def get_delete_list(args, api, query_list):
"""Building the list of resources to be deleted by adding the tag
filtering user options to the
previous ones for all the filtered resource types.
"""
resource_selectors = filtered_selectors(args, api)
delete_list = []
if resource_selectors:
for selector, api_call, filter_linked in resource_selectors:
query_value = args.all_tag
type_query_list = query_list[:]
if args.all_tag or selector:
if selector:
query_value = selector
type_query_list.append("tags__in=%s" % query_value)
if type_query_list and filter_linked:
type_query_list.append(filter_linked)
if type_query_list:
status_code = STATUS_CODES[args.status]
delete_list.extend(u.list_ids(api_call,
";".join(type_query_list),
status_code=status_code))
return delete_list
def get_delete_list(args, api, query_list):
"""Building the list of resources to be deleted by adding the tag
filtering user options to the
previous ones for all the filtered resource types.
"""
resource_selectors = filtered_selectors(args, api)
delete_list = []
if resource_selectors:
for selector, api_call, filter_linked in resource_selectors:
query_value = args.all_tag
type_query_list = query_list[:]
if args.all_tag or selector:
if selector:
query_value = selector
type_query_list.append("tags__in=%s" % query_value)
if type_query_list and filter_linked:
type_query_list.append(filter_linked)
if type_query_list:
status_code = STATUS_CODES[args.status]
delete_list.extend(
u.list_ids(api_call,
";".join(type_query_list),
status_code=status_code))
return delete_list
def transform_dataset_options(command_args, api):
"""Retrieves the dataset ids from the different input options
"""
try:
dataset_ids = None
command_args.dataset_ids = []
# Parses dataset/id if provided.
if command_args.datasets:
dataset_ids = u.read_datasets(command_args.datasets)
if len(dataset_ids) == 1:
command_args.dataset = dataset_ids[0]
command_args.dataset_ids = dataset_ids
except Exception:
pass
# Reading test dataset ids is delayed till the very moment of use to ensure
# that the newly generated resources files can be used there too
command_args.test_dataset_ids = []
try:
# Retrieve dataset/ids if provided.
if command_args.dataset_tag:
dataset_ids = dataset_ids.extend(
u.list_ids(api.list_datasets,
"tags__in=%s" % command_args.dataset_tag))
if len(dataset_ids) == 1:
command_args.dataset = dataset_ids[0]
command_args.dataset_ids = dataset_ids
except Exception:
pass
def transform_dataset_options(command_args, api):
"""Retrieves the dataset ids from the different input options
"""
dataset_ids = None
command_args.dataset_ids = []
# Parses dataset/id if provided.
if command_args.datasets:
dataset_ids = u.read_datasets(command_args.datasets)
if len(dataset_ids) == 1:
command_args.dataset = dataset_ids[0]
command_args.dataset_ids = dataset_ids
# Reading test dataset ids is delayed till the very moment of use to ensure
# that the newly generated resources files can be used there too
command_args.test_dataset_ids = []
# Retrieve dataset/ids if provided.
if command_args.dataset_tag:
dataset_ids = dataset_ids.extend(
u.list_ids(api.list_datasets,
"tags__in=%s" % command_args.dataset_tag))
if len(dataset_ids) == 1:
command_args.dataset = dataset_ids[0]
command_args.dataset_ids = dataset_ids
def delete_resources(command_args, api):
"""Deletes the resources selected by the user given options
"""
if command_args.predictions is None:
path = a.NOW
else:
path = u.check_dir(command_args.predictions)
session_file = "%s%s%s" % (path, os.sep, SESSIONS_LOG)
message = u.dated("Retrieving objects to delete.\n")
u.log_message(message, log_file=session_file,
console=command_args.verbosity)
delete_list = []
if command_args.delete_list:
delete_list = map(str.strip,
command_args.delete_list.split(','))
if command_args.delete_file:
if not os.path.exists(command_args.delete_file):
sys.exit("File %s not found" % command_args.delete_file)
delete_list.extend([line for line
in open(command_args.delete_file, "r")])
resource_selectors = [
(command_args.source_tag, api.list_sources),
(command_args.dataset_tag, api.list_datasets),
(command_args.model_tag, api.list_models),
(command_args.prediction_tag, api.list_predictions),
(command_args.evaluation_tag, api.list_evaluations),
(command_args.ensemble_tag, api.list_ensembles),
(command_args.batch_prediction_tag, api.list_batch_predictions)]
for selector, api_call in resource_selectors:
query_string = None
if command_args.all_tag:
query_string = "tags__in=%s" % command_args.all_tag
elif selector:
query_string = "tags__in=%s" % selector
if query_string:
delete_list.extend(u.list_ids(api_call, query_string))
message = u.dated("Deleting objects.\n")
u.log_message(message, log_file=session_file,
console=command_args.verbosity)
message = "\n".join(delete_list)
u.log_message(message, log_file=session_file)
u.delete(api, delete_list)
if sys.platform == "win32" and sys.stdout.isatty():
message = (u"\nGenerated files:\n\n" +
unicode(u.print_tree(path, " "), "utf-8") + u"\n")
else:
message = "\nGenerated files:\n\n" + u.print_tree(path, " ") + "\n"
u.log_message(message, log_file=session_file,
console=command_args.verbosity)
def transform_dataset_options(command_args, api):
"""Retrieves the dataset ids from the different input options
"""
command_args.dataset_ids = []
command_args.test_dataset_ids = []
try:
dataset_ids = None
# Parses dataset/id if provided.
if command_args.datasets:
dataset_ids = u.read_datasets(command_args.datasets)
if dataset_ids:
command_args.dataset = dataset_ids[-1]
command_args.dataset_ids = dataset_ids
except Exception:
pass
# Reading test dataset ids is delayed till the very moment of use to ensure
# that the newly generated resources files can be used there too
try:
# Retrieve dataset/ids if provided.
if command_args.dataset_tag:
dataset_ids = dataset_ids.extend(
u.list_ids(api.list_datasets,
"tags__in=%s" % command_args.dataset_tag))
if dataset_ids:
command_args.dataset = dataset_ids[-1]
command_args.dataset_ids = dataset_ids
except Exception:
pass
# if datasets_json is set, read it info in datasets
try:
if hasattr(command_args, 'datasets_json') \
and command_args.datasets_json:
command_args.dataset_ids = json.loads(command_args.datasets_json)
if dataset_ids:
command_args.dataset = command_args.dataset_ids[-1]
except AttributeError:
pass
def transform_dataset_options(command_args, api):
"""Retrieves the dataset ids from the different input options
"""
command_args.dataset_ids = []
command_args.test_dataset_ids = []
try:
dataset_ids = None
# Parses dataset/id if provided.
if command_args.datasets:
dataset_ids = u.read_datasets(command_args.datasets)
if len(dataset_ids) > 0:
command_args.dataset = dataset_ids[-1]
command_args.dataset_ids = dataset_ids
except Exception:
pass
# Reading test dataset ids is delayed till the very moment of use to ensure
# that the newly generated resources files can be used there too
try:
# Retrieve dataset/ids if provided.
if command_args.dataset_tag:
dataset_ids = dataset_ids.extend(
u.list_ids(api.list_datasets,
"tags__in=%s" % command_args.dataset_tag))
if len(dataset_ids) > 0:
command_args.dataset = dataset_ids[-1]
command_args.dataset_ids = dataset_ids
except Exception:
pass
# if datasets_json is set, read it info in datasets
try:
if hasattr(command_args, 'datasets_json') \
and command_args.datasets_json:
command_args.dataset_ids = json.loads(command_args.datasets_json)
if len(dataset_ids) > 0:
command_args.dataset = command_args.dataset_ids[-1]
except AttributeError:
pass
def transform_args(command_args, flags, api, user_defaults):
"""Transforms the formatted argument strings into structured arguments
"""
# Parses attributes in json format if provided
command_args.json_args = {}
json_attribute_options = {
'source': command_args.source_attributes,
'dataset': command_args.dataset_attributes,
'model': command_args.model_attributes,
'ensemble': command_args.ensemble_attributes,
'evaluation': command_args.evaluation_attributes,
'batch_prediction': command_args.batch_prediction_attributes}
for resource_type, attributes_file in json_attribute_options.items():
if attributes_file is not None:
command_args.json_args[resource_type] = u.read_json(
attributes_file)
else:
command_args.json_args[resource_type] = {}
# Parses dataset generators in json format if provided
if command_args.new_fields:
json_generators = u.read_json(command_args.new_fields)
command_args.dataset_json_generators = json_generators
else:
command_args.dataset_json_generators = {}
# Parses multi-dataset attributes in json such as field maps
if command_args.multi_dataset_attributes:
multi_dataset_json = u.read_json(command_args.multi_dataset_attributes)
command_args.multi_dataset_json= multi_dataset_json
else:
command_args.multi_dataset_json = {}
dataset_ids = None
command_args.dataset_ids = []
# Parses dataset/id if provided.
if command_args.datasets:
dataset_ids = u.read_datasets(command_args.datasets)
if len(dataset_ids) == 1:
command_args.dataset = dataset_ids[0]
command_args.dataset_ids = dataset_ids
test_dataset_ids = None
command_args.test_dataset_ids = []
# Parses dataset/id if provided.
if command_args.test_datasets:
test_dataset_ids = u.read_datasets(command_args.test_datasets)
command_args.test_dataset_ids = test_dataset_ids
# Retrieve dataset/ids if provided.
if command_args.dataset_tag:
dataset_ids = dataset_ids.extend(
u.list_ids(api.list_datasets,
"tags__in=%s" % command_args.dataset_tag))
if len(dataset_ids) == 1:
command_args.dataset = dataset_ids[0]
command_args.dataset_ids = dataset_ids
# Reads a json filter if provided.
if command_args.json_filter:
json_filter = u.read_json_filter(command_args.json_filter)
command_args.json_filter = json_filter
# Reads a lisp filter if provided.
if command_args.lisp_filter:
lisp_filter = u.read_lisp_filter(command_args.lisp_filter)
command_args.lisp_filter = lisp_filter
# Adds default tags unless that it is requested not to do so.
if command_args.no_tag:
command_args.tag.append('BigMLer')
command_args.tag.append('BigMLer_%s' % NOW)
# Checks combined votes method
if (command_args.method and command_args.method != COMBINATION_LABEL and
not (command_args.method in COMBINATION_WEIGHTS.keys())):
command_args.method = 0
else:
combiner_methods = dict([[value, key]
for key, value in COMBINER_MAP.items()])
combiner_methods[COMBINATION_LABEL] = COMBINATION
command_args.method = combiner_methods.get(command_args.method, 0)
# Checks missing_strategy
if (command_args.missing_strategy and
not (command_args.missing_strategy in MISSING_STRATEGIES.keys())):
command_args.missing_strategy = 0
else:
command_args.missing_strategy = MISSING_STRATEGIES.get(
command_args.missing_strategy, 0)
# Adds replacement=True if creating ensemble and nothing is specified
if (command_args.number_of_models > 1 and
not command_args.replacement and
not '--no-replacement' in flags and
not 'replacement' in user_defaults and
not '--no-randomize' in flags and
not 'randomize' in user_defaults and
not '--sample-rate' in flags and
not 'sample_rate' in user_defaults):
command_args.replacement = True
# Old value for --prediction-info='full data' maps to 'full'
if command_args.prediction_info == 'full data':
print "WARNING: 'full data' is a deprecated value. Use 'full' instead"
command_args.prediction_info = FULL_FORMAT
# Parses class, weight pairs for objective weight
if command_args.objective_weights:
objective_weights = (
u.read_objective_weights(command_args.objective_weights))
command_args.objective_weights_json = objective_weights
command_args.multi_label_fields_list = []
if command_args.multi_label_fields is not None:
multi_label_fields = command_args.multi_label_fields.strip()
command_args.multi_label_fields_list = multi_label_fields.split(
command_args.args_separator)
# Sets shared_flag if --shared or --unshared has been used
if '--shared' in flags or '--unshared' in flags:
command_args.shared_flag = True
else:
command_args.shared_flag = False
def transform_args(command_args, flags, api, user_defaults):
"""Transforms the formatted argument strings into structured arguments
"""
# Parses attributes in json format if provided
command_args.json_args = {}
for resource_type in RESOURCE_TYPES:
attributes_file = getattr(command_args,
"%s_attributes" % resource_type, None)
if attributes_file is not None:
command_args.json_args[resource_type] = u.read_json(
attributes_file)
else:
command_args.json_args[resource_type] = {}
# Parses dataset generators in json format if provided
if command_args.new_fields:
json_generators = u.read_json(command_args.new_fields)
command_args.dataset_json_generators = json_generators
else:
command_args.dataset_json_generators = {}
# Parses multi-dataset attributes in json such as field maps
if command_args.multi_dataset_attributes:
multi_dataset_json = u.read_json(command_args.multi_dataset_attributes)
command_args.multi_dataset_json = multi_dataset_json
else:
command_args.multi_dataset_json = {}
dataset_ids = None
command_args.dataset_ids = []
