imports

import pandas as pd
import numpy as np
import sklearn
import pickle 
import time 
import datetime
import warnings
warnings.filterwarnings('ignore')

%run ../function_proposed_gcn.py

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

df_results = try_6(fraudTrain, 0.03,1e7,0.8)
df_results = try_6(fraudTrain, 0.02,1e7,0.8, prev_results=df_results)
df_results = try_6(fraudTrain, 0.01,1e7,0.8, prev_results=df_results)
df_results = try_6(fraudTrain, 0.9,1e7,0.8, prev_results=df_results)
df_results = try_6(fraudTrain, 0.8,1e7,0.8, prev_results=df_results)
df_results = try_6(fraudTrain, 0.7,1e7,0.8, prev_results=df_results)
df_results = try_6(fraudTrain, 0.6,1e7,0.8, prev_results=df_results)
df_results = try_6(fraudTrain, 0.5,1e7,0.8, prev_results=df_results)
df_results = try_6(fraudTrain, 0.4,1e7,0.8, prev_results=df_results)
df_results = try_6(fraudTrain, 0.3,1e7,0.8, prev_results=df_results)
df_results = try_6(fraudTrain, 0.2,1e7,0.8, prev_results=df_results)
df_results = try_6(fraudTrain, 0.1,1e7,0.8, prev_results=df_results)
ymdhms = datetime.datetime.fromtimestamp(time.time()).strftime('%Y%m%d-%H%M%S') 
df_results.to_csv(f'../results/{ymdhms}-proposed.csv',index=False)

df_results

	model	time	acc	pre	rec	f1	auc	graph_based	method	throw_rate	train_size	train_cols	train_frate	test_size	test_frate	hyper_params	theta	gamma
0	GCN	None	0.973626	0.660944	0.299029	0.411765	0.971025	True	Proposed	0.030000	150150	amt	0.029710	50050	0.030869	None	10000000.0	0.8
1	GCN	None	0.983310	0.726891	0.235534	0.355784	0.972262	True	Proposed	0.020000	225225	amt	0.020144	75075	0.019567	None	10000000.0	0.8
2	GCN	None	0.990436	0.707692	0.119171	0.203991	0.895770	True	Proposed	0.010000	450450	amt	0.009906	150150	0.010283	None	10000000.0	0.8
3	GCN	None	0.976633	0.976547	0.998003	0.987158	0.950314	True	Proposed	0.900045	5004	amt	0.900080	1669	0.899940	None	10000000.0	0.8
4	GCN	None	0.967501	0.968244	0.992032	0.979993	0.971374	True	Proposed	0.800053	5630	amt	0.799290	1877	0.802344	None	10000000.0	0.8
5	GCN	None	0.949184	0.957171	0.971673	0.964367	0.955698	True	Proposed	0.700000	6435	amt	0.697436	2145	0.707692	None	10000000.0	0.8
6	GCN	None	0.942070	0.937049	0.966847	0.951715	0.962575	True	Proposed	0.600000	7507	amt	0.603170	2503	0.590491	None	10000000.0	0.8
7	GCN	None	0.936397	0.912484	0.962661	0.936901	0.964254	True	Proposed	0.500000	9009	amt	0.503164	3003	0.490509	None	10000000.0	0.8
8	GCN	None	0.927544	0.881068	0.950262	0.914358	0.964189	True	Proposed	0.400000	11261	amt	0.397656	3754	0.407032	None	10000000.0	0.8
9	GCN	None	0.936663	0.853101	0.951007	0.899397	0.972655	True	Proposed	0.300000	15015	amt	0.300766	5005	0.297702	None	10000000.0	0.8
10	GCN	None	0.930075	0.816248	0.840637	0.828263	0.973986	True	Proposed	0.200000	22522	amt	0.199805	7508	0.200586	None	10000000.0	0.8
11	GCN	None	0.945721	0.771200	0.645680	0.702880	0.976863	True	Proposed	0.100000	45045	amt	0.100189	15015	0.099434	None	10000000.0	0.8

try_6(fraudTrain, 0.01,1e8,0.8)
try_6(fraudTrain, 0.01,1e9,0.8, prev_results=df_results)
try_6(fraudTrain, 0.01,1e10,0.8, prev_results=df_results)
try_6(fraudTrain, 0.01,1e8,0.9, prev_results=df_results)
try_6(fraudTrain, 0.01,1e7,0.9, prev_results=df_results)
df_results.to_csv(f'../results/{ymdhms}-proposed.csv',index=False)

df_results