交易数据异常检测

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)
    
    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'])
    
    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.split(x_train_data)): #交叉验证
            #建立罗辑回归模型
            lr = LogisticRegression(C = c_param, penalty='l1')
            
            lr.fit(x_train_data.iloc[indices[0],:],y_train_data.iloc[indices[0],:].values.ravel())
            
            y_pred_undersample = lr.predict(x_train_data.iloc[indices[1],:].values)
            
            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)
            
        results_table.loc[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('float64').idxmax()]['C_parameter']
    print('*****************************************')
    print('Best model to choose from cross validation is with C Paramter =', best_c)
    print('*****************************************')
    
    return best_c
best_c = printing_Kfold_scores(X_train_undersample,y_train_undersample)