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 4.3.3##
## ----------------------------------------------------------------------
##
## 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)## Warning: package 'purrr' was built under R version 4.3.3## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.4
## ✔ forcats 1.0.0 ✔ stringr 1.5.0
## ✔ ggplot2 3.5.1 ✔ tibble 3.2.1
## ✔ lubridate 1.9.2 ✔ tidyr 1.3.1
## ✔ purrr 1.0.4## ── 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 4.3.3## ── Attaching packages ────────────────────────────────────── tidymodels 1.3.0 ──
## ✔ broom 1.0.7 ✔ rsample 1.2.1
## ✔ dials 1.4.0 ✔ tune 1.3.0
## ✔ infer 1.0.7 ✔ workflows 1.2.0
## ✔ modeldata 1.4.0 ✔ workflowsets 1.1.0
## ✔ parsnip 1.3.0 ✔ yardstick 1.3.2
## ✔ recipes 1.1.1## Warning: package 'broom' was built under R version 4.3.3## Warning: package 'dials' was built under R version 4.3.3## Warning: package 'scales' was built under R version 4.3.3## Warning: package 'modeldata' was built under R version 4.3.3## Warning: package 'parsnip' was built under R version 4.3.3## Warning: package 'recipes' was built under R version 4.3.3## Warning: package 'tune' was built under R version 4.3.3## Warning: package 'workflows' was built under R version 4.3.3## Warning: package 'yardstick' was built under R version 4.3.3## ── 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)## Loading required package: PerformanceAnalytics
## Loading required package: xts
## Loading required package: zoo
##
## Attaching package: 'zoo'
##
## The following objects are masked from 'package:base':
##
## as.Date, as.Date.numeric
##
##
## ######################### Warning from 'xts' package ##########################
## # #
## # The dplyr lag() function breaks how base R's lag() function is supposed to #
## # work, which breaks lag(my_xts). Calls to lag(my_xts) that you type or #
## # source() into this session won't work correctly. #
## # #
## # Use stats::lag() to make sure you're not using dplyr::lag(), or you can add #
## # conflictRules('dplyr', exclude = 'lag') to your .Rprofile to stop #
## # dplyr from breaking base R's lag() function. #
## # #
## # Code in packages is not affected. It's protected by R's namespace mechanism #
## # Set `options(xts.warn_dplyr_breaks_lag = FALSE)` to suppress this warning. #
## # #
## ###############################################################################
##
## Attaching package: 'xts'
##
## The following objects are masked from 'package:dplyr':
##
## first, last
##
##
## Attaching package: 'PerformanceAnalytics'
##
## The following object is masked from 'package:graphics':
##
## legend
##
## Loading required package: quantmod
## Loading required package: TTR
##
## Attaching package: 'TTR'
##
## The following object is masked from 'package:dials':
##
## momentum
##
## Registered S3 method overwritten by 'quantmod':
## method from
## as.zoo.data.frame zoodata <- 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()) # Initialize h2o
h2o.init()## Connection successful!
##
## R is connected to the H2O cluster:
## H2O cluster uptime: 1 hours 27 minutes
## 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 3 days
## H2O cluster name: H2O_started_from_R_owner_dit581
## H2O cluster total nodes: 1
## H2O cluster total memory: 1.32 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 3 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.htmlsplit.h2o <- h2o.splitFrame(as.h2o(train_tbl), ratio = c(0.85), seed = 2345)##
|
| | 0%
|
|======================================================================| 100%train_h2o <- split.h2o[[1]]
valid_h2o <- split.h2o[[2]]
test_h2o <- as.h2o(test_tbl)##
|
| | 0%
|
|======================================================================| 100%y <- "Attrition"
x <- setdiff(names(train_tbl), y)
models_h2o <-h2o.automl(
x = x,
y = y,
training_frame = train_h2o,
validation_frame = valid_h2o,
leaderboard_frame = test_h2o,
# max_runtime_secs = 30,
max_models = 10,
exclude_algos = "DeepLearning",
nfolds = 5,
seed = 3456
)##
|
| | 0%
|
|====== | 8%
## 18:56:46.364: User specified a validation frame with cross-validation still enabled. Please note that the models will still be validated using cross-validation only, the validation frame will be used to provide purely informative validation metrics on the trained models.
