基于数据挖掘算法建立银行风控模型

Bp神经网络:
import pandas as pd
import numpy as np
#导入划分数据集函数
from sklearn.model_selection import train_test_split
#读取数据
datafile = './data/bankloan.xls'#文件路径
data = pd.read_excel(datafile)
x = data.iloc[:,:8]
y = data.iloc[:,8]
#划分数据集
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=100)
#导入模型和函数
from keras.models import Sequential
from keras.layers import Dense,Dropout
#导入指标
from keras.metrics import BinaryAccuracy
#导入时间库计时
import time
start_time = time.time()
#-------------------------------------------------------#
model = Sequential()
model.add(Dense(input_dim=8,units=800,activation='relu'))#激活函数relu
model.add(Dropout(0.5))#防止过拟合的掉落函数
model.add(Dense(input_dim=800,units=400,activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(input_dim=400,units=1,activation='sigmoid'))
 
model.compile(loss='binary_crossentropy', optimizer='adam',metrics=[BinaryAccuracy()])
model.fit(x_train,y_train,epochs=100,batch_size=128)
loss,binary_accuracy = model.evaluate(x,y,batch_size=128)
#--------------------------------------------------------#
end_time = time.time()
run_time = end_time-start_time#运行时间
 
print('模型运行时间：{}'.format(run_time))
print('模型损失值：{}'.format(loss))
print('模型精度：{}'.format(binary_accuracy))
 
yp = model.predict(x).reshape(len(y))
yp = np.around(yp,0).astype(int) #转换为整型
from cm_plot import *  # 导入自行编写的混淆矩阵可视化函数
cm_plot(y,yp).show()  # 显示混淆矩阵可视化结果 

混淆矩阵可视化

def cm_plot(y, yp):
  
  from sklearn.metrics import confusion_matrix #

  cm = confusion_matrix(y, yp) 
  
  import matplotlib.pyplot as plt
  plt.matshow(cm, cmap=plt.cm.Greens) 
  plt.colorbar() 
  
  for x in range(len(cm)): 
    for y in range(len(cm)):
      plt.annotate(cm[x,y], xy=(x, y), horizontalalignment='center', verticalalignment='center')
  
  plt.ylabel('True label') 
  plt.xlabel('Predicted label') 
  return plt

截图

标签：plt,cm,yp,风控,算法,time,数据挖掘,import,model
来源： https://www.cnblogs.com/Mrlee28/p/16074619.html