Mercurial Hosting > traffic-intelligence
comparison scripts/learn-poi.py @ 786:1f2b2d1f4fbf dev
added script and code to learn POIs
author | Nicolas Saunier <nicolas.saunier@polymtl.ca> |
---|---|
date | Fri, 11 Mar 2016 17:38:48 -0500 |
parents | |
children | 0a428b449b80 |
comparison
equal
deleted
inserted
replaced
785:3aa6102ccc12 | 786:1f2b2d1f4fbf |
---|---|
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 | |
17 args = parser.parse_args() | |
18 | |
19 objects = storage.loadTrajectoriesFromSqlite(args.databaseFilename, args.trajectoryType) | |
20 | |
21 beginnings = [] | |
22 ends = [] | |
23 for o in objects: | |
24 beginnings.append(o.getPositionAt(0).aslist()) | |
25 ends.append(o.getPositionAt(int(o.length())-1).aslist()) | |
26 | |
27 beginnings = np.array(beginnings) | |
28 ends = np.array(ends) | |
29 | |
30 gmm = mixture.GMM(n_components=args.nClusters, covariance_type = args.covarianceType) | |
31 beginningModel=gmm.fit(beginnings) | |
32 gmm = mixture.GMM(n_components=args.nClusters, covariance_type = args.covarianceType) | |
33 endModel=gmm.fit(ends) | |
34 | |
35 ml.plotGMMClusters(beginningModel, beginnings) | |
36 plt.axis('equal') | |
37 plt.title('Origins') | |
38 print('Origin Clusters:\n{}'.format(ml.computeClusterSizes(beginningModel.predict(beginnings), range(args.nClusters)))) | |
39 | |
40 ml.plotGMMClusters(endModel, ends) | |
41 plt.axis('equal') | |
42 plt.title('Destinations') | |
43 print('Destination Clusters:\n{}'.format(ml.computeClusterSizes(endModel.predict(ends), range(args.nClusters)))) |