Mercurial Hosting > traffic-intelligence

comparison scripts/learn-motion-patterns.py @ 980:23f98ebb113f

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
first tests for clustering algo
author Nicolas Saunier <nicolas.saunier@polymtl.ca>
date Mon, 19 Feb 2018 16:32:59 -0500
parents cc89267b5ff9
children 933670761a57
comparison
equal deleted inserted replaced
979:cc89267b5ff9 980:23f98ebb113f
74 similarities = -np.ones((nTrajectories, nTrajectories)) 74 similarities = -np.ones((nTrajectories, nTrajectories))
75 similarityFunc = lambda x,y : lcss.computeNormalized(x, y) 75 similarityFunc = lambda x,y : lcss.computeNormalized(x, y)
76 # the next line can be called again without reinitializing similarities 76 # the next line can be called again without reinitializing similarities
77 if args.learn: 77 if args.learn:
78 prototypeIndices = ml.prototypeCluster(trajectories, similarities, args.minSimilarity, similarityFunc, args.optimizeCentroid, args.randomInitialization, initialPrototypeIndices) 78 prototypeIndices = ml.prototypeCluster(trajectories, similarities, args.minSimilarity, similarityFunc, args.optimizeCentroid, args.randomInitialization, initialPrototypeIndices)
79 # assignment is done if explicitly passed as argument or if working on the same database (starting prototypes from scratch and assigning the ) 79 # assignment is done if explicitly passed as argument or if working on the same database (starting prototypes from scratch and assigning them)
80 # (otherwise the matchings will not compare and one has to to matchings on a large scale at once)
81 else: 80 else:
82 prototypeIndices = initialPrototypeIndices 81 prototypeIndices = initialPrototypeIndices
83 82
84 if args.assign: 83 if args.assign:
85 prototypeIndices, labels = ml.assignToPrototypeClusters(trajectories, prototypeIndices, similarities, args.minSimilarity, similarityFunc, args.minClusterSize) 84 prototypeIndices, labels = ml.assignToPrototypeClusters(trajectories, prototypeIndices, similarities, args.minSimilarity, similarityFunc, args.minClusterSize)