逻辑回归-信用卡欺诈检测 学习笔记

读取数据 , 了解数据分布

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

data = pd.read_csv('creditcard.csv')
# print(data.head())

count_classes = pd.value_counts(data['Class'], sort=True).sort_index()
count_classes.plot(kind = 'bar')
plt.title('Fraud class histogram')
plt.xlabel('Class')
plt.ylabel('Frequency')

数据预处理

from sklearn.preprocessing import StandardScaler

data['normAmount'] = StandardScaler().fit_transform(data['Amount'].values.reshape(-1,1))
data = data.drop(['Time', 'Amount'], axis = 1)

X = data.loc[:, data.columns != 'Class'] #特征数据
y = data.loc[:, data.columns == 'Class'] #对应标签

number_records_fraud = len(data[data.Class == 1]) #'Class'值为1的个数'
fraud_indices = np.array(data[data.Class == 1].index) #存储'Class'值为1的索引值为矩阵

normal_indices = data[data.Class == 0].index #抽取'Class'值为0的数据标签

random_normal_indices = np.random.choice(normal_indices, number_records_fraud) #随机抽取与'Class'值为1的样本数相等的'Class'值为0的样本索引
random_normal_indices = np.array(random_normal_indices)

under_sample_indices = np.concatenate([fraud_indices, random_normal_indices]) #样本拼接
under_sample_data = data.iloc[under_sample_indices, :]

X_undersample = under_sample_data.loc[:, under_sample_data.columns != 'Class']
y_undersample = under_sample_data.loc[:, under_sample_data.columns == 'Class']

print('Percentage of normal transactions: ', len(under_sample_data[under_sample_data.Class == 0]) / len(under_sample_data))
print('Percentage of fraud transactions: ', len(under_sample_data[under_sample_data.Class == 1]) / len(under_sample_data))
print('Total number of transactions in resampled data: ', len(under_sample_data))

交叉检验 , 下采样数据切分

from sklearn.model_selection import train_test_split

X_train,X_test,y_train,y_test=train_test_split(X,y, test_size = 0.3,random_state