def get_best_clusters(scores, n, sort=False):
"""retrieve the n best scored clusters for the given row/column score matrix"""
if sort:
return {scores.row_names[row]: sorted(util.rorder(scores.row_values(row), n))
for row in xrange(scores.num_rows)}
else:
return {scores.row_names[row]: util.rorder(scores.row_values(row), n)
for row in xrange(scores.num_rows)}
def get_best_clusters(scores, n, sort=False):
"""retrieve the n best scored clusters for the given row/column score matrix"""
if sort:
return {
scores.row_names[row]:
sorted(util.rorder(scores.row_values(row), n))
for row in xrange(scores.num_rows)
}
else:
return {
scores.row_names[row]: util.rorder(scores.row_values(row), n)
for row in xrange(scores.num_rows)
}
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
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