Mercurial > hg > nsaunier > traffic-intelligence

comparison scripts/learn-poi.py @ 787:0a428b449b80 dev

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
improved script to display over world image
author Nicolas Saunier <nicolas.saunier@polymtl.ca>
date Thu, 17 Mar 2016 16:01:19 -0400
parents 1f2b2d1f4fbf
children 180b6b0231c0
comparison
equal deleted inserted replaced
786:1f2b2d1f4fbf 787:0a428b449b80
11 parser = argparse.ArgumentParser(description='The program learns and displays Gaussians fit to beginnings and ends of object trajectories (based on Mohamed Gomaa Mohamed 2015 PhD). TODO: save the data') 11 parser = argparse.ArgumentParser(description='The program learns and displays Gaussians fit to beginnings and ends of object trajectories (based on Mohamed Gomaa Mohamed 2015 PhD). TODO: save the data')
12 parser.add_argument('-d', dest = 'databaseFilename', help = 'name of the Sqlite database file', required = True) 12 parser.add_argument('-d', dest = 'databaseFilename', help = 'name of the Sqlite database file', required = True)
13 parser.add_argument('-t', dest = 'trajectoryType', help = 'type of trajectories to display', choices = ['feature', 'object'], default = 'object') 13 parser.add_argument('-t', dest = 'trajectoryType', help = 'type of trajectories to display', choices = ['feature', 'object'], default = 'object')
14 parser.add_argument('-n', dest = 'nClusters', help = 'number of point clusters', required = True, type = int) 14 parser.add_argument('-n', dest = 'nClusters', help = 'number of point clusters', required = True, type = int)
15 parser.add_argument('--covariance-type', dest = 'covarianceType', help = 'type of covariance of Gaussian model', default = "full") 15 parser.add_argument('--covariance-type', dest = 'covarianceType', help = 'type of covariance of Gaussian model', default = "full")
16 parser.add_argument('-w', dest = 'worldImageFilename', help = 'filename of the world image')
17 parser.add_argument('-u', dest = 'pixelsPerUnit', help = 'number pixels per unit of distance', type = float, default = 1.)
16 18
17 args = parser.parse_args() 19 args = parser.parse_args()
18 20
19 objects = storage.loadTrajectoriesFromSqlite(args.databaseFilename, args.trajectoryType) 21 objects = storage.loadTrajectoriesFromSqlite(args.databaseFilename, args.trajectoryType)
20 22
30 gmm = mixture.GMM(n_components=args.nClusters, covariance_type = args.covarianceType) 32 gmm = mixture.GMM(n_components=args.nClusters, covariance_type = args.covarianceType)
31 beginningModel=gmm.fit(beginnings) 33 beginningModel=gmm.fit(beginnings)
32 gmm = mixture.GMM(n_components=args.nClusters, covariance_type = args.covarianceType) 34 gmm = mixture.GMM(n_components=args.nClusters, covariance_type = args.covarianceType)
33 endModel=gmm.fit(ends) 35 endModel=gmm.fit(ends)
34 36
35 ml.plotGMMClusters(beginningModel, beginnings) 37 fig = plt.figure()
38 if args.worldImageFilename is not None and args.pixelsPerUnit is not None:
39 img = plt.imread(args.worldImageFilename)
40 plt.imshow(img)
41 ml.plotGMMClusters(beginningModel, beginnings, fig, nPixelsPerUnit = args.pixelsPerUnit)
36 plt.axis('equal') 42 plt.axis('equal')
37 plt.title('Origins') 43 plt.title('Origins')
38 print('Origin Clusters:\n{}'.format(ml.computeClusterSizes(beginningModel.predict(beginnings), range(args.nClusters)))) 44 print('Origin Clusters:\n{}'.format(ml.computeClusterSizes(beginningModel.predict(beginnings), range(args.nClusters))))
39 45
40 ml.plotGMMClusters(endModel, ends) 46 fig = plt.figure()
47 if args.worldImageFilename is not None and args.pixelsPerUnit is not None:
48 img = plt.imread(args.worldImageFilename)
49 plt.imshow(img)
50 ml.plotGMMClusters(endModel, ends, fig, nPixelsPerUnit = args.pixelsPerUnit)
41 plt.axis('equal') 51 plt.axis('equal')
42 plt.title('Destinations') 52 plt.title('Destinations')
43 print('Destination Clusters:\n{}'.format(ml.computeClusterSizes(endModel.predict(ends), range(args.nClusters)))) 53 print('Destination Clusters:\n{}'.format(ml.computeClusterSizes(endModel.predict(ends), range(args.nClusters))))