#?coding:UTF-8
‘‘‘
Date:20160923
@author:?zhaozhiyong
‘‘‘

import?numpy?as?np
import?math

MinPts?=?5??#?定義半徑內的最少的數據點的個數

def?load_data（file_path）:
????‘‘‘導入數據
????input:??file_path（string）:文件名
????output:?data（mat）:數據
????‘‘‘
????f?=?open（file_path）
????data?=?[]
????for?line?in?f.readlines（）:
????????data_tmp?=?[]
????????lines?=?line.strip（）.split（“\t“）
????????for?x?in?lines:
????????????data_tmp.append（float（x.strip（）））
????????data.append（data_tmp）
????f.close（）
????return?np.mat（data）

def?epsilon（data?MinPts）:
????‘‘‘計算半徑
????input:??data（mat）:訓練數據
????????????MinPts（int）:半徑內的數據點的個數
????output:?eps（float）:半徑
????‘‘‘
????m?n?=?np.shape（data）
????xMax?=?np.max（data?0）
????xMin?=?np.min（data?0）
????eps?=?（（np.prod（xMax?-?xMin）?*?MinPts?*?math.gamma（0.5?*?n?+?1））?/?（m?*?math.sqrt（math.pi?**?n）））?**?（1.0?/?n）
????return?eps
????
def?distance（data）:
????m?n?=?np.shape（data）
????dis?=?np.mat（np.zeros（（m?m）））
????for?i?in?xrange（m）:
????????for?j?in?xrange（i?m）:
????????????#?計算i和j之間的歐式距離
????????????tmp?=?0
????????????for?k?in?xrange（n）:
????????????????tmp?+=?（data[i?k]?-?data[j?k]）?*?（data[i?k]?-?data[j?k]）
????????????dis[i?j]?=?np.sqrt（tmp）
????????????dis[j?i]?=?dis[i?j]
????return?dis

def?find_eps（distance_D?eps）:
????ind?=?[]
????n?=?np.shape（distance_D）[1]
????for?j?in?xrange（n）:
????????if?distance_D[0?j]?<=?eps:
????????????ind.append（j）
????return?ind

def?dbscan（data?eps?MinPts）:
????m?=?np.shape（data）[0]
????#?區分核心點1，邊界點0和噪音點-1
????types?=?np.mat（np.zeros（（1?m）））
????sub_class?=?np.mat（np.zeros（（1?m）））
????#?用于判斷該點是否處理過，0表示未處理過
????dealed?=?np.mat（np.zeros（（m?1）））
????#?計算每個數據點之間的距離
????dis?=?distance（data）
????#?用于標記類別
????number?=?1
????
????#?對每一個點進行處理
????for?i?in?xrange（m）:
????????#?找到未處理的點
????????if?dealed[i?0]?==?0:
????????????#?找到第i個點到其他所有點的距離
????????????D?=?dis[i?]
????????????#?找到半徑eps內的所有點
????????????ind?=?find_eps（D?eps）
????????????#?區分點的類型
????????????#?邊界點
????????????if?len（ind）?>?1?and?len（ind）?????????????????types[0?i]?=?0
????????????????sub_class[0?i]?=?0
????????????#?噪音點
????????????if?len（ind）?==?1:
????????????????types[0?i]?=?-1
????????????????sub_class[0?i]?=?-1
????????????????dealed[i?0]?=?1
????????????#?核心點
????????????if?len（ind）?>=?MinPts?+?1:
????????????????types[0?i]?=?1
????????????????for?x?in?ind:
????????????????????sub_class[0?x]?=?number
????????????????#?判斷核心點是否密度可達
????????????????while?len（ind）?>?0:
????????????????????dealed[ind[0]?0]?=?1
????????????????????D?=?dis[ind[0]?]
????????????????????tmp?=?ind[0]
????????????????????del?ind[0]
????????????????????ind_1?=?find_eps（D?eps）
????????????????????
????????????????????if?len（ind_1）?>?1:??#?處理非噪音點
????????????????????????for?x1?in?ind_1:
????????????????????????????sub_class[0?x1]?=?number
????????????????????????if?len（ind_1）?>=?MinPts?+?1:
????????????????????????????types[0?tmp]?=?1
????????????????????????else:
????????????????????????????types[0?tmp]?=?0
??????????????????

