def test_similarityMatrixTopK_sparseToSparse(self):
numRows = 20
TopK = 5
dense_input = np.random.random((numRows, numRows))
sparse_input = sps.csr_matrix(dense_input)
dense_output = similarityMatrixTopK(dense_input,
k=TopK,
forceSparseOutput=False,
inplace=False)
sparse_output = similarityMatrixTopK(sparse_input,
k=TopK,
forceSparseOutput=True)
self.assertTrue(np.allclose(dense_output, sparse_output.todense()),
"sparseToSparse CSR incorrect")
sparse_input = sps.csc_matrix(dense_input)
sparse_output = similarityMatrixTopK(sparse_input,
k=TopK,
forceSparseOutput=True)
self.assertTrue(np.allclose(dense_output, sparse_output.todense()),
"sparseToSparse CSC incorrect")
def updateSimilarityMatrix(self):
if self.topK != False:
if self.sparse_weights:
self.W_sparse = similarityMatrixTopK(self.S.T, k=self.topK, forceSparseOutput=True)
else:
self.W = similarityMatrixTopK(self.S.T, k=self.topK, forceSparseOutput=False)
else:
if self.sparse_weights:
self.W_sparse = sps.csr_matrix(self.S.T)
else:
self.W = self.S.T
def test_similarityMatrixTopK_denseToSparse(self):
numRows = 100
TopK = 20
dense = np.random.random((numRows, numRows))
sparse = similarityMatrixTopK(dense, k=TopK, forceSparseOutput=True)
dense = similarityMatrixTopK(dense, k=TopK, forceSparseOutput=False)
self.assertTrue(
np.equal(dense, sparse.todense()).all(), "denseToSparse incorrect")
def get_S_incremental_and_set_W(self):
self.S_incremental = self.cythonEpoch.get_S()
if self.train_with_sparse_weights:
self.W_sparse = self.S_incremental
else:
if self.sparse_weights:
self.W_sparse = similarityMatrixTopK(self.S_incremental,
k=self.topK)
else:
self.W = self.S_incremental
def test_similarityMatrixTopK_denseToDense(self):
numRows = 100
TopK = 20
dense_input = np.random.random((numRows, numRows))
dense_output = similarityMatrixTopK(dense_input,
k=TopK,
forceSparseOutput=False)
numExpectedNonZeroCells = TopK * numRows
numNonZeroCells = np.sum(dense_output != 0)
self.assertEqual(numExpectedNonZeroCells, numNonZeroCells,
"DenseToDense incorrect")
def test_cosine_similarity_TopK_big(self):
from Base.Cython.cosine_similarity import Cosine_Similarity as Cosine_Similarity_Cython
from Base.cosine_similarity import Compute_Similarity as Cosine_Similarity_Python
from Base.cosine_similarity_parallel import Cosine_Similarity_Parallel as Cosine_Similarity_Parallel
n_items = 500
n_users = 1000
TopK = n_items
data_matrix = sps.random(n_users, n_items, density=0.1)
cosine_similarity = Cosine_Similarity_Cython(data_matrix,
topK=TopK,
normalize=False)
W_dense_Cython = cosine_similarity.compute_similarity().toarray()
cosine_similarity = Cosine_Similarity_Python(data_matrix,
topK=TopK,
normalize=False)
W_dense_Python = cosine_similarity.compute_similarity().toarray()
cosine_similarity = Cosine_Similarity_Parallel(data_matrix,
topK=TopK,
normalize=False)
W_dense_Parallel = cosine_similarity.compute_similarity().toarray()
W_dense_mul = data_matrix.T.dot(data_matrix)
W_dense_mul[np.arange(W_dense_mul.shape[0]),
np.arange(W_dense_mul.shape[0])] = 0.0
W_dense_mul = similarityMatrixTopK(W_dense_mul, k=TopK).toarray()
assert np.allclose(W_dense_Cython, W_dense_mul,
atol=1e-4), "W_sparse_Cython not matching control"
assert np.allclose(W_dense_Python, W_dense_mul,
atol=1e-4), "W_dense_Python not matching control"
assert np.allclose(W_dense_Parallel, W_dense_mul,
atol=1e-4), "W_dense_Parallel not matching control"
def test_cosine_similarity_TopK(self):
from Base.Cython.cosine_similarity import Cosine_Similarity as Cosine_Similarity_Cython
from Base.cosine_similarity import Compute_Similarity as Cosine_Similarity_Python
from Base.cosine_similarity_parallel import Cosine_Similarity_Parallel as Cosine_Similarity_Parallel
TopK = 4
data_matrix = np.array([[1, 1, 0, 1], [0, 1, 1, 1], [1, 0, 1, 0]])
data_matrix = sps.csr_matrix(data_matrix)
cosine_similarity = Cosine_Similarity_Cython(data_matrix,
topK=TopK,
normalize=False)
W_dense_Cython = cosine_similarity.compute_similarity().toarray()
cosine_similarity = Cosine_Similarity_Python(data_matrix,
topK=TopK,
normalize=False)
W_dense_Python = cosine_similarity.compute_similarity().toarray()
cosine_similarity = Cosine_Similarity_Parallel(data_matrix,
topK=TopK,
normalize=False)
W_dense_Parallel = cosine_similarity.compute_similarity().toarray()
W_dense_mul = data_matrix.T.dot(data_matrix)
W_dense_mul[np.arange(W_dense_mul.shape[0]),
np.arange(W_dense_mul.shape[0])] = 0.0
W_dense_mul = similarityMatrixTopK(W_dense_mul, k=TopK).toarray()
assert np.allclose(W_dense_Cython, W_dense_mul,
atol=1e-4), "W_sparse_Cython not matching control"
assert np.allclose(W_dense_Python, W_dense_mul,
atol=1e-4), "W_dense_Python not matching control"
assert np.allclose(W_dense_Parallel, W_dense_mul,
atol=1e-4), "W_dense_Parallel not matching control"