4/9
4/9 v2
4/10 v3
4/10 v4
4/10 v5
4/11 v6

ref: https://pyod.readthedocs.io/en/latest/pyod.models.html#all-models

1. Imports

import pandas as pd
import numpy as np
import sklearn
import pickle 
import time 
import datetime

import warnings
warnings.filterwarnings('ignore')

%run ../functions_pyod2.py

with open('../fraudTrain.pkl', 'rb') as file:
    fraudTrain = pickle.load(file)

pyod_preprocess4(비율 다 같게)

pyod(*pyod_preprocess4(fraudTrain, 0.05))

	model	time	acc	pre	rec	f1	auc	graph_based	method	throw_rate	train_size	train_cols	train_frate	test_size	test_frate	hyper_params
0	ECOD	0.215485	0.942424	0.420667	0.423206	0.421932	0.696378	False	pyod	0.05	90090	[amt]	0.050117	30030	0.04965	None
1	GMM	0.057478	0.964802	0.638747	0.670020	0.654010	0.825111	False	pyod	0.05	90090	[amt]	0.050117	30030	0.04965	None
2	HBOS	0.921637	0.949817	0.000000	0.000000	0.000000	0.499720	False	pyod	0.05	90090	[amt]	0.050117	30030	0.04965	None
3	IForest	1.873893	0.964169	0.633269	0.661301	0.646982	0.820647	False	pyod	0.05	90090	[amt]	0.050117	30030	0.04965	None
4	INNE	2.152318	0.964202	0.634541	0.657948	0.646032	0.819075	False	pyod	0.05	90090	[amt]	0.050117	30030	0.04965	None
5	KNN	0.105908	0.960306	0.598941	0.606975	0.602931	0.792871	False	pyod	0.05	90090	[amt]	0.050117	30030	0.04965	None
6	LODA	0.140978	0.949817	0.000000	0.000000	0.000000	0.499720	False	pyod	0.05	90090	[amt]	0.050117	30030	0.04965	None
7	LOF	0.186561	0.906327	0.027182	0.025486	0.026307	0.488916	False	pyod	0.05	90090	[amt]	0.050117	30030	0.04965	None
8	MCD	0.017931	0.964802	0.638747	0.670020	0.654010	0.825111	False	pyod	0.05	90090	[amt]	0.050117	30030	0.04965	None
9	PCA	0.006987	0.947153	0.468000	0.470825	0.469408	0.721432	False	pyod	0.05	90090	[amt]	0.050117	30030	0.04965	None
10	ROD	5.380978	0.900766	0.001340	0.001341	0.001340	0.474549	False	pyod	0.05	90090	[amt]	0.050117	30030	0.04965	None

pyod(*pyod_preprocess4(fraudTrain, 0.04))

	model	time	acc	pre	rec	f1	auc	graph_based	method	throw_rate	train_size	train_cols	train_frate	test_size	test_frate	hyper_params
0	ECOD	0.023447	0.952208	0.425051	0.394286	0.409091	0.685464	False	pyod	0.04	112612	[amt]	0.039347	37538	0.041957	None
1	GMM	0.021602	0.965635	0.598480	0.549841	0.573130	0.766843	False	pyod	0.04	112612	[amt]	0.039347	37538	0.041957	None
2	HBOS	0.006001	0.957616	0.000000	0.000000	0.000000	0.499778	False	pyod	0.04	112612	[amt]	0.039347	37538	0.041957	None
3	IForest	2.398027	0.965635	0.598344	0.550476	0.573413	0.767146	False	pyod	0.04	112612	[amt]	0.039347	37538	0.041957	None
4	INNE	2.700611	0.965795	0.600000	0.554286	0.576238	0.769051	False	pyod	0.04	112612	[amt]	0.039347	37538	0.041957	None
5	KNN	0.137947	0.963983	0.576318	0.534603	0.554677	0.758696	False	pyod	0.04	112612	[amt]	0.039347	37538	0.041957	None
6	LODA	0.173405	0.957616	0.000000	0.000000	0.000000	0.499778	False	pyod	0.04	112612	[amt]	0.039347	37538	0.041957	None
7	LOF	0.236837	0.914593	0.028340	0.031111	0.029661	0.492198	False	pyod	0.04	112612	[amt]	0.039347	37538	0.041957	None
8	MCD	0.021117	0.965635	0.598480	0.549841	0.573130	0.766843	False	pyod	0.04	112612	[amt]	0.039347	37538	0.041957	None
9	PCA	0.007238	0.957137	0.488420	0.455238	0.471245	0.717178	False	pyod	0.04	112612	[amt]	0.039347	37538	0.041957	None
10	ROD	5.345124	0.918536	0.000000	0.000000	0.000000	0.479382	False	pyod	0.04	112612	[amt]	0.039347	37538	0.041957	None

pyod(*pyod_preprocess4(fraudTrain, 0.03))

	model	time	acc	pre	rec	f1	auc	graph_based	method	throw_rate	train_size	train_cols	train_frate	test_size	test_frate	hyper_params
0	ECOD	0.030533	0.961778	0.385501	0.361270	0.372992	0.671280	False	pyod	0.03	150150	[amt]	0.02951	50050	0.031469	None
1	GMM	0.027331	0.969071	0.508772	0.497143	0.502890	0.740774	False	pyod	0.03	150150	[amt]	0.02951	50050	0.031469	None
2	HBOS	0.007710	0.968232	0.000000	0.000000	0.000000	0.499845	False	pyod	0.03	150150	[amt]	0.02951	50050	0.031469	None
3	IForest	3.194997	0.969091	0.509103	0.497143	0.503052	0.740784	False	pyod	0.03	150150	[amt]	0.02951	50050	0.031469	None
4	INNE	3.582502	0.964056	0.427555	0.419683	0.423582	0.700713	False	pyod	0.03	150150	[amt]	0.02951	50050	0.031469	None
5	KNN	0.176555	0.969051	0.508442	0.497143	0.502729	0.740763	False	pyod	0.03	150150	[amt]	0.02951	50050	0.031469	None
6	LODA	0.233562	0.968232	0.000000	0.000000	0.000000	0.499845	False	pyod	0.03	150150	[amt]	0.02951	50050	0.031469	None
7	LOF	0.297428	0.933546	0.030563	0.036190	0.033140	0.499446	False	pyod	0.03	150150	[amt]	0.02951	50050	0.031469	None
8	MCD	0.028167	0.969071	0.508772	0.497143	0.502890	0.740774	False	pyod	0.03	150150	[amt]	0.02951	50050	0.031469	None
9	PCA	0.009130	0.968032	0.491672	0.468571	0.479844	0.726416	False	pyod	0.03	150150	[amt]	0.02951	50050	0.031469	None
10	ROD	6.976347	0.938781	0.000671	0.000635	0.000652	0.484949	False	pyod	0.03	150150	[amt]	0.02951	50050	0.031469	None

pyod(*pyod_preprocess4(fraudTrain, 0.02))

	model	time	acc	pre	rec	f1	auc	graph_based	method	throw_rate	train_size	train_cols	train_frate	test_size	test_frate	hyper_params
0	ECOD	0.044714	0.974212	0.345406	0.349153	0.347269	0.667946	False	pyod	0.02	225225	[amt]	0.020118	75075	0.019647	None
1	GMM	0.048464	0.980060	0.492647	0.499661	0.496129	0.744674	False	pyod	0.02	225225	[amt]	0.020118	75075	0.019647	None
2	HBOS	0.010373	0.979900	0.000000	0.000000	0.000000	0.499769	False	pyod	0.02	225225	[amt]	0.020118	75075	0.019647	None
3	IForest	4.829999	0.980153	0.494949	0.498305	0.496622	0.744057	False	pyod	0.02	225225	[amt]	0.020118	75075	0.019647	None
4	INNE	5.439951	0.978701	0.456461	0.440678	0.448430	0.715081	False	pyod	0.02	225225	[amt]	0.020118	75075	0.019647	None
5	KNN	0.304592	0.978475	0.452716	0.457627	0.455158	0.723270	False	pyod	0.02	225225	[amt]	0.020118	75075	0.019647	None
6	LODA	0.344242	0.979900	0.000000	0.000000	0.000000	0.499769	False	pyod	0.02	225225	[amt]	0.020118	75075	0.019647	None
7	LOF	0.524626	0.959014	0.002484	0.002712	0.002593	0.490446	False	pyod	0.02	225225	[amt]	0.020118	75075	0.019647	None
8	MCD	0.040554	0.980060	0.492647	0.499661	0.496129	0.744674	False	pyod	0.02	225225	[amt]	0.020118	75075	0.019647	None
9	PCA	0.013512	0.980233	0.496928	0.493559	0.495238	0.741773	False	pyod	0.02	225225	[amt]	0.020118	75075	0.019647	None
10	ROD	9.216612	0.955604	0.000000	0.000000	0.000000	0.487378	False	pyod	0.02	225225	[amt]	0.020118	75075	0.019647	None

pyod(*pyod_preprocess4(fraudTrain, 0.01))

	model	time	acc	pre	rec	f1	auc	graph_based	method	throw_rate	train_size	train_cols	train_frate	test_size	test_frate	hyper_params
0	ECOD	0.085884	0.984968	0.234973	0.232275	0.233616	0.612371	False	pyod	0.01	450450	[amt]	0.010046	150150	0.009863	None
1	GMM	0.074160	0.989497	0.467168	0.461175	0.464152	0.727968	False	pyod	0.01	450450	[amt]	0.010046	150150	0.009863	None
2	HBOS	0.019325	0.989863	0.000000	0.000000	0.000000	0.499862	False	pyod	0.01	450450	[amt]	0.010046	150150	0.009863	None
3	IForest	9.515494	0.989570	0.470669	0.460500	0.465529	0.727670	False	pyod	0.01	450450	[amt]	0.010046	150150	0.009863	None
4	INNE	11.160023	0.990050	0.495160	0.449021	0.470963	0.722230	False	pyod	0.01	450450	[amt]	0.010046	150150	0.009863	None
5	KNN	0.666262	0.987992	0.389118	0.381499	0.385271	0.687766	False	pyod	0.01	450450	[amt]	0.010046	150150	0.009863	None
6	LODA	0.693432	0.989863	0.000000	0.000000	0.000000	0.499862	False	pyod	0.01	450450	[amt]	0.010046	150150	0.009863	None
7	LOF	1.075679	0.981239	0.000747	0.000675	0.000709	0.495841	False	pyod	0.01	450450	[amt]	0.010046	150150	0.009863	None
8	MCD	0.081412	0.989497	0.467168	0.461175	0.464152	0.727968	False	pyod	0.01	450450	[amt]	0.010046	150150	0.009863	None
9	PCA	0.026227	0.989497	0.467168	0.461175	0.464152	0.727968	False	pyod	0.01	450450	[amt]	0.010046	150150	0.009863	None
10	ROD	10.522309	0.979880	0.000000	0.000000	0.000000	0.494821	False	pyod	0.01	450450	[amt]	0.010046	150150	0.009863	None

pyod(*pyod_preprocess4(fraudTrain, 0.00573))

