https://archive.ics.uci.edu/ml/datasets/default+of+credit+card+clients Yeh, I. C., & Lien, C. H. (2009). The comparisons of data mining techniques for the predictive accuracy of probability of default of credit card clients. Expert Systems with Applications, 36(2), 2473-2480.
dcc<-read.csv("C:/Course19/BDE/data/UCI_Credit_Card.csv")
dim(dcc) # 30000 obs. of 25 variables## [1] 30000 25# SEX: 1=male, 2=female
dcc$SEX<-as.factor(dcc$SEX)
# EDUCATION: 1=graduate school, 2=university, 3=high school, 0,4,5,6=others
dcc$EDUCATION<-ifelse(dcc$EDUCATION>3,0,dcc$EDUCATION)
dcc$EDUCATION<-as.factor(dcc$EDUCATION)
# MARRIAGE: 1=married, 2=single, 3=divorce, 0=others
dcc$MARRIAGE<-as.factor(dcc$MARRIAGE)
# payment status: -2=no consumption, -1=pay on due, #=delayed months of payment
dcc$PAY_0<-as.factor(dcc$PAY_0) # payment status as of 9/2005
dcc$PAY_2<-as.factor(dcc$PAY_2) # payment status as of 8/2005
dcc$PAY_3<-as.factor(dcc$PAY_3) # payment status as of 7/2005
dcc$PAY_4<-as.factor(dcc$PAY_4) # payment status as of 6/2005
dcc$PAY_5<-as.factor(dcc$PAY_5) # payment status as of 5/2005
dcc$PAY_6<-as.factor(dcc$PAY_6) # payment status as of 4/2005
dcc$default.payment.next.month<-as.factor(dcc$default.payment.next.month)
# numeric data: LIMIT_BAL, BILL_AMT1, ..., BILL_AMT6; PAY_AMT1, ..., PAY_AMT6, AGElibrary(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 http://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, trunch2o.init()##
## H2O is not running yet, starting it now...
##
## Note: In case of errors look at the following log files:
## C:\Users\link_000\AppData\Local\Temp\Rtmp08YpKn/h2o_link_000_started_from_r.out
## C:\Users\link_000\AppData\Local\Temp\Rtmp08YpKn/h2o_link_000_started_from_r.err
##
##
## Starting H2O JVM and connecting: . Connection successful!
##
## R is connected to the H2O cluster:
## H2O cluster uptime: 7 seconds 611 milliseconds
## H2O cluster timezone: America/Los_Angeles
## H2O data parsing timezone: UTC
## H2O cluster version: 3.24.0.1
## H2O cluster version age: 27 days
## H2O cluster name: H2O_started_from_R_link_000_llu778
## H2O cluster total nodes: 1
## H2O cluster total memory: 1.74 GB
## H2O cluster total cores: 4
## H2O cluster allowed cores: 4
## H2O cluster healthy: TRUE
## H2O Connection ip: localhost
## H2O Connection port: 54321
## H2O Connection proxy: NA
## H2O Internal Security: FALSE
## H2O API Extensions: Amazon S3, Algos, AutoML, Core V3, Core V4
## R Version: R version 3.5.3 (2019-03-11)h2o.dcc1<-as.h2o(dcc)##
|
| | 0%
|
|=================================================================| 100%h2o.dcc2<-h2o.interaction(h2o.dcc1,
factors=c("SEX","EDUCATION","MARRIAGE"),
pairwise=T,max_factors=10,min_occurrence=3)##
|
| | 0%
|
|=================================================================| 100%h2o.dcc<-h2o.cbind(h2o.dcc1,h2o.dcc2)
summary(h2o.dcc,exact_quantiles=TRUE)## ID LIMIT_BAL SEX EDUCATION MARRIAGE
## Min. : 1 Min. : 10000 2:18112 2:14030 2:15964
## 1st Qu.: 7501 1st Qu.: 50000 1:11888 1:10585 1:13659
## Median :15000 Median : 140000 3: 4917 3: 323
## Mean :15000 Mean : 167484 0: 468 0: 54
## 3rd Qu.:22500 3rd Qu.: 240000
## Max. :30000 Max. :1000000
## AGE PAY_0 PAY_2 PAY_3 PAY_4 PAY_5
## Min. :21.00 0 :14737 0 :15730 0 :15764 0 :16455 0 :16947
## 1st Qu.:28.00 -1: 5686 -1: 6050 -1: 5938 -1: 5687 -1: 5539
## Median :34.00 1 : 3688 2 : 3927 -2: 4085 -2: 4348 -2: 4546
## Mean :35.49 -2: 2759 -2: 3782 2 : 3819 2 : 3159 2 : 2626
## 3rd Qu.:41.00 2 : 2667 3 : 326 3 : 240 3 : 180 3 : 178
## Max. :79.00 3 : 322 4 : 99 4 : 76 4 : 69 4 : 84
## PAY_6 BILL_AMT1 BILL_AMT2 BILL_AMT3
## 0 :16286 Min. :-165580 Min. :-69777 Min. :-157264
## -1: 5740 1st Qu.: 3559 1st Qu.: 2985 1st Qu.: 2666
## -2: 4895 Median : 22382 Median : 21200 Median : 20089
## 2 : 2766 Mean : 51223 Mean : 49179 Mean : 47013
## 3 : 184 3rd Qu.: 67091 3rd Qu.: 64006 3rd Qu.: 60165
## 4 : 49 Max. : 964511 Max. :983931 Max. :1664089
## BILL_AMT4 BILL_AMT5 BILL_AMT6 PAY_AMT1
## Min. :-170000 Min. :-81334 Min. :-339603 Min. : 0
## 1st Qu.: 2327 1st Qu.: 1763 1st Qu.: 1256 1st Qu.: 1000
## Median : 19052 Median : 18105 Median : 17071 Median : 2100
## Mean : 43263 Mean : 40311 Mean : 38872 Mean : 5664
## 3rd Qu.: 54506 3rd Qu.: 50191 3rd Qu.: 49198 3rd Qu.: 5006
## Max. : 891586 Max. :927171 Max. : 961664 