def __init__(self, anomaly, api=None):
self.resource_id = None
self.sample_size = None
self.input_fields = None
self.mean_depth = None
self.expected_mean_depth = None
self.iforest = None
self.top_anomalies = None
self.id_fields = []
if not (isinstance(anomaly, dict) and 'resource' in anomaly and
anomaly['resource'] is not None):
if api is None:
api = BigML(storage=STORAGE)
self.resource_id = get_anomaly_id(anomaly)
if self.resource_id is None:
raise Exception(api.error_message(anomaly,
resource_type='anomaly',
method='get'))
query_string = ONLY_MODEL
anomaly = retrieve_resource(api, self.resource_id,
query_string=query_string)
else:
self.resource_id = get_anomaly_id(anomaly)
if 'object' in anomaly and isinstance(anomaly['object'], dict):
anomaly = anomaly['object']
self.sample_size = anomaly.get('sample_size')
self.input_fields = anomaly.get('input_fields')
self.id_fields = anomaly.get('id_fields', [])
if 'model' in anomaly and isinstance(anomaly['model'], dict):
ModelFields.__init__(self, anomaly['model'].get('fields'))
if ('top_anomalies' in anomaly['model'] and
isinstance(anomaly['model']['top_anomalies'], list)):
self.mean_depth = anomaly['model'].get('mean_depth')
status = get_status(anomaly)
if 'code' in status and status['code'] == FINISHED:
self.expected_mean_depth = None
if self.mean_depth is None or self.sample_size is None:
raise Exception("The anomaly data is not complete. "
"Score will"
" not be available")
else:
default_depth = (
2 * (DEPTH_FACTOR + \
math.log(self.sample_size - 1) - \
(float(self.sample_size - 1) / self.sample_size)))
self.expected_mean_depth = min(self.mean_depth,
default_depth)
iforest = anomaly['model'].get('trees', [])
if iforest:
self.iforest = [
AnomalyTree(anomaly_tree['root'], self.fields)
for anomaly_tree in iforest]
self.top_anomalies = anomaly['model']['top_anomalies']
else:
raise Exception("The anomaly isn't finished yet")
else:
raise Exception("Cannot create the Anomaly instance. Could not"
" find the 'top_anomalies' key in the"
" resource:\n\n%s" % anomaly['model'].keys())
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, cluster, api=None):
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)
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:
clusters = cluster['clusters']['clusters']
self.centroids = [Centroid(centroid) for centroid in clusters]
self.scales = {}
self.scales.update(cluster['scales'])
self.term_forms = {}
self.tag_clouds = {}
self.term_analysis = {}
fields = cluster['clusters']['fields']
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'])
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 get_resource(self, resource_id):
"""Auxiliar method to retrieve resources. The query string ensures
low bandwith usage and full fields structure.
"""
if (resource_id and not isinstance(resource_id, basestring) and
isinstance(resource_id, list)):
resource_id = resource_id[0]
try:
resource = retrieve_resource(self.api, resource_id,
query_string=GET_QS).get('object')
return resource
except ValueError:
sys.exit("We could not reify the resource. Failed to find"
" information for %s in the"
" creation chain." % resource_id)
def __init__(self, model, api=None):
if not (isinstance(model, dict) and "resource" in model and model["resource"] is not None):
if api is None:
api = BigML(storage=STORAGE)
self.resource_id = get_model_id(model)
if self.resource_id is None:
raise Exception(api.error_message(model, resource_type="model", method="get"))
query_string = ONLY_MODEL
model = retrieve_resource(api, self.resource_id, query_string=query_string)
BaseModel.__init__(self, model, api=api)
if "object" in model and isinstance(model["object"], dict):
model = model["object"]
if "model" in model and isinstance(model["model"], dict):
status = get_status(model)
if "code" in status and status["code"] == FINISHED:
distribution = model["model"]["distribution"]["training"]
self.ids_map = {}
self.tree = Tree(
model["model"]["root"],
self.fields,
objective_field=self.objective_id,
root_distribution=distribution,
parent_id=None,
ids_map=self.ids_map,
)
self.terms = {}
else:
raise Exception("The model isn't finished yet")
else:
raise Exception(
"Cannot create the Model instance. Could not" " find the 'model' key in the resource:\n\n%s" % model
)
if self.tree.regression:
try:
import numpy
import scipy
self.regression_ready = True
except ImportError:
self.regression_ready = False
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, topic_model, api=None):
self.resource_id = None
self.stemmer = None
self.seed = None
self.case_sensitive = False
self.bigrams = False
self.ntopics = None
self.temp = None
self.phi = None
self.term_to_index = None
self.topics = []
if not (isinstance(topic_model, dict) and 'resource' in topic_model and
topic_model['resource'] is not None):
if api is None:
api = BigML(storage=STORAGE)
self.resource_id = get_topic_model_id(topic_model)
if self.resource_id is None:
raise Exception(api.error_message(topic_model,
resource_type='topicmodel',
method='get'))
query_string = ONLY_MODEL
topic_model = retrieve_resource(api, self.resource_id,
query_string=query_string)
else:
self.resource_id = get_topic_model_id(topic_model)
if 'object' in topic_model and isinstance(topic_model['object'], dict):
topic_model = topic_model['object']
if 'topic_model' in topic_model \
and isinstance(topic_model['topic_model'], dict):
status = get_status(topic_model)
if 'code' in status and status['code'] == FINISHED:
model = topic_model['topic_model']
self.topics = model['topics']
if 'language' in model and model['language'] is not None:
lang = model['language']
if lang in CODE_TO_NAME:
self.stemmer = Stemmer.Stemmer(CODE_TO_NAME[lang])
self.term_to_index = {self.stem(term): index for index, term
in enumerate(model['termset'])}
self.seed = abs(model['hashed_seed'])
self.case_sensitive = model['case_sensitive']
self.bigrams = model['bigrams']
self.ntopics = len(model['term_topic_assignments'][0])
self.alpha = model['alpha']
self.ktimesalpha = self.ntopics * self.alpha
self.temp = [0] * self.ntopics
assignments = model['term_topic_assignments']
beta = model['beta']
nterms = len(self.term_to_index)
sums = [sum(n[index] for n in assignments) for index
in range(self.ntopics)]
self.phi = [[0 for _ in range(nterms)]
for _ in range(self.ntopics)]
for k in range(self.ntopics):
norm = sums[k] + nterms * beta
for w in range(nterms):
self.phi[k][w] = (assignments[w][k] + beta) / norm
ModelFields.__init__(self, model['fields'])
else:
raise Exception("The topic model isn't finished yet")
else:
raise Exception("Cannot create the topic model instance. Could not"
" find the 'topic_model' key in the"
" resource:\n\n%s" % topic_model)
def __init__(self, logistic_regression, api=None):
self.resource_id = None
self.class_names = None
self.input_fields = []
self.term_forms = {}
self.tag_clouds = {}
self.term_analysis = {}
self.items = {}
self.item_analysis = {}
self.categories = {}
self.coefficients = {}
self.data_field_types = {}
self.field_codings = {}
self.numeric_fields = {}
self.bias = None
self.missing_numerics = None
self.c = None
self.eps = None
self.lr_normalize = None
self.balance_fields = None
self.regularization = None
old_coefficients = False
# checks whether the information needed for local predictions is in
# the first argument
if isinstance(logistic_regression, dict) and \
not check_model_fields(logistic_regression):
# if the fields used by the logistic regression are not
# available, use only ID to retrieve it again
logistic_regression = get_logistic_regression_id( \
logistic_regression)
self.resource_id = logistic_regression
if not (isinstance(logistic_regression, dict)
and 'resource' in logistic_regression
and logistic_regression['resource'] is not None):
if api is None:
api = BigML(storage=STORAGE)
self.resource_id = get_logistic_regression_id(logistic_regression)
if self.resource_id is None:
raise Exception(
api.error_message(logistic_regression,
resource_type='logistic_regression',
method='get'))
query_string = ONLY_MODEL
logistic_regression = retrieve_resource(api,
self.resource_id,
query_string=query_string)
else:
self.resource_id = get_logistic_regression_id(logistic_regression)
if 'object' in logistic_regression and \
isinstance(logistic_regression['object'], dict):
logistic_regression = logistic_regression['object']
try:
self.input_fields = logistic_regression.get("input_fields", [])
self.dataset_field_types = logistic_regression.get(
"dataset_field_types", {})
objective_field = logistic_regression['objective_fields'] if \
logistic_regression['objective_fields'] else \
logistic_regression['objective_field']
except KeyError:
raise ValueError("Failed to find the logistic regression expected "
"JSON structure. Check your arguments.")
