#!/usr/bin/env?python
from?pprint?import?pprint
import?sys
import?random
import?math
import?timer

class?kmeans（object）:

	def?__init__（self?_X?_k?_xVal?=?0?_stop=False）:
		#?X?is?sample?size?lists?of?dim?length
		#
		#?_xVal?is?the?number?of?records?to?hold?out?cross-validation.
		#?To?use?this?you?must?randomize?input?data!
		#
		#?Setting?_stop=True?causes?iteration?to?stop?when?out?of?cross-validate
		#?error?starts?to?rise.
		#
		self.nFeatures?=?len（_X[0]）
		self.xValSize?=?_xVal
		self.allSize?=?len（_X）
		self.size?=?self.allSize?-?self.xValSize
		self.X?=?_X
		self.k?=?_k
		self.stop?=?_stop
		#?Initialize?group?memebership
		self.dataClusterId?=?[-1?for?i?in?range（0?self.allSize）]?#?index?of?group?for?each?data?pair
		self.clusters?=?{}
		idx?=?0
		#?initialize?to?k?random?data?points
		#?don‘t?assign?x-val?as?a?strat?center
		for?i?in?random.sample（range（0?self.size）?self.k）:
			self.clusters[idx]?=?self.X[i]
			idx?+=?1
		#?output?records
		self.record?=?[]
		self.errorRecord?=?[]
		
	def?dSquared（self?x?y）:
		dist2?=?0.0
		for?jk?in?zip（xy）:
			dist2?+=?（j?-?k）**2
		return?dist2

	def?error（self）:
		res?=?0.0
		for?i?in?range（0?self.size）:
			res?+=?self.dSquared（self.X[i]?self.clusters[self.dataClusterId[i]]）
		#?error?on?non?training?data
		res1?=?0.0
		err1?=?0.0
		for?i?in?range（self.size?self.allSize）:
			res1?+=?self.dSquared（self.X[i]?self.clusters[self.dataClusterId[i]]）
		if?res1?>?0.0:
			err1?=?res1/self.xValSize
		return?res/self.size?err1

	def?nearestCluster（self?x）:
		cmin?=?sys.maxint
		cidx?=?-sys.maxint
		for?j?in?self.clusters:
			dist?=?math.sqrt（self.dSquared（x?self.clusters[j]））
			if?dist?				cmin?=?dist
				cidx?=?j
		return?cidx?cmin

	def?assign（self）:
		for?i?in?range（0?self.allSize）:
			self.dataClusterId[i]?dmin?=?self.nearestCluster（self.X[i]）

	def?updateClusters（self）:
		ctemp?=?{}?#?dim?sums?by?cluster
		for?j?in?range（0?self.k）:
			ctemp[j]?=?[]
			for?k?in?range（0?self.nFeatures）:
				ctemp[j].append（0.0）?#?init?sums
			ctemp[j].append（0）?#?init?counter
		#?only?calculate?clusters?on?training?not?cross-validation?set
		for?i?in?range（0self.size）:
			for?j?in?range（0?self.nFeatures）:
				ctemp[self.dataClusterId[i]][j]?+=?self.X[i][j]
			ctemp[self.dataClusterId[i]][self.nFeatures]?+=?1?#?count
		for?c?in?self.clusters:
			if?ctemp[c][self.nFeatures]?<>?0:
				self.clusters[c]?=?[?ctemp[c][k]/ctemp[c][self.nFeatures]?for?k?in?range（0self.nFeatures）]
			else:
				#?no?members?in?this?cluster
				pass
		return

	def?run（self?nmax?=?100?eps?=?1e-7）:
		prev?=?0.0
		prevXVal?=?float（sys.maxint）
		for?iter?in?range（0nmax）:
			#?update?assignments
			self.assign（）
			#?calculate?error
			err?errXVal?=?self.error（）
			#
			if?self.stop?and?errXVal?-?prevXVal?>=?0.0:
				sys.stderr.write（“Cross-validation?error?increasing?at?step?%d\n“%iter）
				break
			prevXVal?=?errXVal
			#
			if?abs（err-prev）?				sys.stderr.write（“Tolerance?reached?a

