machine_learn/tree/example.py

#!/usr/bin/python
# -*- coding: UTF-8 -*-

from sklearn import tree
from sklearn.datasets import load_wine
from sklearn.model_selection import train_test_split
import numpy
import graphviz

wine = load_wine()
print(wine.data.shape) #178*13
print(wine.target)
#如果wine是一张表，应该长这样：
import pandas as pd
pdata = pd.concat([pd.DataFrame(wine.data),pd.DataFrame(wine.target)],axis=1)

print(wine.feature_names)
print(wine.target_names)

Xtrain, Xtest, Ytrain, Ytest = train_test_split(wine.data,wine.target,test_size=0.3)
numpy.savetxt("foo.csv", Xtrain, delimiter=",")

clf = tree.DecisionTreeClassifier(criterion="entropy", max_features=1, max_depth=1)#实例化，criterion不写的话默认是基尼系数
# clf.n_features_ = 2
clf = clf.fit(Xtrain, Ytrain)
score = clf.score(Xtest, Ytest) #返回预测的准确度
print("score:", score)

feature_name = ['酒精', '苹果酸', '灰', '灰的碱性', '镁', '总酚', '类黄酮',
                '非黄烷类酚类', '花青素', '颜色强度', '色调', 'od280/od315稀释葡萄酒', '脯氨酸']


dot_data = tree.export_graphviz(clf
                                # ,out_file = None
                                , feature_names=feature_name
                                , class_names=["琴酒", "雪莉", "贝尔摩德"]
                                , filled=True  # 让树的每一块有颜色，颜色越浅，表示不纯度越高
                                , rounded=True  # 树的块的形状
                                )
dot_data = dot_data.replace('helvetica', '"Microsoft YaHei"')
graph = graphviz.Source(dot_data)
graph.render("Tree1")
graph  # graph.view()