def analyzeDataClusters():
regex = 'cafe'
neighborLocationExtractionMethod = NeighborLocationsSelection.N_LOCATIONS
inputFile = checkinSequenceLocationRegexAnalysisFolder+neighborLocationExtractionMethod+'/'+regex
for line in FileIO.iterateJsonFromFile(inputFile):
if line['parameters']['checkinsWindow']==10:
for location, data in line['locations'].iteritems():
# data = line['locations']['41.895 -87.623']
if isWithinBoundingBox(getLocationFromLid(location), us_boundary):
print venuesCollection.find_one({'lid': location})['n'], location,'\n'
for l, _ in data['clusters'][:5]:
print [i[0] for i in l]
print '\n ********** \n'
def getKMLForCluster(cluster):
clusterToYield = []
if len(cluster)>3:
for lid in cluster:
title = venuesCollection.find_one({'lid':lid})
if title!=None: clusterToYield.append((getLocationFromLid(lid), unicode(title['n']).encode("utf-8")))
else: clusterToYield.append((getLocationFromLid(lid), ''))
return clusterToYield
def getRandomLocationNames(file, **conf):
data = defaultdict(list)
for d in FileIO.iterateJsonFromFile(file): data[d['location_db_mad']].append(d['location'])
for k in sorted(data):
print k,
for i in range(5):
venue = venuesCollection.find_one({'lid':random.choice(data[k])})
if venue: print unicode(venue['n']).encode("utf-8")+', ',
print
def addCheckinSequenceToDB():
count = 1
for i in FileIO.iterateJsonFromFile(checkinSequenceGraphLocationsFile):
title = ''
lidInfo = venuesCollection.find_one({'lid': i['lid']}, ['n'])
if lidInfo: title = lidInfo['n']
print count, len(i['checkins'])
count+=1
checkinSequenceLocationsCollection.insert({'_id': i['lid'], 'e': i['edges'], 'c': i['checkins'], 'n': title})
def writeLocationToUserMap(place):
name, boundary = place['name'], place['boundary']
GeneralMethods.runCommand('rm -rf %s'%placesLocationToUserMapFile%name)
for location in filteredLocationToUserAndTimeMapIterator(minLocationsTheUserHasCheckedin, minUniqueUsersCheckedInTheLocation, inputFile=locationToUserAndExactTimeMapFile):
lid=getLocationFromLid(location['location'])
if isWithinBoundingBox(lid, boundary):
location['categories'] = ''; location['tags'] = ''; location['name']=''
title = venuesCollection.find_one({'lid':location['location']})
if title: location['name'] = unicode(title['n']).encode("utf-8")
meta = venuesMetaDataCollection.find_one({'_id':location['location']})
if meta: location['categories'] = unicode(meta['c']).encode("utf-8"); location['tags'] = unicode(meta['t']).encode("utf-8")
for user in location['users'].keys()[:]: location['users'][str(user)]=location['users'][user]; del location['users'][user]
location['noOfCheckins']=sum([len(epochs) for user, userVector in location['users'].iteritems() for day, dayVector in userVector.iteritems() for db, epochs in dayVector.iteritems()])
if location['noOfCheckins']>place.get('minLocationCheckins',0): FileIO.writeToFileAsJson(location, placesLocationToUserMapFile%name)
def plotLocationDistribution():
'''Types of locations seen:
=> Locations where different people have to be at same time: Example office, pub
=> Locations that different people choose to go at different times: cafe+party place
Big cluster suggests most people who come to a location go to similar locations (implies similar people).
Their mean suggests the most poplar time to go to that location.
'''
def scale(val): return (val*4)+2#val*2*4+2
for location in FileIO.iterateJsonFromFile(locationClustersFile):
if 'clustering' in location:
classes, classDistribution = getDataDistribution(location['clustering'][1].values())
mu, sigma = location['clustering'][2][0], location['clustering'][2][1]
totalUsers = float(sum(classDistribution))
for dist, mu, sigma in zip(classDistribution, mu, sigma):
if sigma==0: sigma=0.15
print dist/totalUsers
plotNorm(dist/totalUsers, scale(mu), scale(sigma))
title = venuesCollection.find_one({'lid':location['location']})
if title!=None: title = unicode(title['n']).encode("utf-8")
else: title = ''
plt.title('%s (%s)'%(title,location['location']))
plt.xlim(xmin=0,xmax=24)
print 'comes here'
plt.show()
def getLocationName(lid):
if lid not in locationNames:
locationObject = venuesCollection.find_one({'lid':lid})
if locationObject: locationNames[lid] = unicode(locationObject['n']).encode("utf-8")
else: locationNames[lid] = ''
return locationNames[lid]
def getLocationName(lid):
object = venuesCollection.find_one({'lid': lid})
if object: return object['n']
else: return lid