def test_parse_vector(self):
a = DenseVector([3, 4, 6, 7])
self.assertTrue(str(a), '[3.0,4.0,6.0,7.0]')
self.assertTrue(Vectors.parse(str(a)), a)
a = SparseVector(4, [0, 2], [3, 4])
self.assertTrue(str(a), '(4,[0,2],[3.0,4.0])')
self.assertTrue(Vectors.parse(str(a)), a)
a = SparseVector(10, [0, 1], [4, 5])
self.assertTrue(SparseVector.parse(' (10, [0,1 ],[ 4.0,5.0] )'), a)
def test_parse_vector(self):
a = DenseVector([3, 4, 6, 7])
self.assertTrue(str(a), '[3.0,4.0,6.0,7.0]')
self.assertTrue(Vectors.parse(str(a)), a)
a = SparseVector(4, [0, 2], [3, 4])
self.assertTrue(str(a), '(4,[0,2],[3.0,4.0])')
self.assertTrue(Vectors.parse(str(a)), a)
a = SparseVector(10, [0, 1], [4, 5])
self.assertTrue(SparseVector.parse(' (10, [0,1 ],[ 4.0,5.0] )'), a)
def kmeansInitialClusters(dataset):
model = KMeansModel(CENTER_VECTORS)
vectorsRdd = dataset.rdd.map(lambda data: Vectors.parse(Vectors.stringify(data['features'])))
trainedModel = KMeans.train(vectorsRdd, 4, maxIterations=1000, initialModel=model)
result=[]
for d in dataset.collect():
entry = {}
entry["features"] = d["features"]
entry["prediction"] = trainedModel.predict(Vectors.parse(Vectors.stringify(d['features'])))
entry["label"] = d['label']
result.append(entry)
plotDiversitySizeClustering(result, CENTERS, "Size", "Diversity", "Song Analysis by Size and Diversity with Initial Clusters")
centroidArtistSongCount(result, CENTERS)
def test_parse_vector(self):
a = DenseVector([])
self.assertEqual(str(a), "[]")
self.assertEqual(Vectors.parse(str(a)), a)
a = DenseVector([3, 4, 6, 7])
self.assertEqual(str(a), "[3.0,4.0,6.0,7.0]")
self.assertEqual(Vectors.parse(str(a)), a)
a = SparseVector(4, [], [])
self.assertEqual(str(a), "(4,[],[])")
self.assertEqual(SparseVector.parse(str(a)), a)
a = SparseVector(4, [0, 2], [3, 4])
self.assertEqual(str(a), "(4,[0,2],[3.0,4.0])")
self.assertEqual(Vectors.parse(str(a)), a)
a = SparseVector(10, [0, 1], [4, 5])
self.assertEqual(SparseVector.parse(" (10, [0,1 ],[ 4.0,5.0] )"), a)