Max. :873552
## PAY_AMT2 PAY_AMT3 PAY_AMT4 PAY_AMT5
## Min. : 0 Min. : 0 Min. : 0 Min. : 0.0
## 1st Qu.: 833 1st Qu.: 390 1st Qu.: 296 1st Qu.: 252.5
## Median : 2009 Median : 1800 Median : 1500 Median : 1500.0
## Mean : 5921 Mean : 5226 Mean : 4826 Mean : 4799.4
## 3rd Qu.: 5000 3rd Qu.: 4505 3rd Qu.: 4013 3rd Qu.: 4031.5
## Max. :1684259 Max. :896040 Max. :621000 Max. :426529.0
## PAY_AMT6 default.payment.next.month SEX_EDUCATION SEX_MARRIAGE
## Min. : 0.0 0:23364 2_2:8656 2_2:9411
## 1st Qu.: 117.8 1: 6636 2_1:6231 2_1:8469
## Median : 1500.0 1_2:5374 1_2:6553
## Mean : 5215.5 1_1:4354 1_1:5190
## 3rd Qu.: 4000.0 2_3:2927 2_3: 192
## Max. :528666.0 1_3:1990 1_3: 131
## EDUCATION_MARRIAGE
## 2_2:7020
## 2_1:6842
## 1_2:6809
## 1_1:3722
## 3_1:2861
## 3_2:1909dcc.split<-h2o.splitFrame(h2o.dcc,0.5)
train<-dcc.split[[1]]
test<-dcc.split[[2]]yvar<-"default.payment.next.month"
xvar<-c("LIMIT_BAL","SEX","EDUCATION","MARRIAGE","AGE",
"SEX_EDUCATION","SEX_MARRIAGE","EDUCATION_MARRIAGE",
"PAY_0","PAY_2","PAY_3","PAY_4","PAY_5","PAY_6",
"BILL_AMT1","BILL_AMT2","BILL_AMT3","BILL_AMT4","BILL_AMT5","BILL_AMT6",
"PAY_AMT1","PAY_AMT2","PAY_AMT3","PAY_AMT4","PAY_AMT5","PAY_AMT6")auto1<-h2o.automl(xvar,yvar,seed=2019,nfold=10,
training_fram=train,
validation_frame=test,
stopping_metric = "misclassification",
stopping_tolerance = 0.001,
stopping_rounds = 5,
max_runtime_secs = 7200)##
|
| | 0%
|
|==== | 6%
|
|==== | 7%
|
|===== | 8%
|
|====== | 9%
|
|====== | 10%
|
|======= | 11%
|
|======== | 12%
|
|========= | 13%
|
|========= | 14%
|
|========== | 15%
|
|========== | 16%
|
|=========== | 18%
|
|============ | 19%
|
|============= | 20%
|
|============== | 22%
|
|=============== | 23%
|
|=============== | 24%
|
|================ | 24%
|
|================ | 25%
|
|================= | 27%
|
|================== | 27%
|
|================== | 28%
|
|=================== | 30%
|
|==================== | 30%
|
|==================== | 31%
|
|===================== | 32%
|
|====================== | 34%
|
|======================= | 35%
|
|======================= | 36%
|
|========================= | 38%
|
|========================= | 39%
|
|========================== | 40%
|
|=========================== | 41%
|
|=========================== | 42%
|
|============================ | 42%
|
|============================ | 43%
|
|============================ | 44%
|
|============================= | 44%
|
|============================= | 45%
|
|============================== | 46%
|
|============================== | 47%
|
|=============================== | 47%
|
|=============================== | 48%
|
|================================ | 49%
|
|================================ | 50%
|
|================================= | 50%
|
|================================= | 51%
|
|================================== | 52%
|
|================================== | 53%
|
|=================================== | 53%
|
|=================================== | 54%
|
|==================================== | 55%
|
|==================================== | 56%
|
|===================================== | 56%
|
|===================================== | 57%
|
|===================================== | 58%
|
|====================================== | 58%
|
|====================================== | 59%
|
|======================================= | 60%
|
|======================================== | 61%
|
|======================================== | 62%
|
|========================================= | 62%
|
|========================================= | 63%
|
|========================================= | 64%
|
|========================================== | 64%
|
|========================================== | 65%
|
|=========================================== | 66%
|
|============================================ | 67%
|
|============================================ | 68%
|
|============================================= | 69%
|
|============================================= | 70%
|
|============================================== | 70%
|
|============================================== | 71%
|
|=============================================== | 72%
|
|=============================================== | 73%
|
|================================================ | 73%
|
|================================================ | 74%
