信用卡诈骗分析
- 归一化,删去相似属性
- 样本不均衡:1.下采样 2.生成新样本 SMOTE
- LogisticRegression函数使用l1时,要指定参数solver仅能够使用求解方式”liblinear"和"saga“
- 混淆矩阵
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
data = pd.read_csv("creditcard.csv")
data.head()
Time | V1 | V2 | V3 | V4 | V5 | V6 | V7 | V8 | V9 | ... | V21 | V22 | V23 | V24 | V25 | V26 | V27 | V28 | Amount | Class | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | 0.0 | -1.359807 | -0.072781 | 2.536347 | 1.378155 | -0.338321 | 0.462388 | 0.239599 | 0.098698 | 0.363787 | ... | -0.018307 | 0.277838 | -0.110474 | 0.066928 | 0.128539 | -0.189115 | 0.133558 | -0.021053 | 149.62 | 0 |
1 | 0.0 | 1.191857 | 0.266151 | 0.166480 | 0.448154 | 0.060018 | -0.082361 | -0.078803 | 0.085102 | -0.255425 | ... | -0.225775 | -0.638672 | 0.101288 | -0.339846 | 0.167170 | 0.125895 | -0.008983 | 0.014724 | 2.69 | 0 |
2 | 1.0 | -1.358354 | -1.340163 | 1.773209 | 0.379780 | -0.503198 | 1.800499 | 0.791461 | 0.247676 | -1.514654 | ... | 0.247998 | 0.771679 | 0.909412 | -0.689281 | -0.327642 | -0.139097 | -0.055353 | -0.059752 | 378.66 | 0 |
3 | 1.0 | -0.966272 | -0.185226 | 1.792993 | -0.863291 | -0.010309 | 1.247203 | 0.237609 | 0.377436 | -1.387024 | ... | -0.108300 | 0.005274 | -0.190321 | -1.175575 | 0.647376 | -0.221929 | 0.062723 | 0.061458 | 123.50 | 0 |
4 | 2.0 | -1.158233 | 0.877737 | 1.548718 | 0.403034 | -0.407193 | 0.095921 | 0.592941 | -0.270533 | 0.817739 | ... | -0.009431 | 0.798278 | -0.137458 | 0.141267 | -0.206010 | 0.502292 | 0.219422 | 0.215153 | 69.99 | 0 |
5 rows × 31 columns
count_classes = pd.value_counts(data['Class'], sort = True).sort_index()
count_classes.plot(kind = 'bar')
plt.title('class')
plt.xlabel('Class')
plt.ylabel('Frequency')
Text(0, 0.5, 'Frequency')
from sklearn.preprocessing import StandardScaler
# data['normAmount'] = StandardScaler().fit_transform(data['Amount'].reshape(-1,1))
data['normAmount'] = StandardScaler().fit_transform(data['Amount'].values.reshape(-1, 1))
data = data.drop(['Time','Amount'],axis = 1) #去掉不要的特征
data.head()
V1 | V2 | V3 | V4 | V5 | V6 | V7 | V8 | V9 | V10 | ... | V21 | V22 | V23 | V24 | V25 | V26 | V27 | V28 | Class | normAmount | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | -1.359807 | -0.072781 | 2.536347 | 1.378155 | -0.338321 | 0.462388 | 0.239599 | 0.098698 | 0.363787 | 0.090794 | ... | -0.018307 | 0.277838 | -0.110474 | 0.066928 | 0.128539 | -0.189115 | 0.133558 | -0.021053 | 0 | 0.244964 |
1 | 1.191857 | 0.266151 | 0.166480 | 0.448154 | 0.060018 | -0.082361 | -0.078803 | 0.085102 | -0.255425 | -0.166974 | ... | -0.225775 | -0.638672 | 0.101288 | -0.339846 | 0.167170 | 0.125895 | -0.008983 | 0.014724 | 0 | -0.342475 |
2 | -1.358354 | -1.340163 | 1.773209 | 0.379780 | -0.503198 | 1.800499 | 0.791461 | 0.247676 | -1.514654 | 0.207643 | ... | 0.247998 | 0.771679 | 0.909412 | -0.689281 | -0.327642 | -0.139097 | -0.055353 | -0.059752 | 0 | 1.160686 |
3 | -0.966272 | -0.185226 | 1.792993 | -0.863291 | -0.010309 | 1.247203 | 0.237609 | 0.377436 | -1.387024 | -0.054952 | ... | -0.108300 | 0.005274 | -0.190321 | -1.175575 | 0.647376 | -0.221929 | 0.062723 | 0.061458 | 0 | 0.140534 |
4 | -1.158233 | 0.877737 | 1.548718 | 0.403034 | -0.407193 | 0.095921 | 0.592941 | -0.270533 | 0.817739 | 0.753074 | ... | -0.009431 | 0.798278 | -0.137458 | 0.141267 | -0.206010 | 0.502292 | 0.219422 | 0.215153 | 0 | -0.073403 |
5 rows × 30 columns
#下采样解决样本不均衡
X = data.ix[:,data.columns != 'Class']
y = data.ix[:,data.columns == 'Class']
#class为1的个数和索引
number_records_fraud = len(data[data.Class == 1])
fraud_indices = np.array(data[data.Class == 1].index)
#class为0的索引
normal_indices = data[data.Class == 0].index
random_normal_indices = np.random.choice(normal_indices, number_records_fraud, replace = True)
