def distances2_to_point(self, reference_point,
list_of_points, by_name=True):
"""Computes the cluster square of the distance to an arbitrary
reference point for a list of points.
reference_point: (dict) The field values for the point used as
reference
list_of_points: (dict|Centroid) The field values or a Centroid object
which contains these values
by_name: (boolean) Set if the dict information is keyed by field name.
Expects IDs as keys otherwise.
"""
# Checks and cleans input_data leaving the fields used in the model
reference_point, _ = self._prepare_for_distance( \
reference_point, by_name=by_name)
# mimic centroid structure to use it in distance computation
point_info = {"center": reference_point}
reference = Centroid(point_info)
distances = []
for point in list_of_points:
centroid_id = None
if isinstance(point, Centroid):
centroid_id = point.centroid_id
point = point.center
by_name = False
clean_point, unique_terms = self._prepare_for_distance( \
point, by_name=by_name)
if clean_point != reference_point:
result = {"data": point, "distance": reference.distance2( \
clean_point, unique_terms, self.scales)}
if centroid_id is not None:
result.update({"centroid_id": centroid_id})
distances.append(result)
return distances
def __init__(self, cluster, api=None):
self.resource_id = None
self.centroids = None
self.cluster_global = None
self.total_ss = None
self.within_ss = None
self.between_ss = None
self.ratio_ss = None
self.critical_value = None
self.k = None
self.scales = {}
self.term_forms = {}
self.tag_clouds = {}
self.term_analysis = {}
self.item_analysis = {}
self.items = {}
if not (isinstance(cluster, dict) and 'resource' in cluster and
cluster['resource'] is not None):
if api is None:
api = BigML(storage=STORAGE)
self.resource_id = get_cluster_id(cluster)
if self.resource_id is None:
raise Exception(api.error_message(cluster,
resource_type='cluster',
method='get'))
query_string = ONLY_MODEL
cluster = retrieve_resource(api, self.resource_id,
query_string=query_string)
else:
self.resource_id = get_cluster_id(cluster)
if 'object' in cluster and isinstance(cluster['object'], dict):
cluster = cluster['object']
if 'clusters' in cluster and isinstance(cluster['clusters'], dict):
status = get_status(cluster)
if 'code' in status and status['code'] == FINISHED:
the_clusters = cluster['clusters']
cluster_global = the_clusters.get('global')
clusters = the_clusters['clusters']
self.centroids = [Centroid(centroid) for centroid in clusters]
self.cluster_global = cluster_global
if cluster_global:
self.cluster_global = Centroid(cluster_global)
# "global" has no "name" and "count" then we set them
self.cluster_global.name = GLOBAL_CLUSTER_LABEL
self.cluster_global.count = \
self.cluster_global.distance['population']
self.total_ss = the_clusters.get('total_ss')
self.within_ss = the_clusters.get('within_ss')
if not self.within_ss:
self.within_ss = sum(centroid.distance['sum_squares'] for
centroid in self.centroids)
self.between_ss = the_clusters.get('between_ss')
self.ratio_ss = the_clusters.get('ratio_ss')
self.critical_value = cluster.get('critical_value', None)
self.k = cluster.get('k')
self.scales.update(cluster['scales'])
self.term_forms = {}
self.tag_clouds = {}
self.term_analysis = {}
fields = cluster['clusters']['fields']
summary_fields = cluster['summary_fields']
for field_id in summary_fields:
del fields[field_id]
for field_id, field in fields.items():
if field['optype'] == 'text':
self.term_forms[field_id] = {}
self.term_forms[field_id].update(field[
'summary']['term_forms'])
self.tag_clouds[field_id] = {}
self.tag_clouds[field_id].update(field[
'summary']['tag_cloud'])
self.term_analysis[field_id] = {}
self.term_analysis[field_id].update(
field['term_analysis'])
if field['optype'] == 'items':
self.items[field_id] = {}
self.items[field_id].update(
dict(field['summary']['items']))
self.item_analysis[field_id] = {}
self.item_analysis[field_id].update(
field['item_analysis'])
ModelFields.__init__(self, fields)
if not all([field_id in self.fields for
field_id in self.scales]):
raise Exception("Some fields are missing"
" to generate a local cluster."