|
|================================================= | 75%
|
|================================================= | 76%
|
|================================================== | 76%
|
|================================================== | 77%
|
|=================================================== | 78%
|
|=================================================== | 79%
|
|==================================================== | 80%
|
|===================================================== | 81%
|
|===================================================== | 82%
|
|====================================================== | 82%
|
|====================================================== | 83%
|
|====================================================== | 84%
|
|======================================================= | 84%
|
|======================================================= | 85%
|
|======================================================== | 86%
|
|======================================================== | 87%
|
|========================================================= | 87%
|
|========================================================= | 88%
|
|============================================================= | 94%
|
|=================================================================| 100%auto1## An object of class "H2OAutoML"
## Slot "project_name":
## [1] "automl_RTMP_sid_8fc5_50"
##
## Slot "leader":
## Model Details:
## ==============
##
## H2OBinomialModel: stackedensemble
## Model ID: StackedEnsemble_AllModels_AutoML_20190428_005854
## NULL
##
##
## H2OBinomialMetrics: stackedensemble
## ** Reported on training data. **
##
## MSE: 0.1053517
## RMSE: 0.3245792
## LogLoss: 0.3482742
## Mean Per-Class Error: 0.1778003
## AUC: 0.9081976
## pr_auc: 0.75394
## Gini: 0.8163952
##
## Confusion Matrix (vertical: actual; across: predicted) for F1-optimal threshold:
## 0 1 Error Rate
## 0 9618 1968 0.169860 =1968/11586
## 1 607 2661 0.185741 =607/3268
## Totals 10225 4629 0.173354 =2575/14854
##
## Maximum Metrics: Maximum metrics at their respective thresholds
## metric threshold value idx
## 1 max f1 0.187986 0.673927 269
## 2 max f2 0.147765 0.785463 302
## 3 max f0point5 0.462813 0.692887 148
## 4 max accuracy 0.459556 0.855931 149
## 5 max precision 0.913605 1.000000 0
## 6 max recall 0.088053 1.000000 378
## 7 max specificity 0.913605 1.000000 0
## 8 max absolute_mcc 0.187986 0.576352 269
## 9 max min_per_class_accuracy 0.183812 0.822286 272
## 10 max mean_per_class_accuracy 0.160231 0.830676 290
##
## 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: 0.1349173
## RMSE: 0.3673109
## LogLoss: 0.4309416
## Mean Per-Class Error: 0.2920477
## AUC: 0.7823999
## pr_auc: 0.5626649
## Gini: 0.5647999
##
## Confusion Matrix (vertical: actual; across: predicted) for F1-optimal threshold:
## 0 1 Error Rate
## 0 10228 1550 0.131601 =1550/11778
## 1 1524 1844 0.452494 =1524/3368
## Totals 11752 3394 0.202958 =3074/15146
##
## Maximum Metrics: Maximum metrics at their respective thresholds
## metric threshold value idx
## 1 max f1 0.249397 0.545401 230
## 2 max f2 0.120743 0.639063 335
## 3 max f0point5 0.454195 0.586558 149
## 4 max accuracy 0.454195 0.821471 149
## 5 max precision 0.914741 1.000000 0
## 6 max recall 0.072489 1.000000 397
## 7 max specificity 0.914741 1.000000 0
## 8 max absolute_mcc 0.346371 0.424427 190
## 9 max min_per_class_accuracy 0.158365 0.706651 292
## 10 max mean_per_class_accuracy 0.196029 0.714946 262
##
## 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. **
## ** 10-fold cross-validation on training data (Metrics computed for combined holdout predictions) **
##
## MSE: 0.1340485
## RMSE: 0.3661263
## LogLoss: 0.4284002
## Mean Per-Class Error: 0.2872486
## AUC: 0.7845892
## pr_auc: 0.5556414
## Gini: 0.5691785
##
## Confusion Matrix (vertical: actual; across: predicted) for F1-optimal threshold:
## 0 1 Error Rate
## 0 9989 1597 0.137839 =1597/11586
## 1 1427 1841 0.436659 =1427/3268
## Totals 11416 3438 0.203582 =3024/14854
##
## Maximum Metrics: Maximum metrics at their respective thresholds
## metric threshold value idx
## 1 max f1 0.242904 0.549061 240
## 2 max f2 0.114446 0.639919 346
## 3 max f0point5 0.437463 0.581375 159
## 4 max accuracy 0.450709 0.821732 155
## 5 max precision 0.912955 1.000000 0
