决策树 应用

 

数据：将数据复制到csv文件中，即可使用

RID,age,income,student,credit_rating,class_buys_computer
1,youth,high,no,fair,no
2,youth,high,no,excellent,no
3,middle_aged,high,no,fair,yes
4,senior,medium,no,fair,yes
5,senior,low,yes,fair,yes
6,senior,low,yes,excellent,no
7,middle_aged,low,yes,excellent,yes
8,youth,medium,no,fair,no
9,youth,low,yes,fair,yes
10,senior,medium,yes,fair,yes
11,youth,medium,yes,excellent,yes
12,middle_aged,medium,no,excellent,yes
13,middle_aged,high,yes,fair,yes
14,senior,medium,no,excellent,no

代码：为了方便没有设置测试集，直接使用训练数据预测

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', 'rt')

reader= csv.reader(allElectronicsData)
headers = next(reader)

print(headers)
# print(reader.head(0))
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))

pre = clf.predict_proba(dummyX)[:, 1]
print(pre)