Decision Trees：机器学习根据大量数据,已知年龄、收入、是否上海人、私家车价格的人，预测Ta是否有真实购买上海黄浦区楼房的能力—Jason niu

from sklearn.feature_extraction import DictVectorizer

import csv

from sklearn import tree

from sklearn import preprocessing

from sklearn.externals.six import StringIO

allElectronicsData = open(r'F:/AI/DL_month1201/01DTree/niu.csv', 'rt')

reader = csv.reader(allElectronicsData)

headers = next(reader)

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)

vec = DictVectorizer()

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

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

print(vec.get_feature_names())

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

lb = preprocessing.LabelBinarizer()

dummyY = lb.fit_transform(labelList)

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

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

clf = clf.fit(dummyX, dummyY)

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

with open("niu.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))