第一个机器学习scikit-learn可视化例子

scikit-learn，又写作sklearn，是一个开源的基于python语言的机器学习工具包。它通过NumPy, SciPy和
Matplotlib等python数值计算的库实现高效的算法应用，并且涵盖了几乎所有主流机器学习算法。
http://scikit-learn.org/stable/index.html

https://sklearn.apachecn.org/

安装必要的包：

pip install numpy pandas matplotlib scikit-learn  graphviz  scipy jupyter

本例在jupyter里运行，直接复制到jupyter里运行即可。

# -*- coding:utf-8 -*-
from sklearn import tree
from sklearn.datasets import load_wine
from sklearn.model_selection import train_test_split

wine = load_wine()
print(wine.data.shape)
print(wine.target)
#如果wine是一张表，应该长这样：
import pandas as pd
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)
print(Xtrain.shape)
print(Xtest.shape)

clf = tree.DecisionTreeClassifier(criterion="entropy")
clf = clf.fit(Xtrain, Ytrain)
score = clf.score(Xtest, Ytest) #返回预测的准确度
print(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']

import graphviz
dot_data = tree.export_graphviz(clf
                               ,feature_names= feature_name
                               ,class_names=["琴酒","雪莉","贝尔摩德"]
                               ,filled=True
                               ,rounded=True
                               )
graph = graphviz.Source(dot_data)
graph #直接在jupyter里显示为图片
graph.render("tree") #同级目录下生成tree.pdf文件

运行结果：

(178, 13)
[0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1
 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1
 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2
 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2]
['alcohol', 'malic_acid', 'ash', 'alcalinity_of_ash', 'magnesium', 'total_phenols', 'flavanoids', 'nonflavanoid_phenols', 'proanthocyanins', 'color_intensity', 'hue', 'od280/od315_of_diluted_wines', 'proline']
['class_0' 'class_1' 'class_2']
(124, 13)
(54, 13)
0.9629629629629629