def testReadDataNew(self):
db = edb.get_trip_new_db()
trips = db.find()
uuids = set()
for t in trips:
if self.testUUID in t:
uuids.add(t[self.testUUID])
if len(uuids) == 0:
uuids.add(None)
self.uuids = uuids
data = cp.read_data(size=10, old=False)
print 'there are ' + str(len(data))
self.assertTrue(len(data) == 10 or len(data) == 0) #len(data)==0 if the test is run on an empty database
uuid = 'baduuid'
data = cp.read_data(uuid=uuid, old=False)
self.assertTrue(not data)
uuid = self.uuids.pop()
data = cp.read_data(uuid=uuid, old=False)
self.assertTrue(len(data) <= db.find({'user_id' : uuid}).count())
self.uuids.add(uuid)
sum = 0
for uuid in self.uuids:
data = cp.read_data(uuid=uuid, old=False)
sum += len(data)
data = cp.read_data(uuid=uuid, old=False)
self.assertTrue(0 <= len(data) <= db.find().count())
print "len(data) = %s" % len(data)
self.assertTrue(len(data) == sum)
def testReadData(self):
db = edb.get_fake_trips_db()
trips = db.find()
uuids = set()
for t in trips:
uuids.add(t['user_id'])
if len(uuids) == 0:
uuids.add(None)
self.uuids = uuids
data = cp.read_data(size=10)
print 'there are ' + str(len(data))
self.assertTrue(len(data) == 10 or len(data) == 0) #len(data)==0 if the test is run on an empty database
uuid = 'baduuid'
data = cp.read_data(uuid=uuid)
self.assertTrue(not data)
uuid = self.uuids.pop()
data = cp.read_data(uuid = uuid)
self.assertTrue(len(data) <= db.find({'user_id' : uuid}).count())
self.uuids.add(uuid)
sum = 0
for uuid in self.uuids:
data = cp.read_data(uuid=uuid)
sum += len(data)
data = cp.read_data()
self.assertTrue(0 <= len(data) <= db.find().count())
self.assertTrue(len(data) == sum)
for d in data:
self.assertTrue(d.trip_start_location and d.trip_end_location and d.start_time)
def testReadData(self):
data = cp.read_data(uuid=self.testUUID)
# Test to make sure something is happening
self.assertTrue(len(data) > 5)
# Test to make sure that the trips are mapped to the correct uuid
bad_data = cp.read_data(uuid="FakeUUID")
self.assertEqual(len(bad_data), 0)
def testReadData(self): data = cp.read_data(uuid=self.testUUID) # Test to make sure something is happening self.assertTrue(len(data) > 5) # Test to make sure that the trips are mapped to the correct uuid bad_data = cp.read_data(uuid="FakeUUID") self.assertEqual(len(bad_data), 0)
def __init__(self, *args, **kwargs):
super(SimilarityTests, self).__init__(*args, **kwargs)
self.data = cp.read_data(size=100)
#if len(self.data) == 0:
# tg.create_fake_trips()
# self.data = cp.read_data(size=100)
print 'there are ' + str(len(self.data))
def __init__(self, *args, **kwargs):
super(SimilarityTests, self).__init__(*args, **kwargs)
self.data = cp.read_data(size=100)
#if len(self.data) == 0:
# tg.create_fake_trips()
# self.data = cp.read_data(size=100)
print 'there are ' + str(len(self.data))
def testClusterToTourModel(self):
data = cp.cluster_to_tour_model(None, None) #for a negative test case
self.assertTrue(not data) #checking that the code doesn't crash on an empty dataset
data = cp.read_data(size=100)#this and the following lines form the positive test case
data, bins = cp.remove_noise(data, 300)
n, labels, data = cp.cluster(data, len(bins))
tour_dict = cp.main()
self.assertTrue(len(tour_dict) <= n)
def setUp(self):
self.testUUID = uuid.uuid4()
self.data = cp.read_data()
#if len(self.data) == 0:
# tg.create_fake_trips()
# self.data = cp.read_data(size=100)
logging.info("Found %s trips" % len(self.data))
self.ts = esta.TimeSeries.get_time_series(self.testUUID)