## 18:56:46.367: AutoML: XGBoost is not available; skipping it.
|
|======================= | 33%
|
|======================================================================| 100%Examine the output of h20.automl
models_h2o %>% typeof()## [1] "S4"models_h2o %>% slotNames()## [1] "project_name" "leader" "leaderboard" "event_log"
## [5] "modeling_steps" "training_info"models_h2o@leaderboard## model_id auc logloss
## 1 StackedEnsemble_BestOfFamily_1_AutoML_12_20250423_185646 0.8281014 0.3298632
## 2 GLM_1_AutoML_12_20250423_185646 0.8261597 0.3318676
## 3 StackedEnsemble_AllModels_1_AutoML_12_20250423_185646 0.8250809 0.3301943
## 4 GBM_4_AutoML_12_20250423_185646 0.8185545 0.3461163
## 5 DRF_1_AutoML_12_20250423_185646 0.8015102 0.3538021
## 6 GBM_1_AutoML_12_20250423_185646 0.8011866 0.3513716
## aucpr mean_per_class_error rmse mse
## 1 0.9448252 0.2997573 0.3097286 0.09593178
## 2 0.9466326 0.2930421 0.3082111 0.09499409
## 3 0.9461063 0.2946602 0.3112418 0.09687146
## 4 0.9565239 0.3446602 0.3221756 0.10379710
## 5 0.9504370 0.3898058 0.3295324 0.10859158
## 6 0.9481461 0.3478964 0.3268063 0.10680236
##
## [12 rows x 7 columns]models_h2o@leader## Model Details:
## ==============
##
## H2OBinomialModel: stackedensemble
## Model ID: StackedEnsemble_BestOfFamily_1_AutoML_12_20250423_185646
## Model Summary for Stacked Ensemble:
## key value
## 1 Stacking strategy cross_validation
## 2 Number of base models (used / total) 3/4
## 3 # GBM base models (used / total) 1/1
## 4 # GLM base models (used / total) 1/1
## 5 # DRF base models (used / total) 1/2
## 6 Metalearner algorithm GLM
## 7 Metalearner fold assignment scheme Random
## 8 Metalearner nfolds 5
## 9 Metalearner fold_column NA
## 10 Custom metalearner hyperparameters None
##
##
## H2OBinomialMetrics: stackedensemble
## ** Reported on training data. **
##
## MSE: 0.02949019
## RMSE: 0.1717271
## LogLoss: 0.1317953
## Mean Per-Class Error: 0.04117981
## AUC: 0.9913543
## AUCPR: 0.998036
## Gini: 0.9827085
##
## Confusion Matrix (vertical: actual; across: predicted) for F1-optimal threshold:
## Left No Error Rate
## Left 146 12 0.075949 =12/158
## No 5 775 0.006410 =5/780
## Totals 151 787 0.018124 =17/938
##
## Maximum Metrics: Maximum metrics at their respective thresholds
## metric threshold value idx
## 1 max f1 0.606032 0.989151 280
## 2 max f2 0.491206 0.993377 296
## 3 max f0point5 0.612457 0.987245 278
## 4 max accuracy 0.612457 0.981876 278
## 5 max precision 0.999826 1.000000 0
## 6 max recall 0.491206 1.000000 296
## 7 max specificity 0.999826 1.000000 0
## 8 max absolute_mcc 0.612457 0.934652 278
## 9 max min_per_class_accuracy 0.762957 0.955128 248
## 10 max mean_per_class_accuracy 0.701173 0.963145 265
## 11 max tns 0.999826 158.000000 0
## 12 max fns 0.999826 779.000000 0
## 13 max fps 0.020079 158.000000 399
## 14 max tps 0.491206 780.000000 296
## 15 max tnr 0.999826 1.000000 0
## 16 max fnr 0.999826 0.998718 0
