[FRAUD] 데이터정리 시도(8.18-df50com으로 93퍼 accuracy)

Author

김보람

Published

August 18, 2023

imports

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

# sklearn
from sklearn import model_selection # split함수이용
from sklearn import ensemble # RF,GBM
from sklearn import metrics 

# embedding 
from node2vec import Node2Vec
from node2vec.edges import HadamardEmbedder, AverageEmbedder, WeightedL1Embedder, WeightedL2Embedder
def build_graph_bipartite(df_input, graph_type=nx.Graph()):
    df=df_input.copy()
    mapping={x:node_id for node_id, x in enumerate(set(df["cc_num"].values.tolist()+\
                                                      df["merchant"].values.tolist()))}
    
    df["from"]=df["cc_num"].apply(lambda x:mapping[x])  #엣지의 출발점
    df["to"]=df["merchant"].apply(lambda x:mapping[x])  #엣지의 도착점
    
    df = df[['from', 'to', "amt", "is_fraud"]].groupby(['from','to']).agg({"is_fraud":"sum","amt":"sum"}).reset_index()
    df["is_fraud"]=df["is_fraud"].apply(lambda x:1 if x>0 else 0)
    
    G=nx.from_edgelist(df[["from","to"]].values, create_using=graph_type)
    
    nx.set_edge_attributes(G,{(int(x["from"]),int(x["to"])):x["is_fraud"] for idx, x in df[["from","to","is_fraud"]].iterrows()}, "label")  #엣지 속성 설정,각 속성의 사기 여부부     
    nx.set_edge_attributes(G,{(int(x["from"]),int(x["to"])):x["amt"] for idx,x in df[["from","to","amt"]].iterrows()}, "weight") # 엣지 속성 설정, 각 엣지의 거래 금액

    return G


def build_graph_tripartite(df_input, graph_type=nx.Graph()):
    df=df_input.copy()
    mapping={x:node_id for node_id, x in enumerate(set(df.index.values.tolist() + 
                                                       df["cc_num"].values.tolist() +
                                                       df["merchant"].values.tolist()))}
    df["in_node"]= df["cc_num"].apply(lambda x: mapping[x])
    df["out_node"]=df["merchant"].apply(lambda x:mapping[x])
    
        
    G=nx.from_edgelist([(x["in_node"], mapping[idx]) for idx, x in df.iterrows()] +\
                        [(x["out_node"], mapping[idx]) for idx, x in df.iterrows()], create_using=graph_type)
    
    nx.set_edge_attributes(G,{(x["in_node"], mapping[idx]):x["is_fraud"] for idx, x in df.iterrows()}, "label")     
    nx.set_edge_attributes(G,{(x["out_node"], mapping[idx]):x["is_fraud"] for idx, x in df.iterrows()}, "label")   
    nx.set_edge_attributes(G,{(x["in_node"], mapping[idx]):x["amt"] for idx, x in df.iterrows()}, "weight")  
    nx.set_edge_attributes(G,{(x["out_node"], mapping[idx]):x["amt"] for idx, x in df.iterrows()}, "weight")

    return G
    
    
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 embedding(Graph):
    # Graph -> X (feature)
    _edgs = list(Graph.edges)
    subGraph = Graph.edge_subgraph([_edgs[x] for x in range(len(Graph.edges))]).copy()
    subGraph.add_nodes_from(list(set(Graph.nodes) - set(subGraph.nodes)))    
    embedded = AverageEmbedder(Node2Vec(subGraph, weight_key='weight').fit(window=10).wv)
    X = [embedded[str(_edgs[x][0]), str(_edgs[x][1])] for x in range(len(Graph.edges))]
    # Graph -> y (label)
    y = np.array(list(nx.get_edge_attributes(Graph, "label").values()))
    return X,y 

def anal(df):
    Graph = build_graph_bipartite(df)
    X,XX,y,yy = embedding(Graph)
    lrnr = RandomForestClassifier(n_estimators=100, random_state=42) 
    lrnr.fit(X,y)
    yyhat = lrnr.predict(XX)
    df = pd.DataFrame({
        'acc':[sklearn.metrics.accuracy_score(yy,yyhat)], 
        'pre':[sklearn.metrics.precision_score(yy,yyhat)], 
        'rec':[sklearn.metrics.recall_score(yy,yyhat)],
        'f1':[sklearn.metrics.f1_score(yy,yyhat)]}
    )    
    return df

def our_sampling1(df):
    cus_list = set(df.query('is_fraud==1').cc_num.tolist())
    return df.query("cc_num in @ cus_list")
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