def _setup(self):
self.data = cp.read_data()
#if len(self.data) == 0:
# tg.create_fake_trips()
# self.data = cp.read_data(size=100)
print 'there are ' + str(len(self.data))
self.testUUID = uuid.uuid4()
self.ts = esta.TimeSeries.get_time_series(self.testUUID)
def _setup(self):
self.data = cp.read_data()
#if len(self.data) == 0:
# tg.create_fake_trips()
# self.data = cp.read_data(size=100)
print 'there are ' + str(len(self.data))
self.testUUID = uuid.uuid4()
self.ts = esta.TimeSeries.get_time_series(self.testUUID)
def setUp(self):
self.testUUID = uuid.uuid4()
self.data = cp.read_data()
#if len(self.data) == 0:
# tg.create_fake_trips()
# self.data = cp.read_data(size=100)
logging.info("Found %s trips" % len(self.data))
self.ts = esta.TimeSeries.get_time_series(self.testUUID)
def __init__(self, *args, **kwargs):
super(RepresentativesTests, self).__init__(*args, **kwargs)
self.data = cp.read_data(size=100)
#if len(self.data) == 0:
# tg.create_fake_trips()
# self.data = cp.read_data(size=100)
print 'there are ' + str(len(self.data))
n = len(self.data)/5
self.labels = feat.featurization(self.data).cluster(min_clusters=n, max_clusters=n)
def __init__(self, *args, **kwargs):
super(RepresentativesTests, self).__init__(*args, **kwargs)
self.data = cp.read_data(size=100)
#if len(self.data) == 0:
# tg.create_fake_trips()
# self.data = cp.read_data(size=100)
print 'there are ' + str(len(self.data))
n = len(self.data) / 5
self.labels = feat.featurization(self.data).cluster(min_clusters=n,
max_clusters=n)
def testClusterToTourModelNew(self):
data = cp.cluster_to_tour_model(None, None, old=False) #for a negative test case
self.assertTrue(not data) #checking that the code doesn't crash on an empty dataset
user_name = "test1"
data = cp.read_data(uuid=self.testUUID, size=100, old=False) #this and the following lines form the positive test case
data, bins = cp.remove_noise(data, 300, old=False)
n, labels, data = cp.cluster(data, len(bins), old=False)
tour_dict = cp.main(uuid=user_name, old=False)
print 'n = %s | len(tour_dict) = %s' % (n, len(tour_dict))
self.assertTrue(len(tour_dict) <= n)
def testClusterNew(self):
data = cp.read_data(uuid=self.testUUID, size=100, old=False) #this and the following lines form the positive test case
clusters, labels, newdata = cp.cluster([], 10, old=False)
self.assertTrue(len(newdata) == clusters == len(labels) == 0) #checking that the code doesn't crash on an empty dataset
clusters, labels, newdata = cp.cluster(data, 10, old=False)
self.assertTrue(clusters == 0 or 10 <= clusters <= 15)
self.assertTrue(len(labels) == len(newdata))
self.assertTrue(cmp(newdata, data) == 0)
data, bins = cp.remove_noise(data, 200, old=False)
clusters, labels, newdata = cp.cluster(data, 20, old=False)
self.assertTrue(clusters == 0 or 20 <= clusters <= 30)
def testCluster(self):
data = cp.read_data(size=100)
clusters, labels, newdata = cp.cluster([], 10)
self.assertTrue(len(newdata) == clusters == len(labels) == 0) #checking that the code doesn't crash on an empty dataset
clusters, labels, newdata = cp.cluster(data, 10)
self.assertTrue(clusters == 0 or 10 <= clusters <= 15)
self.assertTrue(len(labels) == len(newdata))
self.assertTrue(cmp(newdata, data) == 0)
data, bins = cp.remove_noise(data, 200)
clusters, labels, newdata = cp.cluster(data, 20)
self.assertTrue(clusters == 0 or 20 <= clusters <= 30)
