Mercurial > hg > nsaunier > traffic-intelligence

comparison python/ml.py @ 953:989917b1ed85

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
assign and learn work
author Nicolas Saunier <nicolas.saunier@polymtl.ca>
date Tue, 25 Jul 2017 17:36:07 -0400
parents a9b2beef0db4
children ec1682ed999f
comparison
equal deleted inserted replaced
952:a9b2beef0db4 953:989917b1ed85
136 'Represents a cluster, with a prototype id and the list of instances in cluster' 136 'Represents a cluster, with a prototype id and the list of instances in cluster'
137 def __init__(prototypeId, memberIndices = []): 137 def __init__(prototypeId, memberIndices = []):
138 self.prototypeId = prototypeId 138 self.prototypeId = prototypeId
139 self.memberIndices = memberIndices 139 self.memberIndices = memberIndices
140 140
141 def assignToPrototypeClusters(instances, prototypeIndices, similarities, minSimilarity, similarityFunc = None, minClusterSize = None): 141 def assignToPrototypeClusters(instances, prototypeIndices, similarities, minSimilarity, similarityFunc = None, minClusterSize = 0):
142 '''Assigns instances to prototypes 142 '''Assigns instances to prototypes
143 if minClusterSize is not None, the clusters will be refined by removing iteratively the smallest clusters 143 if minClusterSize is not None, the clusters will be refined by removing iteratively the smallest clusters
144 and reassigning all elements in the cluster until no cluster is smaller than minClusterSize''' 144 and reassigning all elements in the cluster until no cluster is smaller than minClusterSize'''
145 indices = [i for i in range(len(instances)) if i not in prototypeIndices] 145 indices = [i for i in range(len(instances)) if i not in prototypeIndices]
146 labels = [-1]*len(instances) 146 labels = [-1]*len(instances)
164 assign = (clusterSizes[smallestClusterIndex] < minClusterSize) 164 assign = (clusterSizes[smallestClusterIndex] < minClusterSize)
165 if assign: 165 if assign:
166 prototypeIndices.remove(smallestClusterIndex) 166 prototypeIndices.remove(smallestClusterIndex)
167 indices = [i for i in range(similarities.shape[0]) if labels[i] == smallestClusterIndex] 167 indices = [i for i in range(similarities.shape[0]) if labels[i] == smallestClusterIndex]
168 return prototypeIndices, labels 168 return prototypeIndices, labels
169 169 def prototypeCluster(instances, similarities, minSimilarity, similarityFunc = None, optimizeCentroid = True, randomInitialization = False, initialPrototypeIndices = None):
170 def prototypeCluster(instances, similarities, minSimilarity, similarityFunc = None, minClusterSize = 0, optimizeCentroid = True, randomInitialization = False, initialPrototypeIndices = None):
171 '''Finds exemplar (prototype) instance that represent each cluster 170 '''Finds exemplar (prototype) instance that represent each cluster
172 Returns the prototype indices (in the instances list) 171 Returns the prototype indices (in the instances list)
173 172
174 the elements in the instances list must have a length (method __len__), or one can use the random initialization 173 the elements in the instances list must have a length (method __len__), or one can use the random initialization
175 the positions in the instances list corresponds to the similarities 174 the positions in the instances list corresponds to the similarities