## 6 max recall 0.072006 1.000000 397
## 7 max specificity 0.912955 1.000000 0
## 8 max absolute_mcc 0.317563 0.421324 206
## 9 max min_per_class_accuracy 0.159890 0.704557 298
## 10 max mean_per_class_accuracy 0.176587 0.714879 283
##
## Gains/Lift Table: Extract with `h2o.gainsLift(<model>, <data>)` or `h2o.gainsLift(<model>, valid=<T/F>, xval=<T/F>)`
##
## Slot "leaderboard":
## model_id auc logloss
## 1 StackedEnsemble_AllModels_AutoML_20190428_005854 0.7845892 0.4284002
## 2 GBM_grid_1_AutoML_20190428_005854_model_86 0.7840491 0.4262033
## 3 GBM_grid_1_AutoML_20190428_005854_model_137 0.7837912 0.4268730
## 4 GBM_grid_1_AutoML_20190428_005854_model_43 0.7837242 0.4267778
## 5 GBM_grid_1_AutoML_20190428_005854_model_12 0.7837062 0.4264270
## 6 StackedEnsemble_BestOfFamily_AutoML_20190428_005854 0.7835455 0.4286595
## mean_per_class_error rmse mse
## 1 0.2872486 0.3661263 0.1340485
## 2 0.2927212 0.3655607 0.1336346
## 3 0.2923522 0.3659971 0.1339539
## 4 0.2877632 0.3660347 0.1339814
## 5 0.2880333 0.3655293 0.1336117
## 6 0.2914736 0.3661293 0.1340507
##
## [160 rows x 6 columns]auto1@leader## Model Details:
## ==============
##
## H2OBinomialModel: stackedensemble
## Model ID: StackedEnsemble_AllModels_AutoML_20190428_005854
## NULL
##
##
## H2OBinomialMetrics: stackedensemble
## ** Reported on training data. **
##
## MSE: 0.1053517
## RMSE: 0.3245792
## LogLoss: 0.3482742
## Mean Per-Class Error: 0.1778003
## AUC: 0.9081976
## pr_auc: 0.75394
## Gini: 0.8163952
##
## Confusion Matrix (vertical: actual; across: predicted) for F1-optimal threshold:
## 0 1 Error Rate
## 0 9618 1968 0.169860 =1968/11586
## 1 607 2661 0.185741 =607/3268
## Totals 10225 4629 0.173354 =2575/14854
##
## Maximum Metrics: Maximum metrics at their respective thresholds
## metric threshold value idx
## 1 max f1 0.187986 0.673927 269
## 2 max f2 0.147765 0.785463 302
## 3 max f0point5 0.462813 0.692887 148
## 4 max accuracy 0.459556 0.855931 149
## 5 max precision 0.913605 1.000000 0
## 6 max recall 0.088053 1.000000 378
## 7 max specificity 0.913605 1.000000 0
## 8 max absolute_mcc 0.187986 0.576352 269
## 9 max min_per_class_accuracy 0.183812 0.822286 272
## 10 max mean_per_class_accuracy 0.160231 0.830676 290
##
## 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: 0.1349173
## RMSE: 0.3673109
## LogLoss: 0.4309416
## Mean Per-Class Error: 0.2920477
## AUC: 0.7823999
## pr_auc: 0.5626649
## Gini: 0.5647999
##
## Confusion Matrix (vertical: actual; across: predicted) for F1-optimal threshold:
## 0 1 Error Rate
## 0 10228 1550 0.131601 =1550/11778
## 1 1524 1844 0.452494 =1524/3368
## Totals 11752 3394 0.202958 =3074/15146
##
## Maximum Metrics: Maximum metrics at their respective thresholds
## metric threshold value idx
## 1 max f1 0.249397 0.545401 230
## 2 max f2 0.120743 0.639063 335
## 3 max f0point5 0.454195 0.586558 149
## 4 max accuracy 0.454195 0.821471 149
## 5 max precision 0.914741 1.000000 0
## 6 max recall 0.072489 1.000000 397
## 7 max specificity 0.914741 1.000000 0
## 8 max absolute_mcc 0.346371 0.424427 190
## 9 max min_per_class_accuracy 0.158365 0.706651 292
## 10 max mean_per_class_accuracy 0.196029 0.714946 262
##
## 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. **
## ** 10-fold cross-validation on training data (Metrics computed for combined holdout predictions) **
##
## MSE: 0.1340485
## RMSE: 0.3661263
## LogLoss: 0.4284002
## Mean Per-Class Error: 0.2872486
## AUC: 0.7845892
## pr_auc: 0.5556414
## Gini: 0.5691785
##
## Confusion Matrix (vertical: actual; across: predicted) for F1-optimal threshold:
## 0 1 Error Rate
## 0 9989 1597 0.137839 =1597/11586
## 1 1427 1841 0.436659 =1427/3268
## Totals 11416 3438 0.203582 =3024/14854
##
## Maximum Metrics: Maximum metrics at their respective thresholds
## metric threshold value idx
## 1 max f1 0.242904 0.549061 240
## 2 max f2 0.114446 0.639919 346
## 3 max f0point5 0.437463 0.581375 159
## 4 max accuracy 0.450709 0.821732 155
## 5 max precision 0.912955 1.000000 0
## 6 max recall 0.072006 1.000000 397
## 7 max specificity 0.912955 1.000000 0
## 8 max absolute_mcc 0.317563 0.421324 206
## 9 max min_per_class_accuracy 0.159890 0.704557 298
## 10 max mean_per_class_accuracy 0.176587 0.714879 283
##
## Gains/Lift Table: Extract with `h2o.gainsLift(<model>, <data>)` or `h2o.gainsLift(<model>, valid=<T/F>, xval=<T/F>)`lb1<-auto1@leaderboard
print(lb1,nrow(lb1))## model_id auc
