Python featurization Examples

Example #1

File: TestFeaturization.py Project: runt18/e-mission-server

 def testCalculatePoints(self):
     feat = featurization.featurization([])
     self.assertTrue(not feat.data)
     feat = featurization.featurization(None)
     self.assertTrue(not feat.data)
     trip = Trip(None, None, None, None, None, None, None, None)
     data = [trip]
     try:
         feat = featurization.featurization(data)
     except AttributeError:
         self.assertTrue(True)
     except Exception:
         self.assertTrue(False)
     feat = featurization.featurization(self.data)
     self.assertTrue(len(feat.points) == len(feat.data))
     for p in feat.points:
         self.assertTrue(None not in p)

Example #2

File: TestFeaturization.py Project: e-mission/e-mission-server

 def testCalculatePoints(self):
     feat = featurization.featurization([])
     self.assertTrue(not feat.data)
     feat = featurization.featurization(None)
     self.assertTrue(not feat.data)
     trip = etatc._createTripEntry(self, None, None, None, None)
     data = [trip]
     try:
         feat = featurization.featurization(data)
     except AttributeError:
         self.assertTrue(True)
     except Exception:
         self.assertTrue(False)
     feat = featurization.featurization(self.data)
     self.assertTrue(len(feat.points) == len(feat.data))
     for p in feat.points:
         self.assertTrue(None not in p)

Example #3

File: cluster_pipeline.py Project: runt18/e-mission-server

def cluster(data, bins, old=True):
    if not data:
        return 0, [], []
    feat = featurization.featurization(data, old=old)
    min = bins
    max = int(math.ceil(1.5 * bins))
    feat.cluster(min_clusters=min, max_clusters=max)
    logging.debug('number of clusters: %d' % feat.clusters)
    return feat.clusters, feat.labels, feat.data

Example #4

def cluster(data, bins):
    if not data:
        return 0, [], []
    feat = featurization.featurization(data)
    min = bins
    max = int(math.ceil(1.5 * bins))
    feat.cluster(min_clusters=min, max_clusters=max)
    logging.debug('number of clusters: %d' % feat.clusters)
    return feat.clusters, feat.labels, feat.data

Example #5

File: TestFeaturization.py Project: runt18/e-mission-server

 def testCheckClusters(self):
     feat = featurization.featurization(self.data)
     a = feat.check_clusters()
     self.assertTrue(a == None)
     feat.cluster(min_clusters=2, max_clusters=10)
     try:
         feat.check_clusters()
     except Exception:
         self.assertTrue(False)

Example #6

File: TestRepresentatives.py Project: adambrown13/e-mission-server

 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)        

Example #7

File: cluster_pipeline.py Project: samuel-halim95/e-mission-server

def cluster(data, bins):
    if not data:
        return 0, [], []
    feat = featurization.featurization(data)
    min = bins
    max = int(math.ceil(1.5 * bins))
    feat.cluster(min_clusters=min, max_clusters=max)
    print 'number of clusters: ' + str(feat.clusters)
    return feat.clusters, feat.labels, feat.data

Example #8

def cluster(data, nBins):
    logging.debug("Calling cluster(%s, %d)" % (data, nBins))
    if not data:
        return 0, [], []
    feat = featurization.featurization(data)
    min = nBins
    max = int(math.ceil(1.5 * nBins))
    feat.cluster(min_clusters=min, max_clusters=max)
    logging.debug('number of clusters: %d' % feat.clusters)
    return feat.clusters, feat.labels, feat.data, feat.points

Example #9

File: TestRepresentatives.py Project: runt18/e-mission-server

 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)

Example #10

File: TestFeaturization.py Project: runt18/e-mission-server

    def testCluster(self):
        feat = featurization.featurization(self.data)
        feat.cluster(min_clusters=2, max_clusters=10)
        self.assertTrue(len(feat.labels) == len(feat.points))
        self.assertTrue(feat.clusters == len(set(feat.labels)))
        a = feat.cluster(name='kmeans', min_clusters=5, max_clusters=20)
        self.assertTrue(len(feat.labels) == len(feat.points))
        self.assertTrue(feat.clusters == len(set(feat.labels)))
        b = feat.cluster(name='nonname', min_clusters=5, max_clusters=20)
        self.assertTrue(a == b) #defaults to kmeans with invalid clustering method
        feat.cluster(min_clusters=len(self.data)+1)
        c = feat.cluster(min_clusters = 0, max_clusters=20)
        d = feat.cluster(min_clusters = 2, max_clusters=20)
        self.assertTrue(c == d)
        try:
            feat.cluster(min_clusters = 10, max_clusters=2)
        except ValueError:
            self.assertTrue(True)
        except Exception:
            self.assertTrue(False)

