邏輯迴歸-信用卡欺詐檢測
阿新 • • 發佈：2019-02-12
資料來源準備
"Time","V1","V2","V3","V4","V5","V6","V7","V8","V9","V10","V11","V12","V13","V14","V15","V16","V17","V18","V19","V20","V21","V22","V23","V24","V25","V26","V27","V28","Amount","Class"
0,-1.3598071336738,-0.0727811733098497,2.53634673796914,1.37815522427443,-0.338320769942518,0.462387777762292,0.239598554061257 import pandas as pd
import matplotlib.pyplot as plt
import numpy as np輸入資料
data = pd.read_csv("creditcard.csv")
data.head()
由於“amount”這一列範圍區間較大，待會需要做特殊處理
由於做信用卡欺詐檢測這種任務，根據業務特性，很明顯會出現樣本不均衡的情況，因為大部分信用卡使用者都比較正常
其中class=0的為正常值 為1的是異常的
# 計算class=0的有多少個 =1的有多少個
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")
歸一化：“amount”的值可能大於100，而V28卻是[-1,1]之間，不做歸一化，模型會認為“amount”更重要
# sklearn資料預處理模組做資料預處理
from sklearn.preprocessing import StandardScaler
# sklearn的reshape函式設定-1，即讓其自動計算有多少行 得到新的列
data['normAmount'] = StandardScaler().fit_transform(data['Amount'].reshape(-1, 1))
data = data.drop(['Time','Amount'],axis=1)
data.head()
# 取出x值和label值
X = data.ix[:, data.columns != 'Class']
y = data.ix[:, data.columns == 'Class']
# 拿到所有負例的個數和它們的index，用來做過取樣
number_records_fraud = len(data[data.Class == 1])
fraud_indices = np.array(data[data.Class == 1].index)
# 拿到所有正例的index，如果是做欠取樣，那麼需要通過index隨機取
normal_indices = data[data.Class == 0].index
# 從正例的資料集中採集負例個數的樣本
random_normal_indices = np.random.choice(normal_indices, number_records_fraud, replace = False)
# 轉換為numpy的格式
random_normal_indices = np.array(random_normal_indices)
# 合併正例和負例樣本
under_sample_indices = np.concatenate([fraud_indices,random_normal_indices])
# pandas的索引來重新賦值
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']
# Showing ratio
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))列印下采樣後的樣本個數 輸出
Percentage of normal transactions: 0.5
Percentage of fraud transactions: 0.5
Total number of transactions in resampled data: 984交叉驗證：
from sklearn.cross_validation import train_test_split
# 原始資料集切分 random_state 為洗牌隨機切分 -- 切分後的驗證集可以用於驗證下采樣的模型好壞
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))
# 下采樣資料集切分
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))輸出結果
Number transactions train dataset: 199364
Number transactions test dataset: 85443
Total number of transactions: 284807
Number transactions train dataset: 688
Number transactions test dataset: 296
Total number of transactions: 984模型的評估方法–樣本極度不均衡，精度是會騙人的，用recall更好
#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 正則化懲罰 – 懲罰權重引數
def printing_Kfold_scores(x_train_data,y_train_data):
# 5折交叉驗證
fold = KFold(len(y_train_data),5,shuffle=False)
# 由於不知道具體的C值 這裡幾個先驗值逐一試試
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('')
# sklearn KFold交叉驗證分組情況樣本
recall_accs = []
for iteration, indices in enumerate(fold,start=1):
# 正則化選擇引數：penalty 優化演算法選擇引數：solver 分類方式選擇引數：multi_class 型別權重引數： class_weight 樣本權重引數： sample_weight
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]
# iloc比較簡單，它是基於索引位來選取資料集，0:4就是選取 0，1，2，3這四行
lr.fit(x_train_data.iloc[indices[0],:],y_train_data.iloc[indices[0],:].values.ravel())
# 獲取預測值
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輸入結果
best_c = printing_Kfold_scores(X_train_undersample,y_train_undersample)輸出結果
-------------------------------------------
C parameter: 0.01
-------------------------------------------
Iteration 1 : recall score = 0.958904109589
Iteration 2 : recall score = 0.917808219178
Iteration 3 : recall score = 1.0
Iteration 4 : recall score = 0.972972972973
Iteration 5 : recall score = 0.954545454545
Mean recall score 0.960846151257
-------------------------------------------
C parameter: 0.1
-------------------------------------------
Iteration 1 : recall score = 0.835616438356
Iteration 2 : recall score = 0.86301369863
Iteration 3 : recall score = 0.915254237288
Iteration 4 : recall score = 0.932432432432
Iteration 5 : recall score = 0.878787878788
Mean recall score 0.885020937099
-------------------------------------------
C parameter: 1
-------------------------------------------
Iteration 1 : recall score = 0.835616438356
Iteration 2 : recall score = 0.86301369863
Iteration 3 : recall score = 0.966101694915
Iteration 4 : recall score = 0.945945945946
Iteration 5 : recall score = 0.893939393939
Mean recall score 0.900923434357
-------------------------------------------
C parameter: 10
-------------------------------------------
Iteration 1 : recall score = 0.849315068493
Iteration 2 : recall score = 0.86301369863
Iteration 3 : recall score = 0.966101694915
Iteration 4 : recall score = 0.959459459459
Iteration 5 : recall score = 0.893939393939
Mean recall score 0.906365863087
-------------------------------------------
C parameter: 100
-------------------------------------------
Iteration 1 : recall score = 0.86301369863
Iteration 2 : recall score = 0.86301369863
Iteration 3 : recall score = 0.966101694915
Iteration 4 : recall score = 0.959459459459
Iteration 5 : recall score = 0.893939393939
Mean recall score 0.909105589115
*********************************************************************************
Best model to choose from cross validation is with C parameter = 0.01