	model	time	acc	pre	rec	f1	auc	graph_based	method	throw_rate	train_size	train_cols	train_frate	test_size	test_frate	hyper_params
0	ECOD	0.156907	0.989948	0.121999	0.127978	0.124917	0.561393	False	pyod	0.00573	786126	[amt]	0.005771	262042	0.005606	None
1	GMM	0.131852	0.993051	0.384363	0.398230	0.391174	0.697317	False	pyod	0.00573	786126	[amt]	0.005771	262042	0.005606	None
2	HBOS	0.025950	0.994108	0.000000	0.000000	0.000000	0.499856	False	pyod	0.00573	786126	[amt]	0.005771	262042	0.005606	None
3	IForest	18.571275	0.993058	0.384565	0.396869	0.390620	0.696644	False	pyod	0.00573	786126	[amt]	0.005771	262042	0.005606	None
4	INNE	21.641263	0.990383	0.046592	0.036760	0.041096	0.516260	False	pyod	0.00573	786126	[amt]	0.005771	262042	0.005606	None
5	KNN	1.642282	0.992253	0.313373	0.320626	0.316958	0.658333	False	pyod	0.00573	786126	[amt]	0.005771	262042	0.005606	None
6	LODA	1.218959	0.994108	0.000000	0.000000	0.000000	0.499856	False	pyod	0.00573	786126	[amt]	0.005771	262042	0.005606	None
7	LOF	2.041921	0.989193	0.002191	0.002042	0.002114	0.498400	False	pyod	0.00573	786126	[amt]	0.005771	262042	0.005606	None
8	MCD	0.134544	0.993051	0.384363	0.398230	0.391174	0.697317	False	pyod	0.00573	786126	[amt]	0.005771	262042	0.005606	None
9	PCA	0.046515	0.993051	0.384363	0.398230	0.391174	0.697317	False	pyod	0.00573	786126	[amt]	0.005771	262042	0.005606	None
10	ROD	12.957345	0.990639	0.000000	0.000000	0.000000	0.498112	False	pyod	0.00573	786126	[amt]	0.005771	262042	0.005606	None

pyod(*pyod_preprocess4(fraudTrain, 0.006))

	model	time	acc	pre	rec	f1	auc	graph_based	method	throw_rate	train_size	train_cols	train_frate	test_size	test_frate	hyper_params
0	ECOD	0.150555	0.989758	0.121376	0.125000	0.123161	0.559882	False	pyod	0.006	750750	[amt]	0.006082	250250	0.005754	None
1	GMM	0.125489	0.992907	0.388852	0.406944	0.397693	0.701621	False	pyod	0.006	750750	[amt]	0.006082	250250	0.005754	None
2	HBOS	0.022511	0.993914	0.000000	0.000000	0.000000	0.499833	False	pyod	0.006	750750	[amt]	0.006082	250250	0.005754	None
3	IForest	17.988920	0.992915	0.388926	0.404861	0.396734	0.700590	False	pyod	0.006	750750	[amt]	0.006082	250250	0.005754	None
4	INNE	20.341954	0.992040	0.305907	0.302083	0.303983	0.649058	False	pyod	0.006	750750	[amt]	0.006082	250250	0.005754	None
5	KNN	1.267952	0.992064	0.311203	0.312500	0.311850	0.654248	False	pyod	0.006	750750	[amt]	0.006082	250250	0.005754	None
6	LODA	1.175276	0.993914	0.000000	0.000000	0.000000	0.499833	False	pyod	0.006	750750	[amt]	0.006082	250250	0.005754	None
7	LOF	1.946808	0.988779	0.000730	0.000694	0.000712	0.497596	False	pyod	0.006	750750	[amt]	0.006082	250250	0.005754	None
8	MCD	0.133159	0.992907	0.388852	0.406944	0.397693	0.701621	False	pyod	0.006	750750	[amt]	0.006082	250250	0.005754	None
9	PCA	0.045812	0.992907	0.388852	0.406944	0.397693	0.701621	False	pyod	0.006	750750	[amt]	0.006082	250250	0.005754	None
10	ROD	12.714323	0.986681	0.000000	0.000000	0.000000	0.496196	False	pyod	0.006	750750	[amt]	0.006082	250250	0.005754	None

pyod(*pyod_preprocess4(fraudTrain, 0.007))

	model	time	acc	pre	rec	f1	auc	graph_based	method	throw_rate	train_size	train_cols	train_frate	test_size	test_frate	hyper_params
0	ECOD	0.125775	0.988340	0.162347	0.157512	0.159893	0.575873	False	pyod	0.007	643500	[amt]	0.006985	214500	0.007044	None
1	GMM	0.115203	0.992051	0.431108	0.401721	0.415896	0.698980	False	pyod	0.007	643500	[amt]	0.006985	214500	0.007044	None
2	HBOS	0.019187	0.992373	0.000000	0.000000	0.000000	0.499707	False	pyod	0.007	643500	[amt]	0.006985	214500	0.007044	None
3	IForest	15.196773	0.992084	0.433735	0.405030	0.418891	0.700639	False	pyod	0.007	643500	[amt]	0.006985	214500	0.007044	None
4	INNE	17.377946	0.992014	0.408015	0.296492	0.343427	0.646720	False	pyod	0.007	643500	[amt]	0.006985	214500	0.007044	None
5	KNN	1.036415	0.990900	0.345912	0.327598	0.336506	0.661602	False	pyod	0.007	643500	[amt]	0.006985	214500	0.007044	None
6	LODA	0.997776	0.992373	0.000000	0.000000	0.000000	0.499707	False	pyod	0.007	643500	[amt]	0.006985	214500	0.007044	None
7	LOF	1.584724	0.987319	0.002469	0.001985	0.002201	0.498148	False	pyod	0.007	643500	[amt]	0.006985	214500	0.007044	None
8	MCD	0.110441	0.992051	0.431108	0.401721	0.415896	0.698980	False	pyod	0.007	643500	[amt]	0.006985	214500	0.007044	None
9	PCA	0.037883	0.992051	0.431108	0.401721	0.415896	0.698980	False	pyod	0.007	643500	[amt]	0.006985	214500	0.007044	None
10	ROD	10.144907	0.990350	0.000000	0.000000	0.000000	0.498688	False	pyod	0.007	643500	[amt]	0.006985	214500	0.007044	None

pyod(*pyod_preprocess4(fraudTrain, 0.008))

	model	time	acc	pre	rec	f1	auc	graph_based	method	throw_rate	train_size	train_cols	train_frate	test_size	test_frate	hyper_params
0	ECOD	0.108740	0.986653	0.182051	0.187707	0.184836	0.590426	False	pyod	0.008	563062	[amt]	0.00798	187688	0.008061	None
1	GMM	0.098187	0.990964	0.437966	0.426966	0.432396	0.711257	False	pyod	0.008	563062	[amt]	0.00798	187688	0.008061	None
2	HBOS	0.016854	0.991592	0.000000	0.000000	0.000000	0.499825	False	pyod	0.008	563062	[amt]	0.00798	187688	0.008061	None
3	IForest	12.728060	0.991054	0.442039	0.418374	0.429881	0.707041	False	pyod	0.008	563062	[amt]	0.00798	187688	0.008061	None
4	INNE	14.641332	0.991054	0.442039	0.418374	0.429881	0.707041	False	pyod	0.008	563062	[amt]	0.00798	187688	0.008061	None
5	KNN	0.855135	0.989445	0.343583	0.339722	0.341642	0.667224	False	pyod	0.008	563062	[amt]	0.00798	187688	0.008061	None
6	LODA	0.857619	0.991592	0.000000	0.000000	0.000000	0.499825	False	pyod	0.008	563062	[amt]	0.00798	187688	0.008061	None
7	LOF	1.349225	0.984394	0.000000	0.000000	0.000000	0.496197	False	pyod	0.008	563062	[amt]	0.00798	187688	0.008061	None
8	MCD	0.099369	0.990964	0.437966	0.426966	0.432396	0.711257	False	pyod	0.008	563062	[amt]	0.00798	187688	0.008061	None
9	PCA	0.033864	0.990964	0.437966	0.426966	0.432396	0.711257	False	pyod	0.008	563062	[amt]	0.00798	187688	0.008061	None
10	ROD	9.787888	0.985977	0.000000	0.000000	0.000000	0.496995	False	pyod	0.008	563062	[amt]	0.00798	187688	0.008061	None

pyod(*pyod_preprocess4(fraudTrain, 0.009))

	model	time	acc	pre	rec	f1	auc	graph_based	method	throw_rate	train_size	train_cols	train_frate	test_size	test_frate	hyper_params
0	ECOD	0.098144	0.985728	0.218543	0.215545	0.217034	0.604203	False	pyod	0.009	500499	[amt]	0.008941	166834	0.009177	None
1	GMM	0.082140	0.990104	0.460784	0.460483	0.460634	0.727746	False	pyod	0.009	500499	[amt]	0.008941	166834	0.009177	None
2	HBOS	0.014923	0.990446	0.000000	0.000000	0.000000	0.499809	False	pyod	0.009	500499	[amt]	0.008941	166834	0.009177	None
3	IForest	12.402523	0.990152	0.463012	0.457871	0.460427	0.726476	False	pyod	0.009	500499	[amt]	0.008941	166834	0.009177	None
4	INNE	12.438793	0.990128	0.461436	0.453298	0.457331	0.724199	False	pyod	0.009	500499	[amt]	0.008941	166834	0.009177	None
5	KNN	0.742061	0.988683	0.381710	0.376225	0.378947	0.685290	False	pyod	0.009	500499	[amt]	0.008941	166834	0.009177	None
6	LODA	0.745574	0.990446	0.000000	0.000000	0.000000	0.499809	False	pyod	0.009	500499	[amt]	0.008941	166834	0.009177	None
7	LOF	1.171870	0.982480	0.001433	0.001306	0.001367	0.496437	False	pyod	0.009	500499	[amt]	0.008941	166834	0.009177	None
8	MCD	0.089324	0.990104	0.460784	0.460483	0.460634	0.727746	False	pyod	0.009	500499	[amt]	0.008941	166834	0.009177	None
9	PCA	0.030662	0.990104	0.460784	0.460483	0.460634	0.727746	False	pyod	0.009	500499	[amt]	0.008941	166834	0.009177	None
10	ROD	9.356593	0.977894	0.000463	0.000653	0.000542	0.493799	False	pyod	0.009	500499	[amt]	0.008941	166834	0.009177	None

pyod_preprocess7

def pyod_preprocess7(fraudTrain, ratio, n):
    
    df50 = throw(fraudTrain,ratio)
    df_tr, a= sklearn.model_selection.train_test_split(df50)
        
    dfn = fraudTrain[::n]
    dfnn = dfn[~dfn.index.isin(df_tr.index)]
    dfnn = dfnn.reset_index(drop=True)
    b, df_tst = sklearn.model_selection.train_test_split(dfnn)   
    df2, mask = concat(df_tr, df_tst)
    df2['index'] = df2.index
    df = df2.reset_index()
    
