Mercurial Hosting > traffic-intelligence

comparison python/ml.py @ 308:8bafd054cda4

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Added a function to compute LCSS distance between two indcators
author Mohamed Gomaa
date Tue, 25 Dec 2012 02:20:25 -0500
parents d70e9b36889c
children 80cbafd69109
comparison
equal deleted inserted replaced
307:8e66ced156dd 308:8bafd054cda4
1 #! /usr/bin/env python 1 #! /usr/bin/env python
2 '''Libraries for machine learning algorithms''' 2 '''Libraries for machine learning algorithms'''
3
4 import numpy as np
3 5
4 __metaclass__ = type 6 __metaclass__ = type
5 7
6 class Centroid: 8 class Centroid:
7 'Wrapper around instances to add a counter' 9 'Wrapper around instances to add a counter'
53 centroids.append(Centroid(instance)) 55 centroids.append(Centroid(instance))
54 else: 56 else:
55 centroids[i].add(instance) 57 centroids[i].add(instance)
56 58
57 return centroids 59 return centroids
60
61 def spectralClustering(similarityMatrix,k):
62 ''' Steps of Spectral Clustering'''
63 n= len(similarityMatrix)
64 # create Laplacian matrix
65 rowsum = np.sum(similarityMatrix,axis=0)
66 D = np.diag(1 / np.sqrt(rowsum))
67 I = np.identity(n)
68 L = I - np.dot(D,np.dot(similarityMatrix,D))
69 # compute eigenvectors of L
70 U,sigma,V = np.linalg.svd(L)
71 # create feature vector from k first eigenvectors
72 # by stacking eigenvectors as columns
73 features = np.array(V[:k]).T
74 # k-means
75 from scipy.cluster.vq import kmeans, whiten, vq
76 features = whiten(features)
77 centroids,distortion = kmeans(features,k,iter=20) # default iter = 20
78 code,distance = vq(features,centroids) # code starting from 0 (represent first cluster) to k-1 (last cluster)
79 return code,sigma
80