python决策树的应用_决策树算法实现应用【基于Python语言实现】

from sklearn.feature_extraction import DictVectorizer

import csv

from sklearn import tree

from sklearn import preprocessing

from sklearn.externals.six import StringIO

# Read in the csv file and put features into list of dict and list of class label

allElectronicsData = open(r'AllElectronics.csv', 'r')

reader = csv.reader(allElectronicsData)

#http://bugs.python.org/msg82661

#http://www.cnblogs.com/feichexia/archive/2012/10/30/2747225.html

#reader.next()改为reader.__next__() ，并且把open中的rb改为r

#https://docs.python.org/3/library/csv.html#csv.csvreader.__next__

headers = reader.__next__()

print(headers)

featureList = []

labelList = []

for row in reader:

labelList.append(row[len(row)-1])

rowDict = {}

for i in range(1, len(row)-1):

rowDict[headers[i]] = row[i]

featureList.append(rowDict)

print(featureList)

# Vetorize features

vec = DictVectorizer()

dummyX = vec.fit_transform(featureList) .toarray()

print("dummyX: " + str(dummyX))

print(vec.get_feature_names())

print("labelList: " + str(labelList))

# vectorize class labels

lb = preprocessing.LabelBinarizer()

dummyY = lb.fit_transform(labelList)

print("dummyY: " + str(dummyY))

# Using decision tree for classification

# clf = tree.DecisionTreeClassifier()

clf = tree.DecisionTreeClassifier(criterion='entropy')

clf = clf.fit(dummyX, dummyY)

print("clf: " + str(clf))

# Visualize model

with open("allElectronicInformationGainOri.dot", 'w') as f:

f = tree.export_graphviz(clf, feature_names=vec.get_feature_names(), out_file=f)

oneRowX = dummyX[0, :]

print("oneRowX: " + str(oneRowX))

newRowX = oneRowX

newRowX[0] = 1

newRowX[2] = 0

print("newRowX: " + str(newRowX))

predictedY = clf.predict(newRowX)

print("predictedY: " + str(predictedY))4.运行截图：【

将上述

代码和数据

放在同一文件夹下，进入该文件夹下运行该文件】