    
    X = pd.DataFrame(df_tr['amt'])
    y = pd.DataFrame(df_tr['is_fraud'])
    XX = pd.DataFrame(df_tst['amt'])
    yy = pd.DataFrame(df_tst['is_fraud'])
    fraud_ratio = df.is_fraud.mean()
    predictors = {
    'ABOD': ABOD(contamination=fraud_ratio),
#    'ALAD': ALAD(contamination=fraud_ratio),
#    'AnoGAN': AnoGAN(contamination=fraud_ratio),
#    'AutoEncoder':AutoEncoder(contamination=fraud_ratio),
##    'CBLOF': CBLOF(contamination=fraud_ratio,n_clusters=2),
##    'COF': COF(contamination=fraud_ratio),
##    'CD': CD(contamination=fraud_ratio),
    'COPOD': COPOD(contamination=fraud_ratio),
#    'DeepSVDD': DeepSVDD(contamination=fraud_ratio),
#    'DIF': DIF(contamination=fraud_ratio),    
    'ECOD': ECOD(contamination=fraud_ratio),
#    'FeatureBagging': FeatureBagging(contamination=fraud_ratio),
    'GMM': GMM(contamination=fraud_ratio),
    'HBOS': HBOS(contamination=fraud_ratio),
    'IForest': IForest(contamination=fraud_ratio),
    'INNE': INNE(contamination=fraud_ratio),
    'KDE': KDE(contamination=fraud_ratio),
    'KNN': KNN(contamination=fraud_ratio),
####    'KPCA': KPCA(contamination=fraud_ratio),
#    'PyODKernelPCA': PyODKernelPCA(contamination=fraud_ratio),
##    'LMDD': LMDD(contamination=fraud_ratio),
    'LODA': LODA(contamination=fraud_ratio),
    'LOF': LOF(contamination=fraud_ratio),
####    'LOCI': LOCI(contamination=fraud_ratio),
#    'LUNAR': LUNAR(contamination=fraud_ratio),
    'LODA': LODA(contamination=fraud_ratio),
#    'LSCP': LSCP(contamination=fraud_ratio),
#    'MAD': MAD(contamination=fraud_ratio),
    'MCD': MCD(contamination=fraud_ratio),
#    'MO_GAAL': MO_GAAL(contamination=fraud_ratio),
    'OCSVM': OCSVM(contamination=fraud_ratio),
    'PCA': PCA(contamination=fraud_ratio),
###    'QMCD': QMCD(contamination=fraud_ratio),
####    'RGraph': RGraph(contamination=fraud_ratio),
    'ROD': ROD(contamination=fraud_ratio),
##    'Sampling': Sampling(contamination=fraud_ratio),
##   'SOD': SOD(contamination=fraud_ratio),
#    'SO_GAAL': SO_GAAL(contamination=fraud_ratio),
####    'SOS': SOS(contamination=fraud_ratio),
#    'SUOD': SUOD(contamination=fraud_ratio),
#    'VAE': VAE(contamination=fraud_ratio),
#    'XGBOD': XGBOD(contamination=fraud_ratio),  
}
    return X, XX, y, yy, predictors, fraud_ratio


def pyod(X,XX,y,yy,predictors,throw_rate):
    model = []
    time_diff = []
    acc = []
    pre = []
    rec = []
    f1 = [] 
    auc = [] 
    graph_based = []
    method = [] 
    train_size = []
    train_cols = []
    train_frate = []
    test_size = []
    test_frate = []
    hyper_params = [] 
    for name, predictor in predictors.items():
        t1 = time.time()
        predictor.fit(X,y)
        t2 = time.time()
        yyhat = predictor.predict(XX)
        scores = evaluate(yy,yyhat)
        model.append(name)
        time_diff.append(t2-t1)
        acc.append(scores['acc'])
        pre.append(scores['pre'])
        rec.append(scores['rec'])
        f1.append(scores['f1'])
        auc.append(scores['auc'])
        graph_based.append(False)
        method.append('pyod')
        train_size.append(len(y)),
        train_cols.append(list(X.columns)),
        train_frate.append(np.array(y).reshape(-1).mean()),
        test_size.append(len(yy)),
        test_frate.append(np.array(yy).reshape(-1).mean())
        hyper_params.append(None)
    df_results = pd.DataFrame(dict(
        model = model,
        time=time_diff,
        acc=acc,
        pre=pre,
        rec=rec,
        f1=f1,
        auc=auc,
        graph_based = graph_based,
        method = method,
        throw_rate = throw_rate,
        train_size = train_size,
        train_cols = train_cols,
        train_frate = train_frate,
        test_size = test_size,
        test_frate = test_frate,
        hyper_params = hyper_params
    ))
    ymdhms = datetime.datetime.fromtimestamp(time.time()).strftime('%Y%m%d-%H%M%S') 
    df_results.to_csv(f'../results/{ymdhms}-pyod.csv',index=False)
    return df_results

pyod(*pyod_preprocess7(fraudTrain, 0.1,10))

	model	time	acc	pre	rec	f1	auc	graph_based	method	throw_rate	train_size	train_cols	train_frate	test_size	test_frate	hyper_params
0	ABOD	2.535909	0.998444	0.000000	0.000000	0.000000	0.500000	False	pyod	0.063751	45045	[amt]	0.098368	25071	0.001556	None
1	COPOD	0.009517	0.976746	0.042088	0.641026	0.078989	0.809147	False	pyod	0.063751	45045	[amt]	0.098368	25071	0.001556	None
2	ECOD	0.009471	0.960791	0.013402	0.333333	0.025768	0.647551	False	pyod	0.063751	45045	[amt]	0.098368	25071	0.001556	None
3	GMM	0.011066	0.984564	0.042105	0.410256	0.076372	0.697858	False	pyod	0.063751	45045	[amt]	0.098368	25071	0.001556	None
4	HBOS	0.003393	0.998245	0.000000	0.000000	0.000000	0.499900	False	pyod	0.063751	45045	[amt]	0.098368	25071	0.001556	None
5	IForest	1.049790	0.984644	0.042328	0.410256	0.076739	0.697897	False	pyod	0.063751	45045	[amt]	0.098368	25071	0.001556	None
6	INNE	1.078408	0.983407	0.041363	0.435897	0.075556	0.710079	False	pyod	0.063751	45045	[amt]	0.098368	25071	0.001556	None
7	KDE	50.022221	0.982729	0.041860	0.461538	0.076759	0.722540	False	pyod	0.063751	45045	[amt]	0.098368	25071	0.001556	None
8	KNN	0.050192	0.980575	0.031381	0.384615	0.058027	0.683060	False	pyod	0.063751	45045	[amt]	0.098368	25071	0.001556	None
9	LODA	0.073967	0.998245	0.000000	0.000000	0.000000	0.499900	False	pyod	0.063751	45045	[amt]	0.098368	25071	0.001556	None
10	LOF	0.087011	0.924973	0.003772	0.179487	0.007388	0.552811	False	pyod	0.063751	45045	[amt]	0.098368	25071	0.001556	None
11	MCD	0.009805	0.984564	0.042105	0.410256	0.076372	0.697858	False	pyod	0.063751	45045	[amt]	0.098368	25071	0.001556	None
12	OCSVM	131.738376	0.982211	0.038549	0.435897	0.070833	0.709480	False	pyod	0.063751	45045	[amt]	0.098368	25071	0.001556	None
13	PCA	0.004337	0.973994	0.018838	0.307692	0.035503	0.641362	False	pyod	0.063751	45045	[amt]	0.098368	25071	0.001556	None
14	ROD	3.712238	0.928722	0.000000	0.000000	0.000000	0.465085	False	pyod	0.063751	45045	[amt]	0.098368	25071	0.001556	None

pyod(*pyod_preprocess7(fraudTrain, 0.2,10))

	model	time	acc	pre	rec	f1	auc	graph_based	method	throw_rate	train_size	train_cols	train_frate	test_size	test_frate	hyper_params
0	ABOD	1.149793	0.998674	0.000000	0.000000	0.000000	0.500000	False	pyod	0.094293	22522	[amt]	0.20016	25647	0.001326	None
1	COPOD	0.005654	0.970952	0.027888	0.617647	0.053367	0.794534	False	pyod	0.094293	22522	[amt]	0.20016	25647	0.001326	None
2	ECOD	0.005484	0.944516	0.010571	0.441176	0.020647	0.693180	False	pyod	0.094293	22522	[amt]	0.20016	25647	0.001326	None
3	GMM	0.007448	0.994931	0.112903	0.411765	0.177215	0.703735	False	pyod	0.094293	22522	[amt]	0.20016	25647	0.001326	None
4	HBOS	0.002558	0.998323	0.000000	0.000000	0.000000	0.499824	False	pyod	0.094293	22522	[amt]	0.20016	25647	0.001326	None
5	IForest	0.598845	0.981986	0.024444	0.323529	0.045455	0.653195	False	pyod	0.094293	22522	[amt]	0.20016	25647	0.001326	None
6	INNE	0.580197	0.966507	0.012987	0.323529	0.024972	0.645445	False	pyod	0.094293	22522	[amt]	0.20016	25647	0.001326	None
7	KDE	11.685877	0.979959	0.025692	0.382353	0.048148	0.681552	False	pyod	0.094293	22522	[amt]	0.20016	25647	0.001326	None
8	KNN	0.023973	0.978048	0.018215	0.294118	0.034305	0.636537	False	pyod	0.094293	22522	[amt]	0.20016	25647	0.001326	None
9	LODA	0.041146	0.998323	0.000000	0.000000	0.000000	0.499824	False	pyod	0.094293	22522	[amt]	0.20016	25647	0.001326	None
10	LOF	0.040807	0.882208	0.002333	0.205882	0.004613	0.544494	False	pyod	0.094293	22522	[amt]	0.20016	25647	0.001326	None
11	MCD	0.006230	0.994931	0.112903	0.411765	0.177215	0.703735	False	pyod	0.094293	22522	[amt]	0.20016	25647	0.001326	None
12	OCSVM	27.242269	0.979413	0.028626	0.441176	0.053763	0.710652	False	pyod	0.094293	22522	[amt]	0.20016	25647	0.001326	None
13	PCA	0.003173	0.919250	0.002443	0.147059	0.004805	0.533667	False	pyod	0.094293	22522	[amt]	0.20016	25647	0.001326	None
14	ROD	2.774923	0.907670	0.000000	0.000000	0.000000	0.454437	False	pyod	0.094293	22522	[amt]	0.20016	25647	0.001326	None

pyod(*pyod_preprocess7(fraudTrain, 0.3,10))

	model	time	acc	pre	rec	f1	auc	graph_based	method	throw_rate	train_size	train_cols	train_frate	test_size	test_frate	hyper_params
0	ABOD	0.807096	0.998800	0.000000	0.000000	0.000000	0.500000	False	pyod	0.111579	15015	[amt]	0.301499	25835	0.0012	None
1	COPOD	0.004366	0.965822	0.023490	0.677419	0.045405	0.821794	False	pyod	0.111579	15015	[amt]	0.301499	25835	0.0012	None
2	ECOD	0.004172	0.931256	0.004543	0.258065	0.008929	0.595065	False	pyod	0.111579	15015	[amt]	0.301499	25835	0.0012	None
3	GMM	0.006388	0.995239	0.057692	0.193548	0.088889	0.594875	False	pyod	0.111579	15015	[amt]	0.301499	25835	0.0012	None
4	HBOS	0.002274	0.998452	0.000000	0.000000	0.000000	0.499826	False	pyod	0.111579	15015	[amt]	0.301499	25835	0.0012	None
5	IForest	0.454341	0.982079	0.011312	0.161290	0.021142	0.572177	False	pyod	0.111579	15015	[amt]	0.301499	25835	0.0012	None
6	INNE	0.404955	0.931682	0.001151	0.064516	0.002261	0.498620	False	pyod	0.111579	15015	[amt]	0.301499	25835	0.0012	None
7	KDE	4.877100	0.969654	0.007843	0.193548	0.015075	0.582067	False	pyod	0.111579	15015	[amt]	0.301499	25835	0.0012	None
8	KNN	0.017089	0.971163	0.006906	0.161290	0.013245	0.566713	False	pyod	0.111579	15015	[amt]	0.301499	25835	0.0012	None
9	LODA	0.030604	0.998452	0.000000	0.000000	0.000000	0.499826	False	pyod	0.111579	15015	[amt]	0.301499	25835	0.0012	None
10	LOF	0.029848	0.854151	0.000801	0.096774	0.001590	0.475918	False	pyod	0.111579	15015	[amt]	0.301499	25835	0.0012	None
11	MCD	0.005008	0.995239	0.057692	0.193548	0.088889	0.594875	False	pyod	0.111579	15015	[amt]	0.301499	25835	0.0012	None
12	OCSVM	10.923152	0.967757	0.007371	0.193548	0.014201	0.581118	False	pyod	0.111579	15015	[amt]	0.301499	25835	0.0012	None
13	PCA	0.002875	0.843313	0.000000	0.000000	0.000000	0.422163	False	pyod	0.111579	15015	[amt]	0.301499	25835	0.0012	None
14	ROD	1.926554	0.998761	0.000000	0.000000	0.000000	0.499981	False	pyod	0.111579	15015	[amt]	0.301499	25835	0.0012	None