if 'logistic_regression' in logistic_regression and \
isinstance(logistic_regression['logistic_regression'], dict):
status = get_status(logistic_regression)
if 'code' in status and status['code'] == FINISHED:
logistic_regression_info = logistic_regression[ \
'logistic_regression']
fields = logistic_regression_info.get('fields', {})
if not self.input_fields:
self.input_fields = [ \
field_id for field_id, _ in
sorted(self.fields.items(),
key=lambda x: x[1].get("column_number"))]
self.coefficients.update(logistic_regression_info.get( \
'coefficients', []))
if not isinstance(self.coefficients.values()[0][0], list):
old_coefficients = True
self.bias = logistic_regression_info.get('bias', True)
self.c = logistic_regression_info.get('c')
self.eps = logistic_regression_info.get('eps')
self.lr_normalize = logistic_regression_info.get('normalize')
self.balance_fields = logistic_regression_info.get( \
'balance_fields')
self.regularization = logistic_regression_info.get( \
'regularization')
self.field_codings = logistic_regression_info.get( \
'field_codings', {})
# old models have no such attribute, so we set it to False in
# this case
self.missing_numerics = logistic_regression_info.get( \
'missing_numerics', False)
objective_id = extract_objective(objective_field)
ModelFields.__init__(self,
fields,
objective_id=objective_id,
terms=True,
categories=True,
numerics=True)
self.field_codings = logistic_regression_info.get( \
'field_codings', {})
self.format_field_codings()
for field_id in self.field_codings:
if field_id not in fields and \
field_id in self.inverted_fields:
self.field_codings.update( \
{self.inverted_fields[field_id]: \
self.field_codings[field_id]})
del self.field_codings[field_id]
if old_coefficients:
self.map_coefficients()
categories = self.fields[self.objective_id].get( \
"summary", {}).get('categories')
if len(self.coefficients.keys()) > len(categories):
self.class_names = [""]
else:
self.class_names = []
self.class_names.extend(
sorted([category[0] for category in categories]))
else:
raise Exception("The logistic regression isn't finished yet")
else:
raise Exception("Cannot create the LogisticRegression instance."
" Could not find the 'logistic_regression' key"
" in the resource:\n\n%s" % logistic_regression)
def __init__(self, time_series, api=None):
self.resource_id = None
self.input_fields = []
self.objective_fields = []
self.all_numeric_objectives = False
self.period = 1
self.ets_models = {}
self.error = None
self.damped_trend = None
self.seasonality = None
self.trend = None
self.time_range = {}
self.field_parameters = {}
self._forecast = {}
# checks whether the information needed for local predictions is in
# the first argument
if isinstance(time_series, dict) and \
not check_model_fields(time_series):
# if the fields used by the logistic regression are not
# available, use only ID to retrieve it again
time_series = get_time_series_id( \
time_series)
self.resource_id = time_series
if not (isinstance(time_series, dict) and 'resource' in time_series
and time_series['resource'] is not None):
if api is None:
api = BigML(storage=STORAGE)
self.resource_id = get_time_series_id(time_series)
if self.resource_id is None:
raise Exception(
api.error_message(time_series,
resource_type='time_series',
method='get'))
query_string = ONLY_MODEL
time_series = retrieve_resource(api,
self.resource_id,
query_string=query_string)
else:
self.resource_id = get_time_series_id(time_series)
if 'object' in time_series and \
isinstance(time_series['object'], dict):
time_series = time_series['object']
try:
self.input_fields = time_series.get("input_fields", [])
self._forecast = time_series.get("forecast")
self.objective_fields = time_series.get("objective_fields", [])
objective_field = time_series['objective_field'] if \
time_series.get('objective_field') else \
time_series['objective_fields']
except KeyError:
raise ValueError("Failed to find the time series expected "
"JSON structure. Check your arguments.")
if 'time_series' in time_series and \
isinstance(time_series['time_series'], dict):
status = get_status(time_series)
if 'code' in status and status['code'] == FINISHED:
time_series_info = time_series['time_series']
fields = time_series_info.get('fields', {})
self.fields = fields
if not self.input_fields:
self.input_fields = [ \
field_id for field_id, _ in
sorted(self.fields.items(),
key=lambda x: x[1].get("column_number"))]
self.all_numeric_objectives = time_series_info.get( \
'all_numeric_objectives')
self.period = time_series_info.get('period', 1)
self.ets_models = time_series_info.get('ets_models', {})
self.error = time_series_info.get('error')
self.damped_trend = time_series_info.get('damped_trend')
self.seasonality = time_series_info.get('seasonality')
self.trend = time_series_info.get('trend')
self.time_range = time_series_info.get('time_range')
self.field_parameters = time_series_info.get( \
'field_parameters', {})
objective_id = extract_objective(objective_field)
ModelFields.__init__(self, fields, objective_id=objective_id)
else:
raise Exception("The time series isn't finished yet")
else:
raise Exception("Cannot create the TimeSeries instance."
" Could not find the 'time_series' key"
" in the resource:\n\n%s" % time_series)
model, csv_properties, fields = u.read_local_resource(
args.model_file,
csv_properties=csv_properties)
models = [model]
model_ids = [model['resource']]
ensemble_ids = []
elif args.ensemble_file:
# model is retrieved from the contents of the given local JSON file
ensemble, csv_properties, fields = u.read_local_resource(
args.ensemble_file,
csv_properties=csv_properties)
model_ids = ensemble['object']['models'][:]
ensemble_ids = [ensemble['resource']]
models = model_ids[:]
model = retrieve_resource(bigml.api.BigML(storage='./storage'),
models[0],
query_string=r.ALL_FIELDS_QS)
models[0] = model
else:
# model is retrieved from the remote object
models, model_ids, ensemble_ids, resume = pm.models_processing(
datasets, models, model_ids,
api, args, resume, fields=fields,
session_file=session_file, path=path, log=log, labels=labels,
multi_label_data=multi_label_data, other_label=other_label)
if models:
model = models[0]
single_model = len(models) == 1
# If multi-label flag is set and no training_set was provided, label
# info is extracted from the user_metadata. If models belong to an
def __init__(self, ensemble, model_fns_dir, api=None):
if api is None:
self.api = BigML(storage=STORAGE)
else:
self.api = api
self.resource_id = None
# to be deprecated
self.ensemble_id = None
self.objective_id = None
self.distributions = None
self.distribution = None
self.models_splits = []
self.multi_model = None
self.boosting = None
self.boosting_offsets = None
self.regression = False
self.fields = None
self.class_names = None
self.importance = {}
self.predict_functions = []
ensemble = self.get_ensemble_resource(ensemble)
self.resource_id = get_ensemble_id(ensemble)
self.ensemble_id = self.resource_id
if lacks_info(ensemble, inner_key="ensemble"):
# avoid checking fields because of old ensembles
ensemble = retrieve_resource(self.api, self.resource_id,
no_check_fields=True)
if ensemble['object'].get('type') == BOOSTING:
self.boosting = ensemble['object'].get('boosting')
models = ensemble['object']['models']
self.distributions = ensemble['object'].get('distributions', [])
self.importance = ensemble['object'].get('importance', [])
self.model_ids = models
# new ensembles have the fields structure
if ensemble['object'].get('ensemble'):
self.fields = ensemble['object'].get( \
'ensemble', {}).get("fields")
self.objective_id = ensemble['object'].get("objective_field")
self.input_fields = ensemble['object'].get("input_fields")
if model_fns_dir:
self.get_model_fns(model_fns_dir)
else:
raise ValueError("The EnsemblePredictor object expects as"
" argument the directory where the models"
" predict functions are stored. To generate "
" them, please check the 'bigmler export'"
" command.")
