R^2: 0.3399708
## Residual Deviance: 622.5058
## AIC: 728.5058
##
## Confusion Matrix (vertical: actual; across: predicted) for F1-optimal threshold:
## No Yes Error Rate
## No 787 45 0.054087 =45/832
## Yes 65 99 0.396341 =65/164
## Totals 852 144 0.110442 =110/996
##
## Maximum Metrics: Maximum metrics at their respective thresholds
## metric threshold value idx
## 1 max f1 0.329891 0.642857 105
## 2 max f2 0.223239 0.685841 166
## 3 max f0point5 0.439442 0.741870 64
## 4 max accuracy 0.439442 0.899598 64
## 5 max precision 0.884233 1.000000 0
## 6 max recall 0.011760 1.000000 389
## 7 max specificity 0.884233 1.000000 0
## 8 max absolute_mcc 0.431101 0.586395 67
## 9 max min_per_class_accuracy 0.184880 0.788462 194
## 10 max mean_per_class_accuracy 0.223239 0.803530 166
## 11 max tns 0.884233 832.000000 0
## 12 max fns 0.884233 163.000000 0
## 13 max fps 0.002109 832.000000 399
## 14 max tps 0.011760 164.000000 389
## 15 max tnr 0.884233 1.000000 0
## 16 max fnr 0.884233 0.993902 0
## 17 max fpr 0.002109 1.000000 399
## 18 max tpr 0.011760 1.000000 389
##
## Gains/Lift Table: Extract with `h2o.gainsLift(<model>, <data>)` or `h2o.gainsLift(<model>, valid=<T/F>, xval=<T/F>)`
## H2OBinomialMetrics: glm
## ** Reported on validation data. **
##
## MSE: 0.08834389
## RMSE: 0.297227
## LogLoss: 0.2999775
## Mean Per-Class Error: 0.1797659
## AUC: 0.8319398
## AUCPR: 0.5005051
## Gini: 0.6638796
## R^2: 0.1856259
## Residual Deviance: 62.99527
## AIC: 168.9953
##
## Confusion Matrix (vertical: actual; across: predicted) for F1-optimal threshold:
## No Yes Error Rate
## No 66 26 0.282609 =26/92
## Yes 1 12 0.076923 =1/13
## Totals 67 38 0.257143 =27/105
##
## Maximum Metrics: Maximum metrics at their respective thresholds
## metric threshold value idx
## 1 max f1 0.191749 0.470588 37
## 2 max f2 0.191749 0.666667 37
## 3 max f0point5 0.457402 0.606061 4
## 4 max accuracy 0.533539 0.904762 2
## 5 max precision 0.658813 1.000000 0
## 6 max recall 0.094711 1.000000 69
## 7 max specificity 0.658813 1.000000 0
## 8 max absolute_mcc 0.457402 0.459069 4
## 9 max min_per_class_accuracy 0.243975 0.769231 29
## 10 max mean_per_class_accuracy 0.191749 0.820234 37
## 11 max tns 0.658813 92.000000 0
## 12 max fns 0.658813 12.000000 0
## 13 max fps 0.008778 92.000000 104
## 14 max tps 0.094711 13.000000 69
## 15 max tnr 0.658813 1.000000 0
## 16 max fnr 0.658813 0.923077 0
## 17 max fpr 0.008778 1.000000 104
## 18 max tpr 0.094711 1.000000 69
##
## Gains/Lift Table: Extract with `h2o.gainsLift(<model>, <data>)` or `h2o.gainsLift(<model>, valid=<T/F>, xval=<T/F>)`# Evaluate the loaded model instead of models_h2o
typeof(best_model)## [1] "S4"slotNames(best_model)## [1] "model_id" "algorithm" "parameters" "allparameters"
## [5] "params" "have_pojo" "have_mojo" "model"# Run performance
performance_h2o <- h2o.performance(best_model, newdata = test_h2o)
