--- a/scripts/process.py	Thu Jul 05 23:17:12 2018 -0400
+++ b/scripts/process.py	Fri Jul 06 11:13:10 2018 -0400
@@ -7,7 +7,7 @@
 #import matplotlib
 #atplotlib.use('Agg')
 import matplotlib.pyplot as plt
-from numpy import percentile, ones
+import numpy as np
 from pandas import DataFrame
 
 from trafficintelligence import storage, events, prediction, cvutils, utils, moving, processing, ml
@@ -37,6 +37,7 @@
 # motion pattern learning and assignment
 parser.add_argument('--prototype-filename', dest = 'outputPrototypeDatabaseFilename', help = 'name of the Sqlite database file to save prototypes', default = 'prototypes.sqlite')
 #parser.add_argument('-i', dest = 'inputPrototypeDatabaseFilename', help = 'name of the Sqlite database file for prototypes to start the algorithm with')
+parser.add_argument('--nobjects-mp', dest = 'nMPObjects', help = 'number of objects/interactions to process', type = int)
 parser.add_argument('--nfeatures-per-object', dest = 'nLongestFeaturesPerObject', help = 'maximum number of features per object to load', type = int)
 parser.add_argument('--epsilon', dest = 'epsilon', help = 'distance for the similarity of trajectory points', type = float)
 parser.add_argument('--metric', dest = 'metric', help = 'metric for the similarity of trajectory points', default = 'cityblock') # default is manhattan distance
@@ -149,7 +150,7 @@
     # learn by site by default -> group videos by site (or by camera view? TODO add cameraviews)
     # by default, load all objects, learn and then assign (BUT not save the assignments)
     for site in sites:
-        print('Learning motion patterns for site {}'.format(site.name))
+        print('Learning motion patterns for site {} ({})'.format(site.idx, site.name))
         objects = {}
         object2VideoSequences = {}
         for cv in site.cameraViews:
@@ -166,16 +167,20 @@
                     object2VideoSequences[obj] = vs
         lcss = utils.LCSS(metric = args.metric, epsilon = args.epsilon)
         similarityFunc = lambda x,y : lcss.computeNormalized(x, y)
-        allobjects = [o for tmpobjects in objects.values() for o in tmpobjects]
-        similarities = -ones((len(allobjects), len(allobjects)))
-        prototypeIndices, labels = processing.learnAssignMotionPatterns(True, True, allobjects, similarities, args.minSimilarity, similarityFunc, args.minClusterSize, args.optimizeCentroid, args.randomInitialization, True, [])
+        trainingObjects = [o for tmpobjects in objects.values() for o in tmpobjects]
+        if args.nMPObjects is not None:
+            m = int(np.floor(float(len(trainingObjects))/args.nMPObjects))
+            trainingObjects = trainingObjects[::m]
+        similarities = -np.ones((len(trainingObjects), len(trainingObjects)))
+        prototypeIndices, labels = processing.learnAssignMotionPatterns(True, True, trainingObjects, similarities, args.minSimilarity, similarityFunc, args.minClusterSize, args.optimizeCentroid, args.randomInitialization, True, [])
         if args.outputPrototypeDatabaseFilename is None:
             outputPrototypeDatabaseFilename = args.databaseFilename
         else:
             outputPrototypeDatabaseFilename = args.outputPrototypeDatabaseFilename
         # TODO maintain mapping from object prototype to db filename + compute nmatchings before
         clusterSizes = ml.computeClusterSizes(labels, prototypeIndices, -1)
-        storage.savePrototypesToSqlite(str(parentPath/site.getPath()/outputPrototypeDatabaseFilename), [moving.Prototype(object2VideoSequences[allobjects[i]].getDatabaseFilename(False), allobjects[i].getNum(), prototypeType, clusterSizes[i]) for i in prototypeIndices])
+        #print([clusterSizes[i] for i in prototypeIndices])
+        storage.savePrototypesToSqlite(str(parentPath/site.getPath()/outputPrototypeDatabaseFilename), [moving.Prototype(object2VideoSequences[trainingObjects[i]].getDatabaseFilename(False), trainingObjects[i].getNum(), prototypeType, clusterSizes[i]) for i in prototypeIndices])
 
 
 elif args.process == 'interaction':