使用sklearn包构建二元决策树预测红酒口感

# -*- coding:utf-8 -*-
import urllib.request
import numpy
from sklearn import tree
from sklearn.tree import DecisionTreeRegressor
from sklearn.externals.six import StringIO
from math import sqrt
import matplotlib.pyplot as plot

#从网页中读取数据
url="http://archive.ics.uci.edu/ml/machine-learning-databases/wine-quality/winequality-red.csv"
data=urllib.request.urlopen(url)

#将数据中第一行的属性读取出来放在names列表中，将其他行的数组读入row中，并将row中最后一列提取
#出来放在labels中作为标签，并使用pop将该列从row去去除掉，最后将剩下的属性值转化为float类型存入xList中
xlist=[]
labels=[]
names=[]
firstline=True
for line in data:
if firstline:
names=line.strip().split(b';')
firstline=False
else:
row=line.strip().split(b';')
labels.append(float(row[-1]))
row.pop()
floatrow=[float(num) for num in row]
xlist.append(floatrow)

#统计行列数目
nrows=len(xlist)
ncols=len(xlist[1])

#使用sklearn学习
winetree=DecisionTreeRegressor(max_depth=4)
winetree.fit(xlist,labels)

#输出训练完成的决策树进winetree.dot文件
with open("winetree2.dot",'w') as f:
f=tree.export_graphviz(winetree,out_file=f)