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 self.boosting:
self.boosting_offsets = ensemble['object'].get('initial_offset',
0) \
if self.regression else dict(ensemble['object'].get( \
'initial_offsets', []))
if not self.regression and self.boosting is None:
try:
objective_field = self.fields[self.objective_id]
categories = objective_field['summary']['categories']
classes = [category[0] for category in categories]
except (AttributeError, KeyError):
classes = set()
for distribution in self.distributions:
for category in distribution['training']['categories']:
classes.add(category[0])
self.class_names = sorted(classes)
def __init__(self, association, api=None):
self.resource_id = None
self.complement = None
self.discretization = {}
self.field_discretizations = {}
self.items = []
self.max_k = None
self.max_lhs = None
self.min_confidence = None
self.min_leverage = None
self.min_support = None
self.min_lift = None
self.search_strategy = DEFAULT_SEARCH_STRATEGY
self.rules = []
self.significance_level = None
if not (isinstance(association, dict) and 'resource' in association and
association['resource'] is not None):
if api is None:
api = BigML(storage=STORAGE)
self.resource_id = get_association_id(association)
if self.resource_id is None:
raise Exception(api.error_message(association,
resource_type='association',
method='get'))
query_string = ONLY_MODEL
association = retrieve_resource(api, self.resource_id,
query_string=query_string)
else:
self.resource_id = get_association_id(association)
if 'object' in association and isinstance(association['object'], dict):
association = association['object']
if 'associations' in association and \
isinstance(association['associations'], dict):
status = get_status(association)
if 'code' in status and status['code'] == FINISHED:
associations = association['associations']
fields = associations['fields']
ModelFields.__init__(self, fields)
self.complement = associations.get('complement', False)
self.discretization = associations.get('discretization', {})
self.field_discretizations = associations.get(
'field_discretizations', {})
self.items = [Item(index, item, fields) for index, item in
enumerate(associations.get('items', []))]
self.max_k = associations.get('max_k', 100)
self.max_lhs = associations.get('max_lhs', 4)
self.min_confidence = associations.get('min_confidence', 0)
self.min_leverage = associations.get('min_leverage', -1)
self.min_support = associations.get('min_support', 0)
self.min_lift = associations.get('min_lift', 0)
self.search_strategy = associations.get('search_strategy', \
DEFAULT_SEARCH_STRATEGY)
self.rules = [AssociationRule(rule) for rule in
associations.get('rules', [])]
self.significance_level = associations.get(
'significance_level', 0.05)
else:
raise Exception("The association isn't finished yet")
else:
raise Exception("Cannot create the Association instance. Could not"
" find the 'associations' key in the "
"resource:\n\n%s" %
association)
def __init__(self, topic_model, api=None):
self.resource_id = None
self.stemmer = None
self.seed = None
self.case_sensitive = False
self.bigrams = False
self.ntopics = None
self.temp = None
self.phi = None
self.term_to_index = None
self.topics = []
if not (isinstance(topic_model, dict) and 'resource' in topic_model
and topic_model['resource'] is not None):
if api is None:
api = BigML(storage=STORAGE)
self.resource_id = get_topic_model_id(topic_model)
if self.resource_id is None:
raise Exception(
api.error_message(topic_model,
resource_type='topicmodel',
method='get'))
query_string = ONLY_MODEL
topic_model = retrieve_resource(api,
self.resource_id,
query_string=query_string)
else:
self.resource_id = get_topic_model_id(topic_model)
if 'object' in topic_model and isinstance(topic_model['object'], dict):
topic_model = topic_model['object']
if 'topic_model' in topic_model \
and isinstance(topic_model['topic_model'], dict):
status = get_status(topic_model)
if 'code' in status and status['code'] == FINISHED:
model = topic_model['topic_model']
self.topics = model['topics']
if 'language' in model and model['language'] is not None:
lang = model['language']
if lang in CODE_TO_NAME:
self.stemmer = Stemmer.Stemmer(CODE_TO_NAME[lang])
self.term_to_index = {
self.stem(term): index
for index, term in enumerate(model['termset'])
}
self.seed = abs(model['hashed_seed'])
self.case_sensitive = model['case_sensitive']
self.bigrams = model['bigrams']
self.ntopics = len(model['term_topic_assignments'][0])
self.alpha = model['alpha']
self.ktimesalpha = self.ntopics * self.alpha
self.temp = [0] * self.ntopics
assignments = model['term_topic_assignments']
beta = model['beta']
nterms = len(self.term_to_index)
sums = [
sum(n[index] for n in assignments)
for index in range(self.ntopics)
]
self.phi = [[0 for _ in range(nterms)]
for _ in range(self.ntopics)]
for k in range(self.ntopics):
norm = sums[k] + nterms * beta
for w in range(nterms):
self.phi[k][w] = (assignments[w][k] + beta) / norm
ModelFields.__init__(self, model['fields'])
else:
raise Exception("The topic model isn't finished yet")
else:
raise Exception("Cannot create the topic model instance. Could not"
" find the 'topic_model' key in the"
" resource:\n\n%s" % topic_model)
def __init__(self, time_series, api=None):
self.resource_id = None
self.input_fields = []
self.objective_fields = []
self.all_numeric_objectives = False
self.period = 1
self.ets_models = {}
self.error = None
self.damped_trend = None
self.seasonality = None
self.trend = None
self.time_range = {}
self.field_parameters = {}
self._forecast = []
# checks whether the information needed for local predictions is in
# the first argument
if isinstance(time_series, dict) and \
not check_model_fields(time_series):
# if the fields used by the logistic regression are not
# available, use only ID to retrieve it again
time_series = get_time_series_id( \
time_series)
self.resource_id = time_series
if not (isinstance(time_series, dict)
and 'resource' in time_series and
time_series['resource'] is not None):
if api is None:
api = BigML(storage=STORAGE)
self.resource_id = get_time_series_id(time_series)
if self.resource_id is None:
raise Exception(
api.error_message(time_series,
resource_type='time_series',
method='get'))
query_string = ONLY_MODEL
time_series = retrieve_resource(
api, self.resource_id, query_string=query_string)
else:
self.resource_id = get_time_series_id(time_series)
if 'object' in time_series and \
isinstance(time_series['object'], dict):
time_series = time_series['object']
try:
self.input_fields = time_series.get("input_fields", [])
self._forecast = time_series.get("forecast")
self.objective_fields = time_series.get(
"objective_fields", [])
objective_field = time_series['objective_field'] if \
time_series.get('objective_field') else \
time_series['objective_fields']
except KeyError:
raise ValueError("Failed to find the time series expected "
"JSON structure. Check your arguments.")
if 'time_series' in time_series and \
isinstance(time_series['time_series'], dict):
status = get_status(time_series)
if 'code' in status and status['code'] == FINISHED:
time_series_info = time_series['time_series']
fields = time_series_info.get('fields', {})
self.fields = fields
if not self.input_fields:
self.input_fields = [ \
field_id for field_id, _ in
sorted(self.fields.items(),
key=lambda x: x[1].get("column_number"))]
self.all_numeric_objectives = time_series_info.get( \
'all_numeric_objectives')
self.period = time_series_info.get('period', 1)
self.ets_models = time_series_info.get('ets_models', {})
self.error = time_series_info.get('error')
self.damped_trend = time_series_info.get('damped_trend')
self.seasonality = time_series_info.get('seasonality')
self.trend = time_series_info.get('trend')
self.time_range = time_series_info.get('time_range')
self.field_parameters = time_series_info.get( \
'field_parameters', {})
objective_id = extract_objective(objective_field)
ModelFields.__init__(
self, fields,
objective_id=objective_id)
else:
raise Exception("The time series isn't finished yet")
else:
raise Exception("Cannot create the TimeSeries instance."
" Could not find the 'time_series' key"
" in the resource:\n\n%s" %
time_series)
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, model, api=None, fields=None):
"""The Model constructor can be given as first argument:
- a model structure
- a model id
- a path to a JSON file containing a model structure
"""
self.resource_id = None
self.ids_map = {}
self.terms = {}
self.regression = False
self.boosting = None
self.class_names = None
if not hasattr(self, 'tree_class'):
self.tree_class = Tree
# the string can be a path to a JSON file
if isinstance(model, basestring):
try:
with open(model) as model_file:
model = json.load(model_file)
self.resource_id = get_model_id(model)
if self.resource_id is None:
raise ValueError("The JSON file does not seem"
" to contain a valid BigML model"
" representation.")
except IOError:
# if it is not a path, it can be a model id
self.resource_id = get_model_id(model)
if self.resource_id is None:
if model.find('model/') > -1:
raise Exception(
api.error_message(model,
resource_type='model',
method='get'))
else:
raise IOError("Failed to open the expected JSON file"
" at %s" % model)
except ValueError:
raise ValueError("Failed to interpret %s."
" JSON file expected.")
