銀行數據風險預測

風險預測-決策樹

主要是使用決策樹進行預測，並且根據樹畫圖顯示
使用Graphviz 畫圖
1.通過官網下載安裝graphviz;
2.進行模型訓練；

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

import pandas as pd
import numpy as np
import pydotplus
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import train_test_split
from sklearn import tree
from sklearn.externals.six import StringIO

path = 'data.csv'
df = pd.read_csv(path, encoding='gbk')
list1 = ['age', 'education', 'career', 'loaction year', 'salary', '債務佔收入比例', '信用卡負債', '其他負債']
X = df[list1]
Y = df['還款情況']

X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.2, random_state=42)

clf = DecisionTreeClassifier()

clf.fit(X_train, Y_train)

Y_pred = clf.predict(X_test)

print('train score:', clf.score(X_train, Y_train))  #訓練集準確率
print('test score:', clf.score(X_test, Y_test))  #測試集準確率
print('parameters:', clf.get_params())  #主要參數
print('parameters importance:', clf.feature_importances_) #特徵重要性

dot_data = StringIO()
tree.export_graphviz(clf, out_file=dot_data)
graph = pydotplus.graph_from_dot_data(dot_data.getvalue())

with open('features.dot', 'w') as f:
    f = tree.export_graphviz(clf, out_file=f)

3.在文件中會生成max_features3.dot文件，打開graphviz包中的
gvedit.exe讀取.dot。