        data = []
        start = Coordinate(47,-122)
        end = Coordinate(47,-123)
        for i in range(10):
            now = datetime.datetime.now()
            a = Trip(None, None, None, None, now, now, start, end)
            data.append(a)
        start = Coordinate(41,-74)
        end = Coordinate(42, -74)
        for i in range(10):
            now = datetime.datetime.now()
            a = Trip(None, None, None, None, now, now, start, end)
            data.append(a)
        feat = featurization.featurization(data)
        feat.cluster()
        self.assertTrue(len(set(feat.labels)) == 2)

Example #11

File: TestFeaturization.py Project: valin1/e-mission-server

    def testCluster(self):
        feat = featurization.featurization(self.data)
        feat.cluster(min_clusters=2, max_clusters=10)
        self.assertTrue(len(feat.labels) == len(feat.points))
        self.assertTrue(feat.clusters == len(set(feat.labels)))
        a = feat.cluster(name='kmeans', min_clusters=5, max_clusters=20)
        self.assertTrue(len(feat.labels) == len(feat.points))
        self.assertTrue(feat.clusters == len(set(feat.labels)))
        b = feat.cluster(name='nonname', min_clusters=5, max_clusters=20)
        self.assertTrue(
            a == b)  #defaults to kmeans with invalid clustering method
        feat.cluster(min_clusters=len(self.data) + 1)
        c = feat.cluster(min_clusters=0, max_clusters=20)
        d = feat.cluster(min_clusters=2, max_clusters=20)
        self.assertTrue(c == d)
        try:
            feat.cluster(min_clusters=10, max_clusters=2)
        except ValueError:
            self.assertTrue(True)
        except Exception:
            self.assertTrue(False)

        data = []
        start = [-122, 47]
        end = [-123, 47]
        now = time.time()
        for i in range(10):
            a = etatc._createTripEntry(self, now, now, start, end)
            data.append(a)
        start = [-74, 41]
        end = [-74, 42]
        for i in range(10):
            a = etatc._createTripEntry(self, now, now, start, end)
            data.append(a)
        feat = featurization.featurization(data)
        feat.cluster()
        self.assertTrue(len(set(feat.labels)) == 2)

Example #12

File: TestFeaturization.py Project: e-mission/e-mission-server

    def testCluster(self):
        feat = featurization.featurization(self.data)
        feat.cluster(min_clusters=2, max_clusters=10)
        self.assertTrue(len(feat.labels) == len(feat.points))
        self.assertTrue(feat.clusters == len(set(feat.labels)))
        a = feat.cluster(name='kmeans', min_clusters=5, max_clusters=20)
        self.assertTrue(len(feat.labels) == len(feat.points))
        self.assertTrue(feat.clusters == len(set(feat.labels)))
        b = feat.cluster(name='nonname', min_clusters=5, max_clusters=20)
        self.assertTrue(a == b) #defaults to kmeans with invalid clustering method
        feat.cluster(min_clusters=len(self.data)+1)
        c = feat.cluster(min_clusters = 0, max_clusters=20)
        d = feat.cluster(min_clusters = 2, max_clusters=20)
        self.assertTrue(c == d)
        try:
            feat.cluster(min_clusters = 10, max_clusters=2)
        except ValueError:
            self.assertTrue(True)
        except Exception:
            self.assertTrue(False)

        data = []
        start = [-122, 47]
        end = [-123,47]
        now = time.time()
        for i in range(10):
            a = etatc._createTripEntry(self, now, now, start, end)
            data.append(a)
        start = [-74, 41]
        end = [-74, 42]
        for i in range(10):
            a = etatc._createTripEntry(self, now, now, start, end)
            data.append(a)
        feat = featurization.featurization(data)
        feat.cluster()
        self.assertTrue(len(set(feat.labels)) == 2)

Example #13

File: TestRepresentatives.py Project: juemura/e-mission-server

 def setUp(self):
     etatc._setup(self)
     n = len(self.data)/5
     self.labels = feat.featurization(self.data).cluster(min_clusters=n, max_clusters=n)

Example #14

 def setUp(self):
     etatc._setup(self)
     n = old_div(len(self.data), 5)
     self.labels = feat.featurization(self.data).cluster(min_clusters=n,
                                                         max_clusters=n)