速学sklearn,学完这些先用着

import pandas as pd
import numpy as np
from sklearn import tree
from sklearn import datasets
from sklearn.model_selection import train_test_split
import graphviz

wine = datasets.load_wine()   # 调取sklearn自带数据库中的红酒数据
# print(wine.data)   # 查看wine的数据
# print(wine.target)   # 查看wine的标签
# print(wine.target_names)   # 标签的名字
# print(wine.feature_names)   # 特征的名字
df = pd.concat([pd.DataFrame(wine.data), pd.DataFrame(wine.target)], axis= 1)   # 将两份数据转为dataframe格式并结合在一起
# print(df)

Xtrain, Xtest, Ytrain, Ytest = train_test_split(wine.data, wine.target, test_size= 0.3)   # 将数据分为训练集和测试集，其中测试集占比30%
# print(Xtrain.shape)
clf = tree.DecisionTreeClassifier(criterion= 'entropy')   # 实例化一个决策树
clf = clf.fit(Xtrain, Ytrain)   # 训练决策树
score = clf.score(Xtest, Ytest)   # 测试训练结果
# print(score)

feature_name = ['酒精', '1', '2','酒精', '1', '2','酒精', '1', '2','酒精', '1', '2', '3']   # 特征名称
dot_data = tree.export_graphviz(clf, feature_names= feature_name, class_names= ['qingjiu', 'xueli', 'beiermo'], filled= True, rounded=True)
graph = graphviz.Source(dot_data)
graph.render("tree")   # 同级目录下生成tree.pdf

• Reference
  1. scikit-learn (sklearn) 官方文档中文版
  2. 菜菜的sklearn课堂01 - 决策树
  3. 《数据挖掘导论》
  4. 《机器学习》