#?-*-?coding:?utf-8?-*-
“““
Created?on?Thu?Jul?26?09:22:46?2018

@author:?wzy
“““
import?numpy?as?np
import?matplotlib.pyplot?as?plt

“““
函數(shù)說明：創(chuàng)建單層決策樹的數(shù)據(jù)集

Parameters:
????None
????
Returns:
????dataMat?-?數(shù)據(jù)矩陣
????classLabels?-?數(shù)據(jù)標(biāo)簽

Modify:
????2018-07-26
“““
def?loadsimpData（）:
????datMat?=?np.matrix（[[1.??2.1]
????????????????????????[1.5?1.6]
????????????????????????[1.3?1.?]
????????????????????????[1.??1.?]
????????????????????????[2.??1.?]]）
????classLabels?=?[1.0?1.0?-1.0?-1.0?1.0]
????return?datMat?classLabels


“““
函數(shù)說明：單層決策樹分類函數(shù)

Parameters:
????dataMatrix?-?數(shù)據(jù)矩陣
????dimen?-?第dimen列，也就是第幾個特征
????threshVal?-?閾值
????threshIneq?-?標(biāo)志
????
Returns:
????retArray?-?分類結(jié)果

Modify:
????2018-07-26
“““
def?stumpClassify（dataMatrix?dimen?threshVal?threshIneq）:
????#?初始化retArray為全1列向量
????retArray?=?np.ones（（np.shape（dataMatrix）[0]?1））
????if?threshIneq?==?‘lt‘:
????????#?如果小于閾值則賦值為-1
????????retArray[dataMatrix[:?dimen]?<=?threshVal]?=?-1.0
????else:
????????#?如果大于閾值則賦值為-1
????????retArray[dataMatrix[:?dimen]?>?threshVal]?=?-1.0
????return?retArray


“““
函數(shù)說明：找到數(shù)據(jù)集上最佳的單層決策樹

Parameters:
????dataArr?-?數(shù)據(jù)矩陣
????classLabels?-?數(shù)據(jù)標(biāo)簽
????D?-?樣本權(quán)重每個樣本權(quán)重相等?1/n
????
Returns:
????bestStump?-?最佳單層決策樹信息
????minError?-?最小誤差
????bestClassEst?-?最佳的分類結(jié)果

Modify:
????2018-07-26
“““
def?buildStump（dataArr?classLabels?D）:
????#?輸入數(shù)據(jù)轉(zhuǎn)為矩陣（5?2）
????dataMatrix?=?np.mat（dataArr）
????#?將標(biāo)簽矩陣進(jìn)行轉(zhuǎn)置（5?1）
????labelMat?=?np.mat（classLabels）.T
????#?m=5?n=2
????m?n?=?np.shape（dataMatrix）
????numSteps?=?10.0
????bestStump?=?{}
????#?（5?1）全零列矩陣
????bestClasEst?=?np.mat（np.zeros（（m?1）））
????#?最小誤差初始化為正無窮大inf
????minError?=?float（‘inf‘）
????#?遍歷所有特征
????for?i?in?range（n）:
????????#?找到（每列）特征中的最小值和最大值
????????rangeMin?=?dataMatrix[:?i].min（）
????????rangeMax?=?dataMatrix[:?i].max（）
????????#?計算步長
????????stepSize?=?（rangeMax?-?rangeMin）?/?numSteps
????????for?j?in?range（-1?int（numSteps）?+?1）:
????????????#?大于和小于的情況均遍歷，lt:Less?than??gt:greater?than
????????????for?inequal?in?[‘lt‘?‘gt‘]:
????????????????#?計算閾值
????????????????threshVal?=?（rangeMin?+?float（j）?*?stepSize）
????????????????#?計算分類結(jié)果
????????????????predictedVals?=?stumpClassify（dataMatrix?i?threshVal?inequal）
????????????????#?初始化誤差矩陣
????????????????errArr?=?np.mat（np.ones（（m?1）））
????????????????#?分類正確的，賦值為0
????????????????errArr[predictedVals?==?labelMat]?=?0
????????????????#?計算誤差
????????????????weightedError?=?D.T?*?errArr
????????????????print（“split:?dim?%d?thresh?%.2f?thresh?ineqal:?%s?the?weighted?error?is?%.3f“?%?（i?threshVal?inequal?weightedError））
????????????????#?找到誤差最小的分類方式
????????????????if?weightedError?????????????????????minError?=?weightedError
????????????????????bestClasEst?=?predictedVals.copy（）
????????????????????bestStump[‘dim‘]?=?i
????????????????????bestStump[‘thresh‘]?=?threshVal
????????????????????bestStump[‘ineq‘]?=?inequa

