[FRAUD] 데이터정리 시도(9.18_df50 정리중(~ing))

Author

김보람

Published

September 18, 2023

imports

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt 
import networkx as nx
import sklearn
import xgboost as xgb

# sklearn
from sklearn import model_selection # split함수이용
from sklearn import ensemble # RF,GBM
from sklearn import metrics
from sklearn.metrics import precision_score, recall_score, f1_score
from sklearn.svm import SVC
from sklearn.ensemble import RandomForestClassifier
from sklearn.naive_bayes import GaussianNB

# gnn
import torch
import torch.nn.functional as F
import torch_geometric
from torch_geometric.nn import GCNConv

def down_sample_textbook(df):
    df_majority = df[df.is_fraud==0].copy()
    df_minority = df[df.is_fraud==1].copy()
    df_maj_dowsampled = sklearn.utils.resample(df_majority, n_samples=len(df_minority), replace=False, random_state=42)
    df_downsampled = pd.concat([df_minority, df_maj_dowsampled])
    return df_downsampled

def compute_time_difference(group):
    n = len(group)
    result = []
    for i in range(n):
        for j in range(n):
            time_difference = abs(group.iloc[i].trans_date_trans_time.value - group.iloc[j].trans_date_trans_time.value)
            result.append([group.iloc[i].name, group.iloc[j].name, time_difference])
    return result


class GCN(torch.nn.Module):
    def __init__(self):
        super().__init__()
        self.conv1 = GCNConv(1, 16)
        self.conv2 = GCNConv(16,2)

    def forward(self, data):
        x, edge_index = data.x, data.edge_index

        x = self.conv1(x, edge_index)
        x = F.relu(x)
        x = F.dropout(x, training=self.training)
        x = self.conv2(x, edge_index)

        return F.log_softmax(x, dim=1)
fraudTrain = pd.read_csv("~/Desktop/fraudTrain.csv").iloc[:,1:]
fraudTrain = fraudTrain.assign(trans_date_trans_time= list(map(lambda x: pd.to_datetime(x), fraudTrain.trans_date_trans_time)))
fraudTrain
trans_date_trans_time cc_num merchant category amt first last gender street city ... lat long city_pop job dob trans_num unix_time merch_lat merch_long is_fraud
0 2019-01-01 00:00:00 2.703190e+15 fraud_Rippin, Kub and Mann misc_net 4.97 Jennifer Banks F 561 Perry Cove Moravian Falls ... 36.0788 -81.1781 3495 Psychologist, counselling 1988-03-09 0b242abb623afc578575680df30655b9 1325376018 36.011293 -82.048315 0
1 2019-01-01 00:00:00 6.304230e+11 fraud_Heller, Gutmann and Zieme grocery_pos 107.23 Stephanie Gill F 43039 Riley Greens Suite 393 Orient ... 48.8878 -118.2105 149 Special educational needs teacher 1978-06-21 1f76529f8574734946361c461b024d99 1325376044 49.159047 -118.186462 0
2 2019-01-01 00:00:00 3.885950e+13 fraud_Lind-Buckridge entertainment 220.11 Edward Sanchez M 594 White Dale Suite 530 Malad City ... 42.1808 -112.2620 4154 Nature conservation officer 1962-01-19 a1a22d70485983eac12b5b88dad1cf95 1325376051 43.150704 -112.154481 0
3 2019-01-01 00:01:00 3.534090e+15 fraud_Kutch, Hermiston and Farrell gas_transport 45.00 Jeremy White M 9443 Cynthia Court Apt. 038 Boulder ... 46.2306 -112.1138 1939 Patent attorney 1967-01-12 6b849c168bdad6f867558c3793159a81 1325376076 47.034331 -112.561071 0
4 2019-01-01 00:03:00 3.755340e+14 fraud_Keeling-Crist misc_pos 41.96 Tyler Garcia M 408 Bradley Rest Doe Hill ... 38.4207 -79.4629 99 Dance movement psychotherapist 1986-03-28 a41d7549acf90789359a9aa5346dcb46 1325376186 38.674999 -78.632459 0
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
1048570 2020-03-10 16:07:00 6.011980e+15 fraud_Fadel Inc health_fitness 77.00 Haley Wagner F 05561 Farrell Crescent Annapolis ... 39.0305 -76.5515 92106 Accountant, chartered certified 1943-05-28 45ecd198c65e81e597db22e8d2ef7361 1362931649 38.779464 -76.317042 0
1048571 2020-03-10 16:07:00 4.839040e+15 fraud_Cremin, Hamill and Reichel misc_pos 116.94 Meredith Campbell F 043 Hanson Turnpike Hedrick ... 41.1826 -92.3097 1583 Geochemist 1999-06-28 c00ce51c6ebb7657474a77b9e0b51f34 1362931670 41.400318 -92.726724 0
1048572 2020-03-10 16:08:00 5.718440e+11 fraud_O'Connell, Botsford and Hand home 21.27 Susan Mills F 005 Cody Estates Louisville ... 38.2507 -85.7476 736284 Engineering geologist 1952-04-02 17c9dc8b2a6449ca2473726346e58e6c 1362931711 37.293339 -84.798122 0
1048573 2020-03-10 16:08:00 4.646850e+18 fraud_Thompson-Gleason health_fitness 9.52 Julia Bell F 576 House Crossroad West Sayville ... 40.7320 -73.1000 4056 Film/video editor 1990-06-25 5ca650881b48a6a38754f841c23b77ab 1362931718 39.773077 -72.213209 0
1048574 2020-03-10 16:08:00 2.283740e+15 fraud_Buckridge PLC misc_pos 6.81 Shannon Williams F 9345 Spencer Junctions Suite 183 Alpharetta ... 34.0770 -84.3033 165556 Prison officer 1997-12-27 8d0a575fe635bbde12f1a2bffc126731 1362931730 33.601468 -83.891921 0

