1.数据集下载 :链接: https://pan.baidu.com/s/1zUxSxwiProvfmAAWjyYb4w 密码: 6eai
代码下载 :链接: https://pan.baidu.com/s/1KyVOEU3p-sfCQIauCXGWIA 密码: tgrh
2.代码的实现:
#添加声明 import tensorflow as tf import numpy as np import pandas as pd import matplotlib.pyplot as plt
#读数据并显示前五行 data = pd.read_csv('creditcard.csv') data.head()
#假设 class=0表示正常 class=1表示异常 用柱状图显示出样本的分布 count_classes = pd.value_counts(data['Class'], sort = True).sort_index() count_classes.plot(kind = 'bar') plt.title('Fraud class histofram') plt.xlabel('Class') plt.ylabel('Frequence') plt.show()
from sklearn.preprocessing import StandardScaler #里面的数据进行操作对Amount的数值进行操作得到normAmount 删除Amount和Time列。由于Amount的数值比较大,对其标准化操作一下。 #reshape中的-1表示 我的数据是1列 多少行你程序自己看着办。 data['normAmount'] = StandardScaler().fit_transform(data['Amount'].reshape(-1,1)) data = data.drop(['Time','Amount'],axis=1) data.head()
#下采样,0和1的样本数据数量一样少 #本数据集中class=1的样本很少,我们取0的样本数和1的样本数一样多。 组成一个下采样集。
X = data.ix[:,data.columns !='Class'] #除了Class列的值 所有列的值都输入进去 y= data.ix[:,data.columns =='Class'] print(len(y)) print(len(X)) number_records_fraud = len(data[data.Class==1]) #取calss=1的数量 fraud_indices = np.array(data[data.Class==1].index) #将class=1的索引存储到fraud_indices normal_indices = data[data.Class==0].index #索引随机选择 random_normal_indices = np.random.choice(normal_indices, number_records_fraud,replace = False) random_normal_indices =np.array(random_normal_indices) #将两个样本结合在一起 under_sample_indices = np.concatenate([fraud_indices,random_normal_indices]) under_sample_data = data.iloc[under_sample_indices,:] #下采样数据集中 X_undersample 和y_undersample标签 X_undersample = under_sample_data.ix[:,under_sample_data.columns!='Class'] y_undersample = under_sample_data.ix[:,under_sample_data.columns=='Class'] print(len(under_sample_data[under_sample_data.Class==1])/len(under_sample_data),len(under_sample_data[under_sample_data.Class==1])) print(len(under_sample_data[under_sample_data.Class==0])/len(under_sample_data),len(under_sample_data[under_sample_data.Class==0])) print(len(under_sample_data))
#交叉验证 数据切分成训练集和测试集 假设训练集平均分三份 1,2训练 3来验证 | 1,3训练 2验证 | 2,3训练 1验证 from sklearn.cross_validation import train_test_split #所有数据集切分 7成的训练 3成的测试 X_train,X_test,y_train,y_test = train_test_split(X,y,test_size = 0.3, random_state = 0) print(len(X_train)) print(len(X_test)) print(len(y_train)) print(len(y_test)) #y_undersample 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,y_undersample,test_size = 0.3, random_state = 0) print(len(X_train_undersample)) print(len(X_test_undersample)) print(len(y_train_undersample)) print(len(y_test_undersample))
#模型建立 #recall召回率 作为模型评估标准 Recall = TP/(FP+TP) from sklearn.linear_model import LogisticRegression from sklearn.cross_validation import KFold,cross_val_score #KFold 几倍的交叉验证 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) #将训练集分成5分 交叉验证 # 惩罚项的惩罚力度 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): # L1正则惩罚 + 惩罚发力度 lr = LogisticRegression(C = c_param, penalty = 'l1') #用训练数据中的训练数据去 训练模型。 lr.fit(x_train_data.iloc[indices[0],:],y_train_data.iloc[indices[0],:].values.ravel()) # 用训练数据里面的 验证数据来验证 y_pred_undersample = lr.predict(x_train_data.iloc[indices[1],:].values) # 计算召回率 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) # 求平均召回率 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.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
best_c = printing_Kfold_scores(X_train_undersample,y_train_undersample) #用下采样样本训练模型
#混淆矩阵的生成。 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 #用测试数据上面跑的结果。 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()
#图中可以看出来 召唤率为 136/(136+11) = 0.92517召唤率比较高 但是存在很高的误杀率:7263个样本。 # 采用L1正则惩罚 C表示惩罚的力度 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 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) #用所有数据训练模型
#误杀率比较低只有 12的样本误杀,但是 召唤率低。 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()
#采用不同的阈值 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) #设置不同的阈值的测试结果 thresholds = [0.1,0.2,0.3,0.4,0.5,0.6,0.7,0.8,0.9] plt.figure(figsize=(10,10)) #当阈值为0.5和0.6的时候整体结果是比较好的。当阈值为0.1,0.2,0.3的时候召唤率是100%但是误杀率也是100% 当阈值是0.8,0.9的时候召唤率低但是误杀率也低。 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) plt.show()
#增加负样本数量 像本次的测试数据一样 负样本太少,导致训练的不是很理想。我们要自动生成一些负样本。 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 #读取样本数据 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) #用SMOTE生成负样本,数量和正样本差不多。 oversampler=SMOTE(random_state=0) os_features,os_labels=oversampler.fit_sample(features_train,labels_train) #生成的负样本的数量 len(os_labels[os_labels==1])
#生成负样本之后在进行训练。 得到的结果比之前要好很多 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()