python_机器学习_监督学习模型_决策树

# -*- coding:utf-8 -*-
from sklearn.feature_extraction import DictVectorizer
import csv
from sklearn import preprocessing
from sklearn import tree  # 要求是数值型的值
from sklearn.externals.six import StringIO


"""
注意： 决策树要求要数值型的值，不能是字符串类型的值
例如： no， yes这样的值是不允许的
需要转换成矩阵
====================================
age            income    student
youth        high    no
youth        high    no
middle_aged    high    no
senior        medium    no
senior        low    yes
====================================

比如上面这种数据：
youth    middle_aged        senior         high    medium    low    ......
1        0                0            1        0        0
1        0                0            1        0        0
.....

"""


allElectronicsData = open(r"C:\Users\Administrator\Desktop\data.xlsx", ‘r‘)
reader = csv.reader(allElectronicsData)
print(reader)
headers = next(reader)

print(headers)
# ["RID", ‘age‘.....]

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)
# [
#    {"credit_rating": "fair", "age": "youth"},
#    .... #作用，方便转换成矩阵。将数据转换成对象
# ]

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

print("dummyX:" + str(dummyX))  # 转换成矩阵的数据了二维
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))

# 存储决策树信息

# Graphviz 将dot转换成pdf的命令： dot -T pdf iris.dot -o output.pdf
# 可以查看decision tree 的形状了（看pdf的值）
with open(r"C:\Users\Administrator\Desktop\code\mechine_learning\allElectronicInformationGainOri.dot", "w") as f:
    f = tree.export_graphviz(clf, feature_names = vec.get_feature_names(), out_file = f)


# 下面的代码属于预测的代码
# 属于转化后的矩阵数值，其实就是进行复制修改
oneRowX = dummyX[0, :]
print("oneRowX: " + str(oneRowX))

newRowX = oneRowX

newRowX[0] = 1
newRowX[2] = 0
print("newRowX: ", str(newRowX))

predictedY = clf.predicted(newRowX)
# 预测 class_buys_labels的值
predicted("predictedY: " + str(predictedY))




if __name__ == ‘__main__‘:
    main()