def seed_column_members(data_matrix, row_membership, num_clusters,
num_clusters_per_column):
"""Default column membership seeder ('best')
In case of multiple input ratio matrices, we assume that these
matrices have been combined into data_matrix"""
num_rows = data_matrix.num_rows
num_cols = data_matrix.num_columns
# create a submatrix for each cluster
cscores = np.zeros([data_matrix.num_columns, num_clusters])
for cluster_num in xrange(1, num_clusters + 1):
current_cluster_rows = []
for row_index in xrange(num_rows):
if row_membership[row_index][0] == cluster_num:
current_cluster_rows.append(data_matrix.row_names[row_index])
submatrix = data_matrix.submatrix_by_name(
row_names=current_cluster_rows)
_, scores = scoring.compute_column_scores_submatrix(submatrix)
cscores.T[cluster_num - 1] = -scores
start_time = util.current_millis()
column_members = [
util.rorder(cscores[i], num_clusters_per_column)
for i in xrange(num_cols)
]
elapsed = util.current_millis() - start_time
logging.info("seed column members in %f s.", elapsed % 1000.0)
return column_members
def seed_column_members(data_matrix, row_membership, num_clusters,
num_clusters_per_column):
"""Default column membership seeder ('best')
In case of multiple input ratio matrices, we assume that these
matrices have been combined into data_matrix"""
num_rows = data_matrix.num_rows()
num_cols = data_matrix.num_columns()
# create a submatrix for each cluster
column_scores = []
for cluster_num in xrange(1, num_clusters + 1):
current_cluster_rows = []
for row_index in xrange(num_rows):
if row_membership[row_index][0] == cluster_num:
current_cluster_rows.append(data_matrix.row_name(row_index))
submatrix = data_matrix.submatrix_by_name(
row_names=current_cluster_rows)
scores = (-scoring.compute_column_scores_submatrix(submatrix))[0]
column_scores.append(scores)
column_members = []
for column_index in xrange(num_cols):
scores_to_order = []
for row_index in xrange(num_clusters):
scores_to_order.append(column_scores[row_index][column_index])
column_members.append(order(scores_to_order)[:num_clusters_per_column])
return column_members
def seed_column_members(data_matrix, row_membership, num_clusters,
num_clusters_per_column):
"""Default column membership seeder ('best')
In case of multiple input ratio matrices, we assume that these
matrices have been combined into data_matrix"""
num_rows = data_matrix.num_rows
num_cols = data_matrix.num_columns
# create a submatrix for each cluster
cscores = np.zeros([data_matrix.num_columns, num_clusters])
for cluster_num in xrange(1, num_clusters + 1):
current_cluster_rows = []
for row_index in xrange(num_rows):
if row_membership[row_index][0] == cluster_num:
current_cluster_rows.append(data_matrix.row_names[row_index])
submatrix = data_matrix.submatrix_by_name(
row_names=current_cluster_rows)
_, scores = scoring.compute_column_scores_submatrix(submatrix)
cscores.T[cluster_num - 1] = -scores
start_time = util.current_millis()
column_members = [util.rorder(cscores[i], num_clusters_per_column)
for i in xrange(num_cols)]
elapsed = util.current_millis() - start_time
logging.debug("seed column members in %f s.", elapsed % 1000.0)
return column_members
def seed_column_members(data_matrix, row_membership, num_clusters,
num_clusters_per_column):
"""Default column membership seeder ('best')
In case of multiple input ratio matrices, we assume that these
matrices have been combined into data_matrix"""
num_rows = data_matrix.num_rows
num_cols = data_matrix.num_columns
# create a submatrix for each cluster
column_scores = []
for cluster_num in xrange(1, num_clusters + 1):
current_cluster_rows = []
for row_index in xrange(num_rows):
if row_membership[row_index][0] == cluster_num:
current_cluster_rows.append(data_matrix.row_names[row_index])
submatrix = data_matrix.submatrix_by_name(
row_names=current_cluster_rows)
scores = -(scoring.compute_column_scores_submatrix(submatrix).values)[0]
column_scores.append(scores)
column_members = []
start_time = util.current_millis()
for column_index in xrange(num_cols):
scores_to_order = []
for row_index in xrange(num_clusters):
scores_to_order.append(column_scores[row_index][column_index])
column_members.append(order(scores_to_order)[:num_clusters_per_column])
elapsed = util.current_millis() - start_time
logging.info("seed column members in %f s.", elapsed % 1000.0)
return column_members
def test_compute_column_scores_submatrix(self):
"""tests compute_column_scores_submatrix"""
matrix = dm.DataMatrix(10, 5, ['R1', 'R2', 'R3', 'R4', 'R5', 'R6',
'R7', 'R8', 'R9', 'R10'],
['C1', 'C2', 'C3', 'C4', 'C5'],
MATRIX1)
result = scoring.compute_column_scores_submatrix(matrix)
scores = result.values[0]
self.assertEqual(5, len(scores))
self.assertAlmostEqual(0.03085775, scores[0])
self.assertAlmostEqual(0.05290099, scores[1])
self.assertAlmostEqual(0.05277032, scores[2])
self.assertAlmostEqual(0.00358045, scores[3])
self.assertAlmostEqual(0.03948821, scores[4])