## 17 max fpr 0.020079 1.000000 399
## 18 max tpr 0.491206 1.000000 296
##
## Gains/Lift Table: Extract with `h2o.gainsLift(<model>, <data>)` or `h2o.gainsLift(<model>, valid=<T/F>, xval=<T/F>)`
## H2OBinomialMetrics: stackedensemble
## ** Reported on validation data. **
##
## MSE: 0.08616319
## RMSE: 0.2935357
## LogLoss: 0.3038717
## Mean Per-Class Error: 0.3192617
## AUC: 0.7613304
## AUCPR: 0.9570023
## Gini: 0.5226608
##
## Confusion Matrix (vertical: actual; across: predicted) for F1-optimal threshold:
## Left No Error Rate
## Left 7 12 0.631579 =12/19
## No 1 143 0.006944 =1/144
## Totals 8 155 0.079755 =13/163
##
## Maximum Metrics: Maximum metrics at their respective thresholds
## metric threshold value idx
## 1 max f1 0.444752 0.956522 154
## 2 max f2 0.221461 0.979592 158
## 3 max f0point5 0.444752 0.935864 154
## 4 max accuracy 0.444752 0.920245 154
## 5 max precision 0.998253 1.000000 0
## 6 max recall 0.221461 1.000000 158
## 7 max specificity 0.998253 1.000000 0
## 8 max absolute_mcc 0.444752 0.536942 154
## 9 max min_per_class_accuracy 0.896025 0.631579 97
## 10 max mean_per_class_accuracy 0.927727 0.721674 80
## 11 max tns 0.998253 19.000000 0
## 12 max fns 0.998253 143.000000 0
## 13 max fps 0.032182 19.000000 162
## 14 max tps 0.221461 144.000000 158
## 15 max tnr 0.998253 1.000000 0
## 16 max fnr 0.998253 0.993056 0
## 17 max fpr 0.032182 1.000000 162
## 18 max tpr 0.221461 1.000000 158
##
## Gains/Lift Table: Extract with `h2o.gainsLift(<model>, <data>)` or `h2o.gainsLift(<model>, valid=<T/F>, xval=<T/F>)`
## H2OBinomialMetrics: stackedensemble
## ** Reported on cross-validation data. **
## ** 5-fold cross-validation on training data (Metrics computed for combined holdout predictions) **
##
## MSE: 0.09307648
## RMSE: 0.3050844
## LogLoss: 0.320178
## Mean Per-Class Error: 0.2351428
## AUC: 0.8503935
## AUCPR: 0.9504109
## Gini: 0.7007871
##
## Confusion Matrix (vertical: actual; across: predicted) for F1-optimal threshold:
## Left No Error Rate
## Left 92 66 0.417722 =66/158
## No 41 739 0.052564 =41/780
## Totals 133 805 0.114072 =107/938
##
## Maximum Metrics: Maximum metrics at their respective thresholds
## metric threshold value idx
## 1 max f1 0.618114 0.932492 284
## 2 max f2 0.200849 0.964109 382
## 3 max f0point5 0.748316 0.925926 231
## 4 max accuracy 0.624335 0.885928 283
## 5 max precision 0.999875 1.000000 0
## 6 max recall 0.157833 1.000000 387
## 7 max specificity 0.999875 1.000000 0
## 8 max absolute_mcc 0.624335 0.570179 283
## 9 max min_per_class_accuracy 0.838339 0.784810 182
## 10 max mean_per_class_accuracy 0.748316 0.799821 231
## 11 max tns 0.999875 158.000000 0
## 12 max fns 0.999875 778.000000 0
## 13 max fps 0.019574 158.000000 399
## 14 max tps 0.157833 780.000000 387
## 15 max tnr 0.999875 1.000000 0
## 16 max fnr 0.999875 0.997436 0
## 17 max fpr 0.019574 1.000000 399
## 18 max tpr 0.157833 1.000000 387
##
## Gains/Lift Table: Extract with `h2o.gainsLift(<model>, <data>)` or `h2o.gainsLift(<model>, valid=<T/F>, xval=<T/F>)`
## Cross-Validation Metrics Summary:
## mean sd cv_1_valid cv_2_valid cv_3_valid cv_4_valid
## accuracy 0.899819 0.024623 0.903846 0.871134 0.888268 0.897959
## auc 0.864869 0.047371 0.850010 0.802424 0.860119 0.878811
## err 0.100181 0.024623 0.096154 0.128866 0.111732 0.102041
## err_count 19.000000 5.477226 20.000000 25.000000 20.000000 20.000000
## f0point5 0.922746 0.021448 0.918782 0.895062 0.911458 0.942118
## cv_5_valid
## accuracy 0.937888
## auc 0.932979
## err 0.062112
## err_count 10.000000
## f0point5 0.946309
##
## ---
## mean sd cv_1_valid cv_2_valid cv_3_valid
## precision 0.910988 0.027245 0.900497 0.878788 0.897436
## r2 0.331436 0.065145 0.295306 0.253730 0.366695
## recall 0.974363 0.027818 1.000000 0.966667 0.972222
## residual_deviance 118.659770 34.186165 114.189445 168.070180 119.287560
## rmse 0.303038 0.041184 0.282136 0.361758 0.315623
## specificity 0.513264 0.164948 0.259259 0.545455 0.542857
## cv_4_valid cv_5_valid
## precision 0.944444 0.933775
## r2 0.319239 0.422210
## recall 0.932927 1.000000
## residual_deviance 120.112110 71.639560
## rmse 0.304957 0.250717
## specificity 0.718750 0.500000?h2o.getModel
?h2o.saveModel
?h2o.loadModel
# Get the model
model <- h2o.getModel("GLM_1_AutoML_7_20250423_184159")
# Save it and capture the full path
model_path <- h2o.saveModel(object = model, path = "h2o_models/", force = TRUE)
# Load the model using the full path returned by saveModel
best_model <- h2o.loadModel(model_path)predictions <- 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 Left No Age Attrition BusinessTravel DailyRate Department
## <fct> <dbl> <dbl> <dbl> <fct> <fct> <dbl> <fct>
## 1 No 0.598 0.402 41 Left Travel_Rarely 1102 Sales
## 2 No 0.0157 0.984 49 No Travel_Frequently 279 Research & …
## 3 No 0.224 0.776 33 No Travel_Frequently 1392 Research & …
## 4 No 0.102 0.898 59 No Travel_Rarely 1324 Research & …
## 5 No 0.0510 0.949 38 No Travel_Frequently 216 Research & …
## 6 No 0.196 0.804 29 No Travel_Rarely 153 Research & …
## 7 No 0.0660 0.934 34 No Travel_Rarely 1346 Research & …
## 8 Left 0.812 0.188 28 Left Travel_Rarely 103 Research & …
## 9 No 0.172 0.828 22 No Non-Travel 1123 Research & …
## 10 No 0.0157 0.984 53 No Travel_Rarely 1219 Sales
## # 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
performance_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_7_20250423_184159"
##
## $model$type
## [1] "Key<Model>"
##
## $model$URL
## [1] "/3/Models/GLM_1_AutoML_7_20250423_184159"
##
##
## $model_checksum
## [1] "-12973514516557616"
##
## $frame
## $frame$name
## [1] "test_tbl_sid_9222_3"
##
##
## $frame_checksum
## [1] "-54192601206779456"
##
## $description
## NULL
##
## $scoring_time
## [1] 1.745449e+12
##
## $predictions
## NULL
##
## $MSE
## [1] 0.09499409
##
## $RMSE
## [1] 0.3082111
##
## $nobs
## [1] 369
##
