import pandas as pd import matplotlib.pyplot as plt import numpy as np# 讀取數據 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") plt.show()

樣本不均衡
樣本數據不均衡的情況時 采用 下采樣 和 過采樣
下采樣 ：讓0和1數據一樣小，樣本同樣少 過采樣： 樣本同樣多

from sklearn.preprocessing import StandardScaler data['normAmount'] = StandardScaler().fit_transform(data['Amount'].values.reshape(-1, 1)) data = data.drop(['Time', 'Amount'], axis=1) print(data.head())

下采樣：

# 下采樣 X = data.ix[:, data.columns !='Class'] y = data.ix[:, data.columns =='Class']number_records_fraud = len(data[data.Class == 1]) fraud_indeices = np.array(data[data.Class == 1].index)normal_indices = data[data.Class == 0].indexrandom_normal_indices = np.random.choice(normal_indices, number_records_fraud, replace=False) random_normal_indices = np.array(random_normal_indices)#合并 under_sample_indices = np.concatenate([fraud_indeices，random_normal_indices])under_sample_data = data.iloc[under_sample_indices,:]X_undersample = under_sample_data.ix[:,under_sample_data.columns !='Class'] X_undersample = under_sample_data.ix[:,under_sample_data.columns =='Class']print('Percentage of nomal transaction:,', len(under_sample_data[under_sample_data.Class == 0])/len(under_sample_data)) print('Percentage of Fraud transaction:,', len(under_sample_data[under_sample_data.Class == 1])/len(under_sample_data)) print('reasmpled data 總的 transactions:', len(under_sample_data))

交叉驗證

#交叉驗證from sklearn.cross_validation import train_test_splitX_train, X_test, y_train, y_test = train_test_split(X,y,test_size=0.3, random_state = 0)X_train_undersample, X_test_undersample, y_train_undersample,y_test_undersample =train_test_split(X_undersample,y_undersample,test_size,random_state) print('') print('Number transact train dataset: ', len(X_train)) print('Number transact test dataset: ', len(X_test)) print('Total number of transaction: ', len(X_train_undersample)+len(X_test_undersample))

總結

以上是生活随笔為你收集整理的机器学习实战之信用卡诈骗（一）的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。