# Parses dataset/id if provided.
if command_args.datasets:
dataset_ids = u.read_datasets(command_args.datasets)
if len(dataset_ids) == 1:
command_args.dataset = dataset_ids[0]
command_args.dataset_ids = dataset_ids
# Reading test dataset ids is delayed till the very moment of use to ensure
# that the newly generated resources files can be used there too
command_args.test_dataset_ids = []
# Retrieve dataset/ids if provided.
if command_args.dataset_tag:
dataset_ids = dataset_ids.extend(
u.list_ids(api.list_datasets,
"tags__in=%s" % command_args.dataset_tag))
if len(dataset_ids) == 1:
command_args.dataset = dataset_ids[0]
command_args.dataset_ids = dataset_ids
# Reads a json filter if provided.
if command_args.json_filter:
json_filter = u.read_json_filter(command_args.json_filter)
command_args.json_filter = json_filter
# Reads a lisp filter if provided.
if command_args.lisp_filter:
lisp_filter = u.read_lisp_filter(command_args.lisp_filter)
command_args.lisp_filter = lisp_filter
# Adds default tags unless that it is requested not to do so.
if command_args.no_tag:
command_args.tag.append('BigMLer')
command_args.tag.append('BigMLer_%s' % NOW)
# Checks combined votes method
try:
if (command_args.method and command_args.method != COMBINATION_LABEL
and not (command_args.method in COMBINATION_WEIGHTS.keys())):
command_args.method = 0
else:
combiner_methods = dict(
[[value, key] for key, value in COMBINER_MAP.items()])
combiner_methods[COMBINATION_LABEL] = COMBINATION
command_args.method = combiner_methods.get(command_args.method, 0)
except AttributeError:
pass
# Checks missing_strategy
try:
if (command_args.missing_strategy and
not (command_args.missing_strategy in
MISSING_STRATEGIES.keys())):
command_args.missing_strategy = 0
else:
command_args.missing_strategy = MISSING_STRATEGIES.get(
command_args.missing_strategy, 0)
except AttributeError:
pass
# Adds replacement=True if creating ensemble and nothing is specified
try:
if (command_args.number_of_models > 1 and
not command_args.replacement and
not '--no-replacement' in flags and
not 'replacement' in user_defaults and
not '--no-randomize' in flags and
not 'randomize' in user_defaults and
not '--sample-rate' in flags and
not 'sample_rate' in user_defaults):
command_args.replacement = True
except AttributeError:
pass
try:
# Old value for --prediction-info='full data' maps to 'full'
if command_args.prediction_info == 'full data':
print ("WARNING: 'full data' is a deprecated value. Use"
" 'full' instead")
command_args.prediction_info = FULL_FORMAT
except AttributeError:
pass
# Parses class, weight pairs for objective weight
try:
if command_args.objective_weights:
objective_weights = (
u.read_objective_weights(command_args.objective_weights))
command_args.objective_weights_json = objective_weights
except AttributeError:
pass
try:
command_args.multi_label_fields_list = []
if command_args.multi_label_fields is not None:
multi_label_fields = command_args.multi_label_fields.strip()
command_args.multi_label_fields_list = multi_label_fields.split(
command_args.args_separator)
except AttributeError:
pass
# Sets shared_flag if --shared or --unshared has been used
if '--shared' in flags or '--unshared' in flags:
command_args.shared_flag = True
else:
command_args.shared_flag = False
# Set remote on if scoring a trainind dataset in bigmler anomaly
try:
if command_args.score:
command_args.remote = True
if not "--prediction-info" in flags:
command_args.prediction_info = FULL_FORMAT
except AttributeError:
pass
command_args.has_models_ = (
(hasattr(command_args, 'model') and command_args.model) or
(hasattr(command_args, 'models') and command_args.models) or
(hasattr(command_args, 'ensemble') and command_args.ensemble) or
(hasattr(command_args, 'ensembles') and command_args.ensembles) or
(hasattr(command_args, 'cluster') and command_args.cluster) or
(hasattr(command_args, 'clusters') and command_args.clusters) or
(hasattr(command_args, 'model_tag') and command_args.model_tag) or
(hasattr(command_args, 'anomaly') and command_args.anomaly) or
(hasattr(command_args, 'anomalies') and command_args.anomalies) or
(hasattr(command_args, 'ensemble_tag')
and command_args.ensemble_tag) or
(hasattr(command_args, 'cluster_tag') and command_args.cluster_tag) or
(hasattr(command_args, 'anomaly_tag') and command_args.anomaly_tag))
command_args.has_datasets_ = (
(hasattr(command_args, 'dataset') and command_args.dataset) or
(hasattr(command_args, 'datasets') and command_args.datasets) or
(hasattr(command_args, 'dataset_tag') and command_args.dataset_tag))
command_args.has_test_datasets_ = (
(hasattr(command_args, 'test_dataset') and
command_args.test_dataset) or
(hasattr(command_args, 'test_datasets') and
command_args.test_datasets) or
(hasattr(command_args, 'test_dataset_tag') and
command_args.test_dataset_tag))
def get_output_args(api, command_args, resume):
"""Returns the output args needed for the main bigmler computation process
"""
try:
if command_args.train_stdin:
if command_args.test_stdin:
sys.exit("The standard input can't be used both for training "
"and testing. Choose one of them")
command_args.training_set = StringIO(sys.stdin.read())
elif command_args.test_stdin:
command_args.test_set = StringIO(sys.stdin.read())
except AttributeError:
pass
try:
if command_args.objective_field:
objective = command_args.objective_field
try:
command_args.objective_field = int(objective)
except ValueError:
if not command_args.train_header:
sys.exit("The %s has been set as objective field but"
" the file has not been marked as containing"
" headers.\nPlease set the --train-header flag if"
" the file has headers or use a column number"
" to set the objective field." % objective)
except AttributeError:
pass
command_args.resume_ = resume
# Reads description if provided.
try:
if command_args.description:
description_arg = u.read_description(command_args.description)
command_args.description_ = description_arg
else:
command_args.description_ = DEFAULT_DESCRIPTION
except AttributeError:
pass
# Parses fields if provided.
try:
if command_args.field_attributes:
field_attributes_arg = (u.read_field_attributes(
command_args.field_attributes))
command_args.field_attributes_ = field_attributes_arg
else:
command_args.field_attributes_ = []
except AttributeError:
pass
try:
if command_args.test_field_attributes:
field_attributes_arg = (u.read_field_attributes(
command_args.test_field_attributes))
command_args.test_field_attributes_ = field_attributes_arg
else:
command_args.test_field_attributes_ = []
except AttributeError:
pass
# Parses types if provided.
try:
if command_args.types:
types_arg = u.read_types(command_args.types)
command_args.types_ = types_arg
else:
command_args.types_ = None
if command_args.test_types:
types_arg = u.read_types(command_args.test_types)
command_args.test_types_ = types_arg
else:
command_args.test_types_ = None
except AttributeError:
pass
# Parses dataset fields if provided.
try:
if command_args.dataset_fields:
dataset_fields_arg = [
field.strip() for field in command_args.dataset_fields.split(
command_args.args_separator)
]
command_args.dataset_fields_ = dataset_fields_arg
else:
command_args.dataset_fields_ = []
except AttributeError:
pass
# Parses model input fields if provided.
try:
if command_args.model_fields:
model_fields_arg = [
field.strip() for field in command_args.model_fields.split(
command_args.args_separator)
]
command_args.model_fields_ = model_fields_arg
else:
command_args.model_fields_ = []
except AttributeError:
pass
# Parses cluster input fields if provided.
try:
if command_args.cluster_fields:
cluster_fields_arg = [
field.strip() for field in command_args.cluster_fields.split(
command_args.args_separator)
]
command_args.cluster_fields_ = cluster_fields_arg
else:
command_args.cluster_fields_ = []
except AttributeError:
pass
# Parses anomaly input fields if provided.
try:
if command_args.anomaly_fields:
anomaly_fields_arg = [
field.strip() for field in command_args.anomaly_fields.split(
command_args.args_separator)
]
command_args.anomaly_fields_ = anomaly_fields_arg
else:
command_args.anomaly_fields_ = []
except AttributeError:
pass
model_ids = []
try:
# Parses model/ids if provided.
if command_args.models:
model_ids = u.read_resources(command_args.models)
command_args.model_ids_ = model_ids
except AttributeError:
pass
# Retrieve model/ids if provided.
try:
if command_args.model_tag:
model_ids = (model_ids + u.list_ids(
api.list_models, "tags__in=%s" % command_args.model_tag))
command_args.model_ids_ = model_ids
except AttributeError:
pass
# Reads votes files in the provided directories.
try:
if command_args.votes_dirs:
dirs = [
directory.strip() for directory in
command_args.votes_dirs.split(command_args.args_separator)
]
votes_path = os.path.dirname(command_args.predictions)
votes_files = u.read_votes_files(dirs, votes_path)
command_args.votes_files_ = votes_files
else:
command_args.votes_files_ = []
except AttributeError:
pass
# Parses fields map if provided.
try:
if command_args.fields_map:
fields_map_arg = u.read_fields_map(command_args.fields_map)
command_args.fields_map_ = fields_map_arg
else:
command_args.fields_map_ = None
except AttributeError:
pass
cluster_ids = []
try:
# Parses cluster/ids if provided.
if command_args.clusters:
cluster_ids = u.read_resources(command_args.clusters)
command_args.cluster_ids_ = cluster_ids
except AttributeError:
pass
# Retrieve cluster/ids if provided.
try:
if command_args.cluster_tag:
cluster_ids = (cluster_ids + u.list_ids(
api.list_clusters, "tags__in=%s" % command_args.cluster_tag))
command_args.cluster_ids_ = cluster_ids
except AttributeError:
pass
# Parses cluster names to generate datasets if provided
try:
if command_args.cluster_datasets:
cluster_datasets_arg = [
dataset.strip()
for dataset in command_args.cluster_datasets.split(
command_args.args_separator)
]
command_args.cluster_datasets_ = cluster_datasets_arg
else:
command_args.cluster_datasets_ = []
except AttributeError:
pass
# Parses cluster names to generate models if provided
try:
if command_args.cluster_models:
cluster_models_arg = [
model.strip() for model in command_args.cluster_models.split(
command_args.args_separator)
]
command_args.cluster_models_ = cluster_models_arg
else:
command_args.cluster_models_ = []
except AttributeError:
pass
anomaly_ids = []
try:
# Parses anomaly/ids if provided.
if command_args.anomalies:
anomaly_ids = u.read_resources(command_args.anomalies)
command_args.anomaly_ids_ = anomaly_ids
except AttributeError:
pass
# Retrieve anomaly/ids if provided.
try:
if command_args.anomaly_tag:
anomaly_ids = (anomaly_ids + u.list_ids(
api.list_anomalies, "tags__in=%s" % command_args.anomaly_tag))
command_args.anomaly_ids_ = anomaly_ids
except AttributeError:
pass
sample_ids = []
try:
# Parses sample/ids if provided.
if command_args.samples:
sample_ids = u.read_resources(command_args.samples)
command_args.sample_ids_ = sample_ids
except AttributeError:
pass
# Retrieve sample/ids if provided.
try:
if command_args.sample_tag:
sample_ids = (sample_ids + u.list_ids(
api.list_samples, "tags__in=%s" % command_args.sample_tag))
command_args.sample_ids_ = sample_ids
except AttributeError:
pass
# Parses sample row fields
try:
if command_args.row_fields:
row_fields_arg = [
field.strip() for field in command_args.row_fields.split(
command_args.args_separator)
]
command_args.row_fields_ = row_fields_arg
else:
command_args.row_fields_ = []
except AttributeError:
pass
# Parses sample stat_fields
try:
if command_args.stat_fields:
stat_fields_arg = [
field.strip() for field in command_args.stat_fields.split(
command_args.args_separator)
]
command_args.stat_fields_ = stat_fields_arg
else:
command_args.stat_fields_ = []
except AttributeError:
pass
return {"api": api, "args": command_args}
def delete_resources(command_args, api):
"""Deletes the resources selected by the user given options
"""
if command_args.predictions is None:
path = a.NOW
else:
path = u.check_dir(command_args.predictions)
session_file = "%s%s%s" % (path, os.sep, SESSIONS_LOG)
message = u.dated("Retrieving objects to delete.\n")
u.log_message(message, log_file=session_file,
console=command_args.verbosity)
delete_list = []
if command_args.delete_list:
delete_list = map(str.strip,
command_args.delete_list.split(','))
if command_args.delete_file:
if not os.path.exists(command_args.delete_file):
sys.exit("File %s not found" % command_args.delete_file)
delete_list.extend([line for line
in open(command_args.delete_file, "r")])
resource_selectors = [
("source", command_args.source_tag, api.list_sources),
("dataset", command_args.dataset_tag, api.list_datasets),
("model", command_args.model_tag, api.list_models),
("prediction", command_args.prediction_tag, api.list_predictions),
("ensemble", command_args.ensemble_tag, api.list_ensembles),
("evaluation", command_args.evaluation_tag, api.list_evaluations),
("batchprediction", command_args.batch_prediction_tag,
api.list_batch_predictions)]
query_string = None
if command_args.older_than:
date_str = get_date(command_args.older_than, api)
if date_str:
query_string = "created__lt=%s" % date_str
else:
sys.exit("The --older-than and --newer-than flags only accept "
"integers (number of days), dates in YYYY-MM-DD format "
" and resource ids. Please, double-check your input.")
if command_args.newer_than:
date_str = get_date(command_args.newer_than, api)
if date_str:
if query_string is None:
query_string = ""
else:
query_string += ";"
query_string += "created__gt=%s" % date_str
else:
sys.exit("The --older-than and --newer-than flags only accept "
"integers (number of days), dates in YYYY-MM-DD format "
" and resource ids. Please, double-check your input.")
if (any([selector[1] is not None for selector in resource_selectors]) or
command_args.all_tag):
if query_string is None:
query_string = ""
else:
query_string += ";"
query_value = command_args.all_tag
for label, selector, api_call in resource_selectors:
combined_query = query_string
if not query_value and selector:
query_value = selector
if command_args.all_tag or selector:
combined_query += "tags__in=%s" % query_value
if label == "model":
# avoid ensemble's models
combined_query += ";ensemble=false"
delete_list.extend(u.list_ids(api_call, combined_query))
else:
if query_string:
for label, selector, api_call in resource_selectors:
combined_query = query_string
if label == "model":
# avoid ensemble's models
combined_query += ";ensemble=false"
delete_list.extend(u.list_ids(api_call, combined_query))
message = u.dated("Deleting objects.\n")
u.log_message(message, log_file=session_file,
console=command_args.verbosity)
message = "\n".join(delete_list)
u.log_message(message, log_file=session_file)
u.delete(api, delete_list)
if sys.platform == "win32" and sys.stdout.isatty():
message = (u"\nGenerated files:\n\n" +
unicode(u.print_tree(path, " "), "utf-8") + u"\n")
else:
message = "\nGenerated files:\n\n" + u.print_tree(path, " ") + "\n"
u.log_message(message, log_file=session_file,
console=command_args.verbosity)
def get_output_args(api, train_stdin, test_stdin, command_args, resume):
"""Returns the output args needed for the main bigmler computation process
"""
if train_stdin:
if test_stdin:
sys.exit("The standard input can't be used both for training and"
" testing. Choose one of them")
command_args.training_set = StringIO.StringIO(sys.stdin.read())
elif test_stdin:
command_args.test_set = StringIO.StringIO(sys.stdin.read())
if command_args.objective_field:
objective = command_args.objective_field
try:
command_args.objective_field = int(objective)
except ValueError:
if not command_args.train_header:
sys.exit("The %s has been set as objective field but"
" the file has not been marked as containing"
" headers.\nPlease set the --train-header flag if"
" the file has headers or use a column number"
" to set the objective field." % objective)
output_args = {
"api": api,
"training_set": command_args.training_set,
"test_set": command_args.test_set,
"output": command_args.predictions,
"objective_field": command_args.objective_field,
"name": command_args.name,
"training_set_header": command_args.train_header,
"test_set_header": command_args.test_header,
"args": command_args,
"resume": resume,
}
# Reads description if provided.
if command_args.description:
description_arg = u.read_description(command_args.description)
output_args.update(description=description_arg)
else:
output_args.update(description="Created using BigMLer")
# Parses fields if provided.
if command_args.field_attributes:
field_attributes_arg = (u.read_field_attributes(
command_args.field_attributes))
output_args.update(field_attributes=field_attributes_arg)
if command_args.test_field_attributes:
field_attributes_arg = (u.read_field_attributes(
command_args.test_field_attributes))
output_args.update(test_field_attributes=field_attributes_arg)
# Parses types if provided.
if command_args.types:
types_arg = u.read_types(command_args.types)
output_args.update(types=types_arg)
if command_args.test_types:
types_arg = u.read_types(command_args.test_types)
output_args.update(test_types=types_arg)
# Parses dataset fields if provided.
if command_args.dataset_fields:
dataset_fields_arg = map(str.strip,
command_args.dataset_fields.split(','))
output_args.update(dataset_fields=dataset_fields_arg)
# Parses model input fields if provided.
if command_args.model_fields:
model_fields_arg = map(str.strip, command_args.model_fields.split(','))
output_args.update(model_fields=model_fields_arg)
model_ids = []
# Parses model/ids if provided.
if command_args.models:
model_ids = u.read_resources(command_args.models)
output_args.update(model_ids=model_ids)
# Retrieve model/ids if provided.
if command_args.model_tag:
model_ids = (model_ids + u.list_ids(
api.list_models, "tags__in=%s" % command_args.model_tag))
output_args.update(model_ids=model_ids)
# Reads votes files in the provided directories.
if command_args.votes_dirs:
dirs = map(str.strip, command_args.votes_dirs.split(','))
votes_path = os.path.dirname(command_args.predictions)
votes_files = u.read_votes_files(dirs, votes_path)
output_args.update(votes_files=votes_files)
# Parses fields map if provided.
if command_args.fields_map:
fields_map_arg = u.read_fields_map(command_args.fields_map)
output_args.update(fields_map=fields_map_arg)
return output_args
def transform_args(command_args, flags, api):
"""Transforms the formatted argument strings into structured arguments
"""
attribute_args(command_args)
# Parses dataset generators in json format if provided
try:
if command_args.new_fields:
json_generators = u.read_json(command_args.new_fields)
command_args.dataset_json_generators = json_generators
else:
command_args.dataset_json_generators = {}
except AttributeError:
pass
# Parses multi-dataset attributes in json such as field maps
try:
if command_args.multi_dataset_attributes:
multi_dataset_json = u.read_json(
command_args.multi_dataset_attributes)
command_args.multi_dataset_json = multi_dataset_json
else:
command_args.multi_dataset_json = {}
except AttributeError:
pass
transform_dataset_options(command_args, api)
script_ids = None
command_args.script_ids = []
# Parses script/id if provided.
try:
if command_args.scripts:
script_ids = u.read_resources(command_args.scripts)
if len(script_ids) == 1:
command_args.script = script_ids[0]
command_args.script_ids = script_ids
except AttributeError:
pass
# Retrieve script/ids if provided.
try:
if command_args.script_tag:
script_ids = script_ids.extend(
u.list_ids(api.list_scripts,
"tags__in=%s" % command_args.script_tag))
if len(script_ids) == 1:
command_args.script = script_ids[0]
command_args.script_ids = script_ids
except AttributeError:
pass
# Reads a json filter if provided.
try:
if command_args.json_filter:
json_filter = u.read_json_filter(command_args.json_filter)
command_args.json_filter = json_filter
except AttributeError:
pass
# Reads a lisp filter if provided.
try:
if command_args.lisp_filter:
lisp_filter = u.read_lisp_filter(command_args.lisp_filter)
command_args.lisp_filter = lisp_filter
except AttributeError:
pass
# Adds default tags unless that it is requested not to do so.
try:
if command_args.no_tag:
command_args.tag.append('BigMLer')
command_args.tag.append('BigMLer_%s' % NOW)
except AttributeError:
pass
# Checks combined votes method
try:
if (command_args.method and command_args.method != COMBINATION_LABEL
and not command_args.method in COMBINATION_WEIGHTS.keys()):
command_args.method = 0
else:
combiner_methods = dict(
[[value, key] for key, value in COMBINER_MAP.items()])
combiner_methods[COMBINATION_LABEL] = COMBINATION
command_args.method = combiner_methods.get(command_args.method, 0)
except AttributeError:
pass
# Checks missing_strategy
try:
if (command_args.missing_strategy and
not (command_args.missing_strategy in
MISSING_STRATEGIES.keys())):
command_args.missing_strategy = 0
else:
command_args.missing_strategy = MISSING_STRATEGIES.get(
command_args.missing_strategy, 0)
except AttributeError:
pass
try:
# Old value for --prediction-info='full data' maps to 'full'
if command_args.prediction_info == 'full data':
print ("WARNING: 'full data' is a deprecated value. Use"
" 'full' instead")
command_args.prediction_info = FULL_FORMAT
except AttributeError:
pass
# Parses class, weight pairs for objective weight
try:
if command_args.objective_weights:
objective_weights = (
u.read_objective_weights(command_args.objective_weights))
command_args.objective_weights_json = objective_weights
except AttributeError:
pass
try:
command_args.multi_label_fields_list = []
if command_args.multi_label_fields is not None:
multi_label_fields = command_args.multi_label_fields.strip()
command_args.multi_label_fields_list = multi_label_fields.split(
command_args.args_separator)
except AttributeError:
pass
# Sets shared_flag if --shared or --unshared has been used
command_args.shared_flag = '--shared' in flags or '--unshared' in flags
# Set remote on if scoring a trainind dataset in bigmler anomaly
try:
if command_args.score:
command_args.remote = True
if not "--prediction-info" in flags:
command_args.prediction_info = FULL_FORMAT
except AttributeError:
pass
command_args.has_supervised_ = (
(hasattr(command_args, 'model') and command_args.model) or
(hasattr(command_args, 'models') and command_args.models) or
(hasattr(command_args, 'ensemble') and command_args.ensemble) or
(hasattr(command_args, 'ensembles') and command_args.ensembles) or
(hasattr(command_args, 'model_tag') and command_args.model_tag) or
(hasattr(command_args, 'logistic_regression') and
command_args.logistic_regression) or
(hasattr(command_args, 'logistic_regressions') and
command_args.logistic_regressions) or
(hasattr(command_args, 'logistic_regression_tag') and
command_args.logistic_regression_tag) or
(hasattr(command_args, 'deepnet') and
command_args.deepnet) or
(hasattr(command_args, 'deepnets') and
command_args.deepnets) or
(hasattr(command_args, 'deepnet_tag') and
command_args.deepnet_tag) or
(hasattr(command_args, 'ensemble_tag')
and command_args.ensemble_tag))
command_args.has_models_ = (
command_args.has_supervised_ or
(hasattr(command_args, 'cluster') and command_args.cluster) or
(hasattr(command_args, 'clusters') and command_args.clusters) or
(hasattr(command_args, 'anomaly') and command_args.anomaly) or
(hasattr(command_args, 'anomalies') and command_args.anomalies) or
(hasattr(command_args, 'cluster_tag') and command_args.cluster_tag) or
(hasattr(command_args, 'anomaly_tag') and command_args.anomaly_tag))
command_args.has_datasets_ = (
(hasattr(command_args, 'dataset') and command_args.dataset) or
(hasattr(command_args, 'datasets') and command_args.datasets) or
(hasattr(command_args, 'dataset_tag') and command_args.dataset_tag))
command_args.has_test_datasets_ = (
(hasattr(command_args, 'test_dataset') and
command_args.test_dataset) or
(hasattr(command_args, 'test_datasets') and
command_args.test_datasets) or
(hasattr(command_args, 'test_dataset_tag') and
command_args.test_dataset_tag))
def get_output_args(api, command_args, resume):
"""Returns the output args needed for the main bigmler computation process
"""
try:
if command_args.train_stdin:
if command_args.test_stdin:
sys.exit("The standard input can't be used both for training "
"and testing. Choose one of them")
command_args.training_set = StringIO(sys.stdin.read())
elif command_args.test_stdin:
command_args.test_set = StringIO(sys.stdin.read())
except AttributeError:
pass
try:
if command_args.objective_field:
objective = command_args.objective_field
try:
command_args.objective_field = int(objective)
except ValueError:
if not command_args.train_header:
sys.exit("The %s has been set as objective field but"
" the file has not been marked as containing"
" headers.\nPlease set the --train-header flag if"
" the file has headers or use a column number"
" to set the objective field." % objective)
except AttributeError:
pass
command_args.resume_ = resume
command_args.predictions = command_args.output
# Reads description if provided.
try:
if command_args.description:
description_arg = u.read_description(command_args.description)
command_args.description_ = description_arg
else:
command_args.description_ = DEFAULT_DESCRIPTION
except AttributeError:
pass
# Parses fields if provided.
try:
if command_args.field_attributes:
field_attributes_arg = (
u.read_field_attributes(command_args.field_attributes))
command_args.field_attributes_ = field_attributes_arg
else:
command_args.field_attributes_ = []
except AttributeError:
pass
try:
if command_args.test_field_attributes:
field_attributes_arg = (
u.read_field_attributes(command_args.test_field_attributes))
command_args.test_field_attributes_ = field_attributes_arg
else:
command_args.test_field_attributes_ = []
except AttributeError:
pass
# Parses types if provided.
try:
if command_args.types:
types_arg = u.read_types(command_args.types)
command_args.types_ = types_arg
else:
command_args.types_ = None
if command_args.test_types:
types_arg = u.read_types(command_args.test_types)
command_args.test_types_ = types_arg
else:
command_args.test_types_ = None
except AttributeError:
pass
# Parses dataset fields if provided.
try:
if command_args.dataset_fields:
dataset_fields_arg = [
field.strip() for field in command_args.dataset_fields.split(
command_args.args_separator)]
command_args.dataset_fields_ = dataset_fields_arg
else:
command_args.dataset_fields_ = []
except AttributeError:
pass
# Parses model input fields if provided.
try:
if command_args.model_fields:
model_fields_arg = [
field.strip() for field in command_args.model_fields.split(
command_args.args_separator)]
command_args.model_fields_ = model_fields_arg
else:
command_args.model_fields_ = []
except AttributeError:
pass
# Parses cluster input fields if provided.
try:
if command_args.cluster_fields:
cluster_fields_arg = [
field.strip() for field in command_args.cluster_fields.split(
command_args.args_separator)]
command_args.cluster_fields_ = cluster_fields_arg
else:
command_args.cluster_fields_ = []
except AttributeError:
pass
# Parses association input fields if provided.
try:
if command_args.association_fields:
association_fields_arg = [
field.strip() for field in \
command_args.association_fields.split( \
command_args.args_separator)]
command_args.association_fields_ = association_fields_arg
else:
command_args.association_fields_ = []
except AttributeError:
pass
# Parses anomaly input fields if provided.
try:
if command_args.anomaly_fields:
anomaly_fields_arg = [
field.strip() for field in command_args.anomaly_fields.split(
command_args.args_separator)]
command_args.anomaly_fields_ = anomaly_fields_arg
else:
command_args.anomaly_fields_ = []
except AttributeError:
pass
# Parses logistic regression input fields if provided.
try:
if command_args.logistic_fields:
logistic_fields_arg = [
field.strip() for field in command_args.logistic_fields.split(
command_args.args_separator)]
command_args.logistic_fields_ = logistic_fields_arg
else:
command_args.logistic_fields_ = []
except AttributeError:
pass
# Parses deepnet input fields if provided.
try:
if command_args.deepnet_fields:
deepnet_fields_arg = [
field.strip() for field in command_args.deepnet_fields.split(
command_args.args_separator)]
command_args.deepnet_fields_ = deepnet_fields_arg
else:
command_args.deepnet_fields_ = []
except AttributeError:
pass
# Parses topic model fields if provided.
try:
if command_args.topic_fields:
topic_fields_arg = [
field.strip() for field in command_args.topic_fields.split(
command_args.args_separator)]
command_args.topic_model_fields_ = topic_fields_arg
else:
command_args.topic_model_fields_ = []
except AttributeError:
pass
# Parses field_codings for deepnet
try:
if command_args.field_codings:
command_args.field_codings_ = u.read_json(
command_args.field_codings)
else:
command_args.field_codings_ = []
except AttributeError:
pass
# Parses imports for scripts and libraries.
try:
if command_args.imports:
imports_arg = [
field.strip() for field in command_args.imports.split(
command_args.args_separator)]
command_args.imports_ = imports_arg
else:
command_args.imports_ = []
except AttributeError:
pass
# Parses objective fields for time-series.
try:
if command_args.objectives:
objective_fields_arg = [
field.strip() for field in command_args.objectives.split(
command_args.args_separator)]
command_args.objective_fields_ = objective_fields_arg
else:
command_args.objective_fields_ = []
except AttributeError:
pass
# Parses range.
try:
if command_args.range:
range_arg = [
value.strip() for value in command_args.range.split(
command_args.args_separator)]
command_args.range_ = range_arg
else:
command_args.range_ = []
except AttributeError:
pass
# Parses parameters for scripts.
try:
if command_args.declare_inputs:
command_args.parameters_ = u.read_json(command_args.declare_inputs)
else:
command_args.parameters_ = []
except AttributeError:
pass
# Parses creation_defaults for executions.
try:
if command_args.creation_defaults:
command_args.creation_defaults_ = u.read_json(
command_args.creation_defaults)
else:
command_args.creation_defaults_ = {}
except AttributeError:
pass
# Parses arguments for executions.
try:
if command_args.inputs:
command_args.arguments_ = u.read_json(command_args.inputs)
else:
command_args.arguments_ = []
except AttributeError:
pass
# Parses input maps for executions.
try:
if command_args.input_maps:
command_args.input_maps_ = u.read_json(command_args.input_maps)
else:
command_args.input_maps_ = []
except AttributeError:
pass
# Parses outputs for executions.
try:
if command_args.outputs:
command_args.outputs_ = u.read_json(command_args.outputs)
else:
command_args.outputs_ = []
except AttributeError:
pass
# Parses outputs for scripts.
try:
if command_args.declare_outputs:
command_args.declare_outputs_ = \
u.read_json(command_args.declare_outputs)
else:
command_args.declare_outputs_ = []
except AttributeError:
pass
model_ids = []
try:
# Parses model/ids if provided.
if command_args.models:
model_ids = u.read_resources(command_args.models)
command_args.model_ids_ = model_ids
except AttributeError:
pass
# Retrieve model/ids if provided.
try:
if command_args.model_tag:
model_ids = (model_ids +
u.list_ids(api.list_models,
"tags__in=%s" % command_args.model_tag))
command_args.model_ids_ = model_ids
except AttributeError:
pass
# Reads votes files in the provided directories.
try:
if command_args.votes_dirs:
dirs = [
directory.strip() for directory in
command_args.votes_dirs.split(
command_args.args_separator)]
votes_path = os.path.dirname(command_args.predictions)
votes_files = u.read_votes_files(dirs, votes_path)
command_args.votes_files_ = votes_files
else:
command_args.votes_files_ = []
except AttributeError:
pass
# Parses fields map if provided.
try:
if command_args.fields_map:
fields_map_arg = u.read_fields_map(command_args.fields_map)
command_args.fields_map_ = fields_map_arg
else:
command_args.fields_map_ = None
except AttributeError:
pass
cluster_ids = []
try:
# Parses cluster/ids if provided.
if command_args.clusters:
cluster_ids = u.read_resources(command_args.clusters)
command_args.cluster_ids_ = cluster_ids
except AttributeError:
pass
# Retrieve cluster/ids if provided.
try:
if command_args.cluster_tag:
cluster_ids = (cluster_ids +
u.list_ids(api.list_clusters,
"tags__in=%s" %
command_args.cluster_tag))
command_args.cluster_ids_ = cluster_ids
except AttributeError:
pass
association_ids = []
try:
# Parses association/ids if provided.
if command_args.associations:
association_ids = u.read_resources(command_args.associations)
command_args.association_ids_ = association_ids
except AttributeError:
pass
# Retrieve association/ids if provided.
try:
if command_args.association_tag:
association_ids = (association_ids +
u.list_ids(api.list_associations,
"tags__in=%s" %
command_args.association_tag))
command_args.association_ids_ = association_ids
except AttributeError:
pass
logistic_regression_ids = []
try:
# Parses logisticregression/ids if provided.
if command_args.logistic_regressions:
logistic_regression_ids = u.read_resources( \
command_args.logistic_regressions)
command_args.logistic_regression_ids_ = logistic_regression_ids
except AttributeError:
pass
# Retrieve logsticregression/ids if provided.
try:
if command_args.logistic_regression_tag:
logistic_regression_ids = (logistic_regression_ids + \
u.list_ids(api.list_logistic_regressions,
"tags__in=%s" %
command_args.logistic_regression_tag))
command_args.logistic_regression_ids_ = logistic_regression_ids
except AttributeError:
pass
deepnet_ids = []
try:
# Parses deepnet/ids if provided.
if command_args.deepnets:
deepnet_ids = u.read_resources( \
command_args.deepnets)
command_args.deepnet_ids_ = deepnet_ids
except AttributeError:
pass
# Retrieve deepnet/ids if provided.
try:
if command_args.deepnet_tag:
deepnet_regression_ids = (deepnet_ids + \
u.list_ids(api.list_deepnets,
"tags__in=%s" % command_args.deepnet_tag))
command_args.deepnet_ids_ = deepnet_ids
except AttributeError:
pass
topic_model_ids = []
try:
# Parses topicmodel/ids if provided.
if command_args.topic_models:
topic_model_ids = u.read_resources(command_args.topic_models)
command_args.topic_model_ids_ = topic_model_ids
except AttributeError:
pass
# Retrieve topicmodel/ids if provided.
try:
if command_args.topic_model_tag:
topic_model_ids = (topic_model_ids +
u.list_ids(api.list_topic_models,
"tags__in=%s" %
command_args.topic_model_tag))
command_args.topic_model_ids_ = topic_model_ids
except AttributeError:
pass
time_series_ids = []
try:
# Parses timeseries/ids if provided.
if command_args.time_series_set:
time_series_ids = u.read_resources(command_args.time_series)
command_args.time_series_ids_ = time_series_ids
except AttributeError:
pass
# Retrieve timeseries/ids if provided.
try:
if command_args.time_series_tag:
time_series_ids = (time_series_ids +
u.list_ids(api.list_time_series,
"tags__in=%s" %
command_args.time_series_tag))
command_args.time_series_ids_ = time_series_ids
except AttributeError:
pass
# Parses cluster names to generate datasets if provided
try:
if command_args.cluster_datasets:
cluster_datasets_arg = [
dataset.strip() for dataset in
command_args.cluster_datasets.split(
command_args.args_separator)]
command_args.cluster_datasets_ = cluster_datasets_arg
else:
command_args.cluster_datasets_ = []
except AttributeError:
pass
# Parses cluster names to generate models if provided
try:
if command_args.cluster_models:
cluster_models_arg = [
model.strip() for model in
command_args.cluster_models.split(
command_args.args_separator)]
command_args.cluster_models_ = cluster_models_arg
else:
command_args.cluster_models_ = []
except AttributeError:
pass
# Parses summary_fields to exclude from the clustering algorithm
try:
if command_args.summary_fields:
summary_fields_arg = [
field.strip() for field in
command_args.summary_fields.split(
command_args.args_separator)]
command_args.summary_fields_ = summary_fields_arg
else:
command_args.summary_fields_ = []
except AttributeError:
pass
anomaly_ids = []
try:
# Parses anomaly/ids if provided.
if command_args.anomalies:
anomaly_ids = u.read_resources(command_args.anomalies)
command_args.anomaly_ids_ = anomaly_ids
except AttributeError:
