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_1(fraudTrain, 0.3, 0.05, 8.028000e+04, 0.3)

df_results = try_1(fraudTrain, 0.3, 0.05, 8.028000e+04, 0.2, prev_results=df_results)

df_results = try_1(fraudTrain, 0.3, 0.005, 8.028000e+04, 0.2, prev_results=df_results)

df_results = try_1(fraudTrain, 0.2, 0.05, 8.028000e+04, 0.2, prev_results=df_results)

df_results = try_1(fraudTrain, 0.2, 0.005, 8.028000e+04, 0.2, prev_results=df_results)

df_results = try_1(fraudTrain, 0.3, 0.005, 8.028000e+04, 0.3, prev_results=df_results)

df_results = try_1(fraudTrain, 0.5, 0.5, 8.028000e+04, 0.3, prev_results=df_results)

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	0.972028	0.652778	0.940000	0.770492	0.956856	True	Proposed	0.3	20020	[level_0, trans_date_trans_time, cc_num, merch...	0.3	20020	0.050	None	80280.0	0.3
1	GCN	None	0.972194	0.650794	0.956667	0.774629	0.964839	True	Proposed	0.3	20020	[level_0, trans_date_trans_time, cc_num, merch...	0.3	20020	0.050	None	80280.0	0.2
2	GCN	None	0.972694	0.143617	0.900000	0.247706	0.936529	True	Proposed	0.3	20020	[level_0, trans_date_trans_time, cc_num, merch...	0.3	20020	0.005	None	80280.0	0.2
3	GCN	None	0.977356	0.711340	0.920000	0.802326	0.950186	True	Proposed	0.2	30030	[level_0, trans_date_trans_time, cc_num, merch...	0.2	30030	0.050	None	80280.0	0.2
4	GCN	None	0.978910	0.171946	0.844444	0.285714	0.912015	True	Proposed	0.2	30030	[level_0, trans_date_trans_time, cc_num, merch...	0.2	30030	0.005	None	80280.0	0.2
5	GCN	None	0.971029	0.136364	0.900000	0.236842	0.935693	True	Proposed	0.3	20020	[level_0, trans_date_trans_time, cc_num, merch...	0.3	20020	0.005	None	80280.0	0.3
6	GCN	None	0.964752	0.969697	0.959467	0.964555	0.964750	True	Proposed	0.5	12012	[level_0, trans_date_trans_time, cc_num, merch...	0.5	12012	0.500	None	80280.0	0.3

train_cols 수정 필요 -> amt만 나오게. ..

time……..(proposed는 시간이 의미가 있낭?)

일단 이렇게 나온 결과값을 엑셀로 저장해야함..

ymdhms = datetime.datetime.fromtimestamp(time.time()).strftime('%Y%m%d-%H%M%S') 
df_results.to_csv(f'./results/{ymdhms}-proposed.csv',index=False)