银行风控模型的建立

Q：银行分控模型的建立。包括训练的结果，训练的误差，画出混淆矩阵，不少于两种方法

1.逻辑回归

import pandas as pd
import numpy as np
# 参数初始化
inputfile = '../data/bankloan.xls'
data = pd.read_excel(inputfile)
X = data.drop(columns='违约')
y = data['违约']
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=1)

model = LogisticRegression()
model.fit(X_train, y_train)
y_pred = model.predict(X_test)
from sklearn.metrics import accuracy_score
score = accuracy_score(y_pred, y_test)
print(score)


#混淆矩阵
def cm_plot(y, y_pred):
  from sklearn.metrics import confusion_matrix #导入混淆矩阵函数
  cm = confusion_matrix(y, y_pred) #混淆矩阵
  import matplotlib.pyplot as plt #导入作图库
  plt.matshow(cm, cmap=plt.cm.Greens) #画混淆矩阵图，配色风格使用cm.Greens，更多风格请参考官网。
  plt.colorbar() #颜色标签
  for x in range(len(cm)): #数据标签
    for y in range(len(cm)):
      plt.annotate(cm[x,y], xy=(x, y), horizontalalignment='center', verticalalignment='center')
  plt.ylabel('True label') #坐标轴标签
  plt.xlabel('Predicted label') #坐标轴标签
  return plt
cm_plot(y_test, y_pred)

2神经网络

# -*- coding: utf-8 -*-
"""
Created on Sun Mar 27 19:10:46 2022

@author: 123
"""
import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
inputfile = './bankloan.xls'
data = pd.read_excel(inputfile)
X = data.drop(columns='违约')
y = data['违约']

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=1)
from keras.models import Sequential
from keras.layers.core import Dense, Activation
from keras.layers import  Activation, Dense, Dropout

model = Sequential()
model.add(Dense(64,input_dim=8,activation='relu'))  #8个特征维度
# Drop防止过拟合的数据处理方式
model.add(Dropout(0.5))
model.add(Dense(64,activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(1,activation='sigmoid'))
 
# 编译模型，定义损失函数，优化函数，绩效评估函数
model.compile(loss='binary_crossentropy',
              optimizer='rmsprop',
              metrics=['accuracy'])     #二元分类，所以指定损失函数为binary_crossentropy
 
# 导入数据进行训练
model.fit(X_train,y_train,epochs=200,batch_size=128)   
#yp = model.predict_classes(X_test).reshape(len(y_test))  # 分类预测
#print(yp)
predict_x=model.predict(X_test) 
classes_x=np.argmax(predict_x,axis=1)

score  = model.evaluate(X_test,y_test,batch_size=128)
print(score)
def cm_plot(y, y_pred):
  from sklearn.metrics import confusion_matrix #导入混淆矩阵函数
  cm = confusion_matrix(y, y_pred) #混淆矩阵
  import matplotlib.pyplot as plt #导入作图库
  plt.matshow(cm, cmap=plt.cm.Greens) #画混淆矩阵图，配色风格使用cm.Greens，更多风格请参考官网。
  plt.colorbar() #颜色标签
  for x in range(len(cm)): #数据标签
    for y in range(len(cm)):
      plt.annotate(cm[x,y], xy=(x, y), horizontalalignment='center', verticalalignment='center')
  plt.ylabel('True label') #坐标轴标签
  plt.xlabel('Predicted label') #坐标轴标签
  return plt

cm_plot(y_test,classes_x)