## 1 StackedEnsemble_AllModels_AutoML_20190428_005854 0.7845892
## 2 GBM_grid_1_AutoML_20190428_005854_model_86 0.7840491
## 3 GBM_grid_1_AutoML_20190428_005854_model_137 0.7837912
## 4 GBM_grid_1_AutoML_20190428_005854_model_43 0.7837242
## 5 GBM_grid_1_AutoML_20190428_005854_model_12 0.7837062
## 6 StackedEnsemble_BestOfFamily_AutoML_20190428_005854 0.7835455
## 7 GBM_grid_1_AutoML_20190428_005854_model_138 0.7833724
## 8 GBM_grid_1_AutoML_20190428_005854_model_132 0.7827903
## 9 GBM_grid_1_AutoML_20190428_005854_model_33 0.7819841
## 10 GBM_grid_1_AutoML_20190428_005854_model_15 0.7819047
## 11 GBM_grid_1_AutoML_20190428_005854_model_123 0.7817980
## 12 GBM_grid_1_AutoML_20190428_005854_model_68 0.7814285
## 13 GBM_grid_1_AutoML_20190428_005854_model_88 0.7813277
## 14 GBM_grid_1_AutoML_20190428_005854_model_122 0.7813205
## 15 GBM_grid_1_AutoML_20190428_005854_model_104 0.7811074
## 16 GBM_grid_1_AutoML_20190428_005854_model_106 0.7811068
## 17 GBM_grid_1_AutoML_20190428_005854_model_40 0.7805322
## 18 GBM_grid_1_AutoML_20190428_005854_model_121 0.7804938
## 19 GBM_grid_1_AutoML_20190428_005854_model_116 0.7803873
## 20 GBM_grid_1_AutoML_20190428_005854_model_96 0.7801368
## 21 GBM_grid_1_AutoML_20190428_005854_model_75 0.7800807
## 22 GBM_grid_1_AutoML_20190428_005854_model_27 0.7796575
## 23 GBM_grid_1_AutoML_20190428_005854_model_21 0.7794936
## 24 GBM_grid_1_AutoML_20190428_005854_model_115 0.7790884
## 25 GBM_grid_1_AutoML_20190428_005854_model_3 0.7788960
## 26 GBM_grid_1_AutoML_20190428_005854_model_80 0.7788785
## 27 GBM_grid_1_AutoML_20190428_005854_model_30 0.7787529
## 28 GBM_grid_1_AutoML_20190428_005854_model_51 0.7786226
## 29 GBM_grid_1_AutoML_20190428_005854_model_89 0.7783652
## 30 GBM_grid_1_AutoML_20190428_005854_model_91 0.7781623
## 31 GBM_grid_1_AutoML_20190428_005854_model_50 0.7781395
## 32 GBM_2_AutoML_20190428_005854 0.7779896
## 33 GBM_grid_1_AutoML_20190428_005854_model_117 0.7779796
## 34 GBM_grid_1_AutoML_20190428_005854_model_48 0.7774461
## 35 GBM_grid_1_AutoML_20190428_005854_model_28 0.7773412
## 36 GBM_grid_1_AutoML_20190428_005854_model_66 0.7773358
## 37 GBM_1_AutoML_20190428_005854 0.7772953
## 38 GBM_grid_1_AutoML_20190428_005854_model_108 0.7770097
## 39 GBM_grid_1_AutoML_20190428_005854_model_10 0.7769689
## 40 GBM_grid_1_AutoML_20190428_005854_model_102 0.7769343
## 41 GBM_grid_1_AutoML_20190428_005854_model_87 0.7768000
## 42 GBM_grid_1_AutoML_20190428_005854_model_131 0.7767256
## 43 GBM_grid_1_AutoML_20190428_005854_model_134 0.7767231
## 44 GBM_grid_1_AutoML_20190428_005854_model_59 0.7767036
## 45 GBM_5_AutoML_20190428_005854 0.7765987
## 46 GBM_grid_1_AutoML_20190428_005854_model_42 0.7765920
## 47 GBM_grid_1_AutoML_20190428_005854_model_139 0.7764079
## 48 GBM_grid_1_AutoML_20190428_005854_model_36 0.7763376
## 49 GBM_grid_1_AutoML_20190428_005854_model_110 0.7761657
## 50 GBM_grid_1_AutoML_20190428_005854_model_119 0.7761364
## 51 GBM_grid_1_AutoML_20190428_005854_model_94 0.7760367
## 52 GBM_grid_1_AutoML_20190428_005854_model_29 0.7760307
## 53 GBM_3_AutoML_20190428_005854 0.7758530
## 54 GBM_grid_1_AutoML_20190428_005854_model_63 0.7756729
## 55 GBM_grid_1_AutoML_20190428_005854_model_24 0.7755545
## 56 GBM_grid_1_AutoML_20190428_005854_model_73 0.7752902
## 57 GBM_grid_1_AutoML_20190428_005854_model_9 0.7752092
## 58 GBM_grid_1_AutoML_20190428_005854_model_52 0.7751698
## 59 GBM_grid_1_AutoML_20190428_005854_model_55 0.7750734
## 60 GBM_grid_1_AutoML_20190428_005854_model_114 0.7749047
## 61 GBM_grid_1_AutoML_20190428_005854_model_125 0.7746972
## 62 GBM_grid_1_AutoML_20190428_005854_model_95 0.7745450
## 63 GBM_grid_1_AutoML_20190428_005854_model_100 0.7743763
## 64 GBM_grid_1_AutoML_20190428_005854_model_45 0.7741453
## 65 GBM_grid_1_AutoML_20190428_005854_model_90 0.7737913
## 66 GBM_grid_1_AutoML_20190428_005854_model_118 0.7735334
## 67 GBM_grid_1_AutoML_20190428_005854_model_79 0.7734547
## 68 GBM_grid_1_AutoML_20190428_005854_model_124 0.7733690
## 69 GBM_grid_1_AutoML_20190428_005854_model_105 0.7726803
## 70 GBM_grid_1_AutoML_20190428_005854_model_53 0.7726691
## 71 GBM_grid_1_AutoML_20190428_005854_model_107 0.7724272
## 72 