1.数据读取

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

data = pd.read_csv("creditcard.csv")
data.head()

展示数据基本信息，如缺失值，字段类型等等

data.info()

2.数据预处理

#统计不同标签对应的样本数
count_classes = pd.value_counts(data['Class'], sort = True).sort_index()
#通过条形图显示出来
count_classes.plot(kind = 'bar')
plt.title("Fraud class histogram")
plt.xlabel("Class")
plt.ylabel("Frequency")

通过条形图显示，正负样本（class分别为1和0的样本）比例失调，通常解决这一问题的方法有：

• 调整正负样本的权重
• 上采样
• 下采样

#对样本的Amount列进行归一化处理
from sklearn import preprocessing
data['normAmount'] = preprocessing.scale(data['Amount'])
#删除无关列
data = data.drop(['Time', 'Amount'], axis=1)
data.head()

生成下采样样本数据集

#筛选出训练数据与相应的分类标签
X = data.loc[:, data.columns != 'Class']
y = data.loc[:, data.columns == 'Class']

# 筛选出信用卡欺诈样本，并统计样本数量
number_records_fraud = len(data[data.Class == 1])
fraud_indices = np.array(data[data.Class == 1].index)

# 筛选出正常样本，并统计样本数量
normal_indices = data[data.Class == 0].index

# 由于信用卡欺诈的样本数量远远小于正常样本数量，我们这里采取下采样，即删去正常样本，使其样本数量和信用卡欺诈样本数量保持一致
random_normal_indices = np.random.choice(normal_indices, number_records_fraud, replace = False)
random_normal_indices = np.array(random_normal_indices)

# 生成下采样样本
under_sample_indices = np.concatenate([fraud_indices,random_normal_indices])
under_sample_data = data.iloc[under_sample_indices,:]

# 分离下采样样本的数据集及标签集
X_undersample = under_sample_data.loc[:, under_sample_data.columns != 'Class']
y_undersample = under_sample_data.loc[:, under_sample_data.columns == 'Class']

# 打印出正负样本比例
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))

3.训练模型——交叉验证、参数选择以及模型评价

训练集及测试集形成：

from sklearn.model_selection import train_test_split

#经过标准化的原始数据集
X_train, X_test, y_train, y_test = train_test_split(X,y,test_size = 0.3, random_state = 0)

print("Number transactions train dataset: ", len(X_train))
print("Number transactions test dataset: ", len(X_test))
print("Total number of transactions: ", len(X_train)+len(X_test))

# 预处理后的下采样数据集
X_train_undersample, X_test_undersample, y_train_undersample, y_test_undersample = train_test_split(X_undersample
                                                                                                   ,y_undersample
                                                                                                   ,test_size = 0.3
                                                                                                   ,random_state = 0)
print("")
print("Number transactions train dataset: ", len(X_train_undersample))
print("Number transactions test dataset: ", len(X_test_undersample))
print("Total number of transactions: ", len(X_train_undersample)+len(X_test_undersample))

C参数值的完整调优过程，比较原始样本集与下采样样本集的召回率的大小

#召回率计算公式：Recall = TP/(TP+FN)
from sklearn.linear_model import LogisticRegression
from sklearn.cross_validation import KFold, cross_val_score
from sklearn.metrics import confusion_matrix,recall_score,classification_report 

def printing_Kfold_scores(x_train_data,y_train_data):
    fold = KFold(len(y_train_data), 5, shuffle=False) 

    # C parameters 取值集合
    c_param_range = [0.01,0.1,1,10,100]

    results_table = pd.DataFrame(index = range(len(c_param_range),2), columns = ['C_parameter', 'Mean recall score'])
    results_table['C_parameter'] = c_param_range

    # 交叉验证后形成两列: 训练集, 测试集
    j = 0
    for c_param in c_param_range:
        print('-------------------------------------------')
        print('C parameter: ', c_param)
        print('-------------------------------------------')
        print('')

        recall_accs = []
        for iteration, indices in enumerate(fold,start=1):

            # 在特定参数C下的逻辑回归模型
            lr = LogisticRegression(C = c_param, penalty = 'l1')
            #取出训练集训练模型
            lr.fit(x_train_data.iloc[indices[0],:],y_train_data.iloc[indices[0],:].values.ravel())
            #取出测试集验证模型
            y_pred_undersample = lr.predict(x_train_data.iloc[indices[1],:].values)

            # 计算当前c参数值下的召回率
            recall_acc = recall_score(y_train_data.iloc[indices[1],:].values,y_pred_undersample)
            recall_accs.append(recall_acc)
            print('Iteration ', iteration,': recall score = ', recall_acc)

