#!/usr/bin/env python #-*-coding:utf-8-*- #決策樹的建立，訓練測試， from sklearn.feature_extraction import DictVectorizer import csv from sklearn import preprocessing from sklearn import tree from sklearn.externals.six import StringIO#讀數據 allElectronicsData=open(r'jueceshu.csv','rb') reader=csv.reader(allElectronicsData) headers=reader.next()featureList=[] labelList=[] #分析數據 for row in reader:#print(row)if(row):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) #轉化數據 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(dummyX))#訓練數據 clf=tree.DecisionTreeClassifier(criterion='entropy') clf=clf.fit(dummyX,dummyY) print('clf'+str(clf)) #轉化為dot模式 with open('allElectronicInformationGainDri.dot','w') as f:f=tree.export_graphviz(clf,feature_names=vec.get_feature_names(),out_file=f)#決策樹的預測 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))

student=no <= 0.5

entropy = 0.9403
samples = 14
value = [5, 9]
True
entropy = 0.0
samples = 5
value = [0, 5]
False
age=senior <= 0.5
entropy = 0.5436
samples = 8
value = [1, 7] age=youth <= 0.5
entropy = 0.9183
samples = 6
value = [4, 2]
credit_rating=excellent <= 0.5
entropy = 0.9183
samples = 3
value = [1, 2] credit_rating=excellent <= 0.5
entropy = 0.9183
samples = 3
value = [1, 2]
entropy = 0.0
samples = 2
value = [0, 2]
entropy = 0.0
samples = 1
value = [1, 0]
entropy = 0.0
samples = 2
value = [0, 2]
entropy = 0.0
samples = 3
value = [3, 0]
entropy = 0.0
samples = 1

value = [1, 0]

1. Python

2. ?Python機器學習的庫：scikit-learn
2.1： 特性： 簡單高效的數據挖掘和機器學習分析 對所有用戶開放，根據不同需求高度可重用性 基于Numpy, SciPy和matplotlib 開源，商用級別：獲得 BSD許可

2.2 覆蓋問題領域： 分類（classification), 回歸（regression), 聚類（clustering), 降維(dimensionality reduction) 模型選擇(model selection), 預處理(preprocessing)

3. 使用用scikit-learn 安裝scikit-learn: pip, easy_install, windows installer 安裝必要package：numpy， SciPy和matplotlib， 可使用Anaconda (包含numpy, scipy等科學計算常用 package） ? ? ?安裝注意問題：Python解釋器版本（2.7 or 3.4？）, 32-bit or 64-bit系統
4. 例子：

文檔： http://scikit-learn.org/stable/modules/tree.html
解釋Python代碼

安裝?Graphviz：?http://www.graphviz.org/ 配置環境變量
? ? ? 轉化dot文件至pdf可視化決策樹：dot -Tpdf iris.dot -o outpu.pdf

數據集：

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,yes,excellent,yes
13,middle_aged,high,yes,fair,yes
14,senior,medium,no,excellent,no

結果：

結果解釋：

?字典代表每一行，每個測試樣例，每個測試集

dummyX代表格式的轉換

? ? ? ? labelList代表結果集

dummyY代表結果集的格式化

clfDecisionTreeClassifier代表決策樹分類器

oneRowX代表其中一個測試集

? ? ? ? newRowX代表一個新的測試集

? ? ? ? predictedY代表預測的結果

? ? ?

? ??

? ? ??

總結

以上是生活随笔為你收集整理的机器学习——决策树的实现的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。