def testClusterToTourModel(self): # Test to make sure it doesn't crash on a empty dataset data = cp.cluster_to_tour_model(None, None) self.assertFalse(data) # Test with the real dataset data = cp.read_data(uuid=self.testUUID) data, bins = cp.remove_noise(data, self.RADIUS) n, labels, data = cp.cluster(data, len(bins)) tour_dict = cp.main(uuid=self.testUUID) self.assertTrue(len(tour_dict) <= n)
def testClusterToTourModel(self):
# Test to make sure it doesn't crash on a empty dataset
data = cp.cluster_to_tour_model(None, None)
self.assertFalse(data)
# Test with the real dataset
data = cp.read_data(uuid=self.testUUID)
data, bins = cp.remove_noise(data, self.RADIUS)
n, labels, data = cp.cluster(data, len(bins))
tour_dict = cp.main(uuid=self.testUUID)
self.assertTrue(len(tour_dict) <= n)
def testRemoveNoise(self): data = cp.read_data(uuid=self.testUUID) # Test to make sure the code doesn't break on an empty dataset new_data, bins = cp.remove_noise(None, self.RADIUS) self.assertTrue(len(new_data) == len(bins) == 0) #Test to make sure some or no data was filtered out, but that nothing was added after filtering new_data, bins = cp.remove_noise(None, self.RADIUS) self.assertTrue(len(new_data) <= len(data)) # Make sure there are not more bins than data; that wouldnt make sense self.assertTrue(len(bins) <= len(data))
def testRemoveNoise(self):
data = cp.read_data(uuid=self.testUUID)
# Test to make sure the code doesn't break on an empty dataset
new_data, bins = cp.remove_noise(None, self.RADIUS)
self.assertTrue(len(new_data) == len(bins) == 0)
#Test to make sure some or no data was filtered out, but that nothing was added after filtering
new_data, bins = cp.remove_noise(None, self.RADIUS)
self.assertTrue(len(new_data) <= len(data))
# Make sure there are not more bins than data; that wouldnt make sense
self.assertTrue(len(bins) <= len(data))
def generate_route_clusters(user):
print "In profile, generating route clusters for %s" % user
data = cp.read_data(uuid=user)
data, bins = cp.remove_noise(data, 300)
num_clusters, labels, data = cp.cluster(data, len(bins))
clusters = {}
for i in range(num_clusters):
idx = labels.index(i)
tripid = data[idx].trip_id
clusters[tripid] = []
for j in range(len(labels)):
if labels[j] == i:
clusters[tripid].append(data[j].trip_id)
update_user_routeClusters(user, clusters)
def generate_route_clusters(user):
print "In profile, generating route clusters for %s" % user
data = cp.read_data(uuid=user)
data, bins = cp.remove_noise(data, 300)
num_clusters, labels, data = cp.cluster(data, len(bins))
clusters = {}
for i in range(num_clusters):
idx = labels.index(i)
tripid = data[idx].trip_id
clusters[tripid] = []
for j in range(len(labels)):
if labels[j] == i:
clusters[tripid].append(data[j].trip_id)
update_user_routeClusters(user, clusters)
def main(colors):
data = cp.read_data() #get the data
colors = get_colors(data, colors) #make colors the right format
data, bins = cp.remove_noise(data, .5, 300) #remove noise from data
###### the next few lines are to evaluate the binning
sim = similarity.similarity(data, .5, 300) #create a similarity object
sim.bins = bins #set the bins, since we calculated them above
sim.evaluate_bins() #evaluate them to create the labels
######
colors = update_colors(bins, colors) #update the colors to reflect deleted bins
labels = sim.labels #get labels
evaluate(numpy.array(colors), numpy.array(labels)) #evaluate the bins
clusters, labels, data = cp.cluster(data, len(bins)) #cluster
evaluate(numpy.array(colors), numpy.array(labels)) #evaluate clustering
