--- a/scripts/process.py	Thu Jul 05 17:06:40 2018 -0400
+++ b/scripts/process.py	Thu Jul 05 17:45:18 2018 -0400
@@ -10,7 +10,7 @@
 from numpy import percentile
 from pandas import DataFrame
 
-from trafficintelligence import storage, events, prediction, cvutils, utils
+from trafficintelligence import storage, events, prediction, cvutils, utils, moving
 from trafficintelligence.metadata import *
 
 parser = argparse.ArgumentParser(description='This program manages the processing of several files based on a description of the sites and video data in an SQLite database following the metadata module.')
@@ -38,12 +38,12 @@
 # motion pattern learning and assignment
 parser.add_argument('--prototype-filename', dest = 'outputPrototypeDatabaseFilename', help = 'name of the Sqlite database file to save prototypes')
 #parser.add_argument('-i', dest = 'inputPrototypeDatabaseFilename', help = 'name of the Sqlite database file for prototypes to start the algorithm with')
-parser.add_argument('--max-nobjectfeatures', dest = 'maxNObjectFeatures', help = 'maximum number of features per object to load', type = int, default = 1)
-parser.add_argument('--maxdist', dest = 'epsilon', help = 'distance for the similarity of trajectory points', type = float, required = True)
+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, required = True)
 parser.add_argument('--metric', dest = 'metric', help = 'metric for the similarity of trajectory points', default = 'cityblock') # default is manhattan distance
-parser.add_argument('-minsimil', dest = 'minSimilarity', help = 'minimum similarity to put a trajectory in a cluster', type = float, required = True)
+parser.add_argument('--minsimil', dest = 'minSimilarity', help = 'minimum similarity to put a trajectory in a cluster', type = float, required = True)
 parser.add_argument('-min-cluster-size', dest = 'minClusterSize', help = 'minimum cluster size', type = int, default = 0)
-parser.add_argument('--learn', dest = 'learn', help = 'learn', action = 'store_true')
+#parser.add_argument('--learn', dest = 'learn', help = 'learn', action = 'store_true')
 parser.add_argument('--optimize', dest = 'optimizeCentroid', help = 'recompute centroid at each assignment', action = 'store_true')
 parser.add_argument('--random', dest = 'randomInitialization', help = 'random initialization of clustering algorithm', action = 'store_true')
 #parser.add_argument('--similarities-filename', dest = 'similaritiesFilename', help = 'filename of the similarities')
@@ -80,15 +80,18 @@
 session = connectDatabase(args.metadataFilename)
 parentPath = Path(args.metadataFilename).parent # files are relative to metadata location
 videoSequences = []
+sites = []
 if args.videoIds is not None:
     videoSequences = [session.query(VideoSequence).get(videoId) for videoId in args.videoIds]
     siteIds = set([vs.cameraView.siteIdx for vs in videoSequences])
 elif args.siteIds is not None:
     siteIds = set(args.siteIds)
     for siteId in siteIds:
-        for site in getSite(session, siteId):
+        tmpsites = getSite(session, siteId)
+        sites.extend(tmpsites)
+        for site in tmpsites:
             for cv in site.cameraViews:
-                videoSequences += cv.videoSequences
+                videoSequences.extend(cv.videoSequences)
 else:
     print('No video/site to process')
 
@@ -145,11 +148,33 @@
 
 elif args.process == 'prototype': # motion pattern learning
     # 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
-    objects = {siteId: [] for siteId in siteIds}
-    for vs in videoSequences:
-        print('Loading '+vs.getDatabaseFilename())
-        objects[vs.cameraView.siteIdx] += storage.loadTrajectoriesFromSqlite(str(parentPath/vs.getDatabaseFilename()), args.trajectoryType, args.nTrajectories, timeStep = args.positionSubsamplingRate)
+    # by default, load all objects, learn and then assign (BUT not save the assignments)
+    for site in sites:
+        objects = {}
+        object2VideoSequences = {}
+        for cv in site.cameraViews:
+            for vs in cv.videoSequences:
+                print('Loading '+vs.getDatabaseFilename())
+                objects[vs.idx] = storage.loadTrajectoriesFromSqlite(str(parentPath/vs.getDatabaseFilename()), args.trajectoryType, args.nTrajectories, timeStep = args.positionSubsamplingRate, nLongestFeaturesPerObject = args.nLongestFeaturesPerObject)
+                if args.trajectoryType == 'object' and args.nLongestFeaturesPerObject is not None:
+                    objectsWithFeatures = objects[vs.idx]
+                    objects[vs.idx] = [f for o in objectsWithFeatures for f in o.getFeatures()]
+                    prototypeType = 'feature'
+                else:
+                    prototypeType = args.trajectoryType
+                for obj in objects[vs.idx]:
+                    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]
+        prototypeIndices, labels = processing.learnAssignMotionPatterns(True, True, allobjects, similarities, args.minsimil, 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(outputPrototypeDatabaseFilename, [moving.Prototype(object2VideoSequences[allobjects[i]].getDatabaseFilename(False), allobjects[i].getNum(), prototypeType) for i in prototypeIndices])
 
 
 elif args.process == 'interaction':

--- a/trafficintelligence/processing.py	Thu Jul 05 17:06:40 2018 -0400
+++ b/trafficintelligence/processing.py	Thu Jul 05 17:45:18 2018 -0400
@@ -41,7 +41,7 @@
         if minClusterSize > 0 and removePrototypesAfterAssignment: # use prototypeIndices anyway
             prototypeIndices = assignedPrototypeIndices
     else:
-        labels = None    
+        labels = None
 
     return prototypeIndices, labels