## $custom_metric_name
## NULL
##
## $custom_metric_value
## [1] 0
##
## $r2
## [1] 0.3023468
##
## $logloss
## [1] 0.3318676
##
## $AUC
## [1] 0.8261597
##
## $pr_auc
## [1] 0.9466326
##
## $Gini
## [1] 0.6523193
##
## $mean_per_class_error
## [1] 0.2930421
##
## $domain
## [1] "Left" "No"
##
## $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
## Left No Error Rate
## Left 26 34 0.5667 = 34 / 60
## No 6 303 0.0194 = 6 / 309
## Totals 32 337 0.1084 = 40 / 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 0.999147 0.006452 0.004042 0.015974 0.165312 1.000000 0.003236 1.000000
## 2 0.999111 0.012862 0.008078 0.031546 0.168022 1.000000 0.006472 1.000000
## 3 0.998745 0.019231 0.012107 0.046729 0.170732 1.000000 0.009709 1.000000
## 4 0.998165 0.025559 0.016129 0.061538 0.173442 1.000000 0.012945 1.000000
## 5 0.998139 0.031847 0.020145 0.075988 0.176152 1.000000 0.016181 1.000000
## absolute_mcc min_per_class_accuracy mean_per_class_accuracy tns fns fps tps
## 1 0.022971 0.003236 0.501618 60 308 0 1
## 2 0.032530 0.006472 0.503236 60 307 0 2
## 3 0.039895 0.009709 0.504854 60 306 0 3
## 4 0.046130 0.012945 0.506472 60 305 0 4
## 5 0.051645 0.016181 0.508091 60 304 0 5
## tnr fnr fpr tpr idx
## 1 1.000000 0.996764 0.000000 0.003236 0
## 2 1.000000 0.993528 0.000000 0.006472 1
## 3 1.000000 0.990291 0.000000 0.009709 2
## 4 1.000000 0.987055 0.000000 0.012945 3
## 5 1.000000 0.983819 0.000000 0.016181 4
##
## ---
## threshold f1 f2 f0point5 accuracy precision recall
## 364 0.216780 0.918276 0.965625 0.875354 0.850949 0.848901 1.000000
## 365 0.192384 0.916914 0.965022 0.873375 0.848238 0.846575 1.000000
## 366 0.187703 0.915556 0.964419 0.871404 0.845528 0.844262 1.000000
## 367 0.187543 0.914201 0.963818 0.869443 0.842818 0.841962 1.000000
## 368 0.103516 0.912851 0.963217 0.867490 0.840108 0.839674 1.000000
## 369 0.063278 0.911504 0.962617 0.865546 0.837398 0.837398 1.000000
## specificity absolute_mcc min_per_class_accuracy mean_per_class_accuracy tns
## 364 0.083333 0.265973 0.083333 0.541667 5
## 365 0.066667 0.237568 0.066667 0.533333 4
## 366 0.050000 0.205458 0.050000 0.525000 3
## 367 0.033333 0.167527 0.033333 0.516667 2
## 368 0.016667 0.118299 0.016667 0.508333 1
## 369 0.000000 0.000000 0.000000 0.500000 0
## fns fps tps tnr fnr fpr tpr idx
## 364 0 55 309 0.083333 0.000000 0.916667 1.000000 363
## 365 0 56 309 0.066667 0.000000 0.933333 1.000000 364
## 366 0 57 309 0.050000 0.000000 0.950000 1.000000 365
## 367 0 58 309 0.033333 0.000000 0.966667 1.000000 366
## 368 0 59 309 0.016667 0.000000 0.983333 1.000000 367
## 369 0 60 309 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 0.445251 0.938080 336
## 2 max f2 0.267535 0.968045 359
## 3 max f0point5 0.521329 0.921459 326
## 4 max accuracy 0.521329 0.891599 326
## 5 max precision 0.999147 1.000000 0
## 6 max recall 0.267535 1.000000 359
## 7 max specificity 0.999147 1.000000 0
## 8 max absolute_mcc 0.521329 