pass
# Retrieve anomaly/ids if provided.
try:
if command_args.anomaly_tag:
anomaly_ids = (anomaly_ids +
u.list_ids(api.list_anomalies,
"tags__in=%s" %
command_args.anomaly_tag))
command_args.anomaly_ids_ = anomaly_ids
except AttributeError:
pass
sample_ids = []
try:
# Parses sample/ids if provided.
if command_args.samples:
sample_ids = u.read_resources(command_args.samples)
command_args.sample_ids_ = sample_ids
except AttributeError:
pass
# Retrieve sample/ids if provided.
try:
if command_args.sample_tag:
sample_ids = (
sample_ids + u.list_ids(api.list_samples,
"tags__in=%s" %
command_args.sample_tag))
command_args.sample_ids_ = sample_ids
except AttributeError:
pass
# Parses sample row fields
try:
if command_args.row_fields:
row_fields_arg = [field.strip() for field in
command_args.row_fields.split(
command_args.args_separator)]
command_args.row_fields_ = row_fields_arg
else:
command_args.row_fields_ = []
except AttributeError:
pass
# Parses sample stat_fields
try:
if command_args.stat_fields:
stat_fields_arg = [field.strip() for field in
command_args.stat_fields.split(
command_args.args_separator)]
command_args.stat_fields_ = stat_fields_arg
else:
command_args.stat_fields_ = []
except AttributeError:
pass
# if boosting arguments are used, set on boosting
try:
if command_args.iterations or command_args.learning_rate \
or command_args.early_holdout:
command_args.boosting = True
except AttributeError:
pass
# Extracts the imports from the JSON metadata file
try:
if command_args.embedded_imports:
command_args.embedded_imports_ = u.read_resources( \
command_args.embedded_imports)
else:
command_args.embedded_imports_ = []
except AttributeError:
pass
# Parses hidden_layers for deepnets.
try:
if command_args.hidden_layers:
command_args.hidden_layers_ = u.read_json(
command_args.hidden_layers)
else:
command_args.hidden_layers_ = []
except AttributeError:
pass
# Parses operating_point for predictions.
try:
if command_args.operating_point:
command_args.operating_point_ = u.read_json(
command_args.operating_point)
else:
command_args.operating_point_ = []
except AttributeError:
pass
return {"api": api, "args": command_args}
def models_processing(datasets,
models,
model_ids,
api,
args,
resume,
fields=None,
session_file=None,
path=None,
log=None,
labels=None,
multi_label_data=None,
other_label=None):
"""Creates or retrieves models from the input data
"""
ensemble_ids = []
# If we have a dataset but not a model, we create the model if the no_model
# flag hasn't been set up.
if datasets and not (args.has_models_ or args.no_model):
dataset = datasets[0]
model_ids = []
models = []
if args.multi_label:
# If --number-of-models is not set or is 1, and there's
# no boosting options on, create one model per
# label. Otherwise, create one ensemble per label with the required
# number of models
if args.number_of_models < 2 and not args.boosting:
models, model_ids, resume = model_per_label(
labels,
datasets,
api,
args,
resume,
fields=fields,
multi_label_data=multi_label_data,
session_file=session_file,
path=path,
log=log)
else:
(ensembles, ensemble_ids, models, model_ids,
resume) = ensemble_per_label(
labels,
dataset,
api,
args,
resume,
fields=fields,
multi_label_data=multi_label_data,
session_file=session_file,
path=path,
log=log)
elif args.number_of_models > 1 or args.boosting:
ensembles = []
# Ensembles of models
(ensembles, ensemble_ids, models, model_ids,
resume) = ensemble_processing(datasets,
api,
args,
resume,
fields=fields,
session_file=session_file,
path=path,
log=log)
ensemble = ensembles[0]
args.ensemble = bigml.api.get_ensemble_id(ensemble)
else:
# Set of partial datasets created setting args.max_categories
if len(datasets) > 1 and args.max_categories:
args.number_of_models = len(datasets)
if ((args.test_datasets and args.evaluate)
or (args.datasets and args.evaluate and args.dataset_off)):
args.number_of_models = len(args.dataset_ids)
# Cross-validation case: we create 2 * n models to be validated
# holding out an n% of data
if args.cross_validation_rate > 0:
if args.number_of_evaluations > 0:
args.number_of_models = args.number_of_evaluations
else:
args.number_of_models = int(MONTECARLO_FACTOR *
args.cross_validation_rate)
if resume:
resume, model_ids = c.checkpoint(c.are_models_created,
path,
args.number_of_models,
debug=args.debug)
if not resume:
message = u.dated(
"Found %s models out of %s. Resuming.\n" %
(len(model_ids), args.number_of_models))
u.log_message(message,
log_file=session_file,
console=args.verbosity)
models = model_ids
args.number_of_models -= len(model_ids)
model_args = r.set_model_args(args,
fields=fields,
objective_id=args.objective_id_,
model_fields=args.model_fields_,
other_label=other_label)
models, model_ids = r.create_models(datasets, models, model_args,
args, api, path, session_file,
log)
# If a model is provided, we use it.
elif args.model:
model_ids = [args.model]
models = model_ids[:]
elif args.models or args.model_tag:
models = model_ids[:]
if args.ensemble:
if not args.ensemble in ensemble_ids:
ensemble_ids.append(args.ensemble)
if not args.evaluate:
ensemble = r.get_ensemble(args.ensemble, api, args.verbosity,
session_file)
model_ids = ensemble['object']['models']
models = model_ids[:]
if args.ensembles or args.ensemble_tag:
model_ids = []
ensemble_ids = []
# Parses ensemble/ids if provided.
if args.ensemble_tag:
ensemble_ids = (ensemble_ids + u.list_ids(
api.list_ensembles, "tags__in=%s" % args.ensemble_tag))
else:
ensemble_ids = u.read_resources(args.ensembles)
for ensemble_id in ensemble_ids:
ensemble = r.get_ensemble(ensemble_id, api)
if args.ensemble is None:
args.ensemble = ensemble_id
model_ids.extend(ensemble['object']['models'])
models = model_ids[:]
# If we are going to predict we must retrieve the models
if model_ids and args.test_set and not args.evaluate:
models, model_ids = r.get_models(models, args, api, session_file)
return models, model_ids, ensemble_ids, resume
def main(args=sys.argv[1:]):
"""Main process
"""
for i in range(0, len(args)):
if args[i].startswith("--"):
args[i] = args[i].replace("_", "-")
# If --clear-logs the log files are cleared
if "--clear-logs" in args:
for log_file in LOG_FILES:
try:
open(log_file, 'w', 0).close()
except IOError:
pass
literal_args = args[:]
for i in range(0, len(args)):
if ' ' in args[i]:
literal_args[i] = '"%s"' % args[i]
message = "bigmler %s\n" % " ".join(literal_args)
# Resume calls are not logged
if not "--resume" in args:
with open(COMMAND_LOG, "a", 0) as command_log:
command_log.write(message)
resume = False
parser = create_parser(defaults=get_user_defaults(), constants={'NOW': NOW,
'MAX_MODELS': MAX_MODELS, 'PLURALITY': PLURALITY})
# Parses command line arguments.
command_args = parser.parse_args(args)
default_output = ('evaluation' if command_args.evaluate
else 'predictions.csv')
if command_args.resume:
debug = command_args.debug
command = u.get_log_reversed(COMMAND_LOG,
command_args.stack_level)
args = shlex.split(command)[1:]
output_dir = u.get_log_reversed(DIRS_LOG,
command_args.stack_level)
defaults_file = "%s%s%s" % (output_dir, os.sep, DEFAULTS_FILE)
parser = create_parser(defaults=get_user_defaults(defaults_file),
constants={'NOW': NOW, 'MAX_MODELS': MAX_MODELS,
'PLURALITY': PLURALITY})
command_args = parser.parse_args(args)
if command_args.predictions is None:
command_args.predictions = ("%s%s%s" %
(output_dir, os.sep,
default_output))
# Logs the issued command and the resumed command
session_file = "%s%s%s" % (output_dir, os.sep, SESSIONS_LOG)
u.log_message(message, log_file=session_file)
message = "\nResuming command:\n%s\n\n" % command
u.log_message(message, log_file=session_file, console=True)
try:
defaults_handler = open(defaults_file, 'r')
contents = defaults_handler.read()
message = "\nUsing the following defaults:\n%s\n\n" % contents
u.log_message(message, log_file=session_file, console=True)
defaults_handler.close()
except IOError:
pass
resume = True
else:
if command_args.predictions is None:
command_args.predictions = ("%s%s%s" %
(NOW, os.sep,
default_output))
if len(os.path.dirname(command_args.predictions).strip()) == 0:
command_args.predictions = ("%s%s%s" %
(NOW, os.sep,
command_args.predictions))
directory = u.check_dir(command_args.predictions)
session_file = "%s%s%s" % (directory, os.sep, SESSIONS_LOG)
u.log_message(message + "\n", log_file=session_file)
try:
defaults_file = open(DEFAULTS_FILE, 'r')
contents = defaults_file.read()
defaults_file.close()
defaults_copy = open("%s%s%s" % (directory, os.sep, DEFAULTS_FILE),
'w', 0)
defaults_copy.write(contents)
defaults_copy.close()
except IOError:
pass
with open(DIRS_LOG, "a", 0) as directory_log:
directory_log.write("%s\n" % os.path.abspath(directory))
if resume and debug:
command_args.debug = True
api_command_args = {
'username': command_args.username,
'api_key': command_args.api_key,
'dev_mode': command_args.dev_mode,
'debug': command_args.debug}
api = bigml.api.BigML(**api_command_args)
if (command_args.evaluate
and not (command_args.training_set or command_args.source
or command_args.dataset)
and not (command_args.test_set and (command_args.model or
command_args.models or command_args.model_tag))):
parser.error("Evaluation wrong syntax.\n"
"\nTry for instance:\n\nbigmler --train data/iris.csv"
" --evaluate\nbigmler --model "
"model/5081d067035d076151000011 --dataset "
"dataset/5081d067035d076151003423 --evaluate")
if command_args.objective_field:
objective = command_args.objective_field
try:
command_args.objective_field = int(objective)
except ValueError:
pass
output_args = {
"api": api,
"training_set": command_args.training_set,
"test_set": command_args.test_set,
"output": command_args.predictions,
"objective_field": command_args.objective_field,
"name": command_args.name,
"training_set_header": command_args.train_header,
"test_set_header": command_args.test_header,
"args": command_args,
"resume": resume,
}
# Reads description if provided.
if command_args.description:
description_arg = u.read_description(command_args.description)
output_args.update(description=description_arg)
else:
output_args.update(description="Created using BigMLer")
# Parses fields if provided.
if command_args.field_attributes:
field_attributes_arg = (
u.read_field_attributes(command_args.field_attributes))
output_args.update(field_attributes=field_attributes_arg)
# Parses types if provided.
if command_args.types:
types_arg = u.read_types(command_args.types)
output_args.update(types=types_arg)
# Parses dataset fields if provided.
if command_args.dataset_fields:
dataset_fields_arg = map(lambda x: x.strip(),
command_args.dataset_fields.split(','))
output_args.update(dataset_fields=dataset_fields_arg)
# Parses model input fields if provided.
if command_args.model_fields:
model_fields_arg = map(lambda x: x.strip(),
command_args.model_fields.split(','))
output_args.update(model_fields=model_fields_arg)
model_ids = []
# Parses model/ids if provided.
if command_args.models:
model_ids = u.read_models(command_args.models)
output_args.update(model_ids=model_ids)
dataset_id = None
# Parses dataset/id if provided.
if command_args.datasets:
dataset_id = u.read_dataset(command_args.datasets)
command_args.dataset = dataset_id
# Retrieve model/ids if provided.
if command_args.model_tag:
model_ids = (model_ids +
u.list_ids(api.list_models,
"tags__in=%s" % command_args.model_tag))
output_args.update(model_ids=model_ids)
# Reads a json filter if provided.
if command_args.json_filter:
json_filter = u.read_json_filter(command_args.json_filter)
command_args.json_filter = json_filter
# Reads a lisp filter if provided.
if command_args.lisp_filter:
lisp_filter = u.read_lisp_filter(command_args.lisp_filter)
