def get_fusion_resource(self, fusion):
"""Extracts the fusion resource info. The fusion argument can be
- a path to a local file
- an fusion id
"""
# the string can be a path to a JSON file
if isinstance(fusion, basestring):
try:
with open(fusion) as fusion_file:
fusion = json.load(fusion_file)
self.resource_id = get_fusion_id(fusion)
if self.resource_id is None:
raise ValueError("The JSON file does not seem"
" to contain a valid BigML fusion"
" representation.")
except IOError:
# if it is not a path, it can be an fusion id
self.resource_id = get_fusion_id(fusion)
if self.resource_id is None:
if fusion.find('fusion/') > -1:
raise Exception(
self.api.error_message(fusion,
resource_type='fusion',
method='get'))
else:
raise IOError("Failed to open the expected JSON file"
" at %s" % fusion)
except ValueError:
raise ValueError("Failed to interpret %s."
" JSON file expected.")
if not isinstance(fusion, dict):
fusion = retrieve_resource(self.api, self.resource_id,
no_check_fields=False)
return fusion
def __init__(self, fusion, api=None, max_models=None, cache_get=None):
if use_cache(cache_get):
# using a cache to store the model attributes
self.__dict__ = load(get_fusion_id(fusion), cache_get)
self.api = get_api_connection(api)
return
self.resource_id = None
self.models_ids = None
self.objective_id = None
self.distribution = None
self.models_splits = []
self.cache_get = None
self.regression = False
self.fields = None
self.class_names = None
self.importance = {}
self.api = get_api_connection(api)
self.resource_id, fusion = get_resource_dict( \
fusion, "fusion", api=self.api)
if 'object' in fusion:
fusion = fusion.get('object', {})
self.model_ids, self.weights = get_models_weight( \
fusion['models'])
model_types = [get_resource_type(model) for model in self.model_ids]
for model_type in model_types:
if model_type not in LOCAL_SUPERVISED:
raise ValueError("The resource %s has not an allowed"
" supervised model type." % model_type)
self.importance = fusion.get('importance', [])
self.missing_numerics = fusion.get('missing_numerics', True)
if fusion.get('fusion'):
self.fields = fusion.get( \
'fusion', {}).get("fields")
self.objective_id = fusion.get("objective_field")
self.input_fields = fusion.get("input_fields")
number_of_models = len(self.model_ids)
# Downloading the model information to cache it
if self.api.storage is not None or cache_get is not None:
for model_id in self.model_ids:
if get_resource_type(model_id) == "fusion":
Fusion(model_id, api=self.api, cache_get=cache_get)
else:
SupervisedModel(model_id,
api=self.api,
cache_get=cache_get)
if max_models is None:
self.models_splits = [self.model_ids]
else:
self.models_splits = [
self.model_ids[index:(index + max_models)]
for index in range(0, number_of_models, max_models)
]
if self.fields:
add_distribution(self)
summary = self.fields[self.objective_id]['summary']
if 'bins' in summary:
distribution = summary['bins']
elif 'counts' in summary:
distribution = summary['counts']
elif 'categories' in summary:
distribution = summary['categories']
else:
distribution = []
self.distribution = distribution
self.regression = \
self.fields[self.objective_id].get('optype') == NUMERIC
if not self.regression:
objective_field = self.fields[self.objective_id]
categories = objective_field['summary']['categories']
classes = [category[0] for category in categories]
self.class_names = sorted(classes)
self.objective_categories = [category for \
category, _ in self.fields[self.objective_id][ \
"summary"]["categories"]]
ModelFields.__init__( \
self, self.fields,
objective_id=self.objective_id)
def __init__(self, fusion, api=None, max_models=None):
if api is None:
self.api = BigML(storage=STORAGE)
else:
self.api = api
self.resource_id = None
self.models_ids = None
self.objective_id = None
self.distribution = None
self.models_splits = []
self.cache_get = None
self.regression = False
self.fields = None
self.class_names = None
self.importance = {}
fusion = self.get_fusion_resource(fusion)
self.resource_id = get_fusion_id(fusion)
if 'object' in fusion:
fusion = fusion.get('object', {})
models = fusion['models']
self.model_ids = models
model_types = [get_resource_type(model) for model in models]
for model_type in model_types:
if model_type not in LOCAL_SUPERVISED:
raise ValueError("The resource %s has not an allowed"
" supervised model type.")
self.importance = fusion.get('importance', [])
self.model_ids = models
if fusion.get('fusion'):
self.fields = fusion.get( \
'fusion', {}).get("fields")
self.objective_id = fusion.get("objective_field")
number_of_models = len(models)
if max_models is None:
self.models_splits = [models]
else:
self.models_splits = [
models[index:(index + max_models)]
for index in range(0, number_of_models, max_models)
]
if self.fields:
summary = self.fields[self.objective_id]['summary']
if 'bins' in summary:
distribution = summary['bins']
elif 'counts' in summary:
distribution = summary['counts']
elif 'categories' in summary:
distribution = summary['categories']
else:
distribution = []
self.distribution = distribution
self.regression = \
self.fields[self.objective_id].get('optype') == 'numeric'
if not self.regression:
objective_field = self.fields[self.objective_id]
categories = objective_field['summary']['categories']
classes = [category[0] for category in categories]
self.class_names = sorted(classes)
self.objective_categories = [category for \
category, _ in self.fields[self.objective_id][ \
"summary"]["categories"]]
ModelFields.__init__( \
self, self.fields,
objective_id=self.objective_id)