?屬性????????????大小?????日期????時間???名稱
-----------?---------??----------?-----??----
?????目錄???????????0??2018-12-17?08:25??MachineLearning\
?????目錄???????????0??2018-07-26?09:23??MachineLearning\AdaBoost_Project1\
?????文件????????7450??2018-07-26?20:57??MachineLearning\AdaBoost_Project1\AdaBoost.py
?????目錄???????????0??2018-12-17?08:23??MachineLearning\AdaBoost_Project2\
?????文件????????7109??2018-07-26?21:51??MachineLearning\AdaBoost_Project2\AdaBoost.py
?????文件???????13547??2018-06-24?16:10??MachineLearning\AdaBoost_Project2\horseColicTest2.txt
?????文件???????60479??2018-06-24?16:10??MachineLearning\AdaBoost_Project2\horseColicTraining2.txt
?????目錄???????????0??2018-12-17?08:23??MachineLearning\AdaBoost_Project3\
?????文件????????1729??2018-07-27?15:19??MachineLearning\AdaBoost_Project3\AdaBoost.py
?????文件???????13547??2018-06-24?16:10??MachineLearning\AdaBoost_Project3\horseColicTest2.txt
?????文件???????60479??2018-06-24?16:10??MachineLearning\AdaBoost_Project3\horseColicTraining2.txt
?????目錄???????????0??2018-12-17?08:23??MachineLearning\AdaBoost_Project4\
?????文件????????7990??2018-07-29?15:16??MachineLearning\AdaBoost_Project4\AdaBoost.py
?????文件???????60479??2018-06-24?16:10??MachineLearning\AdaBoost_Project4\horseColicTraining2.txt
?????目錄???????????0??2018-12-17?08:23??MachineLearning\Apriori_Project1\
?????文件????????7857??2018-08-05?17:14??MachineLearning\Apriori_Project1\Apriori.py
?????文件??????570408??2011-07-13?09:49??MachineLearning\Apriori_Project1\mushroom.dat
?????目錄???????????0??2018-07-29?16:45??MachineLearning\BayesianAnalysisWithPython\
?????文件????????1481??2018-07-29?17:16??MachineLearning\BayesianAnalysisWithPython\Gauss.py
?????目錄???????????0??2018-12-17?08:23??MachineLearning\Bayes_Project1\
?????文件????????7548??2018-07-21?15:29??MachineLearning\Bayes_Project1\Bayes.py
?????目錄???????????0??2018-12-17?08:23??MachineLearning\Bayes_Project2\
?????文件????????8969??2018-07-21?16:40??MachineLearning\Bayes_Project2\Bayes.py
?????目錄???????????0??2018-12-17?08:23??MachineLearning\Bayes_Project2\email\
?????目錄???????????0??2018-12-17?08:23??MachineLearning\Bayes_Project2\email\ham\
?????文件?????????141??2018-06-24?16:10??MachineLearning\Bayes_Project2\email\ham\1.txt
?????文件??????????82??2018-06-24?16:10??MachineLearning\Bayes_Project2\email\ham\10.txt
?????文件?????????122??2018-06-24?16:10??MachineLearning\Bayes_Project2\email\ham\11.txt
?????文件?????????172??2018-06-24?16:10??MachineLearning\Bayes_Project2\email\ham\12.txt
?????文件?????????164??2018-06-24?16:10??MachineLearning\Bayes_Project2\email\ham\13.txt
?????文件?????????162??2018-06-24?16:10??MachineLearning\Bayes_Project2\email\ham\14.txt
............此處省略8959個文件信息