def reify_dataset(self, resource_id):
"""Extracts the REST API arguments from the dataset JSON structure
"""
child = self.get_resource(resource_id)
origin, parent_id = u.get_origin_info(child)
parent = self.get_resource(parent_id)
opts = {"create": {}, "update": {}, "get": {}}
# as two-steps result from a cluster or batch prediction, centroid
# or anomaly score
grandparent = parent
if origin in ['origin_batch_resource', 'cluster']:
if origin == "cluster":
opts['create'].update({"centroid": child['centroid']})
grandparents = u.get_origin_info(parent)
# batch resources have two parents, choose the dataset
if origin == "origin_batch_resource" and \
isinstance(grandparents, list):
for gp_origin, grandparent in grandparents:
if gp_origin == "dataset":
break
else:
_, grandparent = grandparents
grandparent = self.get_resource(grandparent)
# options common to all model types
call = "update" if origin == "origin_batch_resource" else "create"
u.common_dataset_opts(child, grandparent, opts, call=call)
# update options
dataset_defaults = DEFAULTS["dataset"].get("update", {})
for attribute, default_value in dataset_defaults.items():
opts["update"].update(
u.default_setting(child, attribute, *default_value))
# name, exclude automatic naming alternatives
autonames = [u'']
u.non_automatic_name(child, opts, autonames=autonames)
# objective field
resource_fields = Fields({
'resource': child['resource'],
'object': child
})
objective_id = child['objective_field']['id']
preferred_fields = resource_fields.preferred_fields()
# if there's no preferred fields, use the fields structure
if len(preferred_fields.keys()) == 0:
preferred_fields = resource_fields.fields
max_column = sorted([
field['column_number'] for _, field in preferred_fields.items()
if field['optype'] != "text"
],
reverse=True)[0]
objective_column = resource_fields.fields[objective_id][ \
'column_number']
if objective_column != max_column:
opts['create'].update({"objective_field": {"id": objective_id}})
if origin != "origin_batch_resource":
# resize
if (child['size'] != grandparent['size']
and get_resource_type(parent) == 'source'):
opts['create'].update({"size": child['size']})
# generated fields
if child.get('new_fields', None):
new_fields = child['new_fields']
for new_field in new_fields:
new_field['field'] = new_field['generator']
del new_field['generator']
opts['create'].update({"new_fields": new_fields})
u.range_opts(child, grandparent, opts)
# for batch_predictions, batch_clusters, batch_anomalies generated
# datasets, attributes cannot be set at creation time, so we
# must update the resource instead
suffix = None
if origin == "origin_batch_resource":
opts["update"].update(opts["create"])
opts["create"] = {}
suffix = "['object']['output_dataset_resource']"
calls = u.build_calls(resource_id, [parent_id], opts, suffix=suffix)
self.add(resource_id, calls)
def reify_dataset(self, resource_id):
"""Extracts the REST API arguments from the dataset JSON structure
"""
child = self.get_resource(resource_id)
origin, parent_id = u.get_origin_info(child)
parent = self.get_resource(parent_id)
opts = {"create": {}, "update": {}}
# as two-steps result from a cluster or batch prediction, centroid
# or anomaly score
if origin in ["origin_batch_resource", "cluster"]:
if origin == "cluster":
opts["create"].update({"centroid": child["centroid"]})
_, grandparent = u.get_origin_info(parent)
grandparent = self.get_resource(grandparent)
else:
grandparent = parent
# options common to all model types
u.common_dataset_opts(child, grandparent, opts)
# update options
dataset_defaults = DEFAULTS["dataset"].get("update", {})
dataset_defaults.update(COMMON_DEFAULTS.get("update", {}))
for attribute, default_value in dataset_defaults.items():
opts["update"].update(u.default_setting(child, attribute, *default_value))
# name, exclude automatic naming alternatives
autonames = [u""]
suffixes = [
u"filtered",
u"sampled",
u"dataset",
u"extended",
u"- batchprediction",
u"- batchanomalyscore",
u"- batchcentroid",
u"- merged",
]
autonames.extend([u"%s %s" % (grandparent.get("name", ""), suffix) for suffix in suffixes])
autonames.append(u"%s's dataset" % ".".join(parent["name"].split(".")[0:-1]))
autonames.append(u"%s' dataset" % ".".join(parent["name"].split(".")[0:-1]))
autonames.append(u"Cluster %s - %s" % (int(child.get("centroid", "0"), base=16), parent["name"]))
autonames.append(u"Dataset from %s model - segment" % parent["name"])
u.non_automatic_name(child, opts, autonames=autonames)
# objective field
resource_fields = Fields({"resource": child["resource"], "object": child})
objective_id = child["objective_field"]["id"]
preferred_fields = resource_fields.preferred_fields()
max_column = sorted([field["column_number"] for _, field in preferred_fields.items()], reverse=True)[0]
objective_column = resource_fields.fields[objective_id]["column_number"]
if objective_column != max_column:
opts["create"].update({"objective_field": {"id": objective_id}})
# resize
if child["size"] != grandparent["size"] and get_resource_type(parent) == "source":
opts["create"].update({"size": child["size"]})
# generated fields
if child.get("new_fields", None):
new_fields = child["new_fields"]
for new_field in new_fields:
new_field["field"] = new_field["generator"]
del new_field["generator"]
opts["create"].update({"new_fields": new_fields})
u.range_opts(child, grandparent, opts)
calls = u.build_calls(resource_id, [parent_id], opts)
self.add(resource_id, calls)