시도

_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.shape
(12012, 22)
12012*12012
144288144
df50 = df50.reset_index()
N = len(df50)

tr/test

df50_tr,df50_test = sklearn.model_selection.train_test_split(df50, random_state=42)
df50_tr.is_fraud.mean().round(5), df50_test.is_fraud.mean().round(5)
(0.49828, 0.50516)
df50_tr.shape, df50_test.shape
((9009, 23), (3003, 23))
train_mask = np.concatenate((np.full(9009, True), np.full(3003, False)))
test_mask = np.concatenate((np.full(9009, False), np.full(3003, True)))
print("Train Mask:", train_mask)
print("Test Mask:", test_mask)
Train Mask: [ True  True  True ... False False False]
Test Mask: [False False False ...  True  True  True]
train_mask.shape, test_mask.shape
((12012,), (12012,))
train_mask.sum(), test_mask.sum()
(9009, 3003)
df50_com = pd.concat([df50_tr, df50_test])
df50_com = df50_com.reset_index()

edge: 같은 cc_num이면 edge=1, 다르면 edge=0

# edge_index_list2_com = []
# for i in range(N):
#     for j in range(N):
#         if df50_com['cc_num'][i] != df50_com['cc_num'][j]:  
#             edge = 0
#         else:
#             edge = 1
#         edge_index_list2_com.append([i, j, edge])
# #np.save('edge_index_list2_50_com.npy', edge_index_list2_com)

# edge_index_list2_com = np.load('edge_index_list2_50_com.npy')
# edge_index_list2_com
array([[    0,     0,     1],
       [    0,     1,     0],
       [    0,     2,     0],
       ...,
       [12011, 12009,     0],
       [12011, 12010,     0],
       [12011, 12011,     1]])
# edge_one_com = [(i, j) for i, j, edge in edge_index_list2_com if edge == 1]
# edge_one_com[:5]
# len(edge_one_com)
# edge_one_index_com = torch.tensor(edge_one_com, dtype=torch.long).t()
# edge_one_index_com.shape

이건 weight?

# edge_index_list = []
# for i in range(N):
#     for j in range(N):
#         time_difference = (df50_com['trans_date_trans_time'][i] - df50_com['trans_date_trans_time'][j]).total_seconds()
#         edge_index_list.append([i, j, time_difference])
# # np.save('edge_index_list_50_com.npy', edge_index_list)

# edge_index_list2_com = np.load('edge_index_list2_50_com.npy')
# edge_index_list[:5]
[[0, 0, 0.0],
 [0, 1, -20301900.0],
 [0, 2, -28413960.0],
 [0, 3, -23837880.0],
 [0, 4, -26877960.0]]
# edge_index = np.array(edge_index_list)
# edge_index[:,2] = np.abs(edge_index[:,2])
# theta = edge_index[:,2].mean()
# theta
12238996.895508753
# edge_index[:,2] = (np.exp(-edge_index[:,2]/theta)!=1) * np.exp(-edge_index[:,2]/theta)
# edge_index
array([[0.00000000e+00, 0.00000000e+00, 0.00000000e+00],
       [0.00000000e+00, 1.00000000e+00, 1.90369587e-01],
       [0.00000000e+00, 2.00000000e+00, 9.81172367e-02],
       ...,
       [1.20110000e+04, 1.20090000e+04, 9.25720620e-01],
       [1.20110000e+04, 1.20100000e+04, 5.15585903e-01],
       [1.20110000e+04, 1.20110000e+04, 0.00000000e+00]])
# edge_index[:,2]
array([0.        , 0.19036959, 0.09811724, ..., 0.92572062, 0.5155859 ,
       0.        ])

갑자기 헷갈리는데, 이 weight는 어디서 곱하는거지? GNN이 아니라 새로운 코드였던감..