h2o.auc(performance_h2o)## [1] 0.8392665h2o.confusionMatrix(performance_h2o)## Confusion Matrix (vertical: actual; across: predicted) for max f1 @ threshold = 0.336454545130086:
## No Yes Error Rate
## No 292 17 0.055016 =17/309
## Yes 27 33 0.450000 =27/60
## Totals 319 50 0.119241 =44/369predictions <- h2o.predict(best_model, newdata = test_h2o)## | | | 0% | |======================================================================| 100%predictions_tbl <- predictions %>%
as_tibble()
predictions_tbl %>%
bind_cols(test_tbl)## # A tibble: 369 × 35
## predict No Yes Age Attrition BusinessTravel DailyRate Department
## <fct> <dbl> <dbl> <dbl> <fct> <fct> <dbl> <fct>
## 1 No 0.821 0.179 59 No Travel_Rarely 1324 Research &…
## 2 No 0.920 0.0797 35 No Travel_Rarely 809 Research &…
## 3 No 0.891 0.109 34 No Travel_Rarely 1346 Research &…
## 4 No 0.811 0.189 22 No Non-Travel 1123 Research &…
## 5 No 0.974 0.0259 53 No Travel_Rarely 1219 Sales
## 6 No 0.967 0.0326 24 No Non-Travel 673 Research &…
## 7 No 0.898 0.102 21 No Travel_Rarely 391 Research &…
## 8 Yes 0.766 0.234 34 Yes Travel_Rarely 699 Research &…
## 9 No 0.996 0.00448 53 No Travel_Rarely 1282 Research &…
## 10 Yes 0.199 0.801 32 Yes Travel_Frequently 1125 Research &…
## # ℹ 359 more rows
## # ℹ 27 more variables: DistanceFromHome <dbl>, Education <dbl>,
## # EducationField <fct>, EmployeeNumber <dbl>, EnvironmentSatisfaction <dbl>,
## # Gender <fct>, HourlyRate <dbl>, JobInvolvement <dbl>, JobLevel <dbl>,
## # JobRole <fct>, JobSatisfaction <dbl>, MaritalStatus <fct>,
## # MonthlyIncome <dbl>, MonthlyRate <dbl>, NumCompaniesWorked <dbl>,
## # OverTime <fct>, PercentSalaryHike <dbl>, PerformanceRating <dbl>, …?h2o.performance## starting httpd help server ... doneperformance_h2o <- h2o.performance(best_model, newdata = test_h2o)
typeof(performance_h2o)## [1] "S4"slotNames(performance_h2o)## [1] "algorithm" "on_train" "on_valid" "on_xval" "metrics"performance_h2o@metrics## $model
## $model$`__meta`
## $model$`__meta`$schema_version
## [1] 3
##
## $model$`__meta`$schema_name
## [1] "ModelKeyV3"
##
## $model$`__meta`$schema_type
## [1] "Key<Model>"
##
##
## $model$name
## [1] "GLM_1_AutoML_1_20260426_150130"
##
## $model$type
## [1] "Key<Model>"
##
## $model$URL
## [1] "/3/Models/GLM_1_AutoML_1_20260426_150130"
##
##
## $model_checksum
## [1] "-8230819784329863776"
##
## $frame
## $frame$name
## [1] "test_tbl_sid_b9e7_3"
##
##
## $frame_checksum
## [1] "-54413681510283746"
##
## $description
## NULL
##
## $scoring_time
## [1] 1.777232e+12
##
## $predictions
## NULL
##
## $MSE
## [1] 0.09508623
##
## $RMSE
## [1] 0.3083606
##
## $nobs
## [1] 369
##
## $custom_metric_name
## NULL
##
## $custom_metric_value
## [1] 0
##
## $r2
## [1] 0.3016701
##
## $logloss
## [1] 0.3225875
##
## $AUC
## [1] 0.8392665
##
## $pr_auc
## [1] 0.6600645
##
## $Gini
## [1] 0.6785329
##
## $mean_per_class_error
## [1] 0.2525081
##
## $domain
## [1] "No" "Yes"
##
## $cm
## $cm$`__meta`
## $cm$`__meta`$schema_version
## [1] 3
##
## $cm$`__meta`$schema_name
## [1] "ConfusionMatrixV3"