random_normal_indices = np.array(random_normal_indices)
under_sample_indices = np.concatenate([fraud_indices, random_normal_indices])
under_sample_data = data.iloc[under_sample_indices, :] #取值
X_undersample = under_sample_data.ix[:,data.columns != 'Class']
y_undersample = under_sample_data.ix[:,data.columns == 'Class']
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))
Percentage of normal transactions: 0.5
Percentage of fraud transactions: 0.5
Total number of transactions in resampled data: 984
#划分数据集,交叉验证
from sklearn.model_selection import train_test_split
#whole dataset
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.3, random_state = 0)
#undersample dataset
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)
#Recall = TP/(TP+FN)
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection 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(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: #此循环找最好的c值,正则惩罚的权值
print('-------------------------------------------')
print('C parameter: ', c_param)
print('-------------------------------------------')
print('')
recall_accs = []
for iteration, indices in enumerate(fold.split(y_train_data),start=1):
# Call the logistic regression model with a certain C parameter
lr = LogisticRegression(C = c_param, penalty='l1',solver='liblinear')
# 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'].astype(float).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
best_c = printing_Kfold_scores(X_train_undersample,y_train_undersample)
-------------------------------------------
C parameter: 0.01
-------------------------------------------
Iteration 1 : recall score = 0.9452054794520548
Iteration 2 : recall score = 0.9178082191780822
Iteration 3 : recall score = 1.0
Iteration 4 : recall score = 0.972972972972973
Iteration 5 : recall score = 0.9848484848484849
Mean recall score 0.9641670312903191
-------------------------------------------
C parameter: 0.1
-------------------------------------------
Iteration 1 : recall score = 0.8493150684931506
Iteration 2 : recall score = 0.863013698630137
Iteration 3 : recall score = 0.9661016949152542
Iteration 4 : recall score = 0.9324324324324325
Iteration 5 : recall score = 0.8939393939393939
Mean recall score 0.9009604576820737
-------------------------------------------
C parameter: 1
-------------------------------------------
Iteration 1 : recall score = 0.863013698630137
Iteration 2 : recall score = 0.8904109589041096
Iteration 3 : recall score = 0.9661016949152542
Iteration 4 : recall score = 0.9459459459459459
Iteration 5 : recall score = 0.8939393939393939
Mean recall score 0.9118823384669682
-------------------------------------------
C parameter: 10
-------------------------------------------
Iteration 1 : recall score = 0.8767123287671232
Iteration 2 : recall score = 0.9178082191780822
Iteration 3 : recall score = 0.9830508474576272
Iteration 4 : recall score = 0.9324324324324325
Iteration 5 : recall score = 0.9242424242424242
Mean recall score 0.9268492504155379
-------------------------------------------
C parameter: 100
-------------------------------------------
Iteration 1 : recall score = 0.8767123287671232
Iteration 2 : recall score = 0.9178082191780822
Iteration 3 : recall score = 0.9830508474576272
Iteration 4 : recall score = 0.9324324324324325
Iteration 5 : recall score = 0.9242424242424242
Mean recall score 0.9268492504155379
*********************************************************************************
Best model to choose from cross validation is with C parameter = 0.01
*********************************************************************************
D:\Anoconda\lib\site-packages\sklearn\base.py:451: UserWarning: X does not have valid feature names, but LogisticRegression was fitted with feature names