GBM_grid_1_AutoML_20190428_005854_model_69 0.7721979
## 73 GBM_grid_1_AutoML_20190428_005854_model_81 0.7719644
## 74 GBM_grid_1_AutoML_20190428_005854_model_46 0.7719499
## 75 GBM_grid_1_AutoML_20190428_005854_model_32 0.7719390
## 76 GBM_grid_1_AutoML_20190428_005854_model_109 0.7715930
## 77 GBM_grid_1_AutoML_20190428_005854_model_72 0.7714022
## 78 GBM_grid_1_AutoML_20190428_005854_model_2 0.7711870
## 79 GBM_grid_1_AutoML_20190428_005854_model_6 0.7711349
## 80 GBM_grid_1_AutoML_20190428_005854_model_128 0.7709016
## 81 GBM_grid_1_AutoML_20190428_005854_model_129 0.7708949
## 82 GBM_grid_1_AutoML_20190428_005854_model_76 0.7706791
## 83 GBM_grid_1_AutoML_20190428_005854_model_120 0.7700999
## 84 GBM_grid_1_AutoML_20190428_005854_model_44 0.7700745
## 85 GBM_grid_1_AutoML_20190428_005854_model_58 0.7700577
## 86 GBM_grid_1_AutoML_20190428_005854_model_98 0.7691363
## 87 GBM_grid_1_AutoML_20190428_005854_model_47 0.7690418
## 88 GBM_grid_1_AutoML_20190428_005854_model_41 0.7688779
## 89 GBM_grid_1_AutoML_20190428_005854_model_103 0.7686714
## 90 GBM_grid_1_AutoML_20190428_005854_model_82 0.7686220
## 91 GBM_grid_1_AutoML_20190428_005854_model_37 0.7685128
## 92 GBM_4_AutoML_20190428_005854 0.7684412
## 93 GBM_grid_1_AutoML_20190428_005854_model_19 0.7683668
## 94 GLM_grid_1_AutoML_20190428_005854_model_1 0.7680722
## 95 GBM_grid_1_AutoML_20190428_005854_model_65 0.7672923
## 96 GBM_grid_1_AutoML_20190428_005854_model_101 0.7672629
## 97 GBM_grid_1_AutoML_20190428_005854_model_17 0.7671498
## 98 GBM_grid_1_AutoML_20190428_005854_model_31 0.7670723
## 99 GBM_grid_1_AutoML_20190428_005854_model_136 0.7667271
## 100 GBM_grid_1_AutoML_20190428_005854_model_97 0.7666519
## 101 GBM_grid_1_AutoML_20190428_005854_model_25 0.7663417
## 102 DeepLearning_1_AutoML_20190428_005854 0.7662049
## 103 GBM_grid_1_AutoML_20190428_005854_model_14 0.7660972
## 104 GBM_grid_1_AutoML_20190428_005854_model_67 0.7657508
## 105 GBM_grid_1_AutoML_20190428_005854_model_99 0.7653334
## 106 GBM_grid_1_AutoML_20190428_005854_model_135 0.7651210
## 107 GBM_grid_1_AutoML_20190428_005854_model_71 0.7646667
## 108 GBM_grid_1_AutoML_20190428_005854_model_7 0.7642704
## 109 DeepLearning_grid_1_AutoML_20190428_005854_model_3 0.7641383
## 110 GBM_grid_1_AutoML_20190428_005854_model_127 0.7627426
## 111 GBM_grid_1_AutoML_20190428_005854_model_38 0.7627360
## 112 GBM_grid_1_AutoML_20190428_005854_model_77 0.7626592
## 113 GBM_grid_1_AutoML_20190428_005854_model_62 0.7626420
## 114 GBM_grid_1_AutoML_20190428_005854_model_64 0.7614975
## 115 GBM_grid_1_AutoML_20190428_005854_model_83 0.7614574
## 116 GBM_grid_1_AutoML_20190428_005854_model_130 0.7609762
## 117 DeepLearning_grid_1_AutoML_20190428_005854_model_8 0.7609042
## 118 GBM_grid_1_AutoML_20190428_005854_model_126 0.7607253
## 119 GBM_grid_1_AutoML_20190428_005854_model_57 0.7603355
## 120 GBM_grid_1_AutoML_20190428_005854_model_92 0.7603051
## 121 DRF_1_AutoML_20190428_005854 0.7591447
## 122 XRT_1_AutoML_20190428_005854 0.7590349
## 123 GBM_grid_1_AutoML_20190428_005854_model_5 0.7579557
## 124 GBM_grid_1_AutoML_20190428_005854_model_13 0.7576833
## 125 GBM_grid_1_AutoML_20190428_005854_model_8 0.7575414
## 126 GBM_grid_1_AutoML_20190428_005854_model_78 0.7572563
## 127 DeepLearning_grid_1_AutoML_20190428_005854_model_4 0.7561972
## 128 GBM_grid_1_AutoML_20190428_005854_model_93 0.7557890
## 129 DeepLearning_grid_1_AutoML_20190428_005854_model_10 0.7530193
## 130 GBM_grid_1_AutoML_20190428_005854_model_22 0.7515422
## 131 DeepLearning_grid_1_AutoML_20190428_005854_model_7 0.7491566
## 132 DeepLearning_grid_1_AutoML_20190428_005854_model_2 0.7490283
## 133 GBM_grid_1_AutoML_20190428_005854_model_34 0.7479599
## 134 DeepLearning_grid_1_AutoML_20190428_005854_model_6 0.7473500
## 135 GBM_grid_1_AutoML_20190428_005854_model_23 0.7400360
## 136 DeepLearning_grid_1_AutoML_20190428_005854_model_5 0.7393223
## 137 DeepLearning_grid_1_AutoML_20190428_005854_model_1 0.7368333
## 138 GBM_grid_1_AutoML_20190428_005854_model_74 0.7359017
## 139 GBM_grid_1_AutoML_20190428_005854_model_113 0.7348553
## 140 DeepLearning_grid_1_AutoML_20190428_005854_model_9 0.7324831
## 141 GBM_grid_1_AutoML_20190428_005854_model_20 0.7305836
## 142 GBM_grid_1_AutoML_20190428_005854_model_70 0.7300917
## 143 GBM_grid_1_AutoML_20190428_005854_model_111 