- 导入模块查看数据情况, 并绘类别的直方图
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
%matplotlib inline
data = pd.read_csv("creditcard.csv")
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")
- 预处理, 标准化并去除没用的特征
from sklearn.preprocessing import StandardScaler
data['normAmount'] = StandardScaler().fit_transform(data['Amount'].values.reshape(-1, 1)) # 转换成列向量赋值为新的特征
data = data.drop(['Time','Amount'],axis=1) # 取出两个没用的特征
data.head()
- 下采样策略(因为1类别的数据非常少, 所以取少量0类别的数据与之对应)
# 下采样策略
X = data.ix[:, data.columns != 'Class']
y = data.ix[:, data.columns == 'Class']
# 计算class==1的样本数量并取出对应索引值
number_records_fraud = len(data[data.Class == 1])
fraud_indices = np.array(data[data.Class == 1].index)
# 取出class==0的索引值
normal_indices = data[data.Class == 0].index
# 在normal_indices中随机选择
random_normal_indices = np.random.choice(normal_indices, number_records_fraud, replace = False)
random_normal_indices = np.array(random_normal_indices) # 转成array格式
# 合并
under_sample_indices = np.concatenate([fraud_indices,random_normal_indices])
# iloc基于索引位来选取数据集
under_sample_data = data.iloc[under_sample_indices,:]
X_undersample = under_sample_data.ix[:, under_sample_data.columns != 'Class']
y_undersample = under_sample_data.ix[:, under_sample_data.columns == 'Class']
# 展示
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))
由上可知, 通过下采样之后, 取出984个样本, 0,1的占比都为分别为0.5
- 交叉验证
# 交叉验证
from sklearn.cross_validation import train_test_split
# 对原始数据集也做交叉验证
# test_size:测试集的比例 random_state:随机切分
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))
# 对下采样数据集也做交叉验证
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))
- 模型评估方法
# 模型评估方法
# 查全率 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) # 5折交叉验证
# 正则化惩罚项
c_param_range = [0.01, 0.1, 1, 10, 100] # 惩罚力度
results_table = pd.DataFrame(index = range(len(c_param_range),2), columns = ['C_parameter','Mean recall score'])
results_table['C_parameter'] = c_param_range
# the k-fold will give 2 lists: train_indices = indices[0], test_indices = indices[1]
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):
# 实例化模型
lr = LogisticRegression(C = c_param, penalty = 'l1')
# Use the training data to fit the model. In this case, we use the portion of the fold to train the model
# with indices[0]. We then predict on the portion assigned as the 'test cross validation' with indices[1]
lr.fit(x_train_data.iloc[indices[0],:],y_train_data.iloc[indices[0],:].values.ravel())
# 使用训练数据中的测试集预测
y_pred_undersample = lr.predict(x_train_data.iloc[indices[1],:].values)
# 计算查全率并将其加到表示当前c_parameter的查全率列表中
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)
# 平均查全率
results_table.ix[j,'Mean recall score'] = np.mean(recall_accs)
j += 1
print('')
print('Mean recall score ', np.mean(recall_accs))
print('')
best_c = results_table
best_c.dtypes.eq(object) # you can see the type of best_c
new = best_c.columns[best_c.dtypes.eq(object)] #get the object column of the best_c
best_c[new] = best_c[new].apply(pd.to_numeric, errors = 'coerce', axis=0) # change the type of object
best_c
best_c = results_table.loc[results_table['Mean recall score'].idxmax()]['C_parameter']
# 最后，我们可以检查哪一个C参数(惩罚力度)是最好的选择.
print('*********************************************************************************')
print('Best model to choose from cross validation is with C parameter = ', best_c)
print('*********************************************************************************')
return best_c
best_c = printing_Kfold_scores(X_train_undersample,y_train_undersample)
通过对比发现, 当惩罚项为0.01时, recall值最大
- 混淆矩阵
# 混淆矩阵
def plot_confusion_matrix(cm, classes,
title='Confusion matrix',
cmap=plt.cm.Blues):
"""
此函数打印并绘制混淆矩阵.
"""
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)
# 计算混淆矩阵(下采样数据集)
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]))
# Plot non-normalized confusion matrix
class_names = [0,1]
plt.figure()
plot_confusion_matrix(cnf_matrix
, classes=class_names
, title='Confusion matrix')
plt.show()
下采样数据集的混淆矩阵
lr = LogisticRegression(C = best_c, penalty = 'l1')
lr.fit(X_train_undersample,y_train_undersample.values.ravel())
y_pred = lr.predict(X_test.values)
# 计算混淆矩阵(原始数据集)
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]))
# Plot non-normalized confusion matrix
class_names = [0,1]
plt.figure()
plot_confusion_matrix(cnf_matrix
, classes=class_names
, title='Confusion matrix')
plt.show()
原数据集的混淆矩阵
对比发现下采样建立的模型虽然查全率较好, 但是在原始中发现误杀的比例较多, 也就是精度大大降低了
- 如果不做下采样, 直接对原始数据进行验证, 看看查全率如何
best_c = printing_Kfold_scores(X_train,y_train)
明显发现recall值不如下采样之后的值
lr = LogisticRegression(C = best_c, penalty = 'l1')
lr.fit(X_train,y_train.values.ravel())
y_pred_undersample = lr.predict(X_test.values)
# Compute confusion matrix
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]))
# Plot non-normalized confusion matrix
class_names = [0,1]
plt.figure()
plot_confusion_matrix(cnf_matrix
, classes=class_names
, title='Confusion matrix')
plt.show()
- 改变阈值来观察效果(sogmoid一般是0.5)
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)
# 一般默认使用的阈值是0.5, 现在手动指定阈值
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)
不同阈值得到的recall值
不同阈值对应的混淆矩阵
由此发现, 随着阈值的上升, recall值在降低, 也就是判断信用卡欺诈的条件越来越严格.并且阈值取0.5,0.6时相对效果较好