# checks whether the information needed for local predictions is in
# the first argument
if isinstance(model, dict) and \
not fields and \
not check_model_fields(model):
# if the fields used by the model are not
# available, use only ID to retrieve it again
model = get_model_id(model)
self.resource_id = model
if not (isinstance(model, dict) and 'resource' in model and
model['resource'] is not None):
if api is None:
api = BigML(storage=STORAGE)
if fields is not None and isinstance(fields, dict):
query_string = EXCLUDE_FIELDS
else:
query_string = ONLY_MODEL
model = retrieve_resource(api, self.resource_id,
query_string=query_string)
else:
self.resource_id = get_model_id(model)
BaseModel.__init__(self, model, api=api, fields=fields)
if 'object' in model and isinstance(model['object'], dict):
model = model['object']
if 'model' in model and isinstance(model['model'], dict):
status = get_status(model)
if 'code' in status and status['code'] == FINISHED:
# boosting models are to be handled using the BoostedTree
# class
if model.get("boosted_ensemble"):
self.boosting = model.get('boosting', False)
if self.boosting == {}:
self.boosting = False
self.regression = \
not self.boosting and \
self.fields[self.objective_id]['optype'] == 'numeric' \
or (self.boosting and \
self.boosting.get("objective_class") is None)
if self.boosting:
self.tree = BoostedTree(
model['model']['root'],
self.fields,
objective_field=self.objective_id)
else:
distribution = model['model']['distribution']['training']
# will store global information in the tree: regression and
# max_bins number
tree_info = {'max_bins': 0}
self.tree = self.tree_class(
model['model']['root'],
self.fields,
objective_field=self.objective_id,
root_distribution=distribution,
parent_id=None,
ids_map=self.ids_map,
tree_info=tree_info)
self.tree.regression = tree_info['regression']
if self.tree.regression:
try:
import numpy
import scipy
self._max_bins = tree_info['max_bins']
self.regression_ready = True
except ImportError:
self.regression_ready = False
else:
root_dist = self.tree.distribution
self.class_names = sorted([category[0]
for category in root_dist])
else:
raise Exception("The model isn't finished yet")
else:
raise Exception("Cannot create the Model instance. Could not"
" find the 'model' key in the resource:\n\n%s" %
model)
def __init__(self, deepnet, api=None):
"""The Deepnet constructor can be given as first argument:
- a deepnet structure
- a deepnet id
- a path to a JSON file containing a deepnet structure
"""
self.resource_id = None
self.regression = False
self.network = None
self.networks = None
self.input_fields = []
self.class_names = []
self.preprocess = []
self.optimizer = None
self.missing_numerics = False
# the string can be a path to a JSON file
if isinstance(deepnet, basestring):
try:
with open(deepnet) as deepnet_file:
deepnet = json.load(deepnet_file)
self.resource_id = get_deepnet_id(deepnet)
if self.resource_id is None:
raise ValueError("The JSON file does not seem"
" to contain a valid BigML deepnet"
" representation.")
except IOError:
# if it is not a path, it can be a deepnet id
self.resource_id = get_deepnet_id(deepnet)
if self.resource_id is None:
if deepnet.find('deepnet/') > -1:
raise Exception(
api.error_message(deepnet,
resource_type='deepnet',
method='get'))
else:
raise IOError("Failed to open the expected JSON file"
" at %s" % deepnet)
except ValueError:
raise ValueError("Failed to interpret %s."
" JSON file expected.")
# checks whether the information needed for local predictions is in
# the first argument
if isinstance(deepnet, dict) and \
not check_model_fields(deepnet):
# if the fields used by the deepenet are not
# available, use only ID to retrieve it again
deepnet = get_deepnet_id(deepnet)
self.resource_id = deepnet
if not (isinstance(deepnet, dict) and 'resource' in deepnet and
deepnet['resource'] is not None):
if api is None:
api = BigML(storage=STORAGE)
query_string = ONLY_MODEL
deepnet = retrieve_resource(api, self.resource_id,
query_string=query_string)
else:
self.resource_id = get_deepnet_id(deepnet)
if 'object' in deepnet and isinstance(deepnet['object'], dict):
deepnet = deepnet['object']
self.input_fields = deepnet['input_fields']
if 'deepnet' in deepnet and isinstance(deepnet['deepnet'], dict):
status = get_status(deepnet)
objective_field = deepnet['objective_fields']
deepnet = deepnet['deepnet']
if 'code' in status and status['code'] == FINISHED:
self.fields = deepnet['fields']
ModelFields.__init__(
self, self.fields,
objective_id=extract_objective(objective_field),
terms=True, categories=True)
self.regression = \
self.fields[self.objective_id]['optype'] == NUMERIC
if not self.regression:
self.class_names = [category for category,_ in \
self.fields[self.objective_id][ \
'summary']['categories']]
self.class_names.sort()
self.missing_numerics = deepnet.get('missing_numerics', False)
if 'network' in deepnet:
network = deepnet['network']
self.network = network
self.networks = network.get('networks', [])
self.preprocess = network.get('preprocess')
self.optimizer = network.get('optimizer', {})
else:
raise Exception("The deepnet isn't finished yet")
else:
raise Exception("Cannot create the Deepnet instance. Could not"
" find the 'deepnet' key in the resource:\n\n%s" %
deepnet)
def __init__(self, association, api=None):
self.resource_id = None
self.complement = None
self.discretization = {}
self.field_discretizations = {}
self.items = []
self.max_k = None
self.max_lhs = None
self.min_confidence = None
self.min_leverage = None
self.min_support = None
self.min_lift = None
self.search_strategy = DEFAULT_SEARCH_STRATEGY
self.rules = []
self.significance_level = None
if not (isinstance(association, dict) and 'resource' in association
and association['resource'] is not None):
if api is None:
api = BigML(storage=STORAGE)
self.resource_id = get_association_id(association)
if self.resource_id is None:
raise Exception(
api.error_message(association,
resource_type='association',
method='get'))
query_string = ONLY_MODEL
association = retrieve_resource(api,
self.resource_id,
query_string=query_string)
else:
self.resource_id = get_association_id(association)
if 'object' in association and isinstance(association['object'], dict):
association = association['object']
if 'associations' in association and \
isinstance(association['associations'], dict):
status = get_status(association)
if 'code' in status and status['code'] == FINISHED:
associations = association['associations']
fields = associations['fields']
ModelFields.__init__(self, fields)
self.complement = associations.get('complement', False)
self.discretization = associations.get('discretization', {})
self.field_discretizations = associations.get(
'field_discretizations', {})
self.items = [
Item(index, item, fields)
for index, item in enumerate(associations.get('items', []))
]
self.max_k = associations.get('max_k', 100)
self.max_lhs = associations.get('max_lhs', 4)
self.min_confidence = associations.get('min_confidence', 0)
self.min_leverage = associations.get('min_leverage', -1)
self.min_support = associations.get('min_support', 0)
self.min_lift = associations.get('min_lift', 0)
self.search_strategy = associations.get('search_strategy', \
DEFAULT_SEARCH_STRATEGY)
self.rules = [
AssociationRule(rule)
for rule in associations.get('rules', [])
]
self.significance_level = associations.get(
'significance_level', 0.05)
else:
raise Exception("The association isn't finished yet")
else:
raise Exception("Cannot create the Association instance. Could not"
" find the 'associations' key in the "
"resource:\n\n%s" % association)
def __init__(self, model, api=None):
"""The Model constructor can be given as first argument:
- a model structure
- a model id
- a path to a JSON file containing a model structure
"""
self.resource_id = None
self.ids_map = {}
self.terms = {}
# the string can be a path to a JSON file
if isinstance(model, basestring):
try:
with open(model) as model_file:
model = json.load(model_file)
self.resource_id = get_model_id(model)
if self.resource_id is None:
raise ValueError(
"The JSON file does not seem" " to contain a valid BigML model" " representation."
)
except IOError:
# if it is not a path, it can be a model id
self.resource_id = get_model_id(model)
if self.resource_id is None:
if model.find("model/") > -1:
raise Exception(api.error_message(model, resource_type="model", method="get"))
else:
raise IOError("Failed to open the expected JSON file" " at %s" % model)
except ValueError:
raise ValueError("Failed to interpret %s." " JSON file expected.")
# checks whether the information needed for local predictions is in
# the first argument
if isinstance(model, dict) and not check_model_fields(model):
# if the fields used by the model are not
# available, use only ID to retrieve it again
model = get_model_id(model)
self.resource_id = model
if not (isinstance(model, dict) and "resource" in model and model["resource"] is not None):
if api is None:
api = BigML(storage=STORAGE)
query_string = ONLY_MODEL
model = retrieve_resource(api, self.resource_id, query_string=query_string)
else:
self.resource_id = get_model_id(model)
BaseModel.__init__(self, model, api=api)
if "object" in model and isinstance(model["object"], dict):
model = model["object"]
if "model" in model and isinstance(model["model"], dict):
status = get_status(model)
if "code" in status and status["code"] == FINISHED:
distribution = model["model"]["distribution"]["training"]
# will store global information in the tree: regression and
# max_bins number
tree_info = {"max_bins": 0}
self.tree = Tree(
model["model"]["root"],
self.fields,
objective_field=self.objective_id,
root_distribution=distribution,
parent_id=None,
ids_map=self.ids_map,
tree_info=tree_info,
)
self.tree.regression = tree_info["regression"]
if self.tree.regression:
self._max_bins = tree_info["max_bins"]
else:
raise Exception("The model isn't finished yet")
else:
raise Exception(
"Cannot create the Model instance. Could not" " find the 'model' key in the resource:\n\n%s" % model
)
if self.tree.regression:
try:
import numpy
import scipy
self.regression_ready = True
except ImportError:
self.regression_ready = False
def __init__(self, model, api=None):
"""The Model constructor can be given as first argument:
- a model structure
- a model id
- a path to a JSON file containing a model structure
"""
self.resource_id = None
self.ids_map = {}
self.terms = {}
# the string can be a path to a JSON file
if isinstance(model, basestring):
try:
with open(model) as model_file:
model = json.load(model_file)
self.resource_id = get_model_id(model)
if self.resource_id is None:
raise ValueError("The JSON file does not seem"
" to contain a valid BigML model"
" representation.")
except IOError:
# if it is not a path, it can be a model id
self.resource_id = get_model_id(model)
if self.resource_id is None:
if model.find('model/') > -1:
raise Exception(
api.error_message(model,
resource_type='model',
method='get'))
else:
raise IOError("Failed to open the expected JSON file"
" at %s" % model)
except ValueError:
raise ValueError("Failed to interpret %s."