        # 计算不同c参数值下逻辑回归模型的召回率的均值
        results_table.loc[j, 'Mean recall score'] = np.mean(recall_accs)
        j += 1
        print('')
        print('Mean recall score ', np.mean(recall_accs))
        print('')

    best_c = results_table.loc[pd.Series(results_table['Mean recall score']).values.argmax()]['C_parameter']
    
    # 选择逻辑回归模型召回率最高时对应的参数c值，即为参数c的最优取值
    print('*********************************************************************************')
    print('Best model to choose from cross validation is with C parameter = ', best_c)
    print('*********************************************************************************')
    
    return best_c
#展示下采样数据集在不同参数c下逻辑回归模型的召回率，并选择召回率最高时对应的参数c值
best_c = printing_Kfold_scores(X_train_undersample,y_train_undersample)

#函数功能：可视化混淆矩阵
def plot_confusion_matrix(cm, classes,
                          title='Confusion matrix',
                          cmap=plt.cm.Blues):
    plt.imshow(cm, interpolation='nearest', cmap=cmap)
    plt.title(title)
    plt.colorbar()
    tick_marks = np.arange(len(classes))
    plt.xticks(tick_marks, classes, rotation=0)
    plt.yticks(tick_marks, classes)

    thresh = cm.max() / 2.
    for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])):
        plt.text(j, i, cm[i, j],
                 horizontalalignment="center",
                 color="white" if cm[i, j] > thresh else "black")

    plt.tight_layout()
    plt.ylabel('True label')
    plt.xlabel('Predicted label')
import itertools
lr = LogisticRegression(C = best_c, penalty = 'l1')
lr.fit(X_train_undersample,y_train_undersample.values.ravel())
y_pred_undersample = lr.predict(X_test_undersample.values)

# 计算训练集下的混淆矩阵的召回率
cnf_matrix = confusion_matrix(y_test_undersample,y_pred_undersample)
np.set_printoptions(precision=2)

print("Recall metric in the testing dataset: ", cnf_matrix[1,1]/(cnf_matrix[1,0]+cnf_matrix[1,1]))

# 展示训练集混淆矩阵
class_names = [0,1]
plt.figure()
plot_confusion_matrix(cnf_matrix
                      , classes=class_names
                      , title='Confusion matrix')
plt.show()

lr = LogisticRegression(C = best_c, penalty = 'l1')
lr.fit(X_train_undersample,y_train_undersample.values.ravel())
y_pred = lr.predict(X_test.values)

# 计算下采样数据的召回率
cnf_matrix = confusion_matrix(y_test,y_pred)
np.set_printoptions(precision=2)

print("Recall metric in the testing dataset: ", cnf_matrix[1,1]/(cnf_matrix[1,0]+cnf_matrix[1,1]))

# 展示测试集混淆矩阵
class_names = [0,1]
plt.figure()
plot_confusion_matrix(cnf_matrix
                      , classes=class_names
                      , title='Confusion matrix')
plt.show()

#展示原始数据集在不同参数c下逻辑回归模型的召回率，并选择召回率最高时对应的参数c值
best_c = printing_Kfold_scores(X_train,y_train)

lr = LogisticRegression(C = best_c, penalty = 'l1')
lr.fit(X_train, y_train.values.ravel())
y_pred_undersample = lr.predict(X_test.values)

# 计算原始数据集召回率
cnf_matrix = confusion_matrix(y_test,y_pred_undersample)
np.set_printoptions(precision=2)

print("Recall metric in the testing dataset: ", cnf_matrix[1,1]/(cnf_matrix[1,0]+cnf_matrix[1,1]))

# 可视化混淆矩阵
class_names = [0,1]
plt.figure()
plot_confusion_matrix(cnf_matrix
                      , classes=class_names
                      , title='Confusion matrix')
plt.show()

阈值的参数选择过程

#可视化参数阈值（thresholds）在取不同值时测试集对应的召回率
lr = LogisticRegression(C = 0.01, penalty = 'l1')
lr.fit(X_train_undersample,y_train_undersample.values.ravel())
y_pred_undersample_proba = lr.predict_proba(X_test_undersample.values)

thresholds = [0.1,0.2,0.3,0.4,0.5,0.6,0.7,0.8,0.9]

plt.figure(figsize=(10,10))

j = 1
for i in thresholds:
    y_test_predictions_high_recall = y_pred_undersample_proba[:,1] > i
    
    plt.subplot(3,3,j)
    j += 1
    
    # Compute confusion matrix
    cnf_matrix = confusion_matrix(y_test_undersample,y_test_predictions_high_recall)
    np.set_printoptions(precision=2)

    print("Recall metric in the testing dataset: ", cnf_matrix[1,1]/(cnf_matrix[1,0]+cnf_matrix[1,1]))

    # Plot non-normalized confusion matrix
    class_names = [0,1]
    plot_confusion_matrix(cnf_matrix
                          , classes=class_names
                          , title='Threshold >= %s'%i)