# edge_index_list_plus = []
# for i in range(N):
#     for j in range(N):
#         if df50_com['cc_num'][i] != df50_com['cc_num'][j]:  # cc_num 값이 다르다면
#             time_difference = 0
#         else:
#             time_difference = (df50_com['trans_date_trans_time'][i] - df50_com['trans_date_trans_time'][j]).total_seconds()
#         edge_index_list_plus.append([i, j, time_difference])
# np.save('edge_index_list_plus.npy', edge_index_list_plus)

edge_index_list_plus = np.load('edge_index_list_plus.npy')
edge_index = np.array(edge_index_list_plus)
edge_index.shape
(144288144, 3)
edge_index
array([[0.0000e+00, 0.0000e+00, 0.0000e+00],
       [0.0000e+00, 1.0000e+00, 0.0000e+00],
       [0.0000e+00, 2.0000e+00, 0.0000e+00],
       ...,
       [1.2011e+04, 1.2009e+04, 0.0000e+00],
       [1.2011e+04, 1.2010e+04, 0.0000e+00],
       [1.2011e+04, 1.2011e+04, 0.0000e+00]])
edge_index[:,2] = np.abs(edge_index[:,2])
theta = edge_index[:,2].mean()
theta
10973.519989002007
edge_index[:,2] = (np.exp(-edge_index[:,2]/theta)!=1) * np.exp(-edge_index[:,2]/theta)
edge_index
array([[0.0000e+00, 0.0000e+00, 0.0000e+00],
       [0.0000e+00, 1.0000e+00, 0.0000e+00],
       [0.0000e+00, 2.0000e+00, 0.0000e+00],
       ...,
       [1.2011e+04, 1.2009e+04, 0.0000e+00],
       [1.2011e+04, 1.2010e+04, 0.0000e+00],
       [1.2011e+04, 1.2011e+04, 0.0000e+00]])
edge_index_list_updated = edge_index.tolist()
np.array(edge_index_list_updated)[:,2].mean()
8.443606280313275e-05
mm = np.array(edge_index_list_updated)[:,2].mean()

시간이 평균보다 짧다면? . 음..

selected_edges = [(int(row[0]), int(row[1])) for row in edge_index_list_updated if row[2] > mm]
edge_index_selected = torch.tensor(selected_edges, dtype=torch.long).t()
edge_index_selected.shape
torch.Size([2, 51392])

data설정(x, edge_index, y)

x = df50_com['amt']
a = torch.tensor(x, dtype=torch.float)
a = a.reshape(-1,1)
a
tensor([[921.2400],
        [698.2800],
        [220.5600],
        ...,
        [ 17.9700],
        [  7.5800],
        [824.9900]])
y = df50_com['is_fraud']
b = torch.tensor(y,dtype=torch.int64)
b
tensor([1, 1, 0,  ..., 1, 0, 1])
import torch_geometric
data = torch_geometric.data.Data(x=a, edge_index = edge_index_selected, y=b, train_mask = train_mask, test_mask = test_mask)
data
Data(x=[12012, 1], edge_index=[2, 51392], y=[12012], train_mask=[12012], test_mask=[12012])

gnn



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

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)
model = GCN()
model
GCN(
  (conv1): GCNConv(1, 16)
  (conv2): GCNConv(16, 2)
)
optimizer = torch.optim.Adam(model.parameters(), lr=0.01, weight_decay=5e-4)
model.train()
GCN(
  (conv1): GCNConv(1, 16)
  (conv2): GCNConv(16, 2)
)
for epoch in range(200):
    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()
pred = model(data).argmax(dim=1)
correct = (pred[data.test_mask] == data.y[data.test_mask]).sum()
acc = int(correct) / int(data.test_mask.sum())
print(f'Accuracy: {acc:.4f}')
Accuracy: 0.9321
`