" JSON file expected.")
if not (isinstance(model, dict) and 'resource' in model and
model['resource'] is not None):
if api is None:
api = BigML(storage=STORAGE)
query_string = ONLY_MODEL
model = retrieve_resource(api, self.resource_id,
query_string=query_string)
else:
self.resource_id = get_model_id(model)
BaseModel.__init__(self, model, api=api)
if 'object' in model and isinstance(model['object'], dict):
model = model['object']
if 'model' in model and isinstance(model['model'], dict):
status = get_status(model)
if 'code' in status and status['code'] == FINISHED:
distribution = model['model']['distribution']['training']
self.tree = Tree(
model['model']['root'],
self.fields,
objective_field=self.objective_id,
root_distribution=distribution,
parent_id=None,
ids_map=self.ids_map)
else:
raise Exception("The model isn't finished yet")
else:
raise Exception("Cannot create the Model instance. Could not"
" find the 'model' key in the resource:\n\n%s" %
model)
if self.tree.regression:
try:
import numpy
import scipy
self.regression_ready = True
except ImportError:
self.regression_ready = False
def __init__(self, anomaly, api=None):
self.resource_id = None
self.sample_size = None
self.input_fields = None
self.mean_depth = None
self.expected_mean_depth = None
self.iforest = None
self.top_anomalies = None
if not (isinstance(anomaly, dict) and 'resource' in anomaly
and anomaly['resource'] is not None):
if api is None:
api = BigML(storage=STORAGE)
self.resource_id = get_anomaly_id(anomaly)
if self.resource_id is None:
raise Exception(
api.error_message(anomaly,
resource_type='anomaly',
method='get'))
query_string = ONLY_MODEL
anomaly = retrieve_resource(api,
self.resource_id,
query_string=query_string)
else:
self.resource_id = get_anomaly_id(anomaly)
if 'object' in anomaly and isinstance(anomaly['object'], dict):
anomaly = anomaly['object']
self.sample_size = anomaly.get('sample_size')
self.input_fields = anomaly.get('input_fields')
if 'model' in anomaly and isinstance(anomaly['model'], dict):
ModelFields.__init__(self, anomaly['model'].get('fields'))
if ('top_anomalies' in anomaly['model']
and isinstance(anomaly['model']['top_anomalies'], list)):
self.mean_depth = anomaly['model'].get('mean_depth')
status = get_status(anomaly)
if 'code' in status and status['code'] == FINISHED:
self.expected_mean_depth = None
if self.mean_depth is None or self.sample_size is None:
raise Exception("The anomaly data is not complete. "
"Score will"
" not be available")
else:
default_depth = (
2 *
(0.5772156649 + math.log(self.sample_size - 1) -
(float(self.sample_size - 1) / self.sample_size)))
self.expected_mean_depth = min(self.mean_depth,
default_depth)
iforest = anomaly['model'].get('trees', [])
if iforest:
self.iforest = [
AnomalyTree(anomaly_tree['root'], self.fields)
for anomaly_tree in iforest
]
self.top_anomalies = anomaly['model']['top_anomalies']
else:
raise Exception("The anomaly isn't finished yet")
else:
raise Exception("Cannot create the Anomaly instance. Could not"
" find the 'top_anomalies' key in the"
" resource:\n\n%s" % anomaly['model'].keys())
def __init__(self, logistic_regression, api=None):
self.resource_id = None
self.input_fields = []
self.term_forms = {}
self.tag_clouds = {}
self.term_analysis = {}
self.items = {}
self.item_analysis = {}
self.categories = {}
self.coefficients = {}
self.data_field_types = {}
self.numeric_fields = {}
self.bias = None
self.missing_numerics = None
self.c = None
self.eps = None
self.lr_normalize = None
self.regularization = None
if not (isinstance(logistic_regression, dict)
and 'resource' in logistic_regression and
logistic_regression['resource'] is not None):
if api is None:
api = BigML(storage=STORAGE)
self.resource_id = get_logistic_regression_id(logistic_regression)
if self.resource_id is None:
raise Exception(
api.error_message(logistic_regression,
resource_type='logistic_regression',
method='get'))
query_string = ONLY_MODEL
logistic_regression = retrieve_resource(
api, self.resource_id, query_string=query_string)
else:
self.resource_id = get_logistic_regression_id(logistic_regression)
if 'object' in logistic_regression and \
isinstance(logistic_regression['object'], dict):
logistic_regression = logistic_regression['object']
try:
self.input_fields = logistic_regression.get("input_fields", [])
self.dataset_field_types = logistic_regression.get(
"dataset_field_types", {})
objective_field = logistic_regression['objective_fields'] if \
logistic_regression['objective_fields'] else \
logistic_regression['objective_field']
except KeyError:
raise ValueError("Failed to find the logistic regression expected "
"JSON structure. Check your arguments.")
if 'logistic_regression' in logistic_regression and \
isinstance(logistic_regression['logistic_regression'], dict):
status = get_status(logistic_regression)
if 'code' in status and status['code'] == FINISHED:
logistic_regression_info = logistic_regression[ \
'logistic_regression']
fields = logistic_regression_info.get('fields', {})
if not self.input_fields:
self.input_fields = [ \
field_id for field_id, _ in
sorted(self.fields.items(),
key=lambda x: x[1].get("column_number"))]
self.coefficients.update(logistic_regression_info.get( \
'coefficients', []))
self.bias = logistic_regression_info.get('bias', 0)
self.c = logistic_regression_info.get('c')
self.eps = logistic_regression_info.get('eps')
self.lr_normalize = logistic_regression_info.get('normalize')
self.regularization = logistic_regression_info.get( \
'regularization')
# old models have no such attribute, so we set it to False in
# this case
self.missing_numerics = logistic_regression_info.get( \
'missing_numerics', False)
objective_id = extract_objective(objective_field)
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] = [tag for [tag, _] in 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] = [item for item, _ in \
field['summary']['items']]
self.item_analysis[field_id] = {}
self.item_analysis[field_id].update(
field['item_analysis'])
if field['optype'] == 'categorical':
self.categories[field_id] = [category for \
[category, _] in field['summary']['categories']]
if self.missing_numerics and field['optype'] == 'numeric':
self.numeric_fields[field_id] = True
ModelFields.__init__(
self, fields,
objective_id=objective_id)
self.map_coefficients()
else:
raise Exception("The logistic regression isn't finished yet")
else:
raise Exception("Cannot create the LogisticRegression instance."
" Could not find the 'logistic_regression' key"
" in the resource:\n\n%s" %
logistic_regression)
def compute_output(api, args):
""" Creates one or more models using the `training_set` or uses the ids
of previously created BigML models to make predictions for the `test_set`.
