@knight 2015-06-17T12:53:05.000000Z 字数 4725 阅读 1460

# K-均值聚类

python 机器学习

1. from numpy import *
2. def loadDataSet(fileName): #general function to parse tab -delimited floats
3. dataMat = [] #assume last column is target value
4. fr = open(fileName)
6. curLine = line.strip().split('\t')
7. fltLine = map(float,curLine) #map all elements to float()
8. dataMat.append(fltLine)
9. return dataMat
10. def distEclud(vecA, vecB):
11. return sqrt(sum(power(vecA - vecB, 2))) #la.norm(vecA-vecB)
12. def randCent(dataSet, k):
13. n = shape(dataSet)[1]
14. centroids = mat(zeros((k,n)))#create centroid mat
15. for j in range(n):#create random cluster centers, within bounds of each dimension
16. minJ = min(dataSet[:,j])
17. rangeJ = float(max(dataSet[:,j]) - minJ)
18. centroids[:,j] = mat(minJ + rangeJ * random.rand(k,1))
19. return centroids
20. def kMeans(dataSet, k, distMeas=distEclud, createCent=randCent):
21. m = shape(dataSet)[0]
22. clusterAssment = mat(zeros((m,2)))#create mat to assign data points
23. #to a centroid, also holds SE of each point
24. centroids = createCent(dataSet, k)
25. clusterChanged = True
26. while clusterChanged:
27. clusterChanged = False
28. for i in range(m):#for each data point assign it to the closest centroid
29. minDist = inf; minIndex = -1
30. for j in range(k):
31. distJI = distMeas(centroids[j,:],dataSet[i,:])
32. if distJI < minDist:
33. minDist = distJI; minIndex = j
34. if clusterAssment[i,0] != minIndex: clusterChanged = True
35. clusterAssment[i,:] = minIndex,minDist**2
36. print centroids
37. for cent in range(k):#recalculate centroids
38. ptsInClust = dataSet[nonzero(clusterAssment[:,0].A==cent)[0]]#get all the point in this cluster
39. centroids[cent,:] = mean(ptsInClust, axis=0) #assign centroid to mean
40. return centroids, clusterAssment
41. def biKmeans(dataSet, k, distMeas=distEclud):
42. m = shape(dataSet)[0]
43. clusterAssment = mat(zeros((m,2)))
44. centroid0 = mean(dataSet, axis=0).tolist()[0]
45. centList =[centroid0] #create a list with one centroid
46. for j in range(m):#calc initial Error
47. clusterAssment[j,1] = distMeas(mat(centroid0), dataSet[j,:])**2
48. while (len(centList) < k):
49. lowestSSE = inf
50. for i in range(len(centList)):
51. ptsInCurrCluster = dataSet[nonzero(clusterAssment[:,0].A==i)[0],:]#get the data points currently in cluster i
52. centroidMat, splitClustAss = kMeans(ptsInCurrCluster, 2, distMeas)
53. sseSplit = sum(splitClustAss[:,1])#compare the SSE to the currrent minimum
54. sseNotSplit = sum(clusterAssment[nonzero(clusterAssment[:,0].A!=i)[0],1])
55. print "sseSplit, and notSplit: ",sseSplit,sseNotSplit
56. if (sseSplit + sseNotSplit) < lowestSSE:
57. bestCentToSplit = i
58. bestNewCents = centroidMat
59. bestClustAss = splitClustAss.copy()
60. lowestSSE = sseSplit + sseNotSplit
61. bestClustAss[nonzero(bestClustAss[:,0].A == 1)[0],0] = len(centList) #change 1 to 3,4, or whatever
62. bestClustAss[nonzero(bestClustAss[:,0].A == 0)[0],0] = bestCentToSplit
63. print 'the bestCentToSplit is: ',bestCentToSplit
64. print 'the len of bestClustAss is: ', len(bestClustAss)
65. centList[bestCentToSplit] = bestNewCents[0,:].tolist()[0]#replace a centroid with two best centroids
66. centList.append(bestNewCents[1,:].tolist()[0])
67. clusterAssment[nonzero(clusterAssment[:,0].A == bestCentToSplit)[0],:]= bestClustAss#reassign new clusters, and SSE
68. return mat(centList), clusterAssment
69. import urllib
70. import json
72. apiStem = 'http://where.yahooapis.com/geocode?' #create a dict and constants for the goecoder
73. params = {}
74. params['flags'] = 'J'#JSON return type
75. params['appid'] = 'aaa0VN6k'
76. params['location'] = '%s %s' % (stAddress, city)
77. url_params = urllib.urlencode(params)
78. yahooApi = apiStem + url_params #print url_params
79. print yahooApi
80. c=urllib.urlopen(yahooApi)
82. from time import sleep
83. def massPlaceFind(fileName):
84. fw = open('places.txt', 'w')
86. line = line.strip()
87. lineArr = line.split('\t')
88. retDict = geoGrab(lineArr[1], lineArr[2])
89. if retDict['ResultSet']['Error'] == 0:
90. lat = float(retDict['ResultSet']['Results'][0]['latitude'])
91. lng = float(retDict['ResultSet']['Results'][0]['longitude'])
92. print "%s\t%f\t%f" % (lineArr[0], lat, lng)
93. fw.write('%s\t%f\t%f\n' % (line, lat, lng))
94. else: print "error fetching"
95. sleep(1)
96. fw.close()
97. def distSLC(vecA, vecB):#Spherical Law of Cosines
98. a = sin(vecA[0,1]*pi/180) * sin(vecB[0,1]*pi/180)
99. b = cos(vecA[0,1]*pi/180) * cos(vecB[0,1]*pi/180) * \
100. cos(pi * (vecB[0,0]-vecA[0,0]) /180)
101. return arccos(a + b)*6371.0 #pi is imported with numpy
102. import matplotlib
103. import matplotlib.pyplot as plt
104. def clusterClubs(numClust=5):
105. datList = []
107. lineArr = line.split('\t')
108. datList.append([float(lineArr[4]), float(lineArr[3])])
109. datMat = mat(datList)
110. myCentroids, clustAssing = biKmeans(datMat, numClust, distMeas=distSLC)
111. fig = plt.figure()
112. rect=[0.1,0.1,0.8,0.8]
113. scatterMarkers=['s', 'o', '^', '8', 'p', \
114. 'd', 'v', 'h', '>', '<']
115. axprops = dict(xticks=[], yticks=[])
118. ax0.imshow(imgP)