0.7294821
## 144 GBM_grid_1_AutoML_20190428_005854_model_60 0.7259162
## 145 GBM_grid_1_AutoML_20190428_005854_model_26 0.7251253
## 146 GBM_grid_1_AutoML_20190428_005854_model_133 0.7248563
## 147 GBM_grid_1_AutoML_20190428_005854_model_85 0.7222474
## 148 GBM_grid_1_AutoML_20190428_005854_model_1 0.7219988
## 149 GBM_grid_1_AutoML_20190428_005854_model_54 0.7208174
## 150 GBM_grid_1_AutoML_20190428_005854_model_11 0.7163489
## 151 GBM_grid_1_AutoML_20190428_005854_model_39 0.7104816
## 152 GBM_grid_1_AutoML_20190428_005854_model_16 0.7082462
## 153 GBM_grid_1_AutoML_20190428_005854_model_35 0.7065265
## 154 GBM_grid_1_AutoML_20190428_005854_model_61 0.7021981
## 155 GBM_grid_1_AutoML_20190428_005854_model_112 0.6889614
## 156 GBM_grid_1_AutoML_20190428_005854_model_84 0.6866473
## 157 GBM_grid_1_AutoML_20190428_005854_model_56 0.6519863
## 158 GBM_grid_1_AutoML_20190428_005854_model_49 0.6387311
## 159 GBM_grid_1_AutoML_20190428_005854_model_4 0.6383451
## 160 GBM_grid_1_AutoML_20190428_005854_model_18 0.6330776
## logloss mean_per_class_error rmse mse
## 1 0.4284002 0.2872486 0.3661263 0.1340485
## 2 0.4262033 0.2927212 0.3655607 0.1336346
## 3 0.4268730 0.2923522 0.3659971 0.1339539
## 4 0.4267778 0.2877632 0.3660347 0.1339814
## 5 0.4264270 0.2880333 0.3655293 0.1336117
## 6 0.4286595 0.2914736 0.3661293 0.1340507
## 7 0.4260761 0.2860017 0.3654629 0.1335632
## 8 0.4263360 0.2831976 0.3655786 0.1336477
## 9 0.4270237 0.2880176 0.3656863 0.1337265
## 10 0.4277595 0.2867979 0.3661563 0.1340704
## 11 0.4274629 0.2857936 0.3656537 0.1337026
## 12 0.4843599 0.2899205 0.3947729 0.1558456
## 13 0.4311983 0.2905053 0.3684324 0.1357424
## 14 0.4286863 0.2916543 0.3668331 0.1345665
## 15 0.4283423 0.2943806 0.3665691 0.1343729
## 16 0.4659483 0.2884730 0.3854304 0.1485566
## 17 0.4289828 0.2889990 0.3670843 0.1347509
## 18 0.4283582 0.2874573 0.3665965 0.1343930
## 19 0.4283206 0.2869748 0.3665333 0.1343467
## 20 0.4303216 0.2873394 0.3674178 0.1349959
## 21 0.4303546 0.2896575 0.3677584 0.1352462
## 22 0.4695490 0.2834517 0.3869988 0.1497680
## 23 0.4781541 0.2885278 0.3916056 0.1533550
## 24 0.4540697 0.2926858 0.3790474 0.1436769
## 25 0.4505416 0.2873234 0.3774279 0.1424518
## 26 0.4304204 0.2903527 0.3676727 0.1351832
## 27 0.4314620 0.2872971 0.3685747 0.1358473
## 28 0.4320193 0.2935844 0.3687253 0.1359584
## 29 0.4960161 0.2879438 0.4004804 0.1603845
## 30 0.4744780 0.2913406 0.3897613 0.1519139
## 31 0.4825716 0.2901443 0.3939431 0.1551912
## 32 0.4317314 0.2933806 0.3684093 0.1357254
## 33 0.4701317 0.2882963 0.3874525 0.1501194
## 34 0.4830982 0.2908347 0.3941348 0.1553423
## 35 0.4311799 0.2916114 0.3677632 0.1352498
## 36 0.4750331 0.2899673 0.3901293 0.1522008
## 37 0.4320265 0.2940399 0.3685252 0.1358108
## 38 0.4615672 0.2893870 0.3828591 0.1465811
## 39 0.4910977 0.2895793 0.3980942 0.1584790
## 40 0.4930738 0.2899518 0.3989748 0.1591809
## 41 0.4753310 0.2876139 0.3903356 0.1523619
## 42 0.4784486 0.2920112 0.3916231 0.1533686
## 43 0.4612904 0.2918270 0.3829241 0.1466309
## 44 0.4675723 0.2933568 0.3863909 0.1492979
## 45 0.4317284 0.2951380 0.3679787 0.1354083
## 46 0.4537563 0.2904580 0.3789615 0.1436118
## 47 0.4319114 0.2942984 0.3683019 0.1356463
## 48 0.4876252 0.2871784 0.3961975 0.1569725
## 49 0.4503137 0.2885004 0.3772528 0.1423197
## 50 0.4327359 0.2995432 0.3688053 0.1360173
## 51 0.4322812 0.2913646 0.3680934 0.1354928
## 52 0.4333637 0.2948284 0.3695462 0.1365644
## 53 0.4340248 0.2970568 0.3693277 0.1364029
## 54 0.4337004 0.2969270 0.3696418 0.1366351
## 55 0.4675889 0.2902970 0.3865182 0.1493963
## 56 0.4530423 0.2929097 0.3786770 0.1433962
## 57 0.4911489 0.2873592 0.3979085 0.1583311
## 58 0.4545779 0.2942555 0.3792965 0.1438658
## 59 0.4932649 0.2913446 0.3991566 0.1593260
## 60 0.4344768 0.2942330 0.3694114 0.1364648
## 61 0.4751989 0.2976092 0.3900383 0.1521299
## 62 0.4341119 0.2951587 0.3696780 0.1366618
## 63 0.4497458 0.2945809 0.3769315 0.1420774
## 64 0.4599202 0.2938947 0.3821276 0.1460215
## 65 0.4627455 0.2932629 0.3834949 0.1470683
## 66 0.4572856 0.2907209 0.3806026 0.1448584
## 67 0.4529622 0.2987432 0.3784496 0.1432241
## 68 0.4700808 0.2916235 0.3877168 0.1503243
## 69 0.4884361 0.2896541 0.3966042 0.1572949
## 70 0.4923340 0.2901597 0.3985913 