pyod(*pyod_preprocess7(fraudTrain, 0.4,10))

	model	time	acc	pre	rec	f1	auc	graph_based	method	throw_rate	train_size	train_cols	train_frate	test_size	test_frate	hyper_params
0	ABOD	0.628257	0.998264	0.000000	0.000000	0.000000	0.500000	False	pyod	0.122109	11261	[amt]	0.399254	25927	0.001736	None
1	COPOD	0.003717	0.963166	0.036660	0.800000	0.070107	0.881725	False	pyod	0.122109	11261	[amt]	0.399254	25927	0.001736	None
2	ECOD	0.003578	0.925753	0.010926	0.466667	0.021352	0.696609	False	pyod	0.122109	11261	[amt]	0.399254	25927	0.001736	None
3	GMM	0.006066	0.995102	0.140351	0.355556	0.201258	0.675885	False	pyod	0.122109	11261	[amt]	0.399254	25927	0.001736	None
4	HBOS	0.002137	0.998072	0.000000	0.000000	0.000000	0.499903	False	pyod	0.122109	11261	[amt]	0.399254	25927	0.001736	None
5	IForest	0.371490	0.979288	0.028736	0.333333	0.052910	0.656872	False	pyod	0.122109	11261	[amt]	0.399254	25927	0.001736	None
6	INNE	0.317849	0.911174	0.002205	0.111111	0.004323	0.511838	False	pyod	0.122109	11261	[amt]	0.399254	25927	0.001736	None
7	KDE	2.806262	0.949744	0.009360	0.266667	0.018086	0.608799	False	pyod	0.122109	11261	[amt]	0.399254	25927	0.001736	None
8	KNN	0.012062	0.962086	0.010438	0.222222	0.019940	0.592797	False	pyod	0.122109	11261	[amt]	0.399254	25927	0.001736	None
9	LODA	0.025498	0.998072	0.000000	0.000000	0.000000	0.499903	False	pyod	0.122109	11261	[amt]	0.399254	25927	0.001736	None
10	LOF	0.020565	0.848768	0.001543	0.133333	0.003051	0.491672	False	pyod	0.122109	11261	[amt]	0.399254	25927	0.001736	None
11	MCD	0.004548	0.995102	0.140351	0.355556	0.201258	0.675885	False	pyod	0.122109	11261	[amt]	0.399254	25927	0.001736	None
12	OCSVM	6.097080	0.950052	0.010955	0.311111	0.021164	0.631137	False	pyod	0.122109	11261	[amt]	0.399254	25927	0.001736	None
13	PCA	0.002755	0.810198	0.000000	0.000000	0.000000	0.405803	False	pyod	0.122109	11261	[amt]	0.399254	25927	0.001736	None
14	ROD	1.610515	0.998264	0.000000	0.000000	0.000000	0.500000	False	pyod	0.122109	11261	[amt]	0.399254	25927	0.001736	None

pyod(*pyod_preprocess7(fraudTrain, 0.5,10))

	model	time	acc	pre	rec	f1	auc	graph_based	method	throw_rate	train_size	train_cols	train_frate	test_size	test_frate	hyper_params
0	ABOD	0.513475	0.998845	0.000000	0.000000	0.000000	0.500000	False	pyod	0.128852	9009	[amt]	0.497058	25977	0.001155	None
1	COPOD	0.003306	0.961928	0.022886	0.766667	0.044444	0.864410	False	pyod	0.128852	9009	[amt]	0.497058	25977	0.001155	None
2	ECOD	0.003209	0.921161	0.005392	0.366667	0.010628	0.644234	False	pyod	0.128852	9009	[amt]	0.497058	25977	0.001155	None
3	GMM	0.005530	0.996266	0.096386	0.266667	0.141593	0.631888	False	pyod	0.128852	9009	[amt]	0.497058	25977	0.001155	None
4	HBOS	0.002074	0.998614	0.000000	0.000000	0.000000	0.499884	False	pyod	0.128852	9009	[amt]	0.497058	25977	0.001155	None
5	IForest	0.324964	0.942180	0.002703	0.133333	0.005298	0.538224	False	pyod	0.128852	9009	[amt]	0.497058	25977	0.001155	None
6	INNE	0.261853	0.875313	0.000933	0.100000	0.001849	0.488105	False	pyod	0.128852	9009	[amt]	0.497058	25977	0.001155	None
7	KDE	1.900880	0.941564	0.003338	0.166667	0.006545	0.554563	False	pyod	0.128852	9009	[amt]	0.497058	25977	0.001155	None
8	KNN	0.009369	0.954498	0.004303	0.166667	0.008389	0.561038	False	pyod	0.128852	9009	[amt]	0.497058	25977	0.001155	None
9	LODA	0.021968	0.998614	0.000000	0.000000	0.000000	0.499884	False	pyod	0.128852	9009	[amt]	0.497058	25977	0.001155	None
10	LOF	0.015975	0.831851	0.000691	0.100000	0.001372	0.466349	False	pyod	0.128852	9009	[amt]	0.497058	25977	0.001155	None
11	MCD	0.004099	0.996266	0.096386	0.266667	0.141593	0.631888	False	pyod	0.128852	9009	[amt]	0.497058	25977	0.001155	None
12	OCSVM	3.776082	0.942488	0.004065	0.200000	0.007968	0.571673	False	pyod	0.128852	9009	[amt]	0.497058	25977	0.001155	None
13	PCA	0.002546	0.783000	0.000000	0.000000	0.000000	0.391953	False	pyod	0.128852	9009	[amt]	0.497058	25977	0.001155	None
14	ROD	1.637666	0.998845	0.000000	0.000000	0.000000	0.500000	False	pyod	0.128852	9009	[amt]	0.497058	25977	0.001155	None

pyod(*pyod_preprocess7(fraudTrain, 0.09,10))

	model	time	acc	pre	rec	f1	auc	graph_based	method	throw_rate	train_size	train_cols	train_frate	test_size	test_frate	hyper_params
0	ABOD	3.230120	0.998237	0.000000	0.000000	0.000000	0.500000	False	pyod	0.060459	50049	[amt]	0.089732	24960	0.001763	None
1	COPOD	0.011822	0.977284	0.052991	0.704545	0.098569	0.841155	False	pyod	0.060459	50049	[amt]	0.089732	24960	0.001763	None
2	ECOD	0.011770	0.964223	0.022497	0.454545	0.042872	0.709834	False	pyod	0.060459	50049	[amt]	0.089732	24960	0.001763	None
3	GMM	0.055667	0.983253	0.063084	0.613636	0.114407	0.798771	False	pyod	0.060459	50049	[amt]	0.089732	24960	0.001763	None
4	HBOS	0.004632	0.997837	0.000000	0.000000	0.000000	0.499799	False	pyod	0.060459	50049	[amt]	0.089732	24960	0.001763	None
5	IForest	1.450632	0.982973	0.060046	0.590909	0.109015	0.787287	False	pyod	0.060459	50049	[amt]	0.089732	24960	0.001763	None
6	INNE	1.661278	0.977644	0.037770	0.477273	0.070000	0.727900	False	pyod	0.060459	50049	[amt]	0.089732	24960	0.001763	None
7	KDE	71.262674	0.982412	0.060134	0.613636	0.109533	0.798350	False	pyod	0.060459	50049	[amt]	0.089732	24960	0.001763	None
8	KNN	0.061291	0.980569	0.049080	0.545455	0.090056	0.763396	False	pyod	0.060459	50049	[amt]	0.089732	24960	0.001763	None
9	LODA	0.131766	0.997837	0.000000	0.000000	0.000000	0.499799	False	pyod	0.060459	50049	[amt]	0.089732	24960	0.001763	None
10	LOF	0.134313	0.924880	0.002175	0.090909	0.004249	0.508631	False	pyod	0.060459	50049	[amt]	0.089732	24960	0.001763	None
11	MCD	0.012015	0.983253	0.063084	0.613636	0.114407	0.798771	False	pyod	0.060459	50049	[amt]	0.089732	24960	0.001763	None
12	OCSVM	187.261724	0.981611	0.055675	0.590909	0.101761	0.786605	False	pyod	0.060459	50049	[amt]	0.089732	24960	0.001763	None
13	PCA	0.014000	0.978446	0.037453	0.454545	0.069204	0.716958	False	pyod	0.060459	50049	[amt]	0.089732	24960	0.001763	None
14	ROD	7.488965	0.938101	0.000000	0.000000	0.000000	0.469879	False	pyod	0.060459	50049	[amt]	0.089732	24960	0.001763	None

pyod(*pyod_preprocess7(fraudTrain, 0.08,10))

	model	time	acc	pre	rec	f1	auc	graph_based	method	throw_rate	train_size	train_cols	train_frate	test_size	test_frate	hyper_params
0	ABOD	4.189796	0.998226	0.000000	0.000000	0.000000	0.500000	False	pyod	0.05627	56306	[amt]	0.080276	24803	0.001774	None
1	COPOD	0.014530	0.976777	0.041379	0.545455	0.076923	0.761499	False	pyod	0.05627	56306	[amt]	0.080276	24803	0.001774	None
2	ECOD	0.014443	0.965811	0.019139	0.363636	0.036364	0.665259	False	pyod	0.05627	56306	[amt]	0.080276	24803	0.001774	None
3	GMM	0.038358	0.983067	0.048077	0.454545	0.086957	0.719276	False	pyod	0.05627	56306	[amt]	0.080276	24803	0.001774	None
4	HBOS	0.004105	0.997944	0.000000	0.000000	0.000000	0.499859	False	pyod	0.05627	56306	[amt]	0.080276	24803	0.001774	None
5	IForest	1.553486	0.983389	0.049020	0.454545	0.088496	0.719437	False	pyod	0.05627	56306	[amt]	0.080276	24803	0.001774	None
6	INNE	1.848711	0.982502	0.048611	0.477273	0.088235	0.730336	False	pyod	0.05627	56306	[amt]	0.080276	24803	0.001774	None
7	KDE	88.011782	0.982220	0.045767	0.454545	0.083160	0.718852	False	pyod	0.05627	56306	[amt]	0.080276	24803	0.001774	None
8	KNN	0.071372	0.980809	0.036481	0.386364	0.066667	0.684114	False	pyod	0.05627	56306	[amt]	0.080276	24803	0.001774	None
9	LODA	0.137621	0.997944	0.000000	0.000000	0.000000	0.499859	False	pyod	0.05627	56306	[amt]	0.080276	24803	0.001774	None
10	LOF	0.159186	0.930371	0.001776	0.068182	0.003462	0.500043	False	pyod	0.05627	56306	[amt]	0.080276	24803	0.001774	None
11	MCD	0.013139	0.983067	0.048077	0.454545	0.086957	0.719276	False	pyod	0.05627	56306	[amt]	0.080276	24803	0.001774	None
12	OCSVM	260.031710	0.981131	0.043103	0.454545	0.078740	0.718306	False	pyod	0.05627	56306	[amt]	0.080276	24803	0.001774	None
13	PCA	0.005343	0.977140	0.028829	0.363636	0.053422	0.670933	False	pyod	0.05627	56306	[amt]	0.080276	24803	0.001774	None
14	ROD	6.357995	0.939322	0.000000	0.000000	0.000000	0.470496	False	pyod	0.05627	56306	[amt]	0.080276	24803	0.001774	None

pyod(*pyod_preprocess7(fraudTrain, 0.07,10))

