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 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 fit(self, topK=100, alpha=0.5):
self.topK = topK
self.alpha = alpha
W = self.Similarity_1 * self.alpha + self.Similarity_2 * (1 -
self.alpha)
self.W_sparse = similarityMatrixTopK(W, k=self.topK).tocsr()
def fit(self, W_sparse, selectTopK=False, topK=100):
assert W_sparse.shape[0] == W_sparse.shape[1],\
"ItemKNNCustomSimilarityRecommender: W_sparse matrice is not square. Current shape is {}".format(W_sparse.shape)
assert self.URM_train.shape[1] == W_sparse.shape[0],\
"ItemKNNCustomSimilarityRecommender: URM_train and W_sparse matrices are not consistent. " \
"The number of columns in URM_train must be equal to the rows in W_sparse. " \
"Current shapes are: URM_train {}, W_sparse {}".format(self.URM_train.shape, W_sparse.shape)
if selectTopK:
W_sparse = similarityMatrixTopK(W_sparse, k=topK)
self.W_sparse = check_matrix(W_sparse, format='csr')
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")