1048575 rows × 22 columns

데이터정리

_df1 = fraudTrain[fraudTrain["is_fraud"] == 0].sample(frac=0.20, random_state=42)
_df2 = fraudTrain[fraudTrain["is_fraud"] == 1]
df02 = pd.concat([_df1,_df2])
df02.shape
(214520, 22)
df50 = down_sample_textbook(df02)
df50 = df50.reset_index()
df50.shape
(12012, 23)

tr/test

df50_tr,df50_test = sklearn.model_selection.train_test_split(df50, random_state=42)
df50_tr.shape, df50_test.shape
((9009, 23), (3003, 23))
N = len(df50)
train_mask = [i in df50_tr.index for i in range(N)]
test_mask = [i in df50_test.index for i in range(N)]
train_mask = np.array(train_mask)
test_mask = np.array(test_mask)
train_mask.sum(), test_mask.sum()
(9009, 3003)
train_mask.shape, test_mask.shape
((12012,), (12012,))

edge_index 설정

# groups = df50.groupby('cc_num')
# edge_index_list_plus = [compute_time_difference(group) for _, group in groups]
# edge_index_list_plus_flat = [item for sublist in edge_index_list_plus for item in sublist]
# edge_index_list_plus_nparr = np.array(edge_index_list_plus_flat)
# np.save('edge_index_list_plus50.npy', edge_index_list_plus_nparr)
edge_index = np.load('edge_index_list_plus50.npy')
edge_index.shape
(200706, 3)
theta = edge_index[:,2].mean()
edge_index = np.load('edge_index_list_plus50.npy').astype(np.float64)
edge_index[:,2] = (np.exp(-edge_index[:,2]/theta) != 1)*(np.exp(-edge_index[:,2]/theta))
edge_index = edge_index.tolist()
mean_ = np.array(edge_index)[:,2].mean()
mean_
0.5098736436405648
edge_index[:5]
[[1023.0, 1023.0, 0.0],
 [1023.0, 1024.0, 0.9994677478343093],
 [1023.0, 1028.0, 0.9902065900321946],
 [1023.0, 1031.0, 0.97983815585674],
 [1023.0, 1032.0, 0.97983815585674]]
selected_edges = [(int(row[0]), int(row[1])) for row in edge_index if row[2] > mean_]
edge_index_selected = torch.tensor(selected_edges, dtype=torch.long).t()
edge_index_selected.shape
torch.Size([2, 93730])

data설정(x, edge_index, y)

x = torch.tensor(df50['amt'], dtype=torch.float).reshape(-1,1)
y = torch.tensor(df50['is_fraud'],dtype=torch.int64)
data = torch_geometric.data.Data(x=x, edge_index = edge_index_selected, y=y, train_mask = train_mask, test_mask = test_mask)
data
Data(x=[12012, 1], edge_index=[2, 93730], y=[12012], train_mask=[12012], test_mask=[12012])

정리

구분 Train Test 모형 설명변수 비고
분석1 df50_tr df50_test GNN amt
분석2 df50_tr df50_test 로지스틱 회귀 amt
분석3 df50_tr df50_test SVM amt
분석4 df50_tr df50_test 랜덤포레스트 amt
분석5 df50_tr df50_test 부스팅 amt
분석6 df50_tr df50_test Naive Bayes amt 
lst = [_results1, _results2,_results3,_results4,_results5, _results6]
pd.concat(lst)
accuracy_score precision_score recall_score f1_score
분석1 0.889111 0.865884 0.923533 0.893780
분석2 0.849484 0.933279 0.756098 0.835397
분석3 0.850150 0.935510 0.755438 0.835886
분석4 0.847153 0.850331 0.846407 0.848365
분석5 0.880120 0.886957 0.874094 0.880478
분석6 0.857143 0.957143 0.750824 0.841522

분석 1(GNN)

