def local_prediction(models, test_reader, output, args, exclude=None):
"""Get local model and issue prediction
"""
# Only one model at present
local_model = SupervisedModel(models[0], api=args.retrieve_api_)
kwargs = {"full": True}
if has_value(args.operating_point_):
kwargs.update({"operating_point": args.operating_point_})
for input_data in test_reader:
input_data_dict = test_reader.dict(input_data, filtering=False)
prediction_info = local_model.predict(input_data_dict, **kwargs)
write_prediction(prediction_info, output, args.prediction_info,
input_data, exclude)
def predict_probability(self, input_data,
missing_strategy=LAST_PREDICTION,
compact=False):
"""For classification models, Predicts a probability for
each possible output class, based on input values. The input
fields must be a dictionary keyed by field name or field ID.
For regressions, the output is a single element list
containing the prediction.
:param input_data: Input data to be predicted
:param missing_strategy: LAST_PREDICTION|PROPORTIONAL missing strategy
for missing fields
:param compact: If False, prediction is returned as a list of maps, one
per class, with the keys "prediction" and "probability"
mapped to the name of the class and it's probability,
respectively. If True, returns a list of probabilities
ordered by the sorted order of the class names.
"""
votes = MultiVoteList([])
if not self.missing_numerics:
check_no_missing_numerics(input_data, self.fields)
for models_split in self.models_splits:
models = []
for model in models_split:
if get_resource_type(model) == "fusion":
models.append(Fusion(model, api=self.api))
else:
models.append(SupervisedModel(model, api=self.api))
votes_split = []
for model in models:
try:
prediction = model.predict_probability( \
input_data,
missing_strategy=missing_strategy,
compact=True)
except ValueError:
# logistic regressions can raise this error if they
# have missing_numerics=False and some numeric missings
# are found
continue
if self.regression:
prediction = prediction[0]
if self.weights is not None:
prediction = self.weigh(prediction, model.resource_id)
else:
if self.weights is not None:
prediction = self.weigh( \
prediction, model.resource_id)
# we need to check that all classes in the fusion
# are also in the composing model
if not self.regression and \
self.class_names != model.class_names:
try:
prediction = rearrange_prediction( \
model.class_names,
self.class_names,
prediction)
except AttributeError:
# class_names should be defined, but just in case
pass
votes_split.append(prediction)
votes.extend(votes_split)
if self.regression:
total_weight = len(votes.predictions) if self.weights is None \
else sum(self.weights)
prediction = sum([prediction for prediction in \
votes.predictions]) / float(total_weight)
if compact:
output = [prediction]
else:
output = {"prediction": prediction}
else:
output = votes.combine_to_distribution(normalize=True)
if not compact:
output = [{'category': class_name,
'probability': probability}
for class_name, probability in
zip(self.class_names, output)]
return output
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 = {}
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.")
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")
number_of_models = len(self.model_ids)
# Downloading the model information to cache it
if self.api.storage is not None:
for model_id in self.model_ids:
if get_resource_type(model_id) == "fusion":
Fusion(model_id, api=self.api)
else:
SupervisedModel(model_id, api=self.api)
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:
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 create_local_supervised_ensemble(step):
world.local_ensemble = SupervisedModel(world.ensemble_id, world.api)
world.local_model = Model(world.local_ensemble.model_ids[0], world.api)
def i_create_a_local_supervised_model(step, model_type=None):
if model_type is None:
model = world.model
else:
model = getattr(world, model_type)
world.local_model = SupervisedModel(model)