*********************************************************************************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')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()
lr = LogisticRegression(C = best_c, penalty = 'l1')
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()
best_c = printing_Kfold_scores(X_train,y_train)原始資料集的召回率遠遠低於下采樣資料集的召回率
-------------------------------------------
C parameter: 0.01
-------------------------------------------
Iteration 1 : recall score = 0.492537313433
Iteration 2 : recall score = 0.602739726027
Iteration 3 : recall score = 0.683333333333
Iteration 4 : recall score = 0.569230769231
Iteration 5 : recall score = 0.45
Mean recall score 0.559568228405
-------------------------------------------
C parameter: 0.1
-------------------------------------------
Iteration 1 : recall score = 0.567164179104
Iteration 2 : recall score = 0.616438356164
Iteration 3 : recall score = 0.683333333333
Iteration 4 : recall score = 0.584615384615
Iteration 5 : recall score = 0.525
Mean recall score 0.595310250644
-------------------------------------------
C parameter: 1
-------------------------------------------
Iteration 1 : recall score = 0.55223880597
Iteration 2 : recall score = 0.616438356164
Iteration 3 : recall score = 0.716666666667
Iteration 4 : recall score = 0.615384615385
Iteration 5 : recall score = 0.5625
Mean recall score 0.612645688837
-------------------------------------------
C parameter: 10
-------------------------------------------
Iteration 1 : recall score = 0.55223880597
Iteration 2 : recall score = 0.616438356164
Iteration 3 : recall score = 0.733333333333
Iteration 4 : recall score = 0.615384615385
Iteration 5 : recall score = 0.575
Mean recall score 0.61847902217
-------------------------------------------
C parameter: 100
-------------------------------------------
Iteration 1 : recall score = 0.55223880597
Iteration 2 : recall score = 0.616438356164
Iteration 3 : recall score = 0.733333333333
Iteration 4 : recall score = 0.615384615385
Iteration 5 : recall score = 0.575
Mean recall score 0.61847902217
*********************************************************************************
Best model to choose from cross validation is with C parameter = 10.0
*********************************************************************************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()
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) 輸出
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
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_splitcredit_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)過取樣演算法
2、根據樣本不平衡比例設定一個取樣比例以確定取樣倍率N，對於每一個少數類樣本x，從其k近鄰中隨機選擇若干個樣本，假設選擇的近鄰為xn。
3、對於每一個隨機選出的近鄰xn，分別與原樣本按照如下的公式構建新的樣本
xnew=x+rand(0,1)∗|x−xn|
oversampler=SMOTE(random_state=0)
os_features,os_labels=oversampler.fit_sample(features_train,labels_train)len(os_labels[os_labels==1])輸出結果
227454os_features = pd.DataFrame(os_features)
os_labels = pd.DataFrame(os_labels)
best_c = printing_Kfold_scores(os_features,os_labels)輸出結果
-------------------------------------------
C parameter: 0.01
-------------------------------------------
Iteration 1 : recall score = 0.890322580645
Iteration 2 : recall score = 0.894736842105
Iteration 3 : recall score = 0.968861347792
Iteration 4 : recall score = 0.957595541926
Iteration 5 : recall score = 0.958430881173
Mean recall score 0.933989438728
-------------------------------------------
C parameter: 0.1
-------------------------------------------
Iteration 1 : recall score = 0.890322580645
Iteration 2 : recall score = 0.894736842105
Iteration 3 : recall score = 0.970410534469
Iteration 4 : recall score = 0.959980655302
Iteration 5 : recall score = 0.960178498807
Mean recall score 0.935125822266
-------------------------------------------
C parameter: 1
-------------------------------------------
Iteration 1 : recall score = 0.890322580645
Iteration 2 : recall score = 0.894736842105
Iteration 3 : recall score = 0.970454796946
Iteration 4 : recall score = 0.96014552489
Iteration 5 : recall score = 0.960596168431
Mean recall score 0.935251182603
-------------------------------------------
C parameter: 10
-------------------------------------------
Iteration 1 : recall score = 0.890322580645
Iteration 2 : recall score = 0.894736842105
Iteration 3 : recall score = 0.97065397809
Iteration 4 : recall score = 0.960343368396
Iteration 5 : recall score = 0.960530220596
Mean recall score 0.935317397966
-------------------------------------------
C parameter: 100
-------------------------------------------
Iteration 1 : recall score = 0.890322580645
Iteration 2 : recall score = 0.894736842105
Iteration 3 : recall score = 0.970543321899
Iteration 4 : recall score = 0.960211472725
Iteration 5 : recall score = 0.960903924995
Mean recall score 0.935343628474
*********************************************************************************
Best model to choose from cross validation is with C parameter = 100.0
*********************************************************************************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()