"""
source = None
dataset = None
model = None
models = None
fields = None
other_label = OTHER
ensemble_ids = []
multi_label_data = None
multi_label_fields = []
#local_ensemble = None
test_dataset = None
datasets = None
# variables from command-line options
resume = args.resume_
model_ids = args.model_ids_
output = args.output
dataset_fields = args.dataset_fields_
check_args_coherence(args)
path = u.check_dir(output)
session_file = "%s%s%s" % (path, os.sep, SESSIONS_LOG)
csv_properties = {}
# If logging is required set the file for logging
log = None
if args.log_file:
u.check_dir(args.log_file)
log = args.log_file
# If --clear_logs the log files are cleared
clear_log_files([log])
# labels to be used in multi-label expansion
labels = (None if args.labels is None else [
label.strip() for label in args.labels.split(args.args_separator)
])
if labels is not None:
labels = sorted([label for label in labels])
# multi_label file must be preprocessed to obtain a new extended file
if args.multi_label and args.training_set is not None:
(args.training_set, multi_label_data) = ps.multi_label_expansion(
args.training_set,
args.train_header,
args,
path,
labels=labels,
session_file=session_file)
args.train_header = True
args.objective_field = multi_label_data["objective_name"]
all_labels = l.get_all_labels(multi_label_data)
if not labels:
labels = all_labels
else:
all_labels = labels
if args.objective_field:
csv_properties.update({'objective_field': args.objective_field})
if args.source_file:
# source is retrieved from the contents of the given local JSON file
source, csv_properties, fields = u.read_local_resource(
args.source_file, csv_properties=csv_properties)
else:
# source is retrieved from the remote object
source, resume, csv_properties, fields = ps.source_processing(
api,
args,
resume,
csv_properties=csv_properties,
multi_label_data=multi_label_data,
session_file=session_file,
path=path,
log=log)
if source is not None:
args.source = bigml.api.get_source_id(source)
if args.multi_label and source:
multi_label_data = l.get_multi_label_data(source)
(args.objective_field, labels, all_labels,
multi_label_fields) = l.multi_label_sync(args.objective_field, labels,
multi_label_data, fields,
multi_label_fields)
if fields and args.export_fields:
fields.summary_csv(os.path.join(path, args.export_fields))
if args.dataset_file:
# dataset is retrieved from the contents of the given local JSON file
model_dataset, csv_properties, fields = u.read_local_resource(
args.dataset_file, csv_properties=csv_properties)
if not args.datasets:
datasets = [model_dataset]
dataset = model_dataset
else:
datasets = u.read_datasets(args.datasets)
if not datasets:
# dataset is retrieved from the remote object
datasets, resume, csv_properties, fields = pd.dataset_processing(
source,
api,
args,
resume,
fields=fields,
csv_properties=csv_properties,
multi_label_data=multi_label_data,
session_file=session_file,
path=path,
log=log)
if datasets:
dataset = datasets[0]
if args.to_csv is not None:
resume = pd.export_dataset(dataset,
api,
args,
resume,
session_file=session_file,
path=path)
# Now we have a dataset, let's check if there's an objective_field
# given by the user and update it in the fields structure
args.objective_id_ = get_objective_id(args, fields)
# If test_split is used, split the dataset in a training and a test dataset
# according to the given split
if args.test_split > 0:
dataset, test_dataset, resume = pd.split_processing(
dataset,
api,
args,
resume,
multi_label_data=multi_label_data,
session_file=session_file,
path=path,
log=log)
datasets[0] = dataset
# Check if the dataset has a categorical objective field and it
# has a max_categories limit for categories
if args.max_categories > 0 and len(datasets) == 1:
if pd.check_max_categories(fields.fields[args.objective_id_]):
distribution = pd.get_categories_distribution(
dataset, args.objective_id_)
if distribution and len(distribution) > args.max_categories:
categories = [element[0] for element in distribution]
other_label = pd.create_other_label(categories, other_label)
datasets, resume = pd.create_categories_datasets(
dataset,
distribution,
fields,
args,
api,
resume,
session_file=session_file,
path=path,
log=log,
other_label=other_label)
else:
sys.exit("The provided objective field is not categorical nor "
"a full terms only text field. "
"Only these fields can be used with"
" --max-categories")
# If multi-dataset flag is on, generate a new dataset from the given
# list of datasets
if args.multi_dataset:
dataset, resume = pd.create_new_dataset(datasets,
api,
args,
resume,
fields=fields,
session_file=session_file,
path=path,
log=log)
datasets = [dataset]
# Check if the dataset has a generators file associated with it, and
# generate a new dataset with the specified field structure. Also
# if the --to-dataset flag is used to clone or sample the original dataset
if args.new_fields or (args.sample_rate != 1 and args.no_model) or \
(args.lisp_filter or args.json_filter) and not has_source(args):
if fields is None:
if isinstance(dataset, basestring):
dataset = u.check_resource(dataset, api=api)
fields = Fields(dataset, csv_properties)
args.objective_id_ = get_objective_id(args, fields)
args.objective_name_ = fields.field_name(args.objective_id_)
dataset, resume = pd.create_new_dataset(dataset,
api,
args,
resume,
fields=fields,
session_file=session_file,
path=path,
log=log)
datasets[0] = dataset
# rebuild fields structure for new ids and fields
csv_properties.update({
'objective_field': args.objective_name_,
'objective_field_present': True
})
fields = pd.get_fields_structure(dataset, csv_properties)
args.objective_id_ = get_objective_id(args, fields)
if args.multi_label and dataset and multi_label_data is None:
multi_label_data = l.get_multi_label_data(dataset)
(args.objective_field, labels, all_labels,
multi_label_fields) = l.multi_label_sync(args.objective_field, labels,
multi_label_data, fields,
multi_label_fields)
if dataset:
# retrieves max_categories data, if any
args.max_categories = get_metadata(dataset, 'max_categories',
args.max_categories)
other_label = get_metadata(dataset, 'other_label', other_label)
if fields and args.export_fields:
fields.summary_csv(os.path.join(path, args.export_fields))
if args.model_file:
# model is retrieved from the contents of the given local JSON file
model, csv_properties, fields = u.read_local_resource(
args.model_file, csv_properties=csv_properties)
models = [model]
model_ids = [model['resource']]
ensemble_ids = []
elif args.ensemble_file:
# model is retrieved from the contents of the given local JSON file
ensemble, csv_properties, fields = u.read_local_resource(
args.ensemble_file, csv_properties=csv_properties)
model_ids = ensemble['object']['models'][:]
ensemble_ids = [ensemble['resource']]
models = model_ids[:]
model = retrieve_resource(args.retrieve_api_,
models[0],
query_string=r.ALL_FIELDS_QS)
models[0] = model
else:
# model is retrieved from the remote object
models, model_ids, ensemble_ids, resume = pm.models_processing(
datasets,
models,
model_ids,
api,
args,
resume,
fields=fields,
session_file=session_file,
path=path,
log=log,
labels=labels,
multi_label_data=multi_label_data,
other_label=other_label)
if models:
model = models[0]
single_model = len(models) == 1
# If multi-label flag is set and no training_set was provided, label
# info is extracted from the user_metadata. If models belong to an
# ensemble, the ensemble must be retrieved to get the user_metadata.
if model and args.multi_label and multi_label_data is None:
if ensemble_ids and isinstance(ensemble_ids[0], dict):
resource = ensemble_ids[0]
elif belongs_to_ensemble(model):
ensemble_id = get_ensemble_id(model)
resource = rens.get_ensemble(ensemble_id,
api=api,
verbosity=args.verbosity,
session_file=session_file)
else:
resource = model
multi_label_data = l.get_multi_label_data(resource)
# We update the model's public state if needed
if model:
if (isinstance(model, basestring)
or bigml.api.get_status(model)['code'] != bigml.api.FINISHED):
if not args.evaluate and not a.has_train(args) and \
not a.has_test(args):
query_string = MINIMUM_MODEL
elif not args.test_header:
query_string = r.ALL_FIELDS_QS
else:
query_string = "%s;%s" % (r.ALL_FIELDS_QS, r.FIELDS_QS)
model = u.check_resource(model,
api.get_model,
query_string=query_string)
models[0] = model
if (args.black_box or args.white_box or
(args.shared_flag and r.shared_changed(args.shared, model))):
model_args = {}
if args.shared_flag and r.shared_changed(args.shared, model):
model_args.update(shared=args.shared)
if args.black_box or args.white_box:
model_args.update(rmod.set_publish_model_args(args))
if model_args:
model = rmod.update_model(model,
model_args,
args,
api=api,
path=path,
session_file=session_file)
models[0] = model
# We get the fields of the model if we haven't got
# them yet and need them
if model and not args.evaluate and (a.has_test(args)
or args.export_fields):
# if we are using boosted ensembles to predict, activate boosting
if model['object'].get('boosted_ensemble'):
args.boosting = True
# If more than one model, use the full field structure
if (not single_model and not args.multi_label
and belongs_to_ensemble(model)):
if ensemble_ids:
ensemble_id = ensemble_ids[0]
args.ensemble_ids_ = ensemble_ids
else:
ensemble_id = get_ensemble_id(model)
fields = pm.get_model_fields(model,
csv_properties,
args,
single_model=single_model,
multi_label_data=multi_label_data)
# Free memory after getting fields
# local_ensemble = None
gc.collect()
# Fills in all_labels from user_metadata
if args.multi_label and not all_labels:
(args.objective_field, labels, all_labels,
multi_label_fields) = l.multi_label_sync(args.objective_field, labels,
multi_label_data, fields,
multi_label_fields)
if model:
# retrieves max_categories data, if any
args.max_categories = get_metadata(model, 'max_categories',
args.max_categories)
other_label = get_metadata(model, 'other_label', other_label)
if fields and args.export_fields:
fields.summary_csv(os.path.join(path, args.export_fields))
# If predicting
if (models and (a.has_test(args) or (test_dataset and args.remote))
and not args.evaluate):
models_per_label = 1
if test_dataset is None:
test_dataset = get_test_dataset(args)
if args.multi_label:
# When prediction starts from existing models, the
# multi_label_fields can be retrieved from the user_metadata
# in the models
if args.multi_label_fields is None and multi_label_fields:
multi_label_field_names = [
field[1] for field in multi_label_fields
]
args.multi_label_fields = ",".join(multi_label_field_names)
test_set = ps.multi_label_expansion(args.test_set,
args.test_header,
args,
path,
labels=labels,
session_file=session_file,
input_flag=True)[0]
test_set_header = True
# Remote predictions: predictions are computed as batch predictions
# in bigml.com except when --no-batch flag is set on or multi-label
# or max-categories are used
if (args.remote and not args.no_batch and not args.multi_label
and not args.method == COMBINATION):
# create test source from file
test_name = "%s - test" % args.name
if args.test_source is None:
test_properties = ps.test_source_processing(
api,
args,
resume,
session_file=session_file,
path=path,
log=log)
(test_source, resume, csv_properties,
test_fields) = test_properties
else:
test_source_id = bigml.api.get_source_id(args.test_source)
test_source = api.check_resource(test_source_id)
if test_dataset is None:
# create test dataset from test source
dataset_args = rds.set_basic_dataset_args(args, name=test_name)
test_dataset, resume = pd.alternative_dataset_processing(
test_source,
"test",
dataset_args,
api,
args,
resume,
session_file=session_file,
path=path,
log=log)
else:
test_dataset_id = bigml.api.get_dataset_id(test_dataset)
test_dataset = api.check_resource(test_dataset_id)
csv_properties.update(objective_field=None,
objective_field_present=False)
test_fields = pd.get_fields_structure(test_dataset, csv_properties)
if args.to_dataset and args.dataset_off:
model = api.check_resource(model['resource'],
query_string=r.ALL_FIELDS_QS)
model_fields = Fields(model)
objective_field_name = model_fields.field_name( \
model_fields.objective_field)
if objective_field_name in test_fields.fields_by_name.keys():
args.prediction_name = "%s (predicted)" % \
objective_field_name
batch_prediction_args = rbp.set_batch_prediction_args(
args, fields=fields, dataset_fields=test_fields)
remote_predict(model,
test_dataset,
batch_prediction_args,
args,
api,
resume,
prediction_file=output,
session_file=session_file,
path=path,
log=log)
else:
models_per_label = args.number_of_models
if (args.multi_label and ensemble_ids
and args.number_of_models == 1):
# use case where ensembles are read from a file
models_per_label = len(models) / len(ensemble_ids)
predict(models,
fields,
args,
api=api,
log=log,
resume=resume,
session_file=session_file,
labels=labels,
models_per_label=models_per_label,
other_label=other_label,
multi_label_data=multi_label_data)
# When combine_votes flag is used, retrieve the predictions files saved
# in the comma separated list of directories and combine them
if args.votes_files_:
model_id = re.sub(r'.*(model_[a-f0-9]{24})__predictions\.csv$', r'\1',
args.votes_files_[0]).replace("_", "/")
try:
model = u.check_resource(model_id, api.get_model)
except ValueError, exception:
sys.exit("Failed to get model %s: %s" % (model_id, str(exception)))
local_model = Model(model)
message = u.dated("Combining votes.\n")
u.log_message(message, log_file=session_file, console=args.verbosity)
combine_votes(args.votes_files_,
local_model.to_prediction,
output,
method=args.method)
def compute_output(api, args):
""" Creates one or more models using the `training_set` or uses the ids
of previously created BigML models to make predictions for the `test_set`.
"""
source = None
dataset = None
model = None
models = None
fields = None
other_label = OTHER
ensemble_ids = []
multi_label_data = None
multi_label_fields = []
# local_ensemble = None
test_dataset = None
datasets = None
# variables from command-line options
resume = args.resume_
model_ids = args.model_ids_
output = args.predictions
dataset_fields = args.dataset_fields_
check_args_coherence(args)
path = u.check_dir(output)
session_file = "%s%s%s" % (path, os.sep, SESSIONS_LOG)
csv_properties = {}
# If logging is required set the file for logging
log = None
if args.log_file:
u.check_dir(args.log_file)
log = args.log_file
# If --clear_logs the log files are cleared
clear_log_files([log])
# labels to be used in multi-label expansion
labels = None if args.labels is None else [label.strip() for label in args.labels.split(args.args_separator)]
if labels is not None:
labels = sorted([label for label in labels])
# multi_label file must be preprocessed to obtain a new extended file
if args.multi_label and args.training_set is not None:
(args.training_set, multi_label_data) = ps.multi_label_expansion(
args.training_set, args.train_header, args, path, labels=labels, session_file=session_file
)
args.train_header = True
args.objective_field = multi_label_data["objective_name"]
all_labels = l.get_all_labels(multi_label_data)
if not labels:
labels = all_labels
else:
all_labels = labels
if args.objective_field:
csv_properties.update({"objective_field": args.objective_field})
if args.source_file:
# source is retrieved from the contents of the given local JSON file
source, csv_properties, fields = u.read_local_resource(args.source_file, csv_properties=csv_properties)
else:
# source is retrieved from the remote object
source, resume, csv_properties, fields = ps.source_processing(
api,
args,
resume,
csv_properties=csv_properties,
multi_label_data=multi_label_data,
session_file=session_file,
path=path,
log=log,
)
if args.multi_label and source:
multi_label_data = l.get_multi_label_data(source)
(args.objective_field, labels, all_labels, multi_label_fields) = l.multi_label_sync(
args.objective_field, labels, multi_label_data, fields, multi_label_fields
)
if args.dataset_file:
# dataset is retrieved from the contents of the given local JSON file
model_dataset, csv_properties, fields = u.read_local_resource(args.dataset_file, csv_properties=csv_properties)
if not args.datasets:
datasets = [model_dataset]
dataset = model_dataset
else:
datasets = u.read_datasets(args.datasets)
if not datasets:
# dataset is retrieved from the remote object
datasets, resume, csv_properties, fields = pd.dataset_processing(
source,
api,
args,
resume,
fields=fields,
csv_properties=csv_properties,
multi_label_data=multi_label_data,
session_file=session_file,
path=path,
log=log,
)
if datasets:
dataset = datasets[0]
if args.to_csv is not None:
resume = pd.export_dataset(dataset, api, args, resume, session_file=session_file, path=path)
# Now we have a dataset, let's check if there's an objective_field
# given by the user and update it in the fields structure
args.objective_id_ = get_objective_id(args, fields)
# If test_split is used, split the dataset in a training and a test dataset
# according to the given split
if args.test_split > 0:
dataset, test_dataset, resume = pd.split_processing(
dataset, api, args, resume, multi_label_data=multi_label_data, session_file=session_file, path=path, log=log
)
datasets[0] = dataset
# Check if the dataset has a categorical objective field and it
# has a max_categories limit for categories
if args.max_categories > 0 and len(datasets) == 1:
if pd.check_max_categories(fields.fields[args.objective_id_]):
distribution = pd.get_categories_distribution(dataset, args.objective_id_)
if distribution and len(distribution) > args.max_categories:
categories = [element[0] for element in distribution]
other_label = pd.create_other_label(categories, other_label)
datasets, resume = pd.create_categories_datasets(
dataset,
distribution,
fields,
args,
api,
resume,
session_file=session_file,
path=path,
log=log,
other_label=other_label,
)
else:
sys.exit(
"The provided objective field is not categorical nor "
"a full terms only text field. "
"Only these fields can be used with"
" --max-categories"
)
# If multi-dataset flag is on, generate a new dataset from the given
# list of datasets
if args.multi_dataset:
dataset, resume = pd.create_new_dataset(
datasets, api, args, resume, fields=fields, session_file=session_file, path=path, log=log
)
datasets = [dataset]
# Check if the dataset has a generators file associated with it, and
# generate a new dataset with the specified field structure. Also
# if the --to-dataset flag is used to clone or sample the original dataset
if (
args.new_fields
or (args.sample_rate != 1 and args.no_model)
or (args.lisp_filter or args.json_filter)
and not has_source(args)
):
if fields is None:
if isinstance(dataset, basestring):
dataset = check_resource(dataset, api=api)
fields = Fields(dataset, csv_properties)
args.objective_id_ = get_objective_id(args, fields)
args.objective_name_ = fields.field_name(args.objective_id_)
dataset, resume = pd.create_new_dataset(
dataset, api, args, resume, fields=fields, session_file=session_file, path=path, log=log
)
datasets[0] = dataset
# rebuild fields structure for new ids and fields
csv_properties.update({"objective_field": args.objective_name_, "objective_field_present": True})
fields = pd.get_fields_structure(dataset, csv_properties)
args.objective_id_ = get_objective_id(args, fields)
if args.multi_label and dataset and multi_label_data is None:
multi_label_data = l.get_multi_label_data(dataset)
(args.objective_field, labels, all_labels, multi_label_fields) = l.multi_label_sync(
args.objective_field, labels, multi_label_data, fields, multi_label_fields
)
if dataset:
# retrieves max_categories data, if any
args.max_categories = get_metadata(dataset, "max_categories", args.max_categories)
other_label = get_metadata(dataset, "other_label", other_label)
if args.model_file:
# model is retrieved from the contents of the given local JSON file
model, csv_properties, fields = u.read_local_resource(args.model_file, csv_properties=csv_properties)
models = [model]
model_ids = [model["resource"]]
ensemble_ids = []
elif args.ensemble_file:
# model is retrieved from the contents of the given local JSON file
ensemble, csv_properties, fields = u.read_local_resource(args.ensemble_file, csv_properties=csv_properties)
model_ids = ensemble["object"]["models"][:]
ensemble_ids = [ensemble["resource"]]
models = model_ids[:]
model = retrieve_resource(bigml.api.BigML(storage="./storage"), models[0], query_string=r.ALL_FIELDS_QS)
models[0] = model
else:
# model is retrieved from the remote object
models, model_ids, ensemble_ids, resume = pm.models_processing(
datasets,
models,
model_ids,
api,
args,
resume,
fields=fields,
session_file=session_file,
path=path,
log=log,
labels=labels,
multi_label_data=multi_label_data,
other_label=other_label,
)
if models:
model = models[0]