command_args.lisp_filter = lisp_filter
# Adds default tags unless that it is requested not to do so.
if command_args.no_tag:
command_args.tag.append('BigMLer')
command_args.tag.append('BigMLer_%s' % NOW)
# Checks combined votes method
if (command_args.method and
not command_args.method in COMBINATION_WEIGHTS.keys()):
command_args.method = 0
else:
combiner_methods = dict([[value, key]
for key, value in COMBINER_MAP.items()])
command_args.method = combiner_methods.get(command_args.method, 0)
# Reads votes files in the provided directories.
if command_args.votes_dirs:
dirs = map(lambda x: x.strip(), command_args.votes_dirs.split(','))
votes_path = os.path.dirname(command_args.predictions)
votes_files = u.read_votes_files(dirs, votes_path)
output_args.update(votes_files=votes_files)
# Parses fields map if provided.
if command_args.fields_map:
fields_map_arg = u.read_fields_map(command_args.fields_map)
output_args.update(fields_map=fields_map_arg)
# Parses resources ids if provided.
if command_args.delete:
if command_args.predictions is None:
path = NOW
else:
path = u.check_dir(command_args.predictions)
session_file = "%s%s%s" % (path, os.sep, SESSIONS_LOG)
message = u.dated("Retrieving objects to delete.\n")
u.log_message(message, log_file=session_file,
console=command_args.verbosity)
delete_list = []
if command_args.delete_list:
delete_list = map(lambda x: x.strip(),
command_args.delete_list.split(','))
if command_args.delete_file:
if not os.path.exists(command_args.delete_file):
raise Exception("File %s not found" % command_args.delete_file)
delete_list.extend([line for line
in open(command_args.delete_file, "r")])
if command_args.all_tag:
query_string = "tags__in=%s" % command_args.all_tag
delete_list.extend(u.list_ids(api.list_sources, query_string))
delete_list.extend(u.list_ids(api.list_datasets, query_string))
delete_list.extend(u.list_ids(api.list_models, query_string))
delete_list.extend(u.list_ids(api.list_predictions, query_string))
delete_list.extend(u.list_ids(api.list_evaluations, query_string))
# Retrieve sources/ids if provided
if command_args.source_tag:
query_string = "tags__in=%s" % command_args.source_tag
delete_list.extend(u.list_ids(api.list_sources, query_string))
# Retrieve datasets/ids if provided
if command_args.dataset_tag:
query_string = "tags__in=%s" % command_args.dataset_tag
delete_list.extend(u.list_ids(api.list_datasets, query_string))
# Retrieve model/ids if provided
if command_args.model_tag:
query_string = "tags__in=%s" % command_args.model_tag
delete_list.extend(u.list_ids(api.list_models, query_string))
# Retrieve prediction/ids if provided
if command_args.prediction_tag:
query_string = "tags__in=%s" % command_args.prediction_tag
delete_list.extend(u.list_ids(api.list_predictions, query_string))
# Retrieve evaluation/ids if provided
if command_args.evaluation_tag:
query_string = "tags__in=%s" % command_args.evaluation_tag
delete_list.extend(u.list_ids(api.list_evaluations, query_string))
message = u.dated("Deleting objects.\n")
u.log_message(message, log_file=session_file,
console=command_args.verbosity)
message = "\n".join(delete_list)
u.log_message(message, log_file=session_file)
u.delete(api, delete_list)
if sys.platform == "win32" and sys.stdout.isatty():
message = (u"\nGenerated files:\n\n" +
unicode(u.print_tree(path, " "), "utf-8") + u"\n")
else:
message = "\nGenerated files:\n\n" + u.print_tree(path, " ") + "\n"
u.log_message(message, log_file=session_file,
console=command_args.verbosity)
elif (command_args.training_set or command_args.test_set
or command_args.source or command_args.dataset
or command_args.datasets or command_args.votes_dirs):
compute_output(**output_args)
u.log_message("_" * 80 + "\n", log_file=session_file)
def transform_args(command_args, flags, api):
"""Transforms the formatted argument strings into structured arguments
"""
attribute_args(command_args)
# Parses dataset generators in json format if provided
try:
if command_args.new_fields:
json_generators = u.read_json(command_args.new_fields)
command_args.dataset_json_generators = json_generators
else:
command_args.dataset_json_generators = {}
except AttributeError:
pass
# Parses multi-dataset attributes in json such as field maps
try:
if command_args.multi_dataset_attributes:
multi_dataset_json = u.read_json(
command_args.multi_dataset_attributes)
command_args.multi_dataset_json = multi_dataset_json
else:
command_args.multi_dataset_json = {}
except AttributeError:
pass
transform_dataset_options(command_args, api)
script_ids = None
command_args.script_ids = []
# Parses script/id if provided.
try:
if command_args.scripts:
script_ids = u.read_resources(command_args.scripts)
if len(script_ids) == 1:
command_args.script = script_ids[0]
command_args.script_ids = script_ids
except AttributeError:
pass
# Retrieve script/ids if provided.
try:
if command_args.script_tag:
script_ids = script_ids.extend(
u.list_ids(api.list_scripts,
"tags__in=%s" % command_args.script_tag))
if len(script_ids) == 1:
command_args.script = script_ids[0]
command_args.script_ids = script_ids
except AttributeError:
pass
# Reads a json filter if provided.
try:
if command_args.json_filter:
json_filter = u.read_json_filter(command_args.json_filter)
command_args.json_filter = json_filter
except AttributeError:
pass
# Reads a lisp filter if provided.
try:
if command_args.lisp_filter:
lisp_filter = u.read_lisp_filter(command_args.lisp_filter)
command_args.lisp_filter = lisp_filter
except AttributeError:
pass
# Adds default tags unless that it is requested not to do so.
try:
if command_args.no_tag:
command_args.tag.append('BigMLer')
command_args.tag.append('BigMLer_%s' % NOW)
except AttributeError:
pass
# Checks combined votes method
try:
if (command_args.method and command_args.method != COMBINATION_LABEL
and not command_args.method in COMBINATION_WEIGHTS.keys()):
command_args.method = 0
else:
combiner_methods = dict([[value, key]
for key, value in COMBINER_MAP.items()])
combiner_methods[COMBINATION_LABEL] = COMBINATION
command_args.method = combiner_methods.get(command_args.method, 0)
except AttributeError:
pass
# Checks missing_strategy
try:
if (command_args.missing_strategy
and not (command_args.missing_strategy
in MISSING_STRATEGIES.keys())):
command_args.missing_strategy = 0
else:
command_args.missing_strategy = MISSING_STRATEGIES.get(
command_args.missing_strategy, 0)
except AttributeError:
pass
try:
# Old value for --prediction-info='full data' maps to 'full'
if command_args.prediction_info == 'full data':
print("WARNING: 'full data' is a deprecated value. Use"
" 'full' instead")
command_args.prediction_info = FULL_FORMAT
except AttributeError:
pass
# Parses class, weight pairs for objective weight
try:
if command_args.objective_weights:
objective_weights = (u.read_objective_weights(
command_args.objective_weights))
command_args.objective_weights_json = objective_weights
except AttributeError:
pass
try:
command_args.multi_label_fields_list = []
if command_args.multi_label_fields is not None:
multi_label_fields = command_args.multi_label_fields.strip()
command_args.multi_label_fields_list = multi_label_fields.split(
command_args.args_separator)
except AttributeError:
pass
# Sets shared_flag if --shared or --unshared has been used
command_args.shared_flag = '--shared' in flags or '--unshared' in flags
# Set remote on if scoring a trainind dataset in bigmler anomaly
try:
if command_args.score:
command_args.remote = True
if not "--prediction-info" in flags:
command_args.prediction_info = FULL_FORMAT
except AttributeError:
pass
command_args.has_supervised_ = (
(hasattr(command_args, 'model') and command_args.model)
or (hasattr(command_args, 'models') and command_args.models)
or (hasattr(command_args, 'ensemble') and command_args.ensemble)
or (hasattr(command_args, 'ensembles') and command_args.ensembles)
or (hasattr(command_args, 'model_tag') and command_args.model_tag)
or (hasattr(command_args, 'logistic_regression')
and command_args.logistic_regression)
or (hasattr(command_args, 'logistic_regressions')
and command_args.logistic_regressions)
or (hasattr(command_args, 'logistic_regression_tag')
and command_args.logistic_regression_tag)
or (hasattr(command_args, 'deepnet') and command_args.deepnet)
or (hasattr(command_args, 'deepnets') and command_args.deepnets) or
(hasattr(command_args, 'deepnet_tag') and command_args.deepnet_tag) or
(hasattr(command_args, 'ensemble_tag') and command_args.ensemble_tag))
command_args.has_models_ = (
command_args.has_supervised_
or (hasattr(command_args, 'cluster') and command_args.cluster)
or (hasattr(command_args, 'clusters') and command_args.clusters)
or (hasattr(command_args, 'anomaly') and command_args.anomaly)
or (hasattr(command_args, 'anomalies') and command_args.anomalies)
or (hasattr(command_args, 'cluster_tag') and command_args.cluster_tag)
or (hasattr(command_args, 'anomaly_tag') and command_args.anomaly_tag))
command_args.has_datasets_ = (
(hasattr(command_args, 'dataset') and command_args.dataset)
or (hasattr(command_args, 'datasets') and command_args.datasets)
or (hasattr(command_args, 'dataset_ids') and command_args.dataset_ids)
or (hasattr(command_args, 'dataset_tag') and command_args.dataset_tag))
command_args.has_test_datasets_ = (
(hasattr(command_args, 'test_dataset') and command_args.test_dataset)
or
(hasattr(command_args, 'test_datasets') and command_args.test_datasets)
or (hasattr(command_args, 'test_dataset_tag')
and command_args.test_dataset_tag))
command_args.new_dataset = (
(hasattr(command_args, 'datasets_json') and command_args.datasets_json)
or
(hasattr(command_args, 'multi_dataset') and command_args.multi_dataset)
or (hasattr(command_args, 'juxtapose') and command_args.juxtapose)
or (hasattr(command_args, 'sql_query') and command_args.sql_query)
or (hasattr(command_args, 'sql_output_fields')
and command_args.sql_output_fields)
or (hasattr(command_args, 'json_query') and command_args.json_query))
def transform_args(command_args, flags, api, user_defaults):
"""Transforms the formatted argument strings into structured arguments
"""
# Parses attributes in json format if provided
command_args.json_args = {}
json_attribute_options = {
'source': command_args.source_attributes,
'dataset': command_args.dataset_attributes,
'model': command_args.model_attributes,
'ensemble': command_args.ensemble_attributes,
'evaluation': command_args.evaluation_attributes,
'batch_prediction': command_args.batch_prediction_attributes
}
for resource_type, attributes_file in json_attribute_options.items():
if attributes_file is not None:
command_args.json_args[resource_type] = u.read_json(
attributes_file)
else:
command_args.json_args[resource_type] = {}
# Parses dataset generators in json format if provided
if command_args.new_fields:
json_generators = u.read_json(command_args.new_fields)
command_args.dataset_json_generators = json_generators
else:
command_args.dataset_json_generators = {}
# Parses multi-dataset attributes in json such as field maps
if command_args.multi_dataset_attributes:
multi_dataset_json = u.read_json(command_args.multi_dataset_attributes)
command_args.multi_dataset_json = multi_dataset_json
else:
command_args.multi_dataset_json = {}
dataset_ids = None
command_args.dataset_ids = []
# Parses dataset/id if provided.
if command_args.datasets:
dataset_ids = u.read_datasets(command_args.datasets)
if len(dataset_ids) == 1:
command_args.dataset = dataset_ids[0]
command_args.dataset_ids = dataset_ids
# Retrieve dataset/ids if provided.
if command_args.dataset_tag:
dataset_ids = dataset_ids.extend(
u.list_ids(api.list_datasets,
"tags__in=%s" % command_args.dataset_tag))
if len(dataset_ids) == 1:
command_args.dataset = dataset_ids[0]
command_args.dataset_ids = dataset_ids
# Reads a json filter if provided.
if command_args.json_filter:
json_filter = u.read_json_filter(command_args.json_filter)
command_args.json_filter = json_filter
# Reads a lisp filter if provided.
if command_args.lisp_filter:
lisp_filter = u.read_lisp_filter(command_args.lisp_filter)
