def inDegreeSequence(self):
"""
Return a vector of the (in)degree sequence for each vertex.
"""
A = self.nativeAdjacencyMatrix()
j = spmatrix.ll_mat(self.vList.getNumVertices(), 1)
j[:, 0] = 1
degrees = spmatrix.dot(A, j)
degrees = PysparseMatrix(matrix=degrees)
degrees = numpy.array(degrees.getNumpyArray().ravel(), numpy.int)
return degrees
def inDegreeSequence(self):
"""
Return a vector of the (in)degree sequence for each vertex.
"""
A = self.nativeAdjacencyMatrix()
j = spmatrix.ll_mat(self.vList.getNumVertices(), 1)
j[:, 0] = 1
degrees = spmatrix.dot(A, j)
degrees = PysparseMatrix(matrix=degrees)
degrees = numpy.array(degrees.getNumpyArray().ravel(), numpy.int)
return degrees
def association_matrix_to_similarity_matrix(self,
metric="cosine",
dataset="FREESOUND",
save_sim=False,
training_set=None,
out_name_prefix="",
is_general_recommender=False):
if self.verbose:
print "Loading association matrix and tag names, ids files..."
try:
M = spmatrix.ll_mat_from_mtx(RECOMMENDATION_TMP_DATA_DIR +
dataset + "_ASSOCIATION_MATRIX.mtx")
resource_ids = load(RECOMMENDATION_TMP_DATA_DIR + dataset +
"_RESOURCE_IDS.npy")
tag_names = load(RECOMMENDATION_TMP_DATA_DIR + dataset +
"_TAG_NAMES.npy")
except Exception:
raise Exception(
"Error loading association matrix and tag names, ids data")
if metric not in ['cosine', 'binary', 'coocurrence', 'jaccard']:
raise Exception("Wrong similarity metric specified")
if self.verbose:
print "Computing similarity matrix from a resource subset of the whole association matrix..."
# Get index of resources to train (usable index for M)
resource_id_positions = where(
in1d(resource_ids, training_set, assume_unique=True))[0]
# Matrix multiplication (only taking in account resources in training set and ALL tags)
MM = spmatrix.dot(M[resource_id_positions, :],
M[resource_id_positions, :])
# Get similarity matrix
sim_matrix = spmatrix.ll_mat(MM.shape[0], MM.shape[0])
non_zero_index = MM.keys()
for index in non_zero_index:
if metric == 'cosine':
sim_matrix[index[0], index[1]] = MM[index[0], index[1]] * (
1 / (sqrt(MM[index[0], index[0]]) *
sqrt(MM[index[1], index[1]])))
elif metric == 'coocurrence':
sim_matrix[index[0], index[1]] = MM[index[0], index[1]]
elif metric == 'binary':
sim_matrix[index[0],
index[1]] = MM[index[0], index[1]] / MM[index[0],
index[1]]
elif metric == 'jaccard':
sim_matrix[index[0], index[1]] = MM[index[0], index[1]] * (
1 / (MM[index[0], index[0]] + MM[index[1], index[1]] -
MM[index[0], index[1]]))
# Clean out similarity matrix (clean tags that are not used)
tag_positions = []
for i in range(0, sim_matrix.shape[0]):
if sim_matrix[i, i] != 0.0:
tag_positions.append(i)
# Transform sparse similarity matrix to npy format
sim_matrix_npy = mtx2npy(sim_matrix[tag_positions, tag_positions])
tag_names_sim_matrix = tag_names[tag_positions]
if save_sim:
if not is_general_recommender:
# Save sim
path = RECOMMENDATION_TMP_DATA_DIR + dataset + "_%s_SIMILARITY_MATRIX_" % out_name_prefix + metric + "_SUBSET.npy"
if self.verbose:
print "Saving to " + path + "..."
save(path, sim_matrix_npy)
# Save tag names
path = RECOMMENDATION_TMP_DATA_DIR + dataset + "_%s_SIMILARITY_MATRIX_" % out_name_prefix + metric + "_SUBSET_TAG_NAMES.npy"
if self.verbose:
print "Saving to " + path + "..."
save(path, tag_names_sim_matrix)
else:
# Save sim
path = RECOMMENDATION_TMP_DATA_DIR + dataset + "_SIMILARITY_MATRIX_" + metric + ".npy"
if self.verbose:
print "Saving to " + path + "..."
save(path, sim_matrix_npy)
# Save tag names
path = RECOMMENDATION_TMP_DATA_DIR + dataset + "_SIMILARITY_MATRIX_" + metric + "_TAG_NAMES.npy"
if self.verbose:
print "Saving to " + path + "..."
save(path, tag_names_sim_matrix)
return {
'SIMILARITY_MATRIX': sim_matrix_npy,
'TAG_NAMES': tag_names_sim_matrix
}
def association_matrix_to_similarity_matrix(self,
metric="cosine",
dataset="FREESOUND",
save_sim=False,
training_set=None,
out_name_prefix="",
is_general_recommender=False):
if self.verbose:
print "Loading association matrix and tag names, ids files..."
try:
M = spmatrix.ll_mat_from_mtx(RECOMMENDATION_TMP_DATA_DIR + dataset + "_ASSOCIATION_MATRIX.mtx")
resource_ids = load(RECOMMENDATION_TMP_DATA_DIR + dataset + "_RESOURCE_IDS.npy")
tag_names = load(RECOMMENDATION_TMP_DATA_DIR + dataset + "_TAG_NAMES.npy")
except Exception:
raise Exception("Error loading association matrix and tag names, ids data")
if metric not in ['cosine', 'binary', 'coocurrence', 'jaccard']:
raise Exception("Wrong similarity metric specified")
if self.verbose:
print "Computing similarity matrix from a resource subset of the whole association matrix..."