0.558937 326
## 9 max min_per_class_accuracy 0.836479 0.754045 246
## 10 max mean_per_class_accuracy 0.784532 0.777670 269
## 11 max tns 0.999147 60.000000 0
## 12 max fns 0.999147 308.000000 0
## 13 max fps 0.063278 60.000000 368
## 14 max tps 0.267535 309.000000 359
## 15 max tnr 0.999147 1.000000 0
## 16 max fnr 0.999147 0.996764 0
## 17 max fpr 0.063278 1.000000 368
## 18 max tpr 0.267535 1.000000 359
##
## $gains_lift_table
## Gains/Lift Table: Avg response rate: 83.74 %, avg score: 83.06 %
## group cumulative_data_fraction lower_threshold lift cumulative_lift
## 1 1 0.01084011 0.998147 1.194175 1.194175
## 2 2 0.02168022 0.997265 1.194175 1.194175
## 3 3 0.03252033 0.996151 1.194175 1.194175
## 4 4 0.04065041 0.995337 1.194175 1.194175
## 5 5 0.05149051 0.994691 1.194175 1.194175
## 6 6 0.10027100 0.989476 1.061489 1.129625
## 7 7 0.15176152 0.984289 1.194175 1.151526
## 8 8 0.20054201 0.977722 1.127832 1.145762
## 9 9 0.30081301 0.965114 1.129625 1.140383
## 10 10 0.40108401 0.940621 1.129625 1.137694
## 11 11 0.50135501 0.905086 1.129625 1.136080
## 12 12 0.59891599 0.872833 1.094660 1.129333
## 13 13 0.69918699 0.805557 1.097350 1.124746
## 14 14 0.79945799 0.722768 0.903700 1.097022
## 15 15 0.89972900 0.481063 0.903700 1.075477
## 16 16 1.00000000 0.063278 0.322750 1.000000
## response_rate score cumulative_response_rate cumulative_score
## 1 1.000000 0.998792 1.000000 0.998792
## 2 1.000000 0.997532 1.000000 0.998162
## 3 1.000000 0.996595 1.000000 0.997640
## 4 1.000000 0.995419 1.000000 0.997195
## 5 1.000000 0.995147 1.000000 0.996764
## 6 0.888889 0.992093 0.945946 0.994492
## 7 1.000000 0.986868 0.964286 0.991905
## 8 0.944444 0.981369 0.959459 0.989342
## 9 0.945946 0.971666 0.954955 0.983450
## 10 0.945946 0.952813 0.952703 0.975791
## 11 0.945946 0.924508 0.951351 0.965534
## 12 0.916667 0.891392 0.945701 0.953457
## 13 0.918919 0.846932 0.941860 0.938180
## 14 0.756757 0.773947 0.918644 0.917581
## 15 0.756757 0.623841 0.900602 0.884845
## 16 0.270270 0.344159 0.837398 0.830630
## capture_rate cumulative_capture_rate gain cumulative_gain
## 1 0.012945 0.012945 19.417476 19.417476
## 2 0.012945 0.025890 19.417476 19.417476
## 3 0.012945 0.038835 19.417476 19.417476
## 4 0.009709 0.048544 19.417476 19.417476
## 5 0.012945 0.061489 19.417476 19.417476
## 6 0.051780 0.113269 6.148867 12.962477
## 7 0.061489 0.174757 19.417476 15.152566
## 8 0.055016 0.229773 12.783172 14.576227
## 9 0.113269 0.343042 12.962477 14.038310
## 10 0.113269 0.456311 12.962477 13.769352
## 11 0.113269 0.569579 12.962477 13.607977
## 12 0.106796 0.676375 9.466019 12.933269
## 13 0.110032 0.786408 9.734978 12.474599
## 14 0.090615 0.877023 -9.630018 9.702156
## 15 0.090615 0.967638 -9.630018 7.547666
## 16 0.032362 1.000000 -67.725007 0.000000
## kolmogorov_smirnov
## 1 0.012945
## 2 0.025890
## 3 0.038835
## 4 0.048544
## 5 0.061489
## 6 0.079935
## 7 0.141424
## 8 0.179773
## 9 