?屬性????????????大小?????日期????時間???名稱
-----------?---------??----------?-----??----
?????目錄???????????0??2018-04-16?23:33??機器學習算法Python-Machine-Learning-Algorithm-master\
?????目錄???????????0??2018-04-16?23:33??機器學習算法Python-Machine-Learning-Algorithm-master\Chapter12_DBSCAN\
?????文件????????1520??2017-12-01?23:19??機器學習算法Python-Machine-Learning-Algorithm-master\Chapter12_DBSCAN\data.txt
?????文件????????4631??2017-12-01?23:19??機器學習算法Python-Machine-Learning-Algorithm-master\Chapter12_DBSCAN\dbscan.py
?????目錄???????????0??2018-04-16?23:33??機器學習算法Python-Machine-Learning-Algorithm-master\Chapter_1?Logistic?Regression\
?????文件??????????32??2017-12-01?23:19??機器學習算法Python-Machine-Learning-Algorithm-master\Chapter_1?Logistic?Regression\README.md
?????文件????????7251??2017-12-01?23:19??機器學習算法Python-Machine-Learning-Algorithm-master\Chapter_1?Logistic?Regression\data.txt
?????文件????????2420??2017-12-01?23:19??機器學習算法Python-Machine-Learning-Algorithm-master\Chapter_1?Logistic?Regression\lr_test.py
?????文件????????2907??2017-12-01?23:19??機器學習算法Python-Machine-Learning-Algorithm-master\Chapter_1?Logistic?Regression\lr_train.py
?????文件????????6851??2017-12-01?23:19??機器學習算法Python-Machine-Learning-Algorithm-master\Chapter_1?Logistic?Regression\test_data
?????目錄???????????0??2018-04-16?23:33??機器學習算法Python-Machine-Learning-Algorithm-master\Chapter_10?KMeans\
?????文件????????4278??2017-12-01?23:19??機器學習算法Python-Machine-Learning-Algorithm-master\Chapter_10?KMeans\KMeans.py
?????文件????????2746??2017-12-01?23:19??機器學習算法Python-Machine-Learning-Algorithm-master\Chapter_10?KMeans\KMeanspp.py
?????文件????????2800??2017-12-01?23:19??機器學習算法Python-Machine-Learning-Algorithm-master\Chapter_10?KMeans\data.txt
?????目錄???????????0??2018-04-16?23:33??機器學習算法Python-Machine-Learning-Algorithm-master\Chapter_11?MeanShift\
?????文件????????3001??2017-12-01?23:19??機器學習算法Python-Machine-Learning-Algorithm-master\Chapter_11?MeanShift\data
?????文件????????5620??2017-12-01?23:19??機器學習算法Python-Machine-Learning-Algorithm-master\Chapter_11?MeanShift\mean_shift.py
?????目錄???????????0??2018-04-16?23:33??機器學習算法Python-Machine-Learning-Algorithm-master\Chapter_13?LabelPropagation\
?????文件?????????131??2017-12-01?23:19??機器學習算法Python-Machine-Learning-Algorithm-master\Chapter_13?LabelPropagation\cd_data.txt
?????文件????????4356??2017-12-01?23:19??機器學習算法Python-Machine-Learning-Algorithm-master\Chapter_13?LabelPropagation\lb.py
?????目錄???????????0??2018-04-16?23:33??機器學習算法Python-Machine-Learning-Algorithm-master\Chapter_14?CollaborativeFiltering\
?????文件??????????50??2017-12-01?23:19??機器學習算法Python-Machine-Learning-Algorithm-master\Chapter_14?CollaborativeFiltering\data.txt
?????文件????????2386??2017-12-01?23:19??機器學習算法Python-Machine-Learning-Algorithm-master\Chapter_14?CollaborativeFiltering\item_based_recommend.py
?????文件????????3737??2017-12-01?23:19??機器學習算法Python-Machine-Learning-Algorithm-master\Chapter_14?CollaborativeFiltering\user_based_recommend.py
?????目錄???????????0??2018-04-16?23:33??機器學習算法Python-Machine-Learning-Algorithm-master\Chapter_15?MatrixFactorization\
?????文件??????????50??2017-12-01?23:19??機器學習算法Python-Machine-Learning-Algorithm-master\Chapter_15?MatrixFactorization\data.txt
?????文件????????4325??2017-12-01?23:19??機器學習算法Python-Machine-Learning-Algorithm-master\Chapter_15?MatrixFactorization\mf.py
?????文件????????1720??2017-12-01?23:19??機器學習算法Python-Machine-Learning-Algorithm-master\Chapter_15?MatrixFactorization\nmf.py
?????目錄???????????0??2018-04-16?23:33??機器學習算法Python-Machine-Learning-Algorithm-master\Chapter_16?PersonalRank\
?????文件??????????50??2017-12-01?23:19??機器學習算法Python-Machine-Learning-Algorithm-master\Chapter_16?PersonalRank\data.txt
?????文件????????3262??2017-12-01?23:19??機器學習算法Python-Machine-Learning-Algorithm-master\Chapter_16?PersonalRank\personal_rank.py
............此處省略51個文件信息