银行风控模型

            0                   1
0 随机森林得分 0.948571
1 支持向量机得分 0.775714
2 决策树得分 0.945714
3 K邻近得分 0.812857

4 神经网络得分 98.85713958740234

 

import pandas as pd
import time
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier as DTC
from sklearn.ensemble import RandomForestClassifier as RFC
from sklearn import svm
from sklearn import tree
from sklearn.metrics import confusion_matrix
from sklearn.metrics import accuracy_score
#from sklearn.metrics import roc_curve, auc
from sklearn.neighbors import KNeighborsClassifier as KNN
#导入plot_roc_curve,roc_curve和roc_auc_score模块
from sklearn.metrics import plot_roc_curve,roc_curve,auc,roc_auc_score
filePath = r'F:\python\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)

#模型
svm_clf = svm.SVC()#支持向量机
dtc_clf = DTC(criterion='entropy')#决策树
rfc_clf = RFC(n_estimators=10)#随机森林
knn_clf = KNN()#K邻近

#训练
knn_clf.fit(x_train,y_train)
rfc_clf.fit(x_train,y_train)
dtc_clf.fit(x_train,y_train)
svm_clf.fit(x_train, y_train)

#ROC曲线比较
fig,ax = plt.subplots(figsize=(12,10))
rfc_roc = plot_roc_curve(estimator=rfc_clf, X=x,
y=y, ax=ax, linewidth=1)
svm_roc = plot_roc_curve(estimator=svm_clf, X=x,
y=y, ax=ax, linewidth=1)
dtc_roc = plot_roc_curve(estimator=dtc_clf, X=x,
y=y, ax=ax, linewidth=1)
knn_roc = plot_roc_curve(estimator=knn_clf, X=x,
y=y, ax=ax, linewidth=1)
ax.legend(fontsize=12)
plt.show()

#模型评价
rfc_yp = rfc_clf.predict(x)
rfc_score = accuracy_score(y, rfc_yp)
svm_yp = svm_clf.predict(x)
svm_score = accuracy_score(y, svm_yp)
dtc_yp = dtc_clf.predict(x)
dtc_score = accuracy_score(y, dtc_yp)
knn_yp = knn_clf.predict(x)
knn_score = accuracy_score(y, knn_yp)
score = {"随机森林得分":rfc_score,"支持向量机得分":svm_score,"决策树得分":dtc_score,"K邻近得分":knn_score}
score = sorted(score.items(),key = lambda score:score[0],reverse=True)
print(pd.DataFrame(score))

#中文标签、负号正常显示
plt.rcParams['font.sans-serif'] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False

#绘制混淆矩阵
figure = plt.subplots(figsize=(12,10))
plt.subplot(2,2,1)
plt.title('随机森林')
rfc_cm = confusion_matrix(y, rfc_yp)
heatmap = sns.heatmap(rfc_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")

plt.subplot(2,2,2)
plt.title('支持向量机')
svm_cm = confusion_matrix(y, svm_yp)
heatmap = sns.heatmap(svm_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")

plt.subplot(2,2,3)
plt.title('决策树')
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")

plt.subplot(2,2,4)
plt.title('K邻近')
knn_cm = confusion_matrix(y, knn_yp)
heatmap = sns.heatmap(knn_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")
plt.show()

#画出决策树
import pandas as pd
import os
os.environ["PATH"] += os.pathsep + r'F:\Graphviz\bin'
from sklearn.tree import export_graphviz
x = pd.DataFrame(x)

with open(r"F:\python\data\tree.dot", 'w') as f:
export_graphviz(dtc_clf, 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_clf, out_file=None, #regr_1 是对应分类器
feature_names=x.columns, #对应特征的名字
class_names= ['不违约','违约'], #对应类别的名字
filled=True, rounded=True,
special_characters=True)

#让graphviz显示中文用"MicrosoftYaHei"代替'helvetica'
graph = pydotplus.graph_from_dot_data(dot_data.replace('helvetica',"MicrosoftYaHei"))
#graph.write_png('F:\python\data\banklodan_tree.png') #保存图像
plt.show(Image(graph.create_png()))

 

# -*- coding: utf-8 -*-
'''神经网络测试'''
import pandas as pd
from keras.models import Sequential
from keras.layers.core import Dense, Activation

# 参数初始化

filePath = r'F:\python\data\bankloan.xls'
data = pd.read_excel(filePath)

x_test = data.iloc[:,:2].values
y_test = data.iloc[:,2].values

model = Sequential() # 建立模型
model.add(Dense(input_dim = 2, units = 10))
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 = 10, 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 = 100, batch_size = 10) # 训练模型，学习一千次

score = model.evaluate(x_test,y_test,batch_size=128) # 模型评估
print(score)