single_model = len(models) == 1
# If multi-label flag is set and no training_set was provided, label
# info is extracted from the user_metadata. If models belong to an
# ensemble, the ensemble must be retrieved to get the user_metadata.
if model and args.multi_label and multi_label_data is None:
if len(ensemble_ids) > 0 and isinstance(ensemble_ids[0], dict):
resource = ensemble_ids[0]
elif belongs_to_ensemble(model):
ensemble_id = get_ensemble_id(model)
resource = r.get_ensemble(ensemble_id, api=api, verbosity=args.verbosity, session_file=session_file)
else:
resource = model
multi_label_data = l.get_multi_label_data(resource)
# We update the model's public state if needed
if model:
if isinstance(model, basestring) or bigml.api.get_status(model)["code"] != bigml.api.FINISHED:
if not args.evaluate and not a.has_train(args):
query_string = MINIMUM_MODEL
elif not args.test_header:
query_string = r.ALL_FIELDS_QS
else:
query_string = "%s;%s" % (r.ALL_FIELDS_QS, r.FIELDS_QS)
model = u.check_resource(model, api.get_model, query_string=query_string)
models[0] = model
if args.black_box or args.white_box or (args.shared_flag and r.shared_changed(args.shared, model)):
model_args = {}
if args.shared_flag and r.shared_changed(args.shared, model):
model_args.update(shared=args.shared)
if args.black_box or args.white_box:
model_args.update(r.set_publish_model_args(args))
if model_args:
model = r.update_model(model, model_args, args, api=api, path=path, session_file=session_file)
models[0] = model
# We get the fields of the model if we haven't got
# them yet and need them
if model and not args.evaluate and args.test_set:
# If more than one model, use the full field structure
if not single_model and not args.multi_label and belongs_to_ensemble(model):
if len(ensemble_ids) > 0:
ensemble_id = ensemble_ids[0]
else:
ensemble_id = get_ensemble_id(model)
fields = pm.get_model_fields(
model, csv_properties, args, single_model=single_model, multi_label_data=multi_label_data
)
# Free memory after getting fields
# local_ensemble = None
gc.collect()
# Fills in all_labels from user_metadata
if args.multi_label and not all_labels:
(args.objective_field, labels, all_labels, multi_label_fields) = l.multi_label_sync(
args.objective_field, labels, multi_label_data, fields, multi_label_fields
)
if model:
# retrieves max_categories data, if any
args.max_categories = get_metadata(model, "max_categories", args.max_categories)
other_label = get_metadata(model, "other_label", other_label)
# If predicting
if models and (a.has_test(args) or (test_dataset and args.remote)) and not args.evaluate:
models_per_label = 1
if test_dataset is None:
test_dataset = get_test_dataset(args)
if args.multi_label:
# When prediction starts from existing models, the
# multi_label_fields can be retrieved from the user_metadata
# in the models
if args.multi_label_fields is None and multi_label_fields:
multi_label_field_names = [field[1] for field in multi_label_fields]
args.multi_label_fields = ",".join(multi_label_field_names)
test_set = ps.multi_label_expansion(
args.test_set, args.test_header, args, path, labels=labels, session_file=session_file, input_flag=True
)[0]
test_set_header = True
# Remote predictions: predictions are computed as batch predictions
# in bigml.com except when --no-batch flag is set on or multi-label
# or max-categories are used
if (
args.remote
and not args.no_batch
and not args.multi_label
and not args.method in [THRESHOLD_CODE, COMBINATION]
):
# create test source from file
test_name = "%s - test" % args.name
if args.test_source is None:
test_properties = ps.test_source_processing(
api, args, resume, session_file=session_file, path=path, log=log
)
(test_source, resume, csv_properties, test_fields) = test_properties
else:
test_source_id = bigml.api.get_source_id(args.test_source)
test_source = api.check_resource(test_source_id)
if test_dataset is None:
# create test dataset from test source
dataset_args = r.set_basic_dataset_args(args, name=test_name)
test_dataset, resume = pd.alternative_dataset_processing(
test_source, "test", dataset_args, api, args, resume, session_file=session_file, path=path, log=log
)
else:
test_dataset_id = bigml.api.get_dataset_id(test_dataset)
test_dataset = api.check_resource(test_dataset_id)
csv_properties.update(objective_field=None, objective_field_present=False)
test_fields = pd.get_fields_structure(test_dataset, csv_properties)
batch_prediction_args = r.set_batch_prediction_args(args, fields=fields, dataset_fields=test_fields)
remote_predict(
model,
test_dataset,
batch_prediction_args,
args,
api,
resume,
prediction_file=output,
session_file=session_file,
path=path,
log=log,
)
else:
models_per_label = args.number_of_models
if args.multi_label and len(ensemble_ids) > 0 and args.number_of_models == 1:
# use case where ensembles are read from a file
models_per_label = len(models) / len(ensemble_ids)
predict(
models,
fields,
args,
api=api,
log=log,
resume=resume,
session_file=session_file,
labels=labels,
models_per_label=models_per_label,
other_label=other_label,
multi_label_data=multi_label_data,
)
# When combine_votes flag is used, retrieve the predictions files saved
# in the comma separated list of directories and combine them
if args.votes_files_:
model_id = re.sub(r".*(model_[a-f0-9]{24})__predictions\.csv$", r"\1", args.votes_files_[0]).replace("_", "/")
try:
model = u.check_resource(model_id, api.get_model)
except ValueError, exception:
sys.exit("Failed to get model %s: %s" % (model_id, str(exception)))
local_model = Model(model)
message = u.dated("Combining votes.\n")
u.log_message(message, log_file=session_file, console=args.verbosity)
combine_votes(args.votes_files_, local_model.to_prediction, output, method=args.method)
def __init__(self, model, api=None):
"""The Model constructor can be given as first argument:
- a model structure
- a model id
- a path to a JSON file containing a model structure
"""
self.resource_id = None
self.ids_map = {}
self.terms = {}
# the string can be a path to a JSON file
if isinstance(model, basestring):
try:
with open(model) as model_file:
model = json.load(model_file)
self.resource_id = get_model_id(model)
if self.resource_id is None:
raise ValueError("The JSON file does not seem"
" to contain a valid BigML model"
" representation.")
except IOError:
# if it is not a path, it can be a model id
self.resource_id = get_model_id(model)
if self.resource_id is None:
if model.find('model/') > -1:
raise Exception(
api.error_message(model,
resource_type='model',
method='get'))
else:
raise IOError("Failed to open the expected JSON file"
" at %s" % model)
except ValueError:
raise ValueError("Failed to interpret %s."
" JSON file expected.")
# checks whether the information needed for local predictions is in
# the first argument
if isinstance(model, dict) and \
not check_model_fields(model):
# if the fields used by the model are not
# available, use only ID to retrieve it again
model = get_model_id(model)
self.resource_id = model
if not (isinstance(model, dict) and 'resource' in model and
model['resource'] is not None):
if api is None:
api = BigML(storage=STORAGE)
query_string = ONLY_MODEL
model = retrieve_resource(api, self.resource_id,
query_string=query_string)
else:
self.resource_id = get_model_id(model)
BaseModel.__init__(self, model, api=api)
if 'object' in model and isinstance(model['object'], dict):
model = model['object']
if 'model' in model and isinstance(model['model'], dict):
status = get_status(model)
if 'code' in status and status['code'] == FINISHED:
distribution = model['model']['distribution']['training']
# will store global information in the tree: regression and
# max_bins number
tree_info = {'max_bins': 0}
self.tree = Tree(
model['model']['root'],
self.fields,
objective_field=self.objective_id,
root_distribution=distribution,
parent_id=None,
ids_map=self.ids_map,
tree_info=tree_info)
self.tree.regression = tree_info['regression']
if self.tree.regression:
self._max_bins = tree_info['max_bins']
else:
raise Exception("The model isn't finished yet")
else:
raise Exception("Cannot create the Model instance. Could not"
" find the 'model' key in the resource:\n\n%s" %
model)
if self.tree.regression:
try:
import numpy
import scipy
self.regression_ready = True
except ImportError:
self.regression_ready = False