" Please, provide a cluster with"
" the complete list of fields.")
else:
raise Exception("The cluster isn't finished yet")
else:
raise Exception("Cannot create the Cluster instance. Could not"
" find the 'clusters' key in the resource:\n\n%s" %
cluster)
def __init__(self, cluster, api=None):
self.resource_id = None
self.centroids = None
self.cluster_global = None
self.total_ss = None
self.within_ss = None
self.between_ss = None
self.ratio_ss = None
self.critical_value = None
self.input_fields = []
self.summary_fields = []
self.default_numeric_value = None
self.k = None
self.summary_fields = []
self.scales = {}
self.term_forms = {}
self.tag_clouds = {}
self.term_analysis = {}
self.item_analysis = {}
self.items = {}
self.datasets = {}
self.api = api
if self.api is None:
self.api = BigML(storage=STORAGE)
self.resource_id, cluster = get_resource_dict( \
cluster, "cluster", api=api)
if 'object' in cluster and isinstance(cluster['object'], dict):
cluster = cluster['object']
if 'clusters' in cluster and isinstance(cluster['clusters'], dict):
status = get_status(cluster)
if 'code' in status and status['code'] == FINISHED:
self.default_numeric_value = cluster.get( \
"default_numeric_value")
self.summary_fields = cluster.get("summary_fields", [])
self.input_fields = cluster.get("input_fields", [])
self.datasets = cluster.get("cluster_datasets", {})
the_clusters = cluster['clusters']
cluster_global = the_clusters.get('global')
clusters = the_clusters['clusters']
self.centroids = [Centroid(centroid) for centroid in clusters]
self.cluster_global = cluster_global
if cluster_global:
self.cluster_global = Centroid(cluster_global)
# "global" has no "name" and "count" then we set them
self.cluster_global.name = GLOBAL_CLUSTER_LABEL
self.cluster_global.count = \
self.cluster_global.distance['population']
self.total_ss = the_clusters.get('total_ss')
self.within_ss = the_clusters.get('within_ss')
if not self.within_ss:
self.within_ss = sum(centroid.distance['sum_squares']
for centroid in self.centroids)
self.between_ss = the_clusters.get('between_ss')
self.ratio_ss = the_clusters.get('ratio_ss')
self.critical_value = cluster.get('critical_value', None)
self.k = cluster.get('k')
self.scales.update(cluster['scales'])
self.term_forms = {}
self.tag_clouds = {}
self.term_analysis = {}
fields = cluster['clusters']['fields']
summary_fields = cluster['summary_fields']
for field_id in summary_fields:
try:
del fields[field_id]
except KeyError:
# clusters retrieved from API will only contain
# model fields
pass
for field_id, field in fields.items():
if field['optype'] == 'text':
self.term_forms[field_id] = {}
self.term_forms[field_id].update(
field['summary']['term_forms'])
self.tag_clouds[field_id] = {}
self.tag_clouds[field_id].update(
field['summary']['tag_cloud'])
self.term_analysis[field_id] = {}
self.term_analysis[field_id].update(
field['term_analysis'])
if field['optype'] == 'items':
self.items[field_id] = {}
self.items[field_id].update(
dict(field['summary']['items']))
self.item_analysis[field_id] = {}
self.item_analysis[field_id].update(
field['item_analysis'])
missing_tokens = cluster['clusters'].get('missing_tokens')
ModelFields.__init__(self,
fields,
missing_tokens=missing_tokens)
if not all(
[field_id in self.fields for field_id in self.scales]):
raise Exception("Some fields are missing"
" to generate a local cluster."
" Please, provide a cluster with"
" the complete list of fields.")
else:
raise Exception("The cluster isn't finished yet")
else:
raise Exception("Cannot create the Cluster instance. Could not"
" find the 'clusters' key in the resource:\n\n%s" %
cluster)