def reify_dataset(self, resource_id):
"""Extracts the REST API arguments from the dataset JSON structure
"""
child = self.get_resource(resource_id)
origin, parent_id = u.get_origin_info(child)
parent = self.get_resource(parent_id)
opts = {"create": {}, "update": {}, "get": {}}
# as two-steps result from a cluster or batch prediction, centroid
# or anomaly score
grandparent = parent
if origin in ['origin_batch_resource', 'cluster']:
if origin == "cluster":
opts['create'].update({"centroid": child['centroid']})
grandparents = u.get_origin_info(parent)
# batch resources have two parents, choose the dataset
if origin == "origin_batch_resource" and \
isinstance(grandparents, list):
for gp_origin, grandparent in grandparents:
if gp_origin == "dataset":
break
else:
_, grandparent = grandparents
grandparent = self.get_resource(grandparent)
# options common to all model types
call = "update" if origin == "origin_batch_resource" else "create"
u.common_dataset_opts(child, grandparent, opts, call=call)
# update options
dataset_defaults = DEFAULTS["dataset"].get("update", {})
for attribute, default_value in dataset_defaults.items():
opts["update"].update(
u.default_setting(child, attribute, *default_value))
# name, exclude automatic naming alternatives
autonames = [u'']
u.non_automatic_name(child, opts, autonames=autonames)
# objective field
resource_fields = Fields(
{'resource': child['resource'], 'object': child})
objective_id = child['objective_field']['id']
preferred_fields = resource_fields.preferred_fields()
# if there's no preferred fields, use the fields structure
if len(preferred_fields.keys()) == 0:
preferred_fields = resource_fields.fields
max_column = sorted([field['column_number']
for _, field in preferred_fields.items()
if field['optype'] != "text"],
reverse=True)[0]
objective_column = resource_fields.fields[objective_id][ \
'column_number']
if objective_column != max_column:
opts['create'].update({"objective_field": {"id": objective_id}})
if origin != "origin_batch_resource":
# resize
if (child['size'] != grandparent['size'] and
get_resource_type(parent) == 'source'):
opts['create'].update({"size": child['size']})
# generated fields
if child.get('new_fields', None):
new_fields = child['new_fields']
for new_field in new_fields:
new_field['field'] = new_field['generator']
del new_field['generator']
opts['create'].update({"new_fields": new_fields})
u.range_opts(child, grandparent, opts)
# for batch_predictions, batch_clusters, batch_anomalies generated
# datasets, attributes cannot be set at creation time, so we
# must update the resource instead
suffix = None
if origin == "origin_batch_resource":
opts["update"].update(opts["create"])
opts["create"] = {}
suffix = "['object']['output_dataset_resource']"
calls = u.build_calls(resource_id, [parent_id], opts, suffix=suffix)
self.add(resource_id, calls)
def reify_dataset(self, resource_id):
"""Extracts the REST API arguments from the dataset JSON structure
"""
child = self.get_resource(resource_id)
origin, parent_id = u.get_origin_info(child)
parent = self.get_resource(parent_id)
opts = {"create": {}, "update": {}}
# as two-steps result from a cluster or batch prediction, centroid
# or anomaly score
if origin in ['origin_batch_resource', 'cluster']:
if origin == "cluster":
opts['create'].update({"centroid": child['centroid']})
_, grandparent = u.get_origin_info(parent)
grandparent = self.get_resource(grandparent)
else:
grandparent = parent
# options common to all model types
u.common_dataset_opts(child, grandparent, opts)
# update options
dataset_defaults = DEFAULTS["dataset"].get("update", {})
dataset_defaults.update(COMMON_DEFAULTS.get("update", {}))
for attribute, default_value in dataset_defaults.items():
opts["update"].update(
u.default_setting(child, attribute, *default_value))
# name, exclude automatic naming alternatives
autonames = [u'']
suffixes = [
u"filtered", u"sampled", u"dataset", u"extended",
u"- batchprediction", u"- batchanomalyscore", u"- batchcentroid",
u"- merged"
]
autonames.extend([
u'%s %s' % (grandparent.get('name', ''), suffix)
for suffix in suffixes
])
autonames.append(u"%s's dataset" %
'.'.join(parent['name'].split('.')[0:-1]))
autonames.append(u"%s' dataset" %
'.'.join(parent['name'].split('.')[0:-1]))
autonames.append(
u"Cluster %s - %s" %
(int(child.get('centroid', "0"), base=16), parent['name']))
autonames.append(u"Dataset from %s model - segment" % parent['name'])
u.non_automatic_name(child, opts, autonames=autonames)
# objective field
resource_fields = Fields({
'resource': child['resource'],
'object': child
})
objective_id = child['objective_field']['id']
preferred_fields = resource_fields.preferred_fields()
max_column = sorted(
[field['column_number'] for _, field in preferred_fields.items()],
reverse=True)[0]
objective_column = resource_fields.fields[objective_id][ \
'column_number']
if objective_column != max_column:
opts['create'].update({"objective_field": {"id": objective_id}})
# resize
if (child['size'] != grandparent['size']
and get_resource_type(parent) == 'source'):
opts['create'].update({"size": child['size']})
# generated fields
if child.get('new_fields', None):
new_fields = child['new_fields']
for new_field in new_fields:
new_field['field'] = new_field['generator']
del new_field['generator']
opts['create'].update({"new_fields": new_fields})
u.range_opts(child, grandparent, opts)
calls = u.build_calls(resource_id, [parent_id], opts)
self.add(resource_id, calls)
