python实现决策树算法

from sklearn.feature_extraction import DictVectorizer
import csv
from sklearn import tree
from sklearn import preprocessing
from sklearn.externals.six import StringIO

# 读取csv数据，并将数据和特征值存入字典和类标签列表
allElectronicsData = open(r'AllElectronics.csv', 'rt')
reader = csv.reader(allElectronicsData)
headers = next(reader)
# 原代码中用的是：
# headers = reader.next()
# 这句代码应该是之前的版本用的，现在已经更新了没有next这个函数

# 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)


# 将特征值矢量化,代表将各种参数进行矢量化
vec = DictVectorizer()
dummyX = vec.fit_transform(featureList).toarray()

# print("dummyX: " + str(dummyX))
# print(vec.get_feature_names())

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

# 将类标签列表矢量化，就是最后的结果
lb = preprocessing.LabelBinarizer()
dummyY = lb.fit_transform(labelList)
# print("dummyY: " + str(dummyY))

# 使用决策树进行分类
clf = tree.DecisionTreeClassifier()
# clf = tree.DecisionTreeClassifier(criterion = 'entropy')
clf = clf.fit(dummyX, dummyY)
# print("clf: " + str(clf))

# 将模型进行可视化
with open("allElectrionicInformationOri.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))

# 接下来改变一些数据进行预测
newRowX = oneRowX

newRowX[0] = 0
newRowX[1] = 1
print("newRowX: " + str(newRowX))

predictedY = clf.predict(newRowX.reshape(1, -1)) # 预测的结果需要加上后面的reshape(1, -1),不然会
# 报错：
# ValueError: Expected 2D array, got 1D array instead:
# array=[0. 1. 1. 0. 1. 1. 0. 0. 1. 0.].
# Reshape your data either using array.reshape(-1, 1)
# if your data has a single feature or array.reshape(1, -1) if it contains a single sample.
print("预测的