	model	time	acc	pre	rec	f1	auc	graph_based	method	throw_rate	train_size	train_cols	train_frate	test_size	test_frate	hyper_params
0	ABOD	2.958657	0.998740	0.000000	0.000000	0.000000	0.500000	False	pyod	0.050606	64350	[amt]	0.069479	24611	0.00126	None
1	COPOD	0.014501	0.978627	0.039106	0.677419	0.073944	0.828213	False	pyod	0.050606	64350	[amt]	0.069479	24611	0.00126	None
2	ECOD	0.014122	0.969241	0.019841	0.483871	0.038119	0.726862	False	pyod	0.050606	64350	[amt]	0.069479	24611	0.00126	None
3	GMM	0.048176	0.983422	0.045783	0.612903	0.085202	0.798396	False	pyod	0.050606	64350	[amt]	0.069479	24611	0.00126	None
4	HBOS	0.004385	0.998497	0.000000	0.000000	0.000000	0.499878	False	pyod	0.050606	64350	[amt]	0.069479	24611	0.00126	None
5	IForest	1.564718	0.983422	0.045783	0.612903	0.085202	0.798396	False	pyod	0.050606	64350	[amt]	0.069479	24611	0.00126	None
6	INNE	1.577002	0.983463	0.041463	0.548387	0.077098	0.766199	False	pyod	0.050606	64350	[amt]	0.069479	24611	0.00126	None
7	KDE	123.222591	0.983056	0.044811	0.612903	0.083516	0.798213	False	pyod	0.050606	64350	[amt]	0.069479	24611	0.00126	None
8	KNN	0.075100	0.980700	0.031646	0.483871	0.059406	0.732599	False	pyod	0.050606	64350	[amt]	0.069479	24611	0.00126	None
9	LODA	0.157073	0.998497	0.000000	0.000000	0.000000	0.499878	False	pyod	0.050606	64350	[amt]	0.069479	24611	0.00126	None
10	LOF	0.204140	0.946528	0.000777	0.032258	0.001517	0.489970	False	pyod	0.050606	64350	[amt]	0.069479	24611	0.00126	None
11	MCD	0.015097	0.983422	0.045783	0.612903	0.085202	0.798396	False	pyod	0.050606	64350	[amt]	0.069479	24611	0.00126	None
12	OCSVM	256.638857	0.982488	0.043379	0.612903	0.081023	0.797928	False	pyod	0.050606	64350	[amt]	0.069479	24611	0.00126	None
13	PCA	0.005676	0.978668	0.028626	0.483871	0.054054	0.731582	False	pyod	0.050606	64350	[amt]	0.069479	24611	0.00126	None
14	ROD	6.052641	0.946325	0.000000	0.000000	0.000000	0.473759	False	pyod	0.050606	64350	[amt]	0.069479	24611	0.00126	None

pyod(*pyod_preprocess7(fraudTrain, 0.06,10))

pyod(*pyod_preprocess7(fraudTrain, 0.05,10))

pyod(*pyod_preprocess7(fraudTrain, 0.04,10))

pyod(*pyod_preprocess7(fraudTrain, 0.03,10))

pyod(*pyod_preprocess7(fraudTrain, 0.02,10))

pyod(*pyod_preprocess7(fraudTrain, 0.01,10))

pyod_preproecess10: 비율 다르게 test_size정할수 잇음

pyod(*pyod_preprocess10(fraudTrain, 0.3, 0.05))

	model	time	acc	pre	rec	f1	auc	graph_based	method	throw_rate	train_size	train_cols	train_frate	test_size	test_frate	hyper_params
0	ABOD	0.774618	0.950050	0.000000	0.000000	0.000000	0.500000	False	pyod	0.3	14014	[amt]	0.407164	6006	0.04995	None
1	COPOD	0.004098	0.749417	0.138138	0.766667	0.234097	0.757589	False	pyod	0.3	14014	[amt]	0.407164	6006	0.04995	None
2	ECOD	0.003965	0.719447	0.116768	0.703333	0.200285	0.711814	False	pyod	0.3	14014	[amt]	0.407164	6006	0.04995	None
3	GMM	0.006296	0.706294	0.093785	0.563333	0.160799	0.638572	False	pyod	0.3	14014	[amt]	0.407164	6006	0.04995	None
4	HBOS	0.002163	0.949717	0.000000	0.000000	0.000000	0.499825	False	pyod	0.3	14014	[amt]	0.407164	6006	0.04995	None
5	IForest	0.421494	0.825674	0.189526	0.760000	0.303393	0.794564	False	pyod	0.3	14014	[amt]	0.407164	6006	0.04995	None
6	INNE	0.374009	0.779387	0.140855	0.670000	0.232774	0.727569	False	pyod	0.3	14014	[amt]	0.407164	6006	0.04995	None
7	KDE	4.314706	0.845155	0.213115	0.780000	0.334764	0.814290	False	pyod	0.3	14014	[amt]	0.407164	6006	0.04995	None
8	KNN	0.015324	0.816683	0.176755	0.730000	0.284600	0.775620	False	pyod	0.3	14014	[amt]	0.407164	6006	0.04995	None
9	LODA	0.028843	0.949717	0.000000	0.000000	0.000000	0.499825	False	pyod	0.3	14014	[amt]	0.407164	6006	0.04995	None
10	LOF	0.026128	0.511988	0.051483	0.503333	0.093412	0.507888	False	pyod	0.3	14014	[amt]	0.407164	6006	0.04995	None
11	MCD	0.004677	0.847486	0.215867	0.780000	0.338150	0.815517	False	pyod	0.3	14014	[amt]	0.407164	6006	0.04995	None
12	OCSVM	8.785761	0.808525	0.171561	0.740000	0.278545	0.776064	False	pyod	0.3	14014	[amt]	0.407164	6006	0.04995	None
13	PCA	0.002809	0.454545	0.020619	0.213333	0.037603	0.340280	False	pyod	0.3	14014	[amt]	0.407164	6006	0.04995	None
14	ROD	1.670733	0.583417	0.027062	0.210000	0.047945	0.406525	False	pyod	0.3	14014	[amt]	0.407164	6006	0.04995	None

pyod(*pyod_preprocess10(fraudTrain, 0.3, 0.005))

	model	time	acc	pre	rec	f1	auc	graph_based	method	throw_rate	train_size	train_cols	train_frate	test_size	test_frate	hyper_params
0	ABOD	0.769284	0.995005	0.000000	0.000000	0.000000	0.500000	False	pyod	0.3	14014	[amt]	0.426431	6006	0.004995	None
1	COPOD	0.004046	0.722611	0.015976	0.900000	0.031395	0.810860	False	pyod	0.3	14014	[amt]	0.426431	6006	0.004995	None
2	ECOD	0.003975	0.712121	0.013738	0.800000	0.027012	0.755840	False	pyod	0.3	14014	[amt]	0.426431	6006	0.004995	None
3	GMM	0.006271	0.703130	0.010609	0.633333	0.020868	0.668407	False	pyod	0.3	14014	[amt]	0.426431	6006	0.004995	None
4	HBOS	0.002160	0.994672	0.000000	0.000000	0.000000	0.499833	False	pyod	0.3	14014	[amt]	0.426431	6006	0.004995	None
5	IForest	0.423568	0.837496	0.027000	0.900000	0.052427	0.868591	False	pyod	0.3	14014	[amt]	0.426431	6006	0.004995	None
6	INNE	0.371282	0.764902	0.014747	0.700000	0.028886	0.732614	False	pyod	0.3	14014	[amt]	0.426431	6006	0.004995	None
7	KDE	4.280936	0.835498	0.026680	0.900000	0.051823	0.867587	False	pyod	0.3	14014	[amt]	0.426431	6006	0.004995	None
8	KNN	0.015303	0.805361	0.020219	0.800000	0.039441	0.802694	False	pyod	0.3	14014	[amt]	0.426431	6006	0.004995	None
9	LODA	0.028646	0.994672	0.000000	0.000000	0.000000	0.499833	False	pyod	0.3	14014	[amt]	0.426431	6006	0.004995	None
10	LOF	0.026170	0.494339	0.003632	0.366667	0.007192	0.430823	False	pyod	0.3	14014	[amt]	0.426431	6006	0.004995	None
11	MCD	0.004618	0.835997	0.026759	0.900000	0.051973	0.867838	False	pyod	0.3	14014	[amt]	0.426431	6006	0.004995	None
12	OCSVM	8.879913	0.776557	0.019062	0.866667	0.037303	0.821386	False	pyod	0.3	14014	[amt]	0.426431	6006	0.004995	None
13	PCA	0.002808	0.419414	0.000866	0.100000	0.001718	0.260509	False	pyod	0.3	14014	[amt]	0.426431	6006	0.004995	None
14	ROD	1.891805	0.561605	0.001150	0.100000	0.002274	0.331961	False	pyod	0.3	14014	[amt]	0.426431	6006	0.004995	None

pyod(*pyod_preprocess10(fraudTrain, 0.2, 0.05))

	model	time	acc	pre	rec	f1	auc	graph_based	method	throw_rate	train_size	train_cols	train_frate	test_size	test_frate	hyper_params
0	ABOD	1.091977	0.950050	0.000000	0.000000	0.000000	0.500000	False	pyod	0.2	21021	[amt]	0.264307	9009	0.04995	None
1	COPOD	0.005299	0.855256	0.223803	0.768889	0.346693	0.814343	False	pyod	0.2	21021	[amt]	0.264307	9009	0.04995	None
2	ECOD	0.005203	0.806971	0.151056	0.620000	0.242926	0.718401	False	pyod	0.2	21021	[amt]	0.264307	9009	0.04995	None
3	GMM	0.007281	0.807193	0.136646	0.537778	0.217920	0.679568	False	pyod	0.2	21021	[amt]	0.264307	9009	0.04995	None
4	HBOS	0.002413	0.949828	0.000000	0.000000	0.000000	0.499883	False	pyod	0.2	21021	[amt]	0.264307	9009	0.04995	None
5	IForest	0.563117	0.907759	0.321796	0.764444	0.452930	0.839869	False	pyod	0.2	21021	[amt]	0.264307	9009	0.04995	None
6	INNE	0.537732	0.903985	0.309458	0.748889	0.437947	0.830514	False	pyod	0.2	21021	[amt]	0.264307	9009	0.04995	None
7	KDE	10.283546	0.905206	0.313653	0.755556	0.443286	0.834315	False	pyod	0.2	21021	[amt]	0.264307	9009	0.04995	None
8	KNN	0.021698	0.894439	0.283865	0.731111	0.408950	0.817069	False	pyod	0.2	21021	[amt]	0.264307	9009	0.04995	None
9	LODA	0.039037	0.949828	0.000000	0.000000	0.000000	0.499883	False	pyod	0.2	21021	[amt]	0.264307	9009	0.04995	None
10	LOF	0.037507	0.662893	0.055040	0.355556	0.095323	0.517303	False	pyod	0.2	21021	[amt]	0.264307	9009	0.04995	None
11	MCD	0.005883	0.908980	0.325142	0.764444	0.456233	0.840512	False	pyod	0.2	21021	[amt]	0.264307	9009	0.04995	None
12	OCSVM	20.635448	0.905428	0.314233	0.755556	0.443864	0.834432	False	pyod	0.2	21021	[amt]	0.264307	9009	0.04995	None
13	PCA	0.003042	0.667999	0.027520	0.164444	0.047149	0.429459	False	pyod	0.2	21021	[amt]	0.264307	9009	0.04995	None
14	ROD	2.520514	0.688534	0.017609	0.095556	0.029737	0.407633	False	pyod	0.2	21021	[amt]	0.264307	9009	0.04995	None

pyod(*pyod_preprocess10(fraudTrain, 0.2, 0.005))