# Get index of resources to train (usable index for M)
resource_id_positions = where(in1d(resource_ids, training_set, assume_unique=True))[0]
# Matrix multiplication (only taking in account resources in training set and ALL tags)
MM = spmatrix.dot(M[resource_id_positions, :], M[resource_id_positions, :])
# Get similarity matrix
sim_matrix = spmatrix.ll_mat(MM.shape[0],MM.shape[0])
non_zero_index = MM.keys()
for index in non_zero_index:
if metric == 'cosine':
sim_matrix[index[0], index[1]] = MM[index[0], index[1]] * (1 / (sqrt(MM[index[0], index[0]]) * sqrt(MM[index[1], index[1]])))
elif metric == 'coocurrence':
sim_matrix[index[0], index[1]] = MM[index[0], index[1]]
elif metric == 'binary':
sim_matrix[index[0], index[1]] = MM[index[0], index[1]]/MM[index[0], index[1]]
elif metric == 'jaccard':
sim_matrix[index[0], index[1]] = MM[index[0], index[1]] * (1 / (MM[index[0], index[0]] + MM[index[1], index[1]] - MM[index[0], index[1]]))
# Clean out similarity matrix (clean tags that are not used)
tag_positions = []
for i in range(0, sim_matrix.shape[0]):
if sim_matrix[i, i] != 0.0:
tag_positions.append(i)
# Transform sparse similarity matrix to npy format
sim_matrix_npy = mtx2npy(sim_matrix[tag_positions,tag_positions])
tag_names_sim_matrix = tag_names[tag_positions]
if save_sim:
if not is_general_recommender:
# Save sim
path = RECOMMENDATION_TMP_DATA_DIR + dataset + "_%s_SIMILARITY_MATRIX_" % out_name_prefix + metric + "_SUBSET.npy"
if self.verbose:
print "Saving to " + path + "..."
save(path, sim_matrix_npy)
# Save tag names
path = RECOMMENDATION_TMP_DATA_DIR + dataset + "_%s_SIMILARITY_MATRIX_" % out_name_prefix + metric + "_SUBSET_TAG_NAMES.npy"
if self.verbose:
print "Saving to " + path + "..."
save(path, tag_names_sim_matrix)
else:
# Save sim
path = RECOMMENDATION_TMP_DATA_DIR + dataset + "_SIMILARITY_MATRIX_" + metric + ".npy"
if self.verbose:
print "Saving to " + path + "..."
save(path, sim_matrix_npy)
# Save tag names
path = RECOMMENDATION_TMP_DATA_DIR + dataset + "_SIMILARITY_MATRIX_" + metric + "_TAG_NAMES.npy"
if self.verbose:
print "Saving to " + path + "..."
save(path, tag_names_sim_matrix)
return {'SIMILARITY_MATRIX': sim_matrix_npy, 'TAG_NAMES': tag_names_sim_matrix}
traceback.print_exc()
try:
T[5:9, 4:10] = A[5:9, 4:10]
except:
traceback.print_exc()
print 'Matrix multiplications'
printMatrix(spmatrix.matrixmultiply(I, A))
printMatrix(spmatrix.matrixmultiply(Is, A))
printMatrix(spmatrix.matrixmultiply(O, O))
printMatrix(spmatrix.matrixmultiply(Os, O))
print 'Dot product'
printMatrix(spmatrix.dot(I, A))
print 'Matrix export'
A[:4, :4].export_mtx('A.mtx', 3)
As[:4, :4].export_mtx('As.mtx', 3)
print open('A.mtx').read()
print open('As.mtx').read()
print 'Matrix import'
printMatrix(spmatrix.ll_mat_from_mtx('A.mtx'))
printMatrix(spmatrix.ll_mat_from_mtx('As.mtx'))
print 'Conversion to CSR'
print A[:4, :4]
print A[:4, :4].to_csr()
traceback.print_exc()
try:
T[5:9, 4:10] = A[5:9, 4:10]
except:
traceback.print_exc()
print 'Matrix multiplications'
printMatrix(spmatrix.matrixmultiply(I, A))
printMatrix(spmatrix.matrixmultiply(Is, A))
printMatrix(spmatrix.matrixmultiply(O, O))
printMatrix(spmatrix.matrixmultiply(Os, O))
print 'Dot product'
printMatrix(spmatrix.dot(I, A))
print 'Matrix export'
A[:4,:4].export_mtx('A.mtx', 3)
As[:4,:4].export_mtx('As.mtx', 3)
print open('A.mtx').read()
print open('As.mtx').read()
print 'Matrix import'
printMatrix(spmatrix.ll_mat_from_mtx('A.mtx'))
printMatrix(spmatrix.ll_mat_from_mtx('As.mtx'))
print 'Conversion to CSR'
print A[:4,:4]
print A[:4,:4].to_csr()