##
## $cm$`__meta`$schema_type
## [1] "ConfusionMatrix"
##
##
## $cm$table
## Confusion Matrix: Row labels: Actual class; Column labels: Predicted class
## No Yes Error Rate
## No 292 17 0.0550 = 17 / 309
## Yes 27 33 0.4500 = 27 / 60
## Totals 319 50 0.1192 = 44 / 369
##
##
## $thresholds_and_metric_scores
## Metrics for Thresholds: Binomial metrics as a function of classification thresholds
## threshold f1 f2 f0point5 accuracy precision recall specificity
## 1 0.832201 0.032787 0.020747 0.078125 0.840108 1.000000 0.016667 1.000000
## 2 0.800675 0.064516 0.041322 0.147059 0.842818 1.000000 0.033333 1.000000
## 3 0.772351 0.095238 0.061728 0.208333 0.845528 1.000000 0.050000 1.000000
## 4 0.725671 0.125000 0.081967 0.263158 0.848238 1.000000 0.066667 1.000000
## 5 0.668013 0.153846 0.102041 0.312500 0.850949 1.000000 0.083333 1.000000
## absolute_mcc min_per_class_accuracy mean_per_class_accuracy tns fns fps tps
## 1 0.118299 0.016667 0.508333 309 59 0 1
## 2 0.167527 0.033333 0.516667 309 58 0 2
## 3 0.205458 0.050000 0.525000 309 57 0 3
## 4 0.237568 0.066667 0.533333 309 56 0 4
## 5 0.265973 0.083333 0.541667 309 55 0 5
## tnr fnr fpr tpr idx
## 1 1.000000 0.983333 0.000000 0.016667 0
## 2 1.000000 0.966667 0.000000 0.033333 1
## 3 1.000000 0.950000 0.000000 0.050000 2
## 4 1.000000 0.933333 0.000000 0.066667 3
## 5 1.000000 0.916667 0.000000 0.083333 4
##
## ---
## threshold f1 f2 f0point5 accuracy precision recall
## 364 0.006524 0.283019 0.496689 0.197889 0.176152 0.164835 1.000000
## 365 0.004485 0.282353 0.495868 0.197368 0.173442 0.164384 1.000000
## 366 0.004051 0.281690 0.495050 0.196850 0.170732 0.163934 1.000000
## 367 0.003614 0.281030 0.494234 0.196335 0.168022 0.163488 1.000000
## 368 0.003432 0.280374 0.493421 0.195822 0.165312 0.163043 1.000000
## 369 0.001492 0.279720 0.492611 0.195313 0.162602 0.162602 1.000000
## specificity absolute_mcc min_per_class_accuracy mean_per_class_accuracy tns
## 364 0.016181 0.051645 0.016181 0.508091 5
## 365 0.012945 0.046130 0.012945 0.506472 4
## 366 0.009709 0.039895 0.009709 0.504854 3
## 367 0.006472 0.032530 0.006472 0.503236 2
## 368 0.003236 0.022971 0.003236 0.501618 1
## 369 0.000000 0.000000 0.000000 0.500000 0
## fns fps tps tnr fnr fpr tpr idx
## 364 0 304 60 0.016181 0.000000 0.983819 1.000000 363
## 365 0 305 60 0.012945 0.000000 0.987055 1.000000 364
## 366 0 306 60 0.009709 0.000000 0.990291 1.000000 365
## 367 0 307 60 0.006472 0.000000 0.993528 1.000000 366
## 368 0 308 60 0.003236 0.000000 0.996764 1.000000 367
## 369 0 309 60 0.000000 0.000000 1.000000 1.000000 368
##
## $max_criteria_and_metric_scores
## Maximum Metrics: Maximum metrics at their respective thresholds
## metric threshold value idx
## 1 max f1 0.336455 0.600000 49
## 2 max f2 0.166653 0.652174 127
## 3 max f0point5 0.445676 0.697674 27
## 4 max accuracy 0.445676 0.891599 27
## 5 max precision 0.832201 1.000000 0
## 6 max recall 0.037474 1.000000 297
## 7 max specificity 