map_clusters_by_groundtruth(data, labels, colors, map_individuals=False) #map clusters, make last parameter true to map individual clusters
def testCluster(self): data = cp.read_data(uuid=self.testUUID) # Test to make sure empty dataset doesn't crash the program clusters, labels, new_data = cp.cluster([], 10) self.assertTrue(len(new_data) == clusters == len(labels) == 0) # Test to make sure clustering with noise works clusters, labels, new_data = cp.cluster(data, 10) self.assertEqual(len(labels), len(new_data)) self.assertEqual(cmp(new_data, data), 0) # Test to make sure clustering without noise works data, bins = cp.remove_noise(data, self.RADIUS) clusters, labels, new_data = cp.cluster(data, len(bins)) self.assertTrue(clusters == 0 or len(bins) <= clusters <= len(bins) + 10)
def testCluster(self):
data = cp.read_data(uuid=self.testUUID)
# Test to make sure empty dataset doesn't crash the program
clusters, labels, new_data = cp.cluster([], 10)
self.assertTrue(len(new_data) == clusters == len(labels) == 0)
# Test to make sure clustering with noise works
clusters, labels, new_data = cp.cluster(data, 10)
self.assertEqual(len(labels), len(new_data))
self.assertEqual(cmp(new_data, data), 0)
# Test to make sure clustering without noise works
data, bins = cp.remove_noise(data, self.RADIUS)
clusters, labels, new_data = cp.cluster(data, len(bins))
self.assertTrue(clusters == 0
or len(bins) <= clusters <= len(bins) + 10)
def main(colors):
data = cp.read_data() #get the data
colors = get_colors(data, colors) #make colors the right format
data, bins = cp.remove_noise(data, .5, 300) #remove noise from data
###### the next few lines are to evaluate the binning
sim = similarity.similarity(data, .5, 300) #create a similarity object
sim.bins = bins #set the bins, since we calculated them above
sim.evaluate_bins() #evaluate them to create the labels
######
colors = update_colors(bins,
colors) #update the colors to reflect deleted bins
labels = sim.labels #get labels
evaluate(numpy.array(colors), numpy.array(labels)) #evaluate the bins
clusters, labels, data = cp.cluster(data, len(bins)) #cluster
evaluate(numpy.array(colors), numpy.array(labels)) #evaluate clustering
map_clusters_by_groundtruth(
data, labels, colors, map_individuals=False
) #map clusters, make last parameter true to map individual clusters
def testRemoveNoiseNew(self):
data = cp.read_data(uuid=self.testUUID, size=100, old=False) #this and the following lines form the positive test case
newdata, bins = cp.remove_noise(None, 200, old=False)
self.assertTrue(len(newdata) == len(bins) == 0) #checking that the code doesn't crash on an empty dataset
newdata, bins = cp.remove_noise(data, 100, old=False)
self.assertTrue(len(newdata) <= len(data))
def __init__(self, *args, **kwargs):
super(FeaturizationTests, self).__init__(*args, **kwargs)
self.data = cp.read_data(size=100)
print 'there are ' + str(len(self.data))
def setUp(self):
self.data = cp.read_data()
self.testUUID = uuid.uuid4()
self.ts = esta.TimeSeries.get_time_series(self.testUUID)
print('there are ' + str(len(self.data)))
def testRemoveNoise(self):
data = cp.read_data(size=100)
newdata, bins = cp.remove_noise(None, 200)
self.assertTrue(len(newdata) == len(bins) == 0) #checking that the code doesn't crash on an empty dataset
newdata, bins = cp.remove_noise(data, 100)
self.assertTrue(len(newdata) <= len(data))
def setUp(self):
self.data = cp.read_data()
self.testUUID = uuid.uuid4()
self.ts = esta.TimeSeries.get_time_series(self.testUUID)
print('there are ' + str(len(self.data)))