0.259709
## 10 0.339644
## 11 0.419579
## 12 0.476375
## 13 0.536408
## 14 0.477023
## 15 0.417638
## 16 0.000000
##
## $residual_deviance
## [1] 244.9183
##
## $null_deviance
## [1] 327.7324
##
## $AIC
## [1] 350.9183
##
## $loglikelihood
## [1] 0
##
## $null_degrees_of_freedom
## [1] 368
##
## $residual_degrees_of_freedom
## [1] 316h2o.auc(performance_h2o)## [1] 0.8261597h2o.confusionMatrix(performance_h2o)## Confusion Matrix (vertical: actual; across: predicted) for max f1 @ threshold = 0.445250762165868:
## Left No Error Rate
## Left 26 34 0.566667 =34/60
## No 6 303 0.019417 =6/309
## Totals 32 337 0.108401 =40/369h2o.metric(performance_h2o)## Metrics for Thresholds: Binomial metrics as a function of classification thresholds
## threshold f1 f2 f0point5 accuracy precision recall specificity
## 1 0.999147 0.006452 0.004042 0.015974 0.165312 1.000000 0.003236 1.000000
## 2 0.999111 0.012862 0.008078 0.031546 0.168022 1.000000 0.006472 1.000000
## 3 0.998745 0.019231 0.012107 0.046729 0.170732 1.000000 0.009709 1.000000
## 4 0.998165 0.025559 0.016129 0.061538 0.173442 1.000000 0.012945 1.000000
## 5 0.998139 0.031847 0.020145 0.075988 0.176152 1.000000 0.016181 1.000000
## absolute_mcc min_per_class_accuracy mean_per_class_accuracy tns fns fps tps
## 1 0.022971 0.003236 0.501618 60 308 0 1
## 2 0.032530 0.006472 0.503236 60 307 0 2
## 3 0.039895 0.009709 0.504854 60 306 0 3
## 4 0.046130 0.012945 0.506472 60 305 0 4
## 5 0.051645 0.016181 0.508091 60 304 0 5
## tnr fnr fpr tpr idx
## 1 1.000000 0.996764 0.000000 0.003236 0
## 2 1.000000 0.993528 0.000000 0.006472 1
## 3 1.000000 0.990291 0.000000 0.009709 2
## 4 1.000000 0.987055 0.000000 0.012945 3
## 5 1.000000 0.983819 0.000000 0.016181 4
##
## ---
## threshold f1 f2 f0point5 accuracy precision recall
## 364 0.216780 0.918276 0.965625 0.875354 0.850949 0.848901 1.000000
## 365 0.192384 0.916914 0.965022 0.873375 0.848238 0.846575 1.000000
## 366 0.187703 0.915556 0.964419 0.871404 0.845528 0.844262 1.000000
## 367 0.187543 0.914201 0.963818 0.869443 0.842818 0.841962 1.000000
## 368 0.103516 0.912851 0.963217 0.867490 0.840108 0.839674 1.000000
## 369 0.063278 0.911504 0.962617 0.865546 0.837398 0.837398 1.000000
## specificity absolute_mcc min_per_class_accuracy mean_per_class_accuracy tns
## 364 0.083333 0.265973 0.083333 0.541667 5
## 365 0.066667 0.237568 0.066667 0.533333 4
## 366 0.050000 0.205458 0.050000 0.525000 3
## 367 0.033333 0.167527 0.033333 0.516667 2
## 368 0.016667 0.118299 0.016667 0.508333 1
## 369 0.000000 0.000000 0.000000 0.500000 0
## fns fps tps tnr fnr fpr tpr idx
## 364 0 55 309 0.083333 0.000000 0.916667 1.000000 363
## 365 0 56 309 0.066667 0.000000 0.933333 1.000000 364
## 366 0 57 309 0.050000 0.000000 0.950000 1.000000 365
## 367 0 58 309 0.033333 0.000000 0.966667 1.000000 366
## 368 0 59 309 0.016667 0.000000 0.983333 1.000000 367
## 369 0 60 309 0.000000 0.000000 1.000000 1.000000 368