0.832201 1.000000 0
## 8 max absolute_mcc 0.385320 0.541270 38
## 9 max min_per_class_accuracy 0.186496 0.766667 116
## 10 max mean_per_class_accuracy 0.261206 0.776699 74
## 11 max tns 0.832201 309.000000 0
## 12 max fns 0.832201 59.000000 0
## 13 max fps 0.001492 309.000000 368
## 14 max tps 0.037474 60.000000 297
## 15 max tnr 0.832201 1.000000 0
## 16 max fnr 0.832201 0.983333 0
## 17 max fpr 0.001492 1.000000 368
## 18 max tpr 0.037474 1.000000 297
##
## $gains_lift_table
## Gains/Lift Table: Avg response rate: 16.26 %, avg score: 16.46 %
## group cumulative_data_fraction lower_threshold lift cumulative_lift
## 1 1 0.01084011 0.686463 6.150000 6.150000
## 2 2 0.02168022 0.597920 6.150000 6.150000
## 3 3 0.03252033 0.578017 6.150000 6.150000
## 4 4 0.04065041 0.560962 4.100000 5.740000
## 5 5 0.05149051 0.511268 6.150000 5.826316
## 6 6 0.10027100 0.396418 3.075000 4.487838
## 7 7 0.15176152 0.308420 1.942105 3.624107
## 8 8 0.20054201 0.261886 2.050000 3.241216
## 9 9 0.30081301 0.192344 0.831081 2.437838
## 10 10 0.40108401 0.150235 0.831081 2.036149
## 11 11 0.50135501 0.113130 0.332432 1.695405
## 12 12 0.59891599 0.084068 0.341667 1.474887
## 13 13 0.69918699 0.057416 0.498649 1.334884
## 14 14 0.79945799 0.038044 0.498649 1.230000
## 15 15 0.89972900 0.024545 0.166216 1.111446
## 16 16 1.00000000 0.001492 0.000000 1.000000
## response_rate score cumulative_response_rate cumulative_score
## 1 1.000000 0.782724 1.000000 0.782724
## 2 1.000000 0.636409 1.000000 0.709567
## 3 1.000000 0.588227 1.000000 0.669120
## 4 0.666667 0.573292 0.933333 0.649955
## 5 1.000000 0.530102 0.947368 0.624722
## 6 0.500000 0.446798 0.729730 0.538165
## 7 0.315789 0.349397 0.589286 0.474119
## 8 0.333333 0.282186 0.527027 0.427432
## 9 0.135135 0.227361 0.396396 0.360742
## 10 0.135135 0.168011 0.331081 0.312559
## 11 0.054054 0.131943 0.275676 0.276436
## 12 0.055556 0.097622 0.239819 0.247308
## 13 0.081081 0.070694 0.217054 0.221979
## 14 0.081081 0.049383 0.200000 0.200332
## 15 0.027027 0.031515 0.180723 0.181518
## 16 0.000000 0.013105 0.162602 0.164631
## capture_rate cumulative_capture_rate gain cumulative_gain
## 1 0.066667 0.066667 515.000000 515.000000
## 2 0.066667 0.133333 515.000000 515.000000
## 3 0.066667 0.200000 515.000000 515.000000
## 4 0.033333 0.233333 310.000000 474.000000
## 5 0.066667 0.300000 515.000000 482.631579
## 6 0.150000 0.450000 207.500000 348.783784
## 7 0.100000 0.550000 94.210526 262.410714
## 8 0.100000 0.650000 105.000000 224.121622
## 9 0.083333 0.733333 -16.891892 143.783784
## 10 0.083333 0.816667 -16.891892 103.614865
## 11 0.033333 0.850000 -66.756757 69.540541
## 12 0.033333 0.883333 -65.833333 47.488688
## 13 0.050000 0.933333 -50.135135 33.488372
## 14 0.050000 0.983333 -50.135135 23.000000
## 15 0.016667 1.000000 -83.378378 11.144578
## 16 0.000000 1.000000 -100.000000 0.000000
## kolmogorov_smirnov
## 1 0.066667
## 2 0.133333
## 3 0.200000
## 4 0.230097
## 5 0.296764
## 6 