银行分控模型的建立（神经网络算法和决策树模型）

神经网络算法和决策树模型

模型一：神经网络

# -*- coding: utf-8 -*-
"""
Created on Tue Mar 29 17:34:22 2022

@author: LZL
"""

'''神经网络测试'''
import pandas as pd
from tensorflow.keras import Sequential
#from keras.models import Sequential
from tensorflow.keras import layers
from keras.layers.core import Dense, Activation

import numpy as np

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

from keras.metrics import BinaryAccuracy

model = Sequential() # 建立模型
model.add(Dense(input_dim = 8, units = 800))
model.add(Activation('relu'))
model.add(Dense(input_dim = 800, units = 1))
model.add(Activation('sigmoid'))
model.compile(loss = 'binary_crossentropy', optimizer = 'adam', metrics=[BinaryAccuracy()])

model.fit(x_test, y_test, epochs = 100, batch_size = 128)

predict_x=model.predict(x_test)
classes_x=np.argmax(predict_x,axis=1)
yp = classes_x.reshape(len(y_test))
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

cm_plot(y_test,yp).show()# 显示混淆矩阵可视化结果

loss,binary_accuracy = model.evaluate(x_test,y_test,batch_size=128) # 模型评估
print('神经网络模型精度：{}'.format(binary_accuracy))

1.运行结果：

 

 

 

 

2.混淆矩阵：

 

 

 

 

 

 

 

模型二：决策树

# -*- coding: utf-8 -*-
"""
Created on Wed Mar 30 08:13:33 2022

@author: LZL
"""

import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier as DTC


filePath = 'data/bankloan.xls'
data = pd.read_excel(filePath)
x = data.iloc[:,:8]
y = data.iloc[:,8]
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=100)
dtc_clf = DTC(criterion='entropy')#决策树
dtc_clf.fit(x_train,y_train)


from sklearn.metrics import accuracy_score
from sklearn.metrics import roc_auc_score
dtc_yp = dtc_clf.predict(x)
dtc_score = accuracy_score(y, dtc_yp)print('决策树模型精度:{}'.format(dtc_score))


import matplotlib.pyplot as plt 
from sklearn.metrics import confusion_matrix
import seaborn as sns
#绘制混淆矩阵
dtc_cm = confusion_matrix(y, dtc_yp)
heatmap = sns.heatmap(dtc_cm, annot=True, fmt='d')
heatmap.yaxis.set_ticklabels(heatmap.yaxis.get_ticklabels(), rotation=0, ha='right')
heatmap.xaxis.set_ticklabels(heatmap.xaxis.get_ticklabels(), rotation=45, ha='right')
plt.ylabel("true label")
plt.xlabel("predict label")


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

# 数据是类别标签，要将它转换为数据
# 用1来表示“好”“是”“高”这三个属性，用-1来表示“坏”“否”“低”

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("data/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)

graph = pydotplus.graph_from_dot_data(dot_data)
graph.write_png('data/train.png')    #保存图像
Image(graph.create_png())

1.运行结果：

2. 混淆矩阵：

3.决策树分类结果图：

对比结果：

神经网络模型精度为：0.8114285469055176 < 决策树模型精度为：0.9514285714285714，因此银行分控模型的建立更建议用决策树模型