command_args.lisp_filter = lisp_filter
# Adds default tags unless that it is requested not to do so.
if command_args.no_tag:
command_args.tag.append('BigMLer')
command_args.tag.append('BigMLer_%s' % NOW)
# Checks combined votes method
if (command_args.method and command_args.method != COMBINATION_LABEL
and not (command_args.method in COMBINATION_WEIGHTS.keys())):
command_args.method = 0
else:
combiner_methods = dict([[value, key]
for key, value in COMBINER_MAP.items()])
combiner_methods[COMBINATION_LABEL] = COMBINATION
command_args.method = combiner_methods.get(command_args.method, 0)
# Checks missing_strategy
if (command_args.missing_strategy and
not (command_args.missing_strategy in MISSING_STRATEGIES.keys())):
command_args.missing_strategy = 0
else:
command_args.missing_strategy = MISSING_STRATEGIES.get(
command_args.missing_strategy, 0)
# Adds replacement=True if creating ensemble and nothing is specified
if (command_args.number_of_models > 1 and not command_args.replacement
and not '--no-replacement' in flags
and not 'replacement' in user_defaults
and not '--no-randomize' in flags
and not 'randomize' in user_defaults
and not '--sample-rate' in flags
and not 'sample_rate' in user_defaults):
command_args.replacement = True
# Old value for --prediction-info='full data' maps to 'full'
if command_args.prediction_info == 'full data':
print "WARNING: 'full data' is a deprecated value. Use 'full' instead"
command_args.prediction_info = FULL_FORMAT
# Parses class, weight pairs for objective weight
if command_args.objective_weights:
objective_weights = (u.read_objective_weights(
command_args.objective_weights))
command_args.objective_weights_json = objective_weights
command_args.multi_label_fields_list = []
if command_args.multi_label_fields is not None:
multi_label_fields = command_args.multi_label_fields.strip()
command_args.multi_label_fields_list = multi_label_fields.split(',')
def get_output_args(api, command_args, resume):
"""Returns the output args needed for the main bigmler computation process
"""
try:
if command_args.train_stdin:
if command_args.test_stdin:
sys.exit("The standard input can't be used both for training "
"and testing. Choose one of them")
command_args.training_set = StringIO(sys.stdin.read())
elif command_args.test_stdin:
command_args.test_set = StringIO(sys.stdin.read())
except AttributeError:
pass
try:
if command_args.objective_field:
objective = command_args.objective_field
try:
command_args.objective_field = int(objective)
except ValueError:
if not command_args.train_header:
sys.exit("The %s has been set as objective field but"
" the file has not been marked as containing"
" headers.\nPlease set the --train-header flag if"
" the file has headers or use a column number"
" to set the objective field." % objective)
except AttributeError:
pass
command_args.resume_ = resume
command_args.predictions = command_args.output
command_args.projections = command_args.output
# Reads description if provided.
try:
if command_args.description:
description_arg = u.read_description(command_args.description)
command_args.description_ = description_arg
else:
command_args.description_ = DEFAULT_DESCRIPTION
except AttributeError:
pass
# Parses fields if provided.
try:
if command_args.field_attributes:
field_attributes_arg = (u.read_field_attributes(
command_args.field_attributes))
command_args.field_attributes_ = field_attributes_arg
else:
command_args.field_attributes_ = []
except AttributeError:
pass
try:
if command_args.test_field_attributes:
field_attributes_arg = (u.read_field_attributes(
command_args.test_field_attributes))
command_args.test_field_attributes_ = field_attributes_arg
else:
command_args.test_field_attributes_ = []
except AttributeError:
pass
# Parses types if provided.
try:
if command_args.types:
types_arg = u.read_types(command_args.types)
command_args.types_ = types_arg
else:
command_args.types_ = None
if command_args.test_types:
types_arg = u.read_types(command_args.test_types)
command_args.test_types_ = types_arg
else:
command_args.test_types_ = None
except AttributeError:
pass
# Parses dataset fields if provided.
try:
if command_args.dataset_fields:
dataset_fields_arg = [
field.strip() for field in command_args.dataset_fields.split(
command_args.args_separator)
]
command_args.dataset_fields_ = dataset_fields_arg
else:
command_args.dataset_fields_ = []
except AttributeError:
pass
# Parses model input fields if provided.
try:
if command_args.model_fields:
model_fields_arg = [
field.strip() for field in command_args.model_fields.split(
command_args.args_separator)
]
command_args.model_fields_ = model_fields_arg
else:
command_args.model_fields_ = []
except AttributeError:
pass
# Parses cluster input fields if provided.
try:
if command_args.cluster_fields:
cluster_fields_arg = [
field.strip() for field in command_args.cluster_fields.split(
command_args.args_separator)
]
command_args.cluster_fields_ = cluster_fields_arg
else:
command_args.cluster_fields_ = []
except AttributeError:
pass
# Parses association input fields if provided.
try:
if command_args.association_fields:
association_fields_arg = [
field.strip() for field in \
command_args.association_fields.split( \
command_args.args_separator)]
command_args.association_fields_ = association_fields_arg
else:
command_args.association_fields_ = []
except AttributeError:
pass
# Parses anomaly input fields if provided.
try:
if command_args.anomaly_fields:
anomaly_fields_arg = [
field.strip() for field in command_args.anomaly_fields.split(
command_args.args_separator)
]
command_args.anomaly_fields_ = anomaly_fields_arg
else:
command_args.anomaly_fields_ = []
except AttributeError:
pass
# Parses logistic regression input fields if provided.
try:
if command_args.logistic_fields:
logistic_fields_arg = [
field.strip() for field in command_args.logistic_fields.split(
command_args.args_separator)
]
command_args.logistic_fields_ = logistic_fields_arg
else:
command_args.logistic_fields_ = []
except AttributeError:
pass
# Parses linear regression input fields if provided.
try:
if command_args.linear_fields:
linear_fields_arg = [
field.strip() for field in command_args.linear_fields.split(
command_args.args_separator)
]
command_args.linear_fields_ = linear_fields_arg
else:
command_args.linear_fields_ = []
except AttributeError:
pass
# Parses deepnet input fields if provided.
try:
if command_args.deepnet_fields:
deepnet_fields_arg = [
field.strip() for field in command_args.deepnet_fields.split(
command_args.args_separator)
]
command_args.deepnet_fields_ = deepnet_fields_arg
else:
command_args.deepnet_fields_ = []
except AttributeError:
pass
# Parses topic model fields if provided.
try:
if command_args.topic_fields:
topic_fields_arg = [
field.strip() for field in command_args.topic_fields.split(
command_args.args_separator)
]
command_args.topic_model_fields_ = topic_fields_arg
else:
command_args.topic_model_fields_ = []
except AttributeError:
pass
# Parses pca fields if provided.
try:
if command_args.pca_fields:
pca_fields_arg = [
field.strip() for field in command_args.pca_fields.split(
command_args.args_separator)
]
command_args.pca_fields_ = pca_fields_arg
else:
command_args.pca_fields_ = []
except AttributeError:
pass
# Parses field_codings for deepnet
try:
if command_args.field_codings:
command_args.field_codings_ = u.read_json(
command_args.field_codings)
else:
command_args.field_codings_ = []
except AttributeError:
pass
# Parses imports for scripts and libraries.
try:
if command_args.imports:
imports_arg = [
field.strip() for field in command_args.imports.split(
command_args.args_separator)
]
command_args.imports_ = imports_arg
else:
command_args.imports_ = []
except AttributeError:
pass
# Parses objective fields for time-series.
try:
if command_args.objectives:
objective_fields_arg = [
field.strip() for field in command_args.objectives.split(
command_args.args_separator)
]
command_args.objective_fields_ = objective_fields_arg
else:
command_args.objective_fields_ = []
except AttributeError:
pass
# Parses range.
try:
if command_args.range:
range_arg = [
value.strip() for value in command_args.range.split(
command_args.args_separator)
]
command_args.range_ = range_arg
else:
command_args.range_ = []
except AttributeError:
pass
# Parses parameters for scripts.
try:
if command_args.declare_inputs:
command_args.parameters_ = u.read_json(command_args.declare_inputs)
else:
command_args.parameters_ = []
except AttributeError:
pass
# Parses creation_defaults for executions.
try:
if command_args.creation_defaults:
command_args.creation_defaults_ = u.read_json(
command_args.creation_defaults)
else:
command_args.creation_defaults_ = {}
except AttributeError:
pass
# Parses arguments for executions.
try:
if command_args.inputs:
command_args.arguments_ = u.read_json(command_args.inputs)
else:
command_args.arguments_ = []
except AttributeError:
pass
# Parses input maps for executions.
try:
if command_args.input_maps:
command_args.input_maps_ = u.read_json(command_args.input_maps)
else:
command_args.input_maps_ = []
except AttributeError:
pass
# Parses outputs for executions.
try:
if command_args.outputs:
command_args.outputs_ = u.read_json(command_args.outputs)
else:
command_args.outputs_ = []
except AttributeError:
pass
# Parses outputs for scripts.
try:
if command_args.declare_outputs:
command_args.declare_outputs_ = \
u.read_json(command_args.declare_outputs)
else:
command_args.declare_outputs_ = []
except AttributeError:
pass
model_ids = []
try:
# Parses model/ids if provided.
if command_args.models:
model_ids = u.read_resources(command_args.models)
command_args.model_ids_ = model_ids
except AttributeError:
pass
# Retrieve model/ids if provided.
try:
if command_args.model_tag:
model_ids = (model_ids + u.list_ids(
api.list_models, "tags__in=%s" % command_args.model_tag))
command_args.model_ids_ = model_ids
except AttributeError:
pass
# Reads votes files in the provided directories.
try:
if command_args.votes_dirs:
dirs = [
directory.strip() for directory in
command_args.votes_dirs.split(command_args.args_separator)
]
votes_path = os.path.dirname(command_args.predictions)
votes_files = u.read_votes_files(dirs, votes_path)
command_args.votes_files_ = votes_files
else:
command_args.votes_files_ = []
except AttributeError:
pass
# Parses fields map if provided.
try:
if command_args.fields_map:
fields_map_arg = u.read_fields_map(command_args.fields_map)
command_args.fields_map_ = fields_map_arg
else:
command_args.fields_map_ = None
except AttributeError:
pass
cluster_ids = []
try:
# Parses cluster/ids if provided.
if command_args.clusters:
cluster_ids = u.read_resources(command_args.clusters)
command_args.cluster_ids_ = cluster_ids
except AttributeError:
pass
# Retrieve cluster/ids if provided.
try:
if command_args.cluster_tag:
cluster_ids = (cluster_ids + u.list_ids(
api.list_clusters, "tags__in=%s" % command_args.cluster_tag))
command_args.cluster_ids_ = cluster_ids
except AttributeError:
pass
association_ids = []
try:
# Parses association/ids if provided.
if command_args.associations:
association_ids = u.read_resources(command_args.associations)
command_args.association_ids_ = association_ids
except AttributeError:
pass
# Retrieve association/ids if provided.
try:
if command_args.association_tag:
association_ids = (
association_ids +
u.list_ids(api.list_associations,
"tags__in=%s" % command_args.association_tag))
command_args.association_ids_ = association_ids
except AttributeError:
pass
logistic_regression_ids = []
try:
# Parses logisticregression/ids if provided.
if command_args.logistic_regressions:
logistic_regression_ids = u.read_resources( \
command_args.logistic_regressions)
command_args.logistic_regression_ids_ = logistic_regression_ids
except AttributeError:
pass
# Retrieve logsticregression/ids if provided.
try:
if command_args.logistic_regression_tag:
logistic_regression_ids = (logistic_regression_ids + \
u.list_ids(api.list_logistic_regressions,
"tags__in=%s" %
command_args.logistic_regression_tag))
command_args.logistic_regression_ids_ = logistic_regression_ids
except AttributeError:
pass
linear_regression_ids = []
try:
# Parses linearregression/ids if provided.
if command_args.linear_regressions:
linear_regression_ids = u.read_resources( \
command_args.linear_regressions)
command_args.linear_regression_ids_ = linear_regression_ids
except AttributeError:
pass
# Retrieve linearregression/ids if provided.
try:
if command_args.linear_regression_tag:
linear_regression_ids = (linear_regression_ids + \
u.list_ids(api.list_linear_regressions,
"tags__in=%s" %
command_args.linear_regression_tag))
command_args.linear_regression_ids_ = linear_regression_ids
except AttributeError:
pass
deepnet_ids = []
try:
