Mercurial > hg > nsaunier > traffic-intelligence

comparison python/ml.py @ 293:ee3302528cdc

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
rearranged new code by Paul (works now)
author Nicolas Saunier <nicolas.saunier@polymtl.ca>
date Fri, 08 Feb 2013 18:13:29 -0500
parents 5957aa1d69e1
children 6c068047edbf
comparison
equal deleted inserted replaced
292:8b2c8a4015f1 293:ee3302528cdc
56 else: 56 else:
57 centroids[i].add(instance) 57 centroids[i].add(instance)
58 58
59 return centroids 59 return centroids
60 60
61 def spectralClustering(similarityMatrix,k): 61 def spectralClustering(similarityMatrix, k, iter=20):
62 '''Spectral Clustering algorithm''' 62 '''Spectral Clustering algorithm'''
63 n = len(similarityMatrix) 63 n = len(similarityMatrix)
64 # create Laplacian matrix 64 # create Laplacian matrix
65 rowsum = np.sum(similarityMatrix,axis=0) 65 rowsum = np.sum(similarityMatrix,axis=0)
66 D = np.diag(1 / np.sqrt(rowsum)) 66 D = np.diag(1 / np.sqrt(rowsum))
72 # by stacking eigenvectors as columns 72 # by stacking eigenvectors as columns
73 features = np.array(V[:k]).T 73 features = np.array(V[:k]).T
74 # k-means 74 # k-means
75 from scipy.cluster.vq import kmeans, whiten, vq 75 from scipy.cluster.vq import kmeans, whiten, vq
76 features = whiten(features) 76 features = whiten(features)
77 centroids,distortion = kmeans(features,k,iter=20) # default iter = 20 77 centroids,distortion = kmeans(features,k, iter)
78 code,distance = vq(features,centroids) # code starting from 0 (represent first cluster) to k-1 (last cluster) 78 code,distance = vq(features,centroids) # code starting from 0 (represent first cluster) to k-1 (last cluster)
79 return code,sigma 79 return code,sigma