# -*- coding: utf-8 -*-
"""
Created on Sun Sep 26 15:51:26 2021

@author: chenguimei
"""

# 引入数据
From sklearn import datasets
import pandas as pd
import numpy as np

iris = datasets.load_iris()
X = pd.DataFrame(iris.data)
X.columns = iris.feature_names
y = iris.target
PRint("Class labels:",np.unique(y))  #打印分类类别的种类


# 切分训练数据和测试数据
from sklearn.model_selection import train_test_splIT
## 30%测试数据，70%训练数据，stratify=y表示训练数据和测试数据具有相同的类别比例
X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.3,random_state=1,stratify=y)


#决策树模型  
from sklearn.tree import DecisionTreeClassifier
tree = DecisionTreeClassifier(criterion='gini',max_depth=4,random_state=1)
tree.fit(X_train,y_train)
print(X.columns,tree.feature_importances_)

from sklearn.metrics import roc_curve, auc
resu = tree.predict(X_test)
print(resu)
print(y_test)


import eli5
from eli5.sklearn import PErmutationImportance

perm = PermutationImportance(lr, random_state=1).fit(X_test, y_test)
eli5.show_weights(perm, feature_names = X_test.columns.tolist())

from sklearn.inspection._permutation_importance import permutation_importance
from sklearn.datasets import load_iris
from sklearn.metrics import get_scorer
from sklearn.linear_model import LOGisticRegression


permutation_importance(tree, X_test, y_test, get_scorer('accuracy'))