0.1588750
## 71 0.4677913 0.2883473 0.3861760 0.1491319
## 72 0.4733197 0.2896304 0.3889586 0.1512888
## 73 0.4358502 0.2984842 0.3693202 0.1363974
## 74 0.4769119 0.2910502 0.3908753 0.1527835
## 75 0.4661891 0.2894465 0.3858440 0.1488756
## 76 0.4367715 0.2986377 0.3705518 0.1373087
## 77 0.4604037 0.2905245 0.3820455 0.1459588
## 78 0.4501936 0.3014776 0.3725252 0.1387750
## 79 0.4730065 0.2888381 0.3887527 0.1511287
## 80 0.4933798 0.2941972 0.3992311 0.1593855
## 81 0.5005806 0.2963264 0.4024865 0.1619954
## 82 0.4739128 0.2882380 0.3892560 0.1515203
## 83 0.4364086 0.2988925 0.3705209 0.1372858
## 84 0.4772777 0.2935617 0.3910371 0.1529100
## 85 0.5129678 0.2943570 0.4082407 0.1666605
## 86 0.4546796 0.2959385 0.3796543 0.1441374
## 87 0.4637362 0.2876218 0.3837708 0.1472800
## 88 0.4637437 0.2936945 0.3846569 0.1479609
## 89 0.4433791 0.2988773 0.3726034 0.1388333
## 90 0.5154418 0.2954123 0.4093333 0.1675538
## 91 0.4668409 0.3017128 0.3861105 0.1490813
## 92 0.4425970 0.3056319 0.3730853 0.1391926
## 93 0.5190939 0.2987862 0.4109438 0.1688748
## 94 0.4358793 0.2989349 0.3690961 0.1362319
## 95 0.4585502 0.3005169 0.3815893 0.1456104
## 96 0.5131790 0.2945143 0.4083398 0.1667414
## 97 0.4399649 0.3031136 0.3712422 0.1378207
## 98 0.4781054 0.2921878 0.3911881 0.1530281
## 99 0.5170991 0.2965621 0.4100708 0.1681581
## 100 0.5168394 0.2982413 0.4099583 0.1680658
## 101 0.4815235 0.2883672 0.3930034 0.1544517
## 102 0.4365411 0.3017555 0.3695319 0.1365538
## 103 0.5189850 0.2982767 0.4108814 0.1688235
## 104 0.4620905 0.2981870 0.3833270 0.1469396
## 105 0.4409865 0.3031018 0.3717364 0.1381880
## 106 0.4459996 0.3071310 0.3731274 0.1392240
## 107 0.5170745 0.3009867 0.4100544 0.1681446
## 108 0.4705000 0.2905407 0.3870457 0.1498044
## 109 0.4571048 0.2986487 0.3721580 0.1385016
## 110 0.4503568 0.3009296 0.3752562 0.1408172
## 111 0.4442860 0.3029886 0.3738151 0.1397377
## 112 0.4695588 0.2901288 0.3864010 0.1493057
## 113 0.4489343 0.3068844 0.3752505 0.1408130
## 114 0.4713675 0.2981556 0.3880469 0.1505804
## 115 0.4819785 0.2935888 0.3930762 0.1545089
## 116 0.4559917 0.3078926 0.3779459 0.1428431
## 117 0.4453867 0.3037643 0.3722309 0.1385558
## 118 0.4740617 0.3077122 0.3796372 0.1441244
## 119 0.4599051 0.3066131 0.3772222 0.1422966
## 120 0.5142888 0.2976993 0.4088149 0.1671296
## 121 0.4632517 0.3029419 0.3751042 0.1407032
## 122 0.4562921 0.3031449 0.3793194 0.1438832
## 123 0.4557542 0.3061939 0.3775884 0.1425730
## 124 0.4614494 0.3040641 0.3794072 0.1439498
## 125 0.4537262 0.3118658 0.3763356 0.1416285
## 126 0.4962348 0.3094700 0.3841466 0.1475686
## 127 0.4721467 0.3004267 0.3748069 0.1404802
## 128 0.4666974 0.3087720 0.3787182 0.1434274
## 129 0.4630081 0.3087081 0.3813158 0.1454017
## 130 0.5227086 0.3113414 0.3908929 0.1527973
## 131 0.4784283 0.3105604 0.3835717 0.1471273
## 132 0.5060012 0.3053271 0.3845050 0.1478441
## 133 0.4795254 0.3235097 0.3854712 0.1485881
## 134 0.4878850 0.3053418 0.3783231 0.1431284
## 135 0.4889822 0.3207370 0.3871948 0.1499198
## 136 0.4959732 0.3163084 0.3876955 0.1503078
## 137 0.5521662 0.3214344 0.3892846 0.1515425
## 138 0.5424465 0.3271158 0.3962363 0.1570032
## 139 0.5034755 0.3175767 0.3914070 0.1531994
## 140 0.5036029 0.3163857 0.3826506 0.1464215
## 141 0.5083815 0.3266378 0.3939311 0.1551817
## 142 0.5242688 0.3289282 0.3969087 0.1575365
## 143 0.5372104 0.3302987 0.3997837 0.1598270
## 144 0.5362080 0.3311097 0.3996869 0.1597496
## 145 0.8335872 0.3297575 0.4187944 0.1753887
## 146 0.5563548 0.3282537 0.4010129 0.1608113
## 147 0.5587426 0.3350213 0.4054468 0.1643871
## 148 0.6379194 0.3392567 0.4156068 0.1727290
## 149 0.6009640 0.3350690 0.4103699 0.1684034
## 150 0.9561122 0.3359945 0.4308475 0.1856296
## 151 1.0950784 0.3373331 0.4341023 0.1884448
## 152 0.6099999 0.3486897 0.4152002 0.1723912
## 153 0.6352662 0.3450763 0.4178202 0.1745737
## 154 0.8965287 0.3520247 0.4383498 0.1921506
## 155 2.0080321 0.3492056 0.4523629 0.2046322
## 156 2.2874785 0.3443834 0.4548583 0.2068961
## 157 2.1016984 0.3713236 0.4695432 0.2204708
## 158 3.6877740 0.3823314 0.4964431 0.2464558
## 159 2.6333580 0.3756893 0.4771497 0.2276718
## 160 3.9845565 0.3806477 0.4853394 0.2355544
##
## [160 rows x 6 columns]Make sure to shutdown h2o
h2o.shutdown(prompt=F)## [1] TRUE