信用卡欺诈检测python_python数据分析－信用卡欺诈行为检测

import pandas as pd

data=pd.read_csv('creditcard.csv')

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')

from sklearn.preprocessing import StandardScaler

data['normAmount']=StandardScaler().fit_transform(data['Amount'].reshape(-1,1))#对差异较大的列进行标准化操作

data=data.drop(['Time','Amount'],axis=1)

data.head()

x=data.ix[:,data.columns!='Class']

y=data.ix[:,data.columns=='Class']

#class=1--->存在欺诈行为，class＝0--->不存在欺诈行为

number_records_fraud=len(data[data.Class==1])＃找class＝1的个数

fraud_indices=np.array(data[data.Cla