Mercurial > hg > nsaunier > traffic-intelligence

comparison scripts/learn-poi.py @ 795:a34ec862371f

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
merged with dev branch
author Nicolas Saunier <nicolas.saunier@polymtl.ca>
date Mon, 09 May 2016 15:33:11 -0400
parents 0a428b449b80
children 180b6b0231c0
comparison
equal deleted inserted replaced
758:0a05883216cf 795:a34ec862371f
1 #! /usr/bin/env python
2
3 import argparse
4
5 import numpy as np
6 from sklearn import mixture
7 import matplotlib.pyplot as plt
8
9 import storage, ml
10
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)
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)
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.)
18
19 args = parser.parse_args()
20
21 objects = storage.loadTrajectoriesFromSqlite(args.databaseFilename, args.trajectoryType)
22
23 beginnings = []
24 ends = []
25 for o in objects:
26 beginnings.append(o.getPositionAt(0).aslist())
27 ends.append(o.getPositionAt(int(o.length())-1).aslist())
28
29 beginnings = np.array(beginnings)
30 ends = np.array(ends)
31
32 gmm = mixture.GMM(n_components=args.nClusters, covariance_type = args.covarianceType)
33 beginningModel=gmm.fit(beginnings)
34 gmm = mixture.GMM(n_components=args.nClusters, covariance_type = args.covarianceType)
35 endModel=gmm.fit(ends)
36
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)
42 plt.axis('equal')
43 plt.title('Origins')
44 print('Origin Clusters:\n{}'.format(ml.computeClusterSizes(beginningModel.predict(beginnings), range(args.nClusters))))
45
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)
51 plt.axis('equal')
52 plt.title('Destinations')
53 print('Destination Clusters:\n{}'.format(ml.computeClusterSizes(endModel.predict(ends), range(args.nClusters))))