?屬性????????????大小?????日期????時間???名稱
-----------?---------??----------?-----??----
?????目錄???????????0??2014-12-01?17:25??Python-DP-Means-Clustering-master\
?????文件?????????295??2014-12-01?17:25??Python-DP-Means-Clustering-master\.gitignore
?????文件????????1748??2014-12-01?17:25??Python-DP-Means-Clustering-master\DPopt.py
?????文件????????1317??2014-12-01?17:25??Python-DP-Means-Clustering-master\LICENSE
?????文件????????6058??2014-12-01?17:25??Python-DP-Means-Clustering-master\README
?????文件????????6124??2014-12-01?17:25??Python-DP-Means-Clustering-master\cluster.py
?????文件?????????354??2014-12-01?17:25??Python-DP-Means-Clustering-master\costTest.bash
?????文件????????1232??2014-12-01?17:25??Python-DP-Means-Clustering-master\createTestData.py
?????目錄???????????0??2014-12-01?17:25??Python-DP-Means-Clustering-master\img\
?????文件???????18195??2014-12-01?17:25??Python-DP-Means-Clustering-master\img\2d-sample-data.png
?????文件???????96576??2014-12-01?17:25??Python-DP-Means-Clustering-master\img\3d-sample-data.png
?????文件???????20568??2014-12-01?17:25??Python-DP-Means-Clustering-master\img\error.png
?????文件??????241453??2014-12-01?17:25??Python-DP-Means-Clustering-master\img\iters.png
?????文件???????18088??2014-12-01?17:25??Python-DP-Means-Clustering-master\img\opt_error.png
?????文件??????174533??2014-12-01?17:25??Python-DP-Means-Clustering-master\img\opt_iters.png
?????文件???????20973??2014-12-01?17:25??Python-DP-Means-Clustering-master\img\test_errors.png
?????文件???????22520??2014-12-01?17:25??Python-DP-Means-Clustering-master\img\test_errors_20.png
?????文件???????30375??2014-12-01?17:25??Python-DP-Means-Clustering-master\img\test_errors_20_annotated.png
?????文件???????24465??2014-12-01?17:25??Python-DP-Means-Clustering-master\img\test_times-error.png
?????文件???????26844??2014-12-01?17:25??Python-DP-Means-Clustering-master\img\test_times-error_10.png
?????文件???????27245??2014-12-01?17:25??Python-DP-Means-Clustering-master\img\test_times-error_12.png
?????文件???????27581??2014-12-01?17:25??Python-DP-Means-Clustering-master\img\test_times-error_15.png
?????文件???????26937??2014-12-01?17:25??Python-DP-Means-Clustering-master\img\test_times-error_18.png
?????文件???????24941??2014-12-01?17:25??Python-DP-Means-Clustering-master\img\test_times-error_2.png
?????文件???????26406??2014-12-01?17:25??Python-DP-Means-Clustering-master\img\test_times-error_20.png
?????文件???????27115??2014-12-01?17:25??Python-DP-Means-Clustering-master\img\test_times-error_3.png
?????文件???????26713??2014-12-01?17:25??Python-DP-Means-Clustering-master\img\test_times-error_4.png
?????文件???????27006??2014-12-01?17:25??Python-DP-Means-Clustering-master\img\test_times-error_5.png
?????文件???????26386??2014-12-01?17:25??Python-DP-Means-Clustering-master\img\test_times-error_8.png
?????文件???????21904??2014-12-01?17:25??Python-DP-Means-Clustering-master\img\test_times.png
?????目錄???????????0??2014-12-01?17:25??Python-DP-Means-Clustering-master\input\
............此處省略14個文件信息