	model	time	acc	pre	rec	f1	auc	graph_based	method	throw_rate	train_size	train_cols	train_frate	test_size	test_frate	hyper_params
0	ABOD	1.095272	0.995005	0.000000	0.000000	0.000000	0.500000	False	pyod	0.2	21021	[amt]	0.283574	9009	0.004995	None
1	COPOD	0.005250	0.837829	0.024194	0.800000	0.046967	0.819009	False	pyod	0.2	21021	[amt]	0.283574	9009	0.004995	None
2	ECOD	0.005125	0.805639	0.016988	0.666667	0.033131	0.736502	False	pyod	0.2	21021	[amt]	0.283574	9009	0.004995	None
3	GMM	0.007286	0.804973	0.013636	0.533333	0.026593	0.669835	False	pyod	0.2	21021	[amt]	0.283574	9009	0.004995	None
4	HBOS	0.002410	0.994672	0.000000	0.000000	0.000000	0.499833	False	pyod	0.2	21021	[amt]	0.283574	9009	0.004995	None
5	IForest	0.563799	0.909757	0.042857	0.800000	0.081356	0.855154	False	pyod	0.2	21021	[amt]	0.283574	9009	0.004995	None
6	INNE	0.528354	0.892219	0.034205	0.755556	0.065448	0.824230	False	pyod	0.2	21021	[amt]	0.283574	9009	0.004995	None
7	KDE	10.531130	0.903985	0.040359	0.800000	0.076841	0.852253	False	pyod	0.2	21021	[amt]	0.283574	9009	0.004995	None
8	KNN	0.021430	0.893884	0.033777	0.733333	0.064579	0.814012	False	pyod	0.2	21021	[amt]	0.283574	9009	0.004995	None
9	LODA	0.038733	0.994672	0.000000	0.000000	0.000000	0.499833	False	pyod	0.2	21021	[amt]	0.283574	9009	0.004995	None
10	LOF	0.037428	0.660340	0.004926	0.333333	0.009709	0.497657	False	pyod	0.2	21021	[amt]	0.283574	9009	0.004995	None
11	MCD	0.005760	0.908314	0.042204	0.800000	0.080178	0.854429	False	pyod	0.2	21021	[amt]	0.283574	9009	0.004995	None
12	OCSVM	20.519797	0.902875	0.039911	0.800000	0.076030	0.851696	False	pyod	0.2	21021	[amt]	0.283574	9009	0.004995	None
13	PCA	0.003253	0.669331	0.002037	0.133333	0.004012	0.402677	False	pyod	0.2	21021	[amt]	0.283574	9009	0.004995	None
14	ROD	2.924760	0.744145	0.000442	0.022222	0.000867	0.384996	False	pyod	0.2	21021	[amt]	0.283574	9009	0.004995	None

pyod(*pyod_preprocess10(fraudTrain, 0.2, 0.0005))

	model	time	acc	pre	rec	f1	auc	graph_based	method	throw_rate	train_size	train_cols	train_frate	test_size	test_frate	hyper_params
0	ABOD	1.092710	0.999556	0.000000	0.00	0.000000	0.500000	False	pyod	0.2	21021	[amt]	0.285524	9009	0.000444	None
1	COPOD	0.005288	0.835942	0.002027	0.75	0.004043	0.792990	False	pyod	0.2	21021	[amt]	0.285524	9009	0.000444	None
2	ECOD	0.005159	0.805528	0.001710	0.75	0.003413	0.777776	False	pyod	0.2	21021	[amt]	0.285524	9009	0.000444	None
3	GMM	0.010358	0.804529	0.000569	0.25	0.001134	0.527388	False	pyod	0.2	21021	[amt]	0.285524	9009	0.000444	None
4	HBOS	0.002431	0.999223	0.000000	0.00	0.000000	0.499833	False	pyod	0.2	21021	[amt]	0.285524	9009	0.000444	None
5	IForest	0.564802	0.908536	0.003632	0.75	0.007229	0.829303	False	pyod	0.2	21021	[amt]	0.285524	9009	0.000444	None
6	INNE	0.526330	0.856921	0.001552	0.50	0.003094	0.678540	False	pyod	0.2	21021	[amt]	0.285524	9009	0.000444	None
7	KDE	10.406649	0.904096	0.003464	0.75	0.006897	0.827082	False	pyod	0.2	21021	[amt]	0.285524	9009	0.000444	None
8	KNN	0.021723	0.894439	0.002103	0.50	0.004188	0.697307	False	pyod	0.2	21021	[amt]	0.285524	9009	0.000444	None
9	LODA	0.039089	0.999223	0.000000	0.00	0.000000	0.499833	False	pyod	0.2	21021	[amt]	0.285524	9009	0.000444	None
10	LOF	0.037239	0.661672	0.000984	0.75	0.001965	0.705816	False	pyod	0.2	21021	[amt]	0.285524	9009	0.000444	None
11	MCD	0.005762	0.908425	0.003628	0.75	0.007220	0.829248	False	pyod	0.2	21021	[amt]	0.285524	9009	0.000444	None
12	OCSVM	20.567278	0.902431	0.003405	0.75	0.006780	0.826249	False	pyod	0.2	21021	[amt]	0.285524	9009	0.000444	None
13	PCA	0.003019	0.671329	0.000000	0.00	0.000000	0.335813	False	pyod	0.2	21021	[amt]	0.285524	9009	0.000444	None
14	ROD	2.454930	0.748363	0.000000	0.00	0.000000	0.374348	False	pyod	0.2	21021	[amt]	0.285524	9009	0.000444	None

pyod(*pyod_preprocess10(fraudTrain, 0.1, 0.05))

	model	time	acc	pre	rec	f1	auc	graph_based	method	throw_rate	train_size	train_cols	train_frate	test_size	test_frate	hyper_params
0	ABOD	1.946881	0.950050	0.000000	0.000000	0.000000	0.500000	False	pyod	0.1	42042	[amt]	0.12145	18018	0.04995	None
1	COPOD	0.008923	0.940004	0.442246	0.770000	0.561816	0.859471	False	pyod	0.1	42042	[amt]	0.12145	18018	0.04995	None
2	ECOD	0.008774	0.900155	0.251245	0.504444	0.335427	0.712702	False	pyod	0.1	42042	[amt]	0.12145	18018	0.04995	None
3	GMM	0.010457	0.955045	0.535322	0.757778	0.627415	0.861597	False	pyod	0.1	42042	[amt]	0.12145	18018	0.04995	None
4	HBOS	0.003158	0.949495	0.000000	0.000000	0.000000	0.499708	False	pyod	0.1	42042	[amt]	0.12145	18018	0.04995	None
5	IForest	0.962415	0.952103	0.514111	0.748889	0.609679	0.855838	False	pyod	0.1	42042	[amt]	0.12145	18018	0.04995	None
6	INNE	1.006637	0.955156	0.535881	0.763333	0.629698	0.864287	False	pyod	0.1	42042	[amt]	0.12145	18018	0.04995	None
7	KDE	43.868710	0.947441	0.482682	0.727778	0.580416	0.843384	False	pyod	0.1	42042	[amt]	0.12145	18018	0.04995	None
8	KNN	0.044747	0.941947	0.446715	0.680000	0.539207	0.817860	False	pyod	0.1	42042	[amt]	0.12145	18018	0.04995	None
9	LODA	0.084089	0.949495	0.000000	0.000000	0.000000	0.499708	False	pyod	0.1	42042	[amt]	0.12145	18018	0.04995	None
10	LOF	0.076161	0.821567	0.075541	0.228889	0.113593	0.540809	False	pyod	0.1	42042	[amt]	0.12145	18018	0.04995	None
11	MCD	0.009043	0.955433	0.537802	0.766667	0.632158	0.866012	False	pyod	0.1	42042	[amt]	0.12145	18018	0.04995	None
12	OCSVM	92.559464	0.945943	0.473188	0.725556	0.572807	0.841543	False	pyod	0.1	42042	[amt]	0.12145	18018	0.04995	None
13	PCA	0.004151	0.890054	0.195493	0.385556	0.259439	0.651067	False	pyod	0.1	42042	[amt]	0.12145	18018	0.04995	None
14	ROD	3.441422	0.822233	0.001299	0.003333	0.001870	0.434311	False	pyod	0.1	42042	[amt]	0.12145	18018	0.04995	None

pyod(*pyod_preprocess10(fraudTrain, 0.3, 0.005))

	model	time	acc	pre	rec	f1	auc	graph_based	method	throw_rate	train_size	train_cols	train_frate	test_size	test_frate	hyper_params
0	ABOD	0.771734	0.995005	0.000000	0.000000	0.000000	0.500000	False	pyod	0.3	14014	[amt]	0.426431	6006	0.004995	None
1	COPOD	0.004185	0.722611	0.015976	0.900000	0.031395	0.810860	False	pyod	0.3	14014	[amt]	0.426431	6006	0.004995	None
2	ECOD	0.004011	0.712121	0.013738	0.800000	0.027012	0.755840	False	pyod	0.3	14014	[amt]	0.426431	6006	0.004995	None
3	GMM	0.006114	0.703130	0.010609	0.633333	0.020868	0.668407	False	pyod	0.3	14014	[amt]	0.426431	6006	0.004995	None
4	HBOS	0.002146	0.994672	0.000000	0.000000	0.000000	0.499833	False	pyod	0.3	14014	[amt]	0.426431	6006	0.004995	None
5	IForest	0.422542	0.822178	0.024725	0.900000	0.048128	0.860894	False	pyod	0.3	14014	[amt]	0.426431	6006	0.004995	None
6	INNE	0.359052	0.640693	0.007863	0.566667	0.015511	0.603865	False	pyod	0.3	14014	[amt]	0.426431	6006	0.004995	None
7	KDE	4.289624	0.835498	0.026680	0.900000	0.051823	0.867587	False	pyod	0.3	14014	[amt]	0.426431	6006	0.004995	None
8	KNN	0.015256	0.805361	0.020219	0.800000	0.039441	0.802694	False	pyod	0.3	14014	[amt]	0.426431	6006	0.004995	None
9	LODA	0.029047	0.994672	0.000000	0.000000	0.000000	0.499833	False	pyod	0.3	14014	[amt]	0.426431	6006	0.004995	None
10	LOF	0.026283	0.494339	0.003632	0.366667	0.007192	0.430823	False	pyod	0.3	14014	[amt]	0.426431	6006	0.004995	None
11	MCD	0.004666	0.835997	0.026759	0.900000	0.051973	0.867838	False	pyod	0.3	14014	[amt]	0.426431	6006	0.004995	None
12	OCSVM	8.597896	0.776557	0.019062	0.866667	0.037303	0.821386	False	pyod	0.3	14014	[amt]	0.426431	6006	0.004995	None
13	PCA	0.002833	0.419414	0.000866	0.100000	0.001718	0.260509	False	pyod	0.3	14014	[amt]	0.426431	6006	0.004995	None
14	ROD	1.817225	0.561605	0.001150	0.100000	0.002274	0.331961	False	pyod	0.3	14014	[amt]	0.426431	6006	0.004995	None

pyod(*pyod_preprocess10(fraudTrain, 0.2, 0.005))