X = (data.x[data.train_mask]).numpy()
XX = (data.x[data.test_mask]).numpy()
y = (data.y[data.train_mask]).numpy()
yy = (data.y[data.test_mask]).numpy()
model = GCN()
optimizer = torch.optim.Adam(model.parameters(), lr=0.01, weight_decay=5e-4)
model.train()
for epoch in range(400):
    optimizer.zero_grad()
    out = model(data)
    loss = F.nll_loss(out[data.train_mask], data.y[data.train_mask])
    loss.backward()
    optimizer.step()
model.eval()
GCN(
  (conv1): GCNConv(1, 16)
  (conv2): GCNConv(16, 2)
)
pred = model(data).argmax(dim=1)
yyhat = pred[data.test_mask]
metrics = [sklearn.metrics.accuracy_score,
           sklearn.metrics.precision_score,
           sklearn.metrics.recall_score,
           sklearn.metrics.f1_score]
_results1= pd.DataFrame({m.__name__:[m(yy,yyhat).round(6)] for m in metrics},index=['분석1'])
_results1
accuracy_score precision_score recall_score f1_score
분석1 0.889111 0.865884 0.923533 0.89378

분석2(로지스틱 회귀)

X = np.array(df50_tr.loc[:,['amt']])
XX = np.array(df50_test.loc[:,['amt']])
y = np.array(df50_tr.is_fraud)
yy = np.array(df50_test.is_fraud)
lrnr = sklearn.linear_model.LogisticRegression()
lrnr.fit(X,y)
LogisticRegression()
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
#thresh = y.mean()
#yyhat = (lrnr.predict_proba(XX)> thresh)[:,-1]
yyhat = lrnr.predict(XX) 
yyhat
array([0, 1, 0, ..., 0, 0, 1])
metrics = [sklearn.metrics.accuracy_score,
           sklearn.metrics.precision_score,
           sklearn.metrics.recall_score,
           sklearn.metrics.f1_score]
_results2= pd.DataFrame({m.__name__:[m(yy,yyhat).round(6)] for m in metrics},index=['분석2'])
_results2
accuracy_score precision_score recall_score f1_score
분석2 0.849484 0.933279 0.756098 0.835397

분석3(서포트 벡터 머신)

X = np.array(df50_tr.loc[:, ['amt']])
XX = np.array(df50_test.loc[:, ['amt']])
y = np.array(df50_tr.is_fraud)
yy = np.array(df50_test.is_fraud)
lrnr = SVC(kernel='linear')  
lrnr.fit(X,y)
yyhat = lrnr.predict(XX)
metrics = [sklearn.metrics.accuracy_score,
           sklearn.metrics.precision_score,
           sklearn.metrics.recall_score,
           sklearn.metrics.f1_score]
_results3= pd.DataFrame({m.__name__:[m(yy,yyhat).round(6)] for m in metrics},index=['분석3'])
_results3
accuracy_score precision_score recall_score f1_score
분석3 0.85015 0.93551 0.755438 0.835886

분석4(랜덤 포레스트)

X = np.array(df50_tr.loc[:, ['amt']])
XX = np.array(df50_test.loc[:, ['amt']])
y = np.array(df50_tr.is_fraud)
yy = np.array(df50_test.is_fraud)
lrnr = RandomForestClassifier()  
lrnr.fit(X, y)
yyhat = lrnr.predict(XX)
metrics = [sklearn.metrics.accuracy_score,
           sklearn.metrics.precision_score,
           sklearn.metrics.recall_score,
           sklearn.metrics.f1_score]
_results4= pd.DataFrame({m.__name__:[m(yy,yyhat).round(6)] for m in metrics},index=['분석4'])
_results4
accuracy_score precision_score recall_score f1_score
분석4 0.847153 0.850331 0.846407 0.848365

분석5(부스팅)

X = np.array(df50_tr.loc[:, ['amt']])
XX = np.array(df50_test.loc[:, ['amt']])
y = np.array(df50_tr.is_fraud)
yy = np.array(df50_test.is_fraud)
lrnr = xgb.XGBClassifier()  
lrnr.fit(X, y)
yyhat = lrnr.predict(XX)
metrics = [sklearn.metrics.accuracy_score,
           sklearn.metrics.precision_score,
           sklearn.metrics.recall_score,
           sklearn.metrics.f1_score]
_results5= pd.DataFrame({m.__name__:[m(yy,yyhat).round(6)] for m in metrics},index=['분석5'])
_results5
accuracy_score precision_score recall_score f1_score
분석5 0.88012 0.886957 0.874094 0.880478

분석6(Naive Bayes)

X = np.array(df50_tr.loc[:, ['amt']])
XX = np.array(df50_test.loc[:, ['amt']])
y = np.array(df50_tr.is_fraud)
yy = np.array(df50_test.is_fraud)
lrnr = GaussianNB() 
lrnr.fit(X, y)
yyhat = lrnr.predict(XX)
metrics = [sklearn.metrics.accuracy_score,
           sklearn.metrics.precision_score,
           sklearn.metrics.recall_score,
           sklearn.metrics.f1_score]
_results6= pd.DataFrame({m.__name__:[m(yy,yyhat).round(6)] for m in metrics},index=['분석6'])
_results6
accuracy_score precision_score recall_score f1_score
분석6 0.857143 0.957143 0.750824 0.841522