def getLocationsCheckinDistribution(place):
checkinDistribution = {}
for location in locationToUserMapIterator(place):
checkinDistribution[location['location']]=sum([len(epochs) for user, userVector in location['users'].iteritems() for day, dayVector in userVector.iteritems() for db, epochs in dayVector.iteritems()])
dataX, dataY = getDataDistribution(checkinDistribution.values())
plt.loglog(dataX,dataY)
outputFile = placesAnalysisFolder%place['name']+'locationsCheckinDistribution.png'
FileIO.createDirectoryForFile(outputFile)
plt.savefig(outputFile)
def getLocationUserSpecificMads(locationVector):
completeDayBlockDistribution, madOfDayBlockDistributionForUsers = [], []
for user in locationVector['users']:
dayBlockDistributionForUser = []
for day in locationVector['users'][user]:
dayBlockDistributionForUser+=[int(dayBlock) for dayBlock in locationVector['users'][user][day] for i in range(locationVector['users'][user][day][dayBlock])]
completeDayBlockDistribution+=dayBlockDistributionForUser
madOfDayBlockDistributionForUsers.append(getMAD(dayBlockDistributionForUser) )
dataX, dataY = getDataDistribution(completeDayBlockDistribution)
return getMAD(madOfDayBlockDistributionForUsers), getMAD(completeDayBlockDistribution) , dict((str(x),y) for x,y in zip(dataX, dataY))
def plotLocation(locationName, locationId, locationClustering, dayBlockMeans, dayBlockStandardDeviations, colorMap):
classes, classDistribution = getDataDistribution(locationClustering.values())
mu, sigma = dayBlockMeans, dayBlockStandardDeviations
totalUsers = float(sum(classDistribution))
for dist, mu, sigma, color in zip(classDistribution, mu, sigma, [colorMap[c] for c in classes]):
if sigma==0: sigma=0.15
plotNorm(dist/totalUsers, scale(mu), scale(sigma), color=color)
plt.title('%s (%s)'%(locationName,locationId))
plt.xlim(xmin=0,xmax=24)
# plt.show()
plt.savefig(fileName)
plt.clf()
def plotLocationDistribution(file, **conf):
data = []
scale = conf['scale']
for d in FileIO.iterateJsonFromFile(file): data.append(d['location_db_mad'])
plt.xlabel('locations mad'); plt.ylabel('# of locations')
dataX, dataY = getDataDistribution(data)
print dataX, dataY
plt.semilogy(dataX, dataY, marker='o', color='m')
# plt.xlim(xmin=-0.1, xmax=2.6)
# plt.ylim(ymax=10**6)
locs, labels = plt.xticks()
plt.xticks( locs, [x*2*scale+scale for x in locs] )
plt.legend()
plt.show()
def plotLocationToUserDistribution(file, **conf):
data = defaultdict(list)
scale = conf['scale']
for d in FileIO.iterateJsonFromFile(file): data[d['location_db_mad']].append(d['users_db_mad'])
plt.xlabel('users mad'); plt.ylabel('# of locations')
j=1
for i in sorted(data):
plt.subplot(conf['row'], conf['column'],j)
dataX, dataY = getDataDistribution(data[i])
print i, dataX, dataY
plt.semilogy(dataX, dataY, marker='o', label='%s'%(i*2*scale+scale), color='m')
# plt.xlim(xmin=-0.1, xmax=1.1)
# plt.ylim(ymax=10**6)
# locs, labels = plt.xticks()
# plt.xticks( locs, [1]*len(locs) )
locs, labels = plt.xticks()
print locs
plt.xticks( locs, [x*2*scale+scale for x in locs] )
plt.legend()
j+=1
plt.show()
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 analyzeFrequentLocations(minUserLocations, minCalculatedSupport):
# dataX, dataY = [], []
# for itemset, support in Mahout.iterateFrequentLocationsFromFIMahout(minUserLocations, minCalculatedSupport, yieldSupport=True): dataX.append(len(itemset)), dataY.append(support)
# plt.scatter(dataY, dataX)
# plt.title('%s'%minUserLocations), plt.ylabel('Location itemset length'); plt.xlabel('support')
# plt.savefig('sup_vs_itemset_length_%s.pdf'%minUserLocations)
# values = []
# for locations, support in Mahout.iterateFrequentLocationsFromFIMahout(minUserLocations, minCalculatedSupport, yieldSupport=True): values.append(support)
# dataX,dataY = getDataDistribution(values)
# plt.loglog(dataX, dataY)
# plt.title('%s'%minUserLocations), plt.ylabel('Count'); plt.xlabel('support')
# plt.savefig('sup_distribution_%s.pdf'%minUserLocations)
values = []
for itemset, support in Mahout.iterateFrequentLocationsFromFIMahout(
minUserLocations, minCalculatedSupport, yieldSupport=True
):
values.append(len(itemset))
dataX, dataY = getDataDistribution(values)
plt.loglog(dataX, dataY)
plt.title("%s" % minUserLocations), plt.ylabel("Count")
plt.xlabel("Location itemset length")
plt.savefig("location_itemsets_distribution_%s.pdf" % minUserLocations)
def plotLocationGraphEdgeDistribution():
dataX, dataY = getDataDistribution(edge['w'] for edge in FileIO.iterateJsonFromFile(locationGraph))
plt.loglog(dataX, dataY)
plt.savefig('%s.pdf'%'locationGraph')
def plotNoOfClusersPerLocationDistribution(place):
data = [len(location['clusters']) for location in locationClusterMeansIterator(place)]
clusterCount, distribution = getDataDistribution(data)
plt.plot(clusterCount, distribution)
plt.title(getLatexForString('\# of clusters / location (\mu=%0.2f \sigma=%0.2f)'%(np.mean(data), np.std(data))))
plt.show()