	model	time	acc	pre	rec	f1	auc	graph_based	method	throw_rate	train_size	train_cols	train_frate	test_size	test_frate	hyper_params
0	ABOD	1.079066	0.995005	0.000000	0.000000	0.000000	0.500000	False	pyod	0.2	21021	[amt]	0.283574	9009	0.004995	None
1	COPOD	0.005168	0.837829	0.024194	0.800000	0.046967	0.819009	False	pyod	0.2	21021	[amt]	0.283574	9009	0.004995	None
2	ECOD	0.005130	0.805639	0.016988	0.666667	0.033131	0.736502	False	pyod	0.2	21021	[amt]	0.283574	9009	0.004995	None
3	GMM	0.007339	0.804973	0.013636	0.533333	0.026593	0.669835	False	pyod	0.2	21021	[amt]	0.283574	9009	0.004995	None
4	HBOS	0.002404	0.994672	0.000000	0.000000	0.000000	0.499833	False	pyod	0.2	21021	[amt]	0.283574	9009	0.004995	None
5	IForest	0.569661	0.907981	0.042056	0.800000	0.079911	0.854261	False	pyod	0.2	21021	[amt]	0.283574	9009	0.004995	None
6	INNE	0.514986	0.877123	0.029255	0.733333	0.056266	0.805589	False	pyod	0.2	21021	[amt]	0.283574	9009	0.004995	None
7	KDE	10.367432	0.903985	0.040359	0.800000	0.076841	0.852253	False	pyod	0.2	21021	[amt]	0.283574	9009	0.004995	None
8	KNN	0.021266	0.893884	0.033777	0.733333	0.064579	0.814012	False	pyod	0.2	21021	[amt]	0.283574	9009	0.004995	None
9	LODA	0.038907	0.994672	0.000000	0.000000	0.000000	0.499833	False	pyod	0.2	21021	[amt]	0.283574	9009	0.004995	None
10	LOF	0.036725	0.660340	0.004926	0.333333	0.009709	0.497657	False	pyod	0.2	21021	[amt]	0.283574	9009	0.004995	None
11	MCD	0.005748	0.908314	0.042204	0.800000	0.080178	0.854429	False	pyod	0.2	21021	[amt]	0.283574	9009	0.004995	None
12	OCSVM	20.289997	0.902875	0.039911	0.800000	0.076030	0.851696	False	pyod	0.2	21021	[amt]	0.283574	9009	0.004995	None
13	PCA	0.003034	0.669331	0.002037	0.133333	0.004012	0.402677	False	pyod	0.2	21021	[amt]	0.283574	9009	0.004995	None
14	ROD	2.956641	0.744145	0.000442	0.022222	0.000867	0.384996	False	pyod	0.2	21021	[amt]	0.283574	9009	0.004995	None

pyod(*pyod_preprocess10(fraudTrain, 0.09, 0.005))

	model	time	acc	pre	rec	f1	auc	graph_based	method	throw_rate	train_size	train_cols	train_frate	test_size	test_frate	hyper_params
0	ABOD	2.118368	0.995005	0.000000	0.00	0.000000	0.500000	False	pyod	0.09	46714	[amt]	0.126429	20019	0.004995	None
1	COPOD	0.009918	0.936810	0.059046	0.78	0.109782	0.858799	False	pyod	0.09	46714	[amt]	0.126429	20019	0.004995	None
2	ECOD	0.009780	0.910435	0.029461	0.53	0.055819	0.721172	False	pyod	0.09	46714	[amt]	0.126429	20019	0.004995	None
3	GMM	0.012681	0.963784	0.097812	0.76	0.173318	0.862404	False	pyod	0.09	46714	[amt]	0.126429	20019	0.004995	None
4	HBOS	0.003287	0.994655	0.000000	0.00	0.000000	0.499824	False	pyod	0.09	46714	[amt]	0.126429	20019	0.004995	None
5	IForest	1.057976	0.958190	0.081725	0.72	0.146789	0.839693	False	pyod	0.09	46714	[amt]	0.126429	20019	0.004995	None
6	INNE	1.072577	0.962436	0.089421	0.71	0.158837	0.836851	False	pyod	0.09	46714	[amt]	0.126429	20019	0.004995	None
7	KDE	51.495988	0.956491	0.080522	0.74	0.145240	0.848789	False	pyod	0.09	46714	[amt]	0.126429	20019	0.004995	None
8	KNN	0.050351	0.953644	0.069647	0.67	0.126177	0.812534	False	pyod	0.09	46714	[amt]	0.126429	20019	0.004995	None
9	LODA	0.075929	0.994655	0.000000	0.00	0.000000	0.499824	False	pyod	0.09	46714	[amt]	0.126429	20019	0.004995	None
10	LOF	0.086652	0.839752	0.004780	0.15	0.009265	0.496608	False	pyod	0.09	46714	[amt]	0.126429	20019	0.004995	None
11	MCD	0.009637	0.966032	0.103825	0.76	0.182692	0.863533	False	pyod	0.09	46714	[amt]	0.126429	20019	0.004995	None
12	OCSVM	116.052746	0.955992	0.078749	0.73	0.142162	0.843563	False	pyod	0.09	46714	[amt]	0.126429	20019	0.004995	None
13	PCA	0.004285	0.901444	0.017517	0.34	0.033317	0.622131	False	pyod	0.09	46714	[amt]	0.126429	20019	0.004995	None
14	ROD	4.076229	0.850242	0.000345	0.01	0.000667	0.432230	False	pyod	0.09	46714	[amt]	0.126429	20019	0.004995	None

pyod(*pyod_preprocess10(fraudTrain, 0.08, 0.005))

	model	time	acc	pre	rec	f1	auc	graph_based	method	throw_rate	train_size	train_cols	train_frate	test_size	test_frate	hyper_params
0	ABOD	2.355942	0.995027	0.000000	0.000000	0.000000	0.500000	False	pyod	0.08	52553	[amt]	0.112153	22522	0.004973	None
1	COPOD	0.011052	0.945076	0.064965	0.750000	0.119573	0.848025	False	pyod	0.08	52553	[amt]	0.112153	22522	0.004973	None
2	ECOD	0.010783	0.924296	0.033392	0.508929	0.062672	0.717650	False	pyod	0.08	52553	[amt]	0.112153	22522	0.004973	None
3	GMM	0.011898	0.968431	0.106439	0.723214	0.185567	0.846435	False	pyod	0.08	52553	[amt]	0.112153	22522	0.004973	None
4	HBOS	0.003509	0.994583	0.000000	0.000000	0.000000	0.499777	False	pyod	0.08	52553	[amt]	0.112153	22522	0.004973	None
5	IForest	1.144744	0.967587	0.101804	0.705357	0.177928	0.837127	False	pyod	0.08	52553	[amt]	0.112153	22522	0.004973	None
6	INNE	1.216866	0.967587	0.100775	0.696429	0.176072	0.832686	False	pyod	0.08	52553	[amt]	0.112153	22522	0.004973	None
7	KDE	64.947974	0.962703	0.089165	0.705357	0.158317	0.834673	False	pyod	0.08	52553	[amt]	0.112153	22522	0.004973	None
8	KNN	0.059123	0.958929	0.074346	0.633929	0.133083	0.797241	False	pyod	0.08	52553	[amt]	0.112153	22522	0.004973	None
9	LODA	0.083192	0.994583	0.000000	0.000000	0.000000	0.499777	False	pyod	0.08	52553	[amt]	0.112153	22522	0.004973	None
10	LOF	0.101365	0.853921	0.004367	0.125000	0.008439	0.491282	False	pyod	0.08	52553	[amt]	0.112153	22522	0.004973	None
11	MCD	0.010848	0.970429	0.114206	0.732143	0.197590	0.851881	False	pyod	0.08	52553	[amt]	0.112153	22522	0.004973	None
12	OCSVM	147.615001	0.961105	0.085683	0.705357	0.152805	0.833870	False	pyod	0.08	52553	[amt]	0.112153	22522	0.004973	None
13	PCA	0.004609	0.922787	0.023433	0.357143	0.043980	0.641378	False	pyod	0.08	52553	[amt]	0.112153	22522	0.004973	None
14	ROD	6.129475	0.872081	0.000361	0.008929	0.000694	0.442662	False	pyod	0.08	52553	[amt]	0.112153	22522	0.004973	None

pyod(*pyod_preprocess10(fraudTrain, 0.07, 0.005))

	model	time	acc	pre	rec	f1	auc	graph_based	method	throw_rate	train_size	train_cols	train_frate	test_size	test_frate	hyper_params
0	ABOD	2.627215	0.995027	0.000000	0.000000	0.000000	0.500000	False	pyod	0.07	60060	[amt]	0.097869	25740	0.004973	None
1	COPOD	0.012201	0.951360	0.073596	0.757812	0.134163	0.855070	False	pyod	0.07	60060	[amt]	0.097869	25740	0.004973	None
2	ECOD	0.011990	0.932129	0.035571	0.484375	0.066275	0.709371	False	pyod	0.07	60060	[amt]	0.097869	25740	0.004973	None
3	GMM	0.013061	0.972416	0.122078	0.734375	0.209354	0.853991	False	pyod	0.07	60060	[amt]	0.097869	25740	0.004973	None
4	HBOS	0.003768	0.994639	0.000000	0.000000	0.000000	0.499805	False	pyod	0.07	60060	[amt]	0.097869	25740	0.004973	None
5	IForest	1.307437	0.970008	0.112981	0.734375	0.195833	0.852780	False	pyod	0.07	60060	[amt]	0.097869	25740	0.004973	None
6	INNE	1.337039	0.972688	0.123198	0.734375	0.210999	0.854127	False	pyod	0.07	60060	[amt]	0.097869	25740	0.004973	None
7	KDE	84.247617	0.965035	0.094538	0.703125	0.166667	0.834734	False	pyod	0.07	60060	[amt]	0.097869	25740	0.004973	None
8	KNN	0.070247	0.964452	0.087958	0.656250	0.155125	0.811121	False	pyod	0.07	60060	[amt]	0.097869	25740	0.004973	None
9	LODA	0.094346	0.994639	0.000000	0.000000	0.000000	0.499805	False	pyod	0.07	60060	[amt]	0.097869	25740	0.004973	None
10	LOF	0.120878	0.880575	0.005040	0.117188	0.009665	0.500789	False	pyod	0.07	60060	[amt]	0.097869	25740	0.004973	None
11	MCD	0.011881	0.972416	0.122078	0.734375	0.209354	0.853991	False	pyod	0.07	60060	[amt]	0.097869	25740	0.004973	None
12	OCSVM	201.603599	0.965229	0.095037	0.703125	0.167442	0.834832	False	pyod	0.07	60060	[amt]	0.097869	25740	0.004973	None
13	PCA	0.004737	0.936713	0.031815	0.398438	0.058925	0.668920	False	pyod	0.07	60060	[amt]	0.097869	25740	0.004973	None
14	ROD	4.642633	0.886869	0.000359	0.007812	0.000686	0.449537	False	pyod	0.07	60060	[amt]	0.097869	25740	0.004973	None

pyod(*pyod_preprocess10(fraudTrain, 0.06, 0.005))

	model	time	acc	pre	rec	f1	auc	graph_based	method	throw_rate	train_size	train_cols	train_frate	test_size	test_frate	hyper_params
0	ABOD	2.976102	0.995005	0.000000	0.000000	0.000000	0.500000	False	pyod	0.06	70070	[amt]	0.083574	30030	0.004995	None
1	COPOD	0.014337	0.956876	0.079353	0.720000	0.142952	0.839033	False	pyod	0.06	70070	[amt]	0.083574	30030	0.004995	None
2	ECOD	0.014195	0.938795	0.039301	0.480000	0.072654	0.710549	False	pyod	0.06	70070	[amt]	0.083574	30030	0.004995	None
3	GMM	0.014622	0.974126	0.127229	0.713333	0.215943	0.844384	False	pyod	0.06	70070	[amt]	0.083574	30030	0.004995	None
4	HBOS	0.004169	0.994672	0.000000	0.000000	0.000000	0.499833	False	pyod	0.06	70070	[amt]	0.083574	30030	0.004995	None
5	IForest	1.487215	0.971395	0.114255	0.700000	0.196445	0.836379	False	pyod	0.06	70070	[amt]	0.083574	30030	0.004995	None
6	INNE	1.617119	0.974659	0.129697	0.713333	0.219487	0.844652	False	pyod	0.06	70070	[amt]	0.083574	30030	0.004995	None
7	KDE	130.171108	0.968165	0.100990	0.680000	0.175862	0.824806	False	pyod	0.06	70070	[amt]	0.083574	30030	0.004995	None
8	KNN	0.074384	0.967766	0.092629	0.620000	0.161179	0.794756	False	pyod	0.06	70070	[amt]	0.083574	30030	0.004995	None
9	LODA	0.111742	0.994672	0.000000	0.000000	0.000000	0.499833	False	pyod	0.06	70070	[amt]	0.083574	30030	0.004995	None
10	LOF	0.126019	0.902231	0.002500	0.046667	0.004746	0.476596	False	pyod	0.06	70070	[amt]	0.083574	30030	0.004995	None
11	MCD	0.013644	0.974126	0.127229	0.713333	0.215943	0.844384	False	pyod	0.06	70070	[amt]	0.083574	30030	0.004995	None
12	OCSVM	301.447370	0.967566	0.098441	0.673333	0.171769	0.821188	False	pyod	0.06	70070	[amt]	0.083574	30030	0.004995	None
13	PCA	0.005391	0.944988	0.038130	0.413333	0.069820	0.680495	False	pyod	0.06	70070	[amt]	0.083574	30030	0.004995	None
14	ROD	4.724332	0.902131	0.000716	0.013333	0.001359	0.459963	False	pyod	0.06	70070	[amt]	0.083574	30030	0.004995	None

