银行风控模型

一、决策树

代码如下:

# -*- coding: utf-8 -*-
"""
Created on Sun Mar 27 00:01:20 2022

@author: dd
"""

import pandas as pd
# 参数初始化
filename ='D:/ISS/anaconda/bankloan.xls'
data = pd.read_excel(filename)  # 导入数据

x = data.iloc[:,:8].astype(int)
y = data.iloc[:,8].astype(int)

from sklearn.tree import DecisionTreeClassifier as DTC
dtc = DTC(criterion='entropy')  # 建立决策树模型,基于信息熵
dtc.fit(x, y)  # 训练模型

# 导入相关函数,可视化决策树。
# 导出的结果是一个dot文件,需要安装Graphviz才能将它转换为pdf或png等格式。
from sklearn.tree import export_graphviz
x = pd.DataFrame(x)

"""
string1 = '''
edge [fontname="NSimSun"];
node [ fontname="NSimSun" size="15,15"];
{
''' 
string2 = '}'
"""
 
with open("tree.dot", 'w') as f:
    export_graphviz(dtc, feature_names = x.columns, out_file = f)
    f.close()

from IPython.display import Image  
from sklearn import tree
import pydotplus 

dot_data = tree.export_graphviz(dtc, out_file=None,  #regr_1 是对应分类器
                         feature_names=data.columns[:8],   #对应特征的名字
                         class_names=data.columns[8],    #对应类别的名字
                         filled=True, rounded=True,  
                         special_characters=True)  
 
dot_data = dot_data.replace('helvetica 14', 'MicrosoftYaHei 14') #修改字体
graph = pydotplus.graph_from_dot_data(dot_data)  
graph.write_png('D:/ISS/anaconda/tmp/banktree.png')    #保存图像
Image(graph.create_png())

import matplotlib.pyplot as plt
img = plt.imread('D:/ISS/anaconda/tmp/banktree.png')
fig = plt.figure('show picture')
plt.imshow(img)

结果如下:

 

 

 

 

二、神经网络

代码如下:

# -*- coding: utf-8 -*-
"""
Created on Sun Mar 27 00:04:18 2022

@author: dd
"""

import pandas as pd
from tensorflow.python.keras.models import Sequential
from tensorflow.python.keras.layers.core import Dense, Activation


# 参数初始化
inputfile = 'D:/ISS/anaconda/bankloan.xls'
data = pd.read_excel(inputfile)
x_test = data.iloc[:,:8].values
y_test = data.iloc[:,8].values

model = Sequential()  # 建立模型
model.add(Dense(input_dim = 8, units = 8))
model.add(Activation('relu'))  # 用relu函数作为激活函数,能够大幅提供准确度
model.add(Dense(input_dim = 8, units = 1))
model.add(Activation('sigmoid'))  # 由于是0-1输出,用sigmoid函数作为激活函数

model.compile(loss = 'mean_squared_error', optimizer = 'adam')
# 编译模型。由于我们做的是二元分类,所以我们指定损失函数为binary_crossentropy,以及模式为binary
# 另外常见的损失函数还有mean_squared_error、categorical_crossentropy等,请阅读帮助文件。
# 求解方法我们指定用adam,还有sgd、rmsprop等可选

model.fit(x_test, y_test, epochs = 1000, batch_size = 10)  # 训练模型,学习一千次
import numpy as np
predict_x=model.predict(x_test) 
classes_x=np.argmax(predict_x,axis=1)
yp = classes_x.reshape(len(y_test))

score = model.evaluate(x_test, y_test, batch_size=128)  #分类预测精确度
print(score)

from cm_plot import *  # 导入自行编写的混淆矩阵可视化函数
cm_plot(y_test,yp).show()

其中,绘制混淆矩阵的函数cm_plot.py具体代码如下:

#-*- coding: utf-8 -*-
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

结果如下:

 混淆矩阵如下:

 

posted @ 2022-03-27 13:52  邓若言  阅读(337)  评论(0编辑  收藏  举报