逻辑回归模型—信用卡交易数据异常检测

Posted on

1.原始数据

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np

data = pd.read_csv("creditcard.csv")
print("前5行数据:\n",data.head())

# 统计列Class不同值的个数并且升序排序
count_classes = pd.value_counts(data['Class'], sort=True).sort_index()
# 条形图
count_classes.plot(kind='bar')
plt.title("Fraud class histogram")
plt.xlabel("Class")
plt.ylabel("Frequency")
plt.show()
# 结果发现样本Class=0数据量>250000,而Class=1数据量<1000

2.样本不均衡采用的方法

2.1 过采样–让两个样本同样多

1
2
3
4
5
6
7
# Amount列数值分布不均衡
# 数据进行变换  例子：[2,3] reshape [-1,2]  分成2列,自动计算为3行
# 标准化数据，保证Amount列的特征数据方差为1，均值为0，使得预测结果不会被某些维度过大的特征值而主导
data['normAmount'] = StandardScaler().fit_transform(data['Amount'].values.reshape(-1, 1))
# 去掉无用的两列,得到特征数据
data = data.drop(['Time','Amount'],axis=1)
print("去掉两列之后:\n",data.head())

2.2 下采用–让两个样本同样少

3.交叉验证

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
from sklearn.cross_validation import train_test_split
# 交叉验证让模型的评估效果可信
# 原始数据集切分，30%数据当做测试集
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))

# 结果输出
Number transactions train dataset:  199364
Number transactions test dataset:  85443
Total number of transactions:  284807


# 下采样数据集切分 
X_train_undersample, X_test_undersample, y_train_undersample, y_test_undersample = train_test_split(X_undersample

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))

# 结果输出
Number transactions train dataset:  688
Number transactions test dataset:  296
Total number of transactions:  984

4.模型评估

  • 例子：某个班级有男生80人，女生20人，共计100人，目标是找出所有女生，现在某人挑选出50个人，其中20人是女生，另外还错误的把30个男生也当作女生挑选出来
相关（Relevant）,正类 无关（NonRelevant）,负类
被检索到（Retrieved） true positives(TP 正类判定为正类,例子中就是正确的判定”这位是女生”) false positives(FP 负类判定为正类，”存伪”,例子中就是分明是男生却判断为女生，当下伪娘横行，这个错常有人犯）
未被检索到（Not Retrieved） false negatives(FN 正类判定为负类，”去真”,例子中就是分明是女生，却判断为男生–梁山伯同学犯的错就是这个) true negatives(TN 负类判定为负类，男生判断为男生，像我这样的纯爷们一准儿就会在此处)

上述例子，可以得到这几个值:

TP = 20

FP = 30

FN = 0

TN = 50
  • Recall（召回率） = TP/(TP+FN) 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
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):
    # 交叉验证，原始数据切分5部分
    fold = KFold(len(y_train_data),5,shuffle=False) 

    # Different C parameters
    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

    # 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):

            # Call the logistic regression model with a certain C parameter
            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())

            # Predict values using the test indices in the training data
            y_pred_undersample = lr.predict(x_train_data.iloc[indices[1],:].values)

            # Calculate the recall score and append it to a list for recall scores representing the current c_parameter
            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)

        # The mean value of those recall scores is the metric we want to save and get hold of.
        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.loc[results_table['Mean recall score'].idxmax()]['C_parameter']
    
    # Finally, we can check which C parameter is the best amongst the chosen.
    print('*********************************************************************************')
    print('Best model to choose from cross validation is with C parameter = ', best_c)
    print('*********************************************************************************')
    
    return best_c

5.混淆矩阵

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
def plot_confusion_matrix(cm, classes,
                          title='Confusion matrix',
                          cmap=plt.cm.Blues):
    """
    This function prints and plots the confusion matrix.
    """
    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')
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
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)

# Compute confusion matrix
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()

#结果 
Recall metric in the testing dataset:  0.931972789116

6.阀值对结果的影响

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
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) 
                          
#结果
Recall metric in the testing dataset:  1.0
Recall metric in the testing dataset:  1.0
Recall metric in the testing dataset:  1.0
Recall metric in the testing dataset:  0.986394557823
Recall metric in the testing dataset:  0.931972789116
Recall metric in the testing dataset:  0.884353741497
Recall metric in the testing dataset:  0.836734693878
Recall metric in the testing dataset:  0.748299319728
Recall metric in the testing dataset:  0.571428571429

7.SMOTE样本生成策略-过采样

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
import pandas as pd
from imblearn.over_sampling import SMOTE
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import confusion_matrix
from sklearn.model_selection import train_test_split

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

columns=credit_cards.columns
# The labels are in the last column ('Class'). Simply remove it to obtain features columns
features_columns=columns.delete(len(columns)-1)

features=credit_cards[features_columns]
labels=credit_cards['Class']

features_train, features_test, labels_train, labels_test = train_test_split(features, 
                                                                            labels, 
                                                                            test_size=0.2, 
                                                                            random_state=0)
                                                                            
                                                                            oversampler=SMOTE(random_state=0)
os_features,os_labels=oversampler.fit_sample(features_train,labels_train)

len(os_labels[os_labels==1])
# 结果
227454

os_features = pd.DataFrame(os_features)
os_labels = pd.DataFrame(os_labels)
best_c = printing_Kfold_scores(os_features,os_labels)

lr = LogisticRegression(C = best_c, penalty = 'l1')
lr.fit(os_features,os_labels.values.ravel())
y_pred = lr.predict(features_test.values)

# Compute confusion matrix
cnf_matrix = confusion_matrix(labels_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()
# 结果，误杀率降低了
Recall metric in the testing dataset:  0.90099009901