pyod(*pyod_preprocess10(fraudTrain, 0.05, 0.005))

	model	time	acc	pre	rec	f1	auc	graph_based	method	throw_rate	train_size	train_cols	train_frate	test_size	test_frate	hyper_params
0	ABOD	3.488629	0.995005	0.000000	0.000000	0.000000	0.500000	False	pyod	0.05	84084	[amt]	0.069288	36036	0.004995	None
1	COPOD	0.016961	0.965673	0.098099	0.716667	0.172575	0.841795	False	pyod	0.05	84084	[amt]	0.069288	36036	0.004995	None
2	ECOD	0.016851	0.951632	0.049048	0.472222	0.088866	0.713130	False	pyod	0.05	84084	[amt]	0.069288	36036	0.004995	None
3	GMM	0.016793	0.977966	0.143023	0.683333	0.236538	0.831389	False	pyod	0.05	84084	[amt]	0.069288	36036	0.004995	None
4	HBOS	0.004723	0.993451	0.075758	0.027778	0.040650	0.513038	False	pyod	0.05	84084	[amt]	0.069288	36036	0.004995	None
5	IForest	1.739545	0.977522	0.142857	0.700000	0.237288	0.839458	False	pyod	0.05	84084	[amt]	0.069288	36036	0.004995	None
6	INNE	1.911777	0.975941	0.129450	0.666667	0.216802	0.822080	False	pyod	0.05	84084	[amt]	0.069288	36036	0.004995	None
7	KDE	187.149441	0.971917	0.108286	0.638889	0.185185	0.806239	False	pyod	0.05	84084	[amt]	0.069288	36036	0.004995	None
8	KNN	0.094257	0.971612	0.104225	0.616667	0.178313	0.795030	False	pyod	0.05	84084	[amt]	0.069288	36036	0.004995	None
9	LODA	0.131656	0.993451	0.075758	0.027778	0.040650	0.513038	False	pyod	0.05	84084	[amt]	0.069288	36036	0.004995	None
10	LOF	0.160287	0.919192	0.002549	0.038889	0.004785	0.481250	False	pyod	0.05	84084	[amt]	0.069288	36036	0.004995	None
11	MCD	0.015904	0.977966	0.143023	0.683333	0.236538	0.831389	False	pyod	0.05	84084	[amt]	0.069288	36036	0.004995	None
12	OCSVM	487.274559	0.972167	0.109953	0.644444	0.187854	0.809128	False	pyod	0.05	84084	[amt]	0.069288	36036	0.004995	None
13	PCA	0.006028	0.958930	0.054184	0.438889	0.096459	0.700215	False	pyod	0.05	84084	[amt]	0.069288	36036	0.004995	None
14	ROD	5.554918	0.921023	0.000749	0.011111	0.001404	0.468351	False	pyod	0.05	84084	[amt]	0.069288	36036	0.004995	None

pyod(*pyod_preprocess10(fraudTrain, 0.15, 0.005))

	model	time	acc	pre	rec	f1	auc	graph_based	method	throw_rate	train_size	train_cols	train_frate	test_size	test_frate	hyper_params
0	ABOD	1.375164	0.995005	0.000000	0.000000	0.000000	0.500000	False	pyod	0.15	28028	[amt]	0.212145	12012	0.004995	None
1	COPOD	0.006505	0.882118	0.034341	0.833333	0.065963	0.857848	False	pyod	0.15	28028	[amt]	0.212145	12012	0.004995	None
2	ECOD	0.006317	0.856976	0.024656	0.716667	0.047672	0.787174	False	pyod	0.15	28028	[amt]	0.212145	12012	0.004995	None
3	GMM	0.009687	0.881868	0.027140	0.650000	0.052104	0.766516	False	pyod	0.15	28028	[amt]	0.212145	12012	0.004995	None
4	HBOS	0.002680	0.993756	0.394366	0.466667	0.427481	0.731534	False	pyod	0.15	28028	[amt]	0.212145	12012	0.004995	None
5	IForest	0.710505	0.915668	0.044890	0.783333	0.084914	0.849833	False	pyod	0.15	28028	[amt]	0.212145	12012	0.004995	None
6	INNE	0.675775	0.899767	0.034202	0.700000	0.065217	0.800385	False	pyod	0.15	28028	[amt]	0.212145	12012	0.004995	None
7	KDE	17.303729	0.924076	0.051579	0.816667	0.097030	0.870641	False	pyod	0.15	28028	[amt]	0.212145	12012	0.004995	None
8	KNN	0.030849	0.919497	0.045135	0.750000	0.085147	0.835174	False	pyod	0.15	28028	[amt]	0.212145	12012	0.004995	None
9	LODA	0.049980	0.993756	0.394366	0.466667	0.427481	0.731534	False	pyod	0.15	28028	[amt]	0.212145	12012	0.004995	None
10	LOF	0.053216	0.743007	0.003282	0.166667	0.006437	0.456283	False	pyod	0.15	28028	[amt]	0.212145	12012	0.004995	None
11	MCD	0.006773	0.931069	0.056582	0.816667	0.105832	0.874155	False	pyod	0.15	28028	[amt]	0.212145	12012	0.004995	None
12	OCSVM	38.577748	0.919747	0.048902	0.816667	0.092279	0.868466	False	pyod	0.15	28028	[amt]	0.212145	12012	0.004995	None
13	PCA	0.003425	0.800949	0.008435	0.333333	0.016454	0.568315	False	pyod	0.15	28028	[amt]	0.212145	12012	0.004995	None
14	ROD	3.166535	0.732850	0.000634	0.033333	0.001245	0.384848	False	pyod	0.15	28028	[amt]	0.212145	12012	0.004995	None

pyod(*pyod_preprocess10(fraudTrain, 0.25, 0.005))

	model	time	acc	pre	rec	f1	auc	graph_based	method	throw_rate	train_size	train_cols	train_frate	test_size	test_frate	hyper_params
0	ABOD	0.887434	0.995005	0.000000	0.000000	0.000000	0.500000	False	pyod	0.25	16817	[amt]	0.354998	7207	0.004995	None
1	COPOD	0.004493	0.787568	0.020526	0.888889	0.040125	0.837974	False	pyod	0.25	16817	[amt]	0.354998	7207	0.004995	None
2	ECOD	0.004322	0.757319	0.016375	0.805556	0.032097	0.781316	False	pyod	0.25	16817	[amt]	0.354998	7207	0.004995	None
3	GMM	0.006501	0.753157	0.012311	0.611111	0.024136	0.682490	False	pyod	0.25	16817	[amt]	0.354998	7207	0.004995	None
4	HBOS	0.002240	0.994450	0.000000	0.000000	0.000000	0.499721	False	pyod	0.25	16817	[amt]	0.354998	7207	0.004995	None
5	IForest	0.485034	0.855280	0.029879	0.888889	0.057814	0.872000	False	pyod	0.25	16817	[amt]	0.354998	7207	0.004995	None
6	INNE	0.428517	0.793950	0.016032	0.666667	0.031311	0.730628	False	pyod	0.25	16817	[amt]	0.354998	7207	0.004995	None
7	KDE	6.820246	0.868184	0.032720	0.888889	0.063116	0.878484	False	pyod	0.25	16817	[amt]	0.354998	7207	0.004995	None
8	KNN	0.016207	0.854170	0.027027	0.805556	0.052299	0.829985	False	pyod	0.25	16817	[amt]	0.354998	7207	0.004995	None
9	LODA	0.032871	0.994450	0.000000	0.000000	0.000000	0.499721	False	pyod	0.25	16817	[amt]	0.354998	7207	0.004995	None
10	LOF	0.028483	0.578327	0.003636	0.305556	0.007187	0.442626	False	pyod	0.25	16817	[amt]	0.354998	7207	0.004995	None
11	MCD	0.005033	0.870681	0.033333	0.888889	0.064257	0.879739	False	pyod	0.25	16817	[amt]	0.354998	7207	0.004995	None
12	OCSVM	12.390678	0.862495	0.031403	0.888889	0.060664	0.875626	False	pyod	0.25	16817	[amt]	0.354998	7207	0.004995	None
13	PCA	0.002873	0.573054	0.001639	0.138889	0.003239	0.357061	False	pyod	0.25	16817	[amt]	0.354998	7207	0.004995	None
14	ROD	2.206045	0.687942	0.000902	0.055556	0.001775	0.373336	False	pyod	0.25	16817	[amt]	0.354998	7207	0.004995	None

pyod_preprocess3: 비율 다 다르게 n

pyod(*pyod_preprocess3(fraudTrain, 10))

pyod(*pyod_preprocess3(fraudTrain, 9))

pyod(*pyod_preprocess3(fraudTrain, 5))

pyod(*pyod_preprocess3(fraudTrain, 4))

pyod(*pyod_preprocess3(fraudTrain, 2))

안됨(Replace has to be set to `True` when upsampling the population `frac` > 1.)

pyod(*pyod_preprocess4(fraudTrain, 0.005))

pyod(*pyod_preprocess7(fraudTrain, 0.005,10))

pyod(*pyod_preprocess7(fraudTrain, 0.004,10))

pyod(*pyod_preprocess7(fraudTrain, 0.003,10))

pyod(*pyod_preprocess7(fraudTrain, 0.002,10))

pyod(*pyod_preprocess7(fraudTrain, 0.001,10))

contamination must be in (0, 0.5], got: 0.5~ 오류로 아래 것들 안 됨

pyod(*pyod_preprocess3(fraudTrain, 8))

pyod(*pyod_preprocess3(fraudTrain, 7))

pyod(*pyod_preprocess3(fraudTrain, 6))

pyod(*pyod_preprocess3(fraudTrain, 3))

pyod(*pyod_preprocess3(fraudTrain, 1))

pyod(*pyod_preprocess10(fraudTrain, 0.5, 0.5))

pyod(*pyod_preprocess10(fraudTrain, 0.5, 0.05))

pyod(*pyod_preprocess10(fraudTrain, 0.5, 0.005))

pyod(*pyod_preprocess10(fraudTrain, 0.5, 0.0005))

pyod(*pyod_preprocess10(fraudTrain, 0.7, 0.005))

pyod(*pyod_preprocess10(fraudTrain, 0.6, 0.005))

pyod(*pyod_preprocess10(fraudTrain, 0.4, 0.005))

1. Imports

pyod_preprocess4(비율 다 같게)

pyod_preprocess7

pyod_preproecess10: 비율 다르게 test_size정할수 잇음

pyod_preprocess3: 비율 다 다르게 n

안됨(Replace has to be set to True when upsampling the population frac > 1.)

contamination must be in (0, 0.5], got: 0.5~ 오류로 아래 것들 안 됨

안됨(Replace has to be set to `True` when upsampling the population `frac` > 1.)