def clusters_processing(datasets,
clusters,
cluster_ids,
api,
args,
resume,
fields=None,
session_file=None,
path=None,
log=None):
"""Creates or retrieves clusters from the input data
"""
# If we have a dataset but not a model, we create the model if the no_model
# flag hasn't been set up.
if datasets and not (has_clusters(args) or args.no_cluster):
cluster_ids = []
clusters = []
# Only 1 cluster per bigmler command at present
number_of_clusters = 1
if resume:
resume, cluster_ids = c.checkpoint(c.are_clusters_created,
path,
number_of_clusters,
debug=args.debug)
if not resume:
message = u.dated("Found %s clusters out of %s. Resuming.\n" %
(len(cluster_ids), number_of_clusters))
u.log_message(message,
log_file=session_file,
console=args.verbosity)
clusters = cluster_ids
number_of_clusters -= len(cluster_ids)
cluster_args = r.set_cluster_args(args,
fields=fields,
cluster_fields=args.cluster_fields_)
clusters, cluster_ids = r.create_clusters(datasets, clusters,
cluster_args, args, api,
path, session_file, log)
# If a cluster is provided, we use it.
elif args.cluster:
cluster_ids = [args.cluster]
clusters = cluster_ids[:]
elif args.clusters or args.cluster_tag:
clusters = cluster_ids[:]
# If we are going to predict we must retrieve the clusters
if cluster_ids and args.test_set:
clusters, cluster_ids = r.get_clusters(clusters, args, api,
session_file)
return clusters, cluster_ids, resume
def clusters_processing(datasets, clusters, cluster_ids,
api, args, resume, fields=None,
session_file=None, path=None,
log=None):
"""Creates or retrieves clusters from the input data
"""
# If we have a dataset but not a model, we create the model if the no_model
# flag hasn't been set up.
if datasets and not (has_clusters(args) or args.no_cluster):
cluster_ids = []
clusters = []
# Only 1 cluster per bigmler command at present
number_of_clusters = 1
if resume:
resume, cluster_ids = c.checkpoint(
c.are_clusters_created, path, number_of_clusters,
debug=args.debug)
if not resume:
message = u.dated("Found %s clusters out of %s. Resuming.\n"
% (len(cluster_ids),
number_of_clusters))
u.log_message(message, log_file=session_file,
console=args.verbosity)
clusters = cluster_ids
number_of_clusters -= len(cluster_ids)
cluster_args = r.set_cluster_args(args,
fields=fields,
cluster_fields=args.cluster_fields_)
clusters, cluster_ids = r.create_clusters(datasets, clusters,
cluster_args, args, api,
path, session_file, log)
# If a cluster is provided, we use it.
elif args.cluster:
cluster_ids = [args.cluster]
clusters = cluster_ids[:]
elif args.clusters or args.cluster_tag:
clusters = cluster_ids[:]
# If we are going to predict we must retrieve the clusters
if cluster_ids and args.test_set:
clusters, cluster_ids = r.get_clusters(clusters, args, api,
session_file)
return clusters, cluster_ids, resume