# Parses deepnet/ids if provided.
if command_args.deepnets:
deepnet_ids = u.read_resources( \
command_args.deepnets)
command_args.deepnet_ids_ = deepnet_ids
except AttributeError:
pass
# Retrieve deepnet/ids if provided.
try:
if command_args.deepnet_tag:
deepnet_ids = (deepnet_ids + \
u.list_ids(api.list_deepnets,
"tags__in=%s" % command_args.deepnet_tag))
command_args.deepnet_ids_ = deepnet_ids
except AttributeError:
pass
topic_model_ids = []
try:
# Parses topicmodel/ids if provided.
if command_args.topic_models:
topic_model_ids = u.read_resources(command_args.topic_models)
command_args.topic_model_ids_ = topic_model_ids
except AttributeError:
pass
# Retrieve topicmodel/ids if provided.
try:
if command_args.topic_model_tag:
topic_model_ids = (
topic_model_ids +
u.list_ids(api.list_topic_models,
"tags__in=%s" % command_args.topic_model_tag))
command_args.topic_model_ids_ = topic_model_ids
except AttributeError:
pass
time_series_ids = []
try:
# Parses timeseries/ids if provided.
if command_args.time_series_set:
time_series_ids = u.read_resources(command_args.time_series)
command_args.time_series_ids_ = time_series_ids
except AttributeError:
pass
# Retrieve timeseries/ids if provided.
try:
if command_args.time_series_tag:
time_series_ids = (
time_series_ids +
u.list_ids(api.list_time_series,
"tags__in=%s" % command_args.time_series_tag))
command_args.time_series_ids_ = time_series_ids
except AttributeError:
pass
pca_ids = []
try:
# Parses pca/ids if provided.
if command_args.pcas:
pca_ids = u.read_resources(command_args.pcas)
command_args.pca_ids_ = pca_ids
except AttributeError:
pass
# Retrieve pca/ids if provided.
try:
if command_args.pca_tag:
pca_ids = (pca_ids + u.list_ids(
api.pca_series, "tags__in=%s" % command_args.pca_tag))
command_args.pca_ids_ = pca_ids
except AttributeError:
pass
# Parses models list for fusions if provided.
try:
if command_args.fusion_models:
fusion_models_arg = [
model.strip() for model in command_args.fusion_models.split(
command_args.args_separator)
]
command_args.fusion_models_ = fusion_models_arg
else:
command_args.fusion_models_ = []
except AttributeError:
pass
# Parses models list for fusions if provided.
if not has_value(command_args, "fusion_models_"):
try:
if command_args.fusion_models_file:
fusion_models_arg = u.read_json(
command_args.fusion_models_file)
command_args.fusion_models_ = fusion_models_arg
else:
command_args.fusion_models_ = []
except AttributeError:
pass
fusion_ids = []
try:
# Parses fusion/ids if provided.
if command_args.fusions:
fusion_ids = u.read_resources(command_args.fusions)
command_args.fusion_ids_ = fusion_ids
except AttributeError:
pass
# Retrieve fusion/ids if provided.
try:
if command_args.fusion_tag:
fusion_ids = (fusion_ids + u.list_ids(
api.fusion_series, "tags__in=%s" % command_args.fusion_tag))
command_args.fusion_ids_ = fusion_ids
except AttributeError:
pass
# Parses cluster names to generate datasets if provided
try:
if command_args.cluster_datasets:
cluster_datasets_arg = [
dataset.strip()
for dataset in command_args.cluster_datasets.split(
command_args.args_separator)
]
command_args.cluster_datasets_ = cluster_datasets_arg
else:
command_args.cluster_datasets_ = []
except AttributeError:
pass
# Parses cluster names to generate models if provided
try:
if command_args.cluster_models:
cluster_models_arg = [
model.strip() for model in command_args.cluster_models.split(
command_args.args_separator)
]
command_args.cluster_models_ = cluster_models_arg
else:
command_args.cluster_models_ = []
except AttributeError:
pass
# Parses summary_fields to exclude from the clustering algorithm
try:
if command_args.summary_fields:
summary_fields_arg = [
field.strip() for field in command_args.summary_fields.split(
command_args.args_separator)
]
command_args.summary_fields_ = summary_fields_arg
else:
command_args.summary_fields_ = []
except AttributeError:
pass
anomaly_ids = []
try:
# Parses anomaly/ids if provided.
if command_args.anomalies:
anomaly_ids = u.read_resources(command_args.anomalies)
command_args.anomaly_ids_ = anomaly_ids
except AttributeError:
pass
# Retrieve anomaly/ids if provided.
try:
if command_args.anomaly_tag:
anomaly_ids = (anomaly_ids + u.list_ids(
api.list_anomalies, "tags__in=%s" % command_args.anomaly_tag))
command_args.anomaly_ids_ = anomaly_ids
except AttributeError:
pass
sample_ids = []
try:
# Parses sample/ids if provided.
if command_args.samples:
sample_ids = u.read_resources(command_args.samples)
command_args.sample_ids_ = sample_ids
except AttributeError:
pass
# Retrieve sample/ids if provided.
try:
if command_args.sample_tag:
sample_ids = (sample_ids + u.list_ids(
api.list_samples, "tags__in=%s" % command_args.sample_tag))
command_args.sample_ids_ = sample_ids
except AttributeError:
pass
# Parses sample row fields
try:
if command_args.row_fields:
row_fields_arg = [
field.strip() for field in command_args.row_fields.split(
command_args.args_separator)
]
command_args.row_fields_ = row_fields_arg
else:
command_args.row_fields_ = []
except AttributeError:
pass
# Parses sample stat_fields
try:
if command_args.stat_fields:
stat_fields_arg = [
field.strip() for field in command_args.stat_fields.split(
command_args.args_separator)
]
command_args.stat_fields_ = stat_fields_arg
else:
command_args.stat_fields_ = []
except AttributeError:
pass
# if boosting arguments are used, set on boosting
try:
if command_args.iterations or command_args.learning_rate \
or command_args.early_holdout:
command_args.boosting = True
except AttributeError:
pass
# Extracts the imports from the JSON metadata file
try:
if command_args.embedded_imports:
command_args.embedded_imports_ = u.read_resources( \
command_args.embedded_imports)
else:
command_args.embedded_imports_ = []
except AttributeError:
pass
# Parses hidden_layers for deepnets.
try:
if command_args.hidden_layers:
command_args.hidden_layers_ = u.read_json(
command_args.hidden_layers)
else:
command_args.hidden_layers_ = []
except AttributeError:
pass
# Parses operating_point for predictions.
try:
if command_args.operating_point:
command_args.operating_point_ = u.read_json(
command_args.operating_point)
else:
command_args.operating_point_ = []
except AttributeError:
pass
# Parses the json_query
try:
if command_args.json_query:
command_args.json_query_ = u.read_json(command_args.json_query)
else:
command_args.json_query_ = None
except AttributeError:
pass
# Parses the models_file
try:
if command_args.models_file:
command_args.models_file_ = u.read_json(command_args.models_file)
else:
command_args.models_file_ = None
except AttributeError:
pass
# Parses the sql_output_fields
try:
if command_args.sql_output_fields:
command_args.sql_output_fields_ = u.read_json( \
command_args.sql_output_fields)
else:
command_args.sql_output_fields_ = None
except AttributeError:
pass
# Parses connection info for external connectors
try:
if command_args.connection_json:
command_args.connection_json_ = u.read_json(
command_args.connection_json)
else:
command_args.connection_json_ = {}
except AttributeError:
pass
return {"api": api, "args": command_args}
def get_output_args(api, command_args, resume):
"""Returns the output args needed for the main bigmler computation process
"""
try:
if command_args.train_stdin:
if command_args.test_stdin:
sys.exit("The standard input can't be used both for training "
"and testing. Choose one of them")
command_args.training_set = StringIO(sys.stdin.read())
elif command_args.test_stdin:
command_args.test_set = StringIO(sys.stdin.read())
except AttributeError:
pass
try:
if command_args.objective_field:
objective = command_args.objective_field
try:
command_args.objective_field = int(objective)
except ValueError:
if not command_args.train_header:
sys.exit("The %s has been set as objective field but"
" the file has not been marked as containing"
" headers.\nPlease set the --train-header flag if"
" the file has headers or use a column number"
" to set the objective field." % objective)
except AttributeError:
pass
command_args.resume_ = resume
# Reads description if provided.
try:
if command_args.description:
description_arg = u.read_description(command_args.description)
command_args.description_ = description_arg
else:
command_args.description_ = DEFAULT_DESCRIPTION
except AttributeError:
pass
# Parses fields if provided.
try:
if command_args.field_attributes:
field_attributes_arg = (
u.read_field_attributes(command_args.field_attributes))
command_args.field_attributes_ = field_attributes_arg
else:
command_args.field_attributes_ = []
except AttributeError:
pass
try:
if command_args.test_field_attributes:
field_attributes_arg = (
u.read_field_attributes(command_args.test_field_attributes))
command_args.test_field_attributes_ = field_attributes_arg
else:
command_args.test_field_attributes_ = []
except AttributeError:
pass
# Parses types if provided.
try:
if command_args.types:
types_arg = u.read_types(command_args.types)
command_args.types_ = types_arg
else:
command_args.types_ = None
if command_args.test_types:
types_arg = u.read_types(command_args.test_types)
command_args.test_types_ = types_arg
else:
command_args.test_types_ = None
except AttributeError:
pass
# Parses dataset fields if provided.
try:
if command_args.dataset_fields:
dataset_fields_arg = [
field.strip() for field in command_args.dataset_fields.split(
command_args.args_separator)]
command_args.dataset_fields_ = dataset_fields_arg
else:
command_args.dataset_fields_ = []
except AttributeError:
pass
# Parses model input fields if provided.
try:
if command_args.model_fields:
model_fields_arg = [
field.strip() for field in command_args.model_fields.split(
command_args.args_separator)]
command_args.model_fields_ = model_fields_arg
else:
command_args.model_fields_ = []
except AttributeError:
pass
# Parses cluster input fields if provided.
try:
if command_args.cluster_fields:
cluster_fields_arg = [
field.strip() for field in command_args.cluster_fields.split(
command_args.args_separator)]
command_args.cluster_fields_ = cluster_fields_arg
else:
command_args.cluster_fields_ = []
except AttributeError:
pass
# Parses association input fields if provided.
try:
if command_args.association_fields:
association_fields_arg = [
field.strip() for field in \
command_args.association_fields.split( \
command_args.args_separator)]
command_args.association_fields_ = association_fields_arg
else:
command_args.association_fields_ = []
except AttributeError:
pass
# Parses anomaly input fields if provided.
try:
if command_args.anomaly_fields:
anomaly_fields_arg = [
field.strip() for field in command_args.anomaly_fields.split(
command_args.args_separator)]
command_args.anomaly_fields_ = anomaly_fields_arg
else:
command_args.anomaly_fields_ = []
except AttributeError:
pass
# Parses logistic regression input fields if provided.
try:
if command_args.logistic_fields:
logistic_fields_arg = [
field.strip() for field in command_args.logistic_fields.split(
command_args.args_separator)]
command_args.logistic_fields_ = logistic_fields_arg
else:
command_args.logistic_fields_ = []
except AttributeError:
pass
model_ids = []
try:
# Parses model/ids if provided.
if command_args.models:
model_ids = u.read_resources(command_args.models)
command_args.model_ids_ = model_ids
except AttributeError:
pass
# Retrieve model/ids if provided.
try:
if command_args.model_tag:
model_ids = (model_ids +
u.list_ids(api.list_models,
"tags__in=%s" % command_args.model_tag))
command_args.model_ids_ = model_ids
except AttributeError:
pass
# Reads votes files in the provided directories.
try:
if command_args.votes_dirs:
dirs = [
directory.strip() for directory in
command_args.votes_dirs.split(
command_args.args_separator)]
votes_path = os.path.dirname(command_args.predictions)
votes_files = u.read_votes_files(dirs, votes_path)
command_args.votes_files_ = votes_files
else:
command_args.votes_files_ = []
except AttributeError:
pass
# Parses fields map if provided.
try:
if command_args.fields_map:
fields_map_arg = u.read_fields_map(command_args.fields_map)
command_args.fields_map_ = fields_map_arg
else:
command_args.fields_map_ = None
except AttributeError:
pass
cluster_ids = []
try:
# Parses cluster/ids if provided.