0.417638
## 7 0.475566
## 8 0.536731
## 9 0.516505
## 10 0.496278
## 11 0.416343
## 12 0.339644
## 13 0.279612
## 14 0.219579
## 15 0.119741
## 16 0.000000
##
## $residual_deviance
## [1] 238.0696
##
## $null_deviance
## [1] 327.6531
##
## $AIC
## [1] 344.0696
##
## $loglikelihood
## [1] 0
##
## $null_degrees_of_freedom
## [1] 368
##
## $residual_degrees_of_freedom
## [1] 316h2o.auc(performance_h2o)## [1] 0.8392665h2o.confusionMatrix(performance_h2o)## Confusion Matrix (vertical: actual; across: predicted) for max f1 @ threshold = 0.336454545130086:
## No Yes Error Rate
## No 292 17 0.055016 =17/309
## Yes 27 33 0.450000 =27/60
## Totals 319 50 0.119241 =44/369h2o.metric(performance_h2o)## Metrics for Thresholds: Binomial metrics as a function of classification thresholds
## threshold f1 f2 f0point5 accuracy precision recall specificity
## 1 0.832201 0.032787 0.020747 0.078125 0.840108 1.000000 0.016667 1.000000
## 2 0.800675 0.064516 0.041322 0.147059 0.842818 1.000000 0.033333 1.000000
## 3 0.772351 0.095238 0.061728 0.208333 0.845528 1.000000 0.050000 1.000000
## 4 0.725671 0.125000 0.081967 0.263158 0.848238 1.000000 0.066667 1.000000
## 5 0.668013 0.153846 0.102041 0.312500 0.850949 1.000000 0.083333 1.000000
## absolute_mcc min_per_class_accuracy mean_per_class_accuracy tns fns fps tps
## 1 0.118299 0.016667 0.508333 309 59 0 1
## 2 0.167527 0.033333 0.516667 309 58 0 2
## 3 0.205458 0.050000 0.525000 309 57 0 3
## 4 0.237568 0.066667 0.533333 309 56 0 4
## 5 0.265973 0.083333 0.541667 309 55 0 5
## tnr fnr fpr tpr idx
## 1 1.000000 0.983333 0.000000 0.016667 0
## 2 1.000000 0.966667 0.000000 0.033333 1
## 3 1.000000 0.950000 0.000000 0.050000 2
## 4 1.000000 0.933333 0.000000 0.066667 3
## 5 1.000000 0.916667 0.000000 0.083333 4
##
## ---
## threshold f1 f2 f0point5 accuracy precision recall
## 364 0.006524 0.283019 0.496689 0.197889 0.176152 0.164835 1.000000
## 365 0.004485 0.282353 0.495868 0.197368 0.173442 0.164384 1.000000
## 366 0.004051 0.281690 0.495050 0.196850 0.170732 0.163934 1.000000
## 367 0.003614 0.281030 0.494234 0.196335 0.168022 0.163488 1.000000
## 368 0.003432 0.280374 0.493421 0.195822 0.165312 0.163043 1.000000
## 369 0.001492 0.279720 0.492611 0.195313 0.162602 0.162602 1.000000
## specificity absolute_mcc min_per_class_accuracy mean_per_class_accuracy tns
## 364 0.016181 0.051645 0.016181 0.508091 5
## 365 0.012945 0.046130 0.012945 0.506472 4
## 366 0.009709 0.039895 0.009709 0.504854 3
## 367 0.006472 0.032530 0.006472 0.503236 2
## 368 0.003236 0.022971 0.003236 0.501618 1
## 369 0.000000 0.000000 0.000000 0.500000 0
## fns fps tps tnr fnr fpr tpr idx
## 364 0 304 60 0.016181 0.000000 0.983819 1.000000 363
## 365 0 305 60 0.012945 0.000000 0.987055 1.000000 364
## 366 0 306 60 0.009709 0.000000 0.990291 1.000000 365
## 367 0 307 60 0.006472 0.000000 0.993528 1.000000 366
## 368 0 308 60 0.003236 0.000000 0.996764 1.000000 367
## 369 0 309 60 0.000000 0.000000 1.000000 1.000000 368