"X does not have valid feature names, but"
D:\Anoconda\lib\site-packages\sklearn\base.py:451: UserWarning: X does not have valid feature names, but LogisticRegression was fitted with feature names
"X does not have valid feature names, but"
D:\Anoconda\lib\site-packages\sklearn\base.py:451: UserWarning: X does not have valid feature names, but LogisticRegression was fitted with feature names
"X does not have valid feature names, but"
D:\Anoconda\lib\site-packages\sklearn\base.py:451: UserWarning: X does not have valid feature names, but LogisticRegression was fitted with feature names
"X does not have valid feature names, but"
D:\Anoconda\lib\site-packages\sklearn\base.py:451: UserWarning: X does not have valid feature names, but LogisticRegression was fitted with feature names
"X does not have valid feature names, but"
D:\Anoconda\lib\site-packages\ipykernel_launcher.py:37: FutureWarning:
.ix is deprecated. Please use
.loc for label based indexing or
.iloc for positional indexing
See the documentation here:
http://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#ix-indexer-is-deprecated
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="red" 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',solver='liblinear')
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()
Recall metric in the testing dataset: 0.9319727891156463
lr = LogisticRegression(C = best_c, penalty = 'l1',solver='liblinear')
lr.fit(X_train_undersample,y_train_undersample.values.ravel())
y_pred = lr.predict(X_test.values)
# Compute confusion matrix
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()
Recall metric in the testing dataset: 0.9115646258503401
best_c = printing_Kfold_scores(X_train,y_train)
-------------------------------------------
C parameter: 0.01
-------------------------------------------
Iteration 1 : recall score = 0.4925373134328358
Iteration 2 : recall score = 0.6027397260273972
Iteration 3 : recall score = 0.6833333333333333
Iteration 4 : recall score = 0.5692307692307692
Iteration 5 : recall score = 0.45
Mean recall score 0.5595682284048672
-------------------------------------------
C parameter: 0.1
-------------------------------------------
Iteration 1 : recall score = 0.5671641791044776
Iteration 2 : recall score = 0.6164383561643836
Iteration 3 : recall score = 0.6833333333333333
Iteration 4 : recall score = 0.5846153846153846
Iteration 5 : recall score = 0.525
Mean recall score 0.5953102506435158
-------------------------------------------
C parameter: 1
-------------------------------------------
Iteration 1 : recall score = 0.5522388059701493
Iteration 2 : recall score = 0.6164383561643836
Iteration 3 : recall score = 0.7166666666666667
Iteration 4 : recall score = 0.6153846153846154
Iteration 5 : recall score = 0.5625
Mean recall score 0.612645688837163
-------------------------------------------
C parameter: 10
-------------------------------------------
Iteration 1 : recall score = 0.5522388059701493
Iteration 2 : recall score = 0.6164383561643836
Iteration 3 : recall score = 0.7333333333333333
Iteration 4 : recall score = 0.6153846153846154
Iteration 5 : recall score = 0.575
Mean recall score 0.6184790221704963
-------------------------------------------
C parameter: 100
-------------------------------------------
Iteration 1 : recall score = 0.5522388059701493
Iteration 2 : recall score = 0.6164383561643836
Iteration 3 : recall score = 0.7333333333333333
Iteration 4 : recall score = 0.6153846153846154
Iteration 5 : recall score = 0.575
Mean recall score 0.6184790221704963
*********************************************************************************
Best model to choose from cross validation is with C parameter = 10.0
*********************************************************************************
lr = LogisticRegression(C = best_c, penalty = 'l1',solver='liblinear')
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()
Recall metric in the testing dataset: 0.6190476190476191
lr = LogisticRegression(C = 0.01, penalty = 'l1',solver='liblinear')
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)
D:\Anoconda\lib\site-packages\sklearn\base.py:451: UserWarning: X does not have valid feature names, but LogisticRegression was fitted with feature names
"X does not have valid feature names, but"
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: 0.9931972789115646
Recall metric in the testing dataset: 0.9319727891156463
Recall metric in the testing dataset: 0.891156462585034
Recall metric in the testing dataset: 0.8367346938775511
Recall metric in the testing dataset: 0.7551020408163265
Recall metric in the testing dataset: 0.5850340136054422
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)
#生成更多label为1的值
oversampler=SMOTE(random_state=0)
os_features,os_labels=oversampler.fit_sample(features_train,labels_train)
len(os_labels[os_labels==1])
227454
os_features = pd.DataFrame(os_features)
os_labels = pd.DataFrame(os_labels)
best_c = printing_Kfold_scores(os_features,os_labels)
-------------------------------------------
C parameter: 0.01
-------------------------------------------
Iteration 1 : recall score = 0.8903225806451613
Iteration 2 : recall score = 0.8947368421052632
Iteration 3 : recall score = 0.9688170853159235
Iteration 4 : recall score = 0.9578923071850166
Iteration 5 : recall score = 0.9583539420318528
Mean recall score 0.9340245514566435
-------------------------------------------
C parameter: 0.1
-------------------------------------------
Iteration 1 : recall score = 0.8903225806451613
Iteration 2 : recall score = 0.8947368421052632
Iteration 3 : recall score = 0.9698572535133341
Iteration 4 : recall score = 0.9597278552664842
Iteration 5 : recall score = 0.9527483760345566
Mean recall score 0.9334785815129599
-------------------------------------------
C parameter: 1
-------------------------------------------
Iteration 1 : recall score = 0.8903225806451613
Iteration 2 : recall score = 0.8947368421052632
Iteration 3 : recall score = 0.9705433218988603
Iteration 4 : recall score = 0.9603653510073532
Iteration 5 : recall score = 0.9604093162308613
Mean recall score 0.9352754823774998
-------------------------------------------
C parameter: 10
-------------------------------------------
Iteration 1 : recall score = 0.8903225806451613
Iteration 2 : recall score = 0.8947368421052632
Iteration 3 : recall score = 0.9705433218988603
Iteration 4 : recall score = 0.9604093162308613
Iteration 5 : recall score = 0.9589144986315824
Mean recall score 0.9349853119023457
-------------------------------------------
C parameter: 100
-------------------------------------------
Iteration 1 : recall score = 0.8903225806451613
Iteration 2 : recall score = 0.8947368421052632
Iteration 3 : recall score = 0.9704990594223747
Iteration 4 : recall score = 0.960321385783845
Iteration 5 : recall score = 0.9607060814895417
Mean recall score 0.9353171898892372
*********************************************************************************
Best model to choose from cross validation is with C parameter = 100.0
*********************************************************************************
lr = LogisticRegression(C = best_c, penalty = 'l1',solver='liblinear')
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()
Recall metric in the testing dataset: 0.900990099009901