GML - CH8. 신용카드 거래 분석(df원본데이터)

df에서 그냥 처음부터 샘플뽑지 않고 전체 데이터를 한번 돌려보자. f1-score가 어떻게 나오는지 기존 샘플한거랑 비교해보기

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

_df = pd.read_csv("fraudTrain.csv")

_df["is_fraud"].value_counts()

0    1042569
1       6006
Name: is_fraud, dtype: int64

_df["is_fraud"].value_counts()/len(_df)

0    0.994272
1    0.005728
Name: is_fraud, dtype: float64

df = _df

import os
import math
import numpy as np
import networkx as nx
import matplotlib.pyplot as plt
%matplotlib inline

default_edge_color = 'gray'
default_node_color = '#407cc9'
enhanced_node_color = '#f5b042'
enhanced_edge_color = '#cc2f04'

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

from sklearn.utils import resample

df_majority = df[df.is_fraud==0]
df_minority = df[df.is_fraud==1]

df_maj_dowsampled = resample(df_majority,
                             n_samples=len(df_minority),
                             random_state=42)

df_downsampled = pd.concat([df_minority, df_maj_dowsampled])

print(df_downsampled.is_fraud.value_counts())
G_down = build_graph_bipartite(df_downsampled)

1    6006
0    6006
Name: is_fraud, dtype: int64

from sklearn.model_selection import train_test_split


train_edges, test_edges, train_labels, test_labels = train_test_split(list(range(len(G_down.edges))), 
                                                                      list(nx.get_edge_attributes(G_down, "label").values()), 
                                                                      test_size=0.20, 
                                                                      random_state=42)

edgs = list(G_down.edges)
train_graph = G_down.edge_subgraph([edgs[x] for x in train_edges]).copy()
train_graph.add_nodes_from(list(set(G_down.nodes) - set(train_graph.nodes)))

from node2vec import Node2Vec
from node2vec.edges import HadamardEmbedder, AverageEmbedder, WeightedL1Embedder, WeightedL2Embedder

node2vec_train = Node2Vec(train_graph, weight_key='weight')
model_train = node2vec_train.fit(window=10)

Generating walks (CPU: 1):   0%|          | 0/10 [00:00<?, ?it/s]Generating walks (CPU: 1): 100%|██████████| 10/10 [00:03<00:00,  2.53it/s]

from sklearn.ensemble import RandomForestClassifier 
from sklearn import metrics 

classes = [HadamardEmbedder, AverageEmbedder, WeightedL1Embedder, WeightedL2Embedder]
for cl in classes:
    embeddings_train = cl(keyed_vectors=model_train.wv) 

    train_embeddings = [embeddings_train[str(edgs[x][0]), str(edgs[x][1])] for x in train_edges]
    test_embeddings = [embeddings_train[str(edgs[x][0]), str(edgs[x][1])] for x in test_edges]
    
    rf = RandomForestClassifier(n_estimators=1000, random_state=42) 
    rf.fit(train_embeddings, train_labels); 

    y_pred = rf.predict(test_embeddings)
    print(cl)
    print('Precision:', metrics.precision_score(test_labels, y_pred)) 
    print('Recall:', metrics.recall_score(test_labels, y_pred)) 
    print('F1-Score:', metrics.f1_score(test_labels, y_pred))

<class 'node2vec.edges.HadamardEmbedder'>
Precision: 0.7345132743362832
Recall: 0.1424892703862661
F1-Score: 0.23867721063982747
<class 'node2vec.edges.AverageEmbedder'>
Precision: 0.6886792452830188
Recall: 0.751931330472103
F1-Score: 0.7189167008617152
<class 'node2vec.edges.WeightedL1Embedder'>
Precision: 0.6136363636363636
Recall: 0.02317596566523605
F1-Score: 0.04466501240694789
<class 'node2vec.edges.WeightedL2Embedder'>
Precision: 0.66
Recall: 0.02832618025751073
F1-Score: 0.05432098765432099

음 어차피 나중에 downsampled를 하기 때문에 … f1 score값은 샘플을 무얼 하든 큰 차이가 없다. 오히려 더 낮은듯