[机器学习]机器学习笔记整理06-决策树应用

数据集

训练集

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

测试集

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,youth,medium,no,excellent,yes

　代码

#coding=utf-8
#设置python编码

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

#---数据获取---

#使用CSV包，按行读取CSV数据
allElectronicsData = open(r'./AllElectronics.csv','rb')
reader = csv.reader(allElectronicsData)
#获取各个字段及其名
headers = reader.next()
print("headers : " ,headers)

#---数据预处理---
#sklearn只接受数值型的数据
#以CSV中第一行age数据为例
#age：youth middle_age senior
#矩阵:  1       0        0

#特征值List
featureList = []
#类别List , Yes/No
labelList = []

for row in reader:
    #将每一行的结果放入labelList
    labelList.append(row[len(row)-1])
    #对每一行数据创建一个字典(将每行特征数据转为JSON格式),将headers中的字段与实际值对应 如age:youth
    rowDict = {}
    #i从1开始，取消RID的影响
    for i in range(1,len(row)-1):
        rowDict[headers[i]] = row[i]
    featureList.append(rowDict)

# print labelList
# print featureList

#把featureList向量化
vec = DictVectorizer()
dummyX = vec.fit_transform(featureList).toarray()
print("dummyX : " + str(dummyX))
print ("feature mapping : " + str(vec.get_feature_names()))

#把labelList向量化,使用python自带LabelBinarizer
lb = preprocessing.LabelBinarizer()
dummyY = lb.fit_transform(labelList)
# print("dummyY : " + str(dummyY))

#使用tree分类器创建,使用信息熵 ID3算法
clf = tree.DecisionTreeClassifier(criterion='entropy')
clf = clf.fit(dummyX,dummyY)
print ("clf: " +  str(clf))

#创建dot文件并输出树数据
with open('DTreeData.dot','w') as f:
    f = tree.export_graphviz(clf,feature_names= vec.get_feature_names(),out_file=f)

os.system("dot -Tpdf D:\Data\MyCode\codepython\ML_Base_Demo\DecisionTree\DTreeData.dot -o D:\Data\MyCode\codepython\ML_Base_Demo\DecisionTree\DTree.pdf")

#利用生成的决策树进行预测
# oneRow = dummyX[1,:]
# print ("one row : " + str(oneRow))
#
# newRow = oneRow
# newRow[0] = 1
# newRow[2] = 0
# print("new row x : " + str(newRow))
#
# predictedY = clf.predict(newRow)
#
# print ("predict result : " + str(predictedY))


testSet = open(r'test_set.csv','rb')
reader = csv.reader(testSet)
reader.next()

testList = []

for row in reader:
    #将每一行的结果放入labelList
    labelList.append(row[len(row)-1])
    #对每一行数据创建一个字典(将每行特征数据转为JSON格式),将headers中的字段与实际值对应 如age:youth
    rowDict = {}
    #i从1开始，取消RID的影响
    for i in range(1,len(row)-1):
        rowDict[headers[i]] = row[i]
    testList.append(rowDict)
# print testList

#把testList向量化
vec = DictVectorizer()
testX = vec.fit_transform(testList).toarray()
print("testX : " + str(testX))
predictSet = clf.predict(testX)
print predictSet

运行结果

('headers : ', ['RID', 'age', 'income', 'student', 'credit_rating', 'class_buys_computer']) 

dummyX : [[ 0.  0.  1.  0.  1.  1.  0.  0.  1.  0.] 

 [ 0.  0.  1.  1.  0.  1.  0.  0.  1.  0.] 

 [ 1.  0.  0.  0.  1.  1.  0.  0.  1.  0.] 

 [ 0.  1.  0.  0.  1.  0.  0.  1.  1.  0.] 

 [ 0.  1.  0.  0.  1.  0.  1.  0.  0.  1.] 

 [ 0.  1.  0.  1.  0.  0.  1.  0.  0.  1.] 

 [ 1.  0.  0.  1.  0.  0.  1.  0.  0.  1.] 

 [ 0.  0.  1.  0.  1.  0.  0.  1.  1.  0.] 

 [ 0.  0.  1.  0.  1.  0.  1.  0.  0.  1.] 

 [ 0.  1.  0.  0.  1.  0.  0.  1.  0.  1.] 

 [ 0.  0.  1.  1.  0.  0.  0.  1.  0.  1.] 

 [ 1.  0.  0.  1.  0.  0.  0.  1.  1.  0.] 

 [ 1.  0.  0.  0.  1.  1.  0.  0.  0.  1.] 

 [ 0.  1.  0.  1.  0.  0.  0.  1.  1.  0.]] 

feature mapping : ['age=middle_aged', 'age=senior', 'age=youth', 'credit_rating=excellent', 'credit_rating=fair', 'income=high', 'income=low', 'income=medium', 'student=no', 'student=yes'] 

clf: DecisionTreeClassifier(class_weight=None, criterion='entropy', max_depth=None, 

            max_features=None, max_leaf_nodes=None, 

            min_impurity_split=1e-07, min_samples_leaf=1, 

            min_samples_split=2, min_weight_fraction_leaf=0.0, 

            presort=False, random_state=None, splitter='best') 

Error: Could not open "D:\Data\MyCode\codepython\ML_Base_Demo\DecisionTree\DTree.pdf" for writing : Permission denied 

testX : [[ 0.  0.  1.  0.  1.  1.  0.  0.  1.  0.] 

 [ 0.  0.  1.  1.  0.  1.  0.  0.  1.  0.] 

 [ 1.  0.  0.  0.  1.  1.  0.  0.  1.  0.] 

 [ 0.  1.  0.  0.  1.  0.  0.  1.  1.  0.] 

 [ 0.  1.  0.  0.  1.  0.  1.  0.  0.  1.] 

 [ 0.  1.  0.  1.  0.  0.  1.  0.  0.  1.] 

 [ 1.  0.  0.  1.  0.  0.  1.  0.  0.  1.] 

 [ 0.  0.  1.  0.  1.  0.  0.  1.  1.  0.] 

 [ 0.  0.  1.  0.  1.  0.  1.  0.  0.  1.] 

 [ 0.  1.  0.  0.  1.  0.  0.  1.  0.  1.] 

 [ 0.  0.  1.  1.  0.  0.  0.  1.  0.  1.] 

 [ 1.  0.  0.  1.  0.  0.  0.  1.  1.  0.] 

 [ 0.  0.  1.  1.  0.  0.  0.  1.  1.  0.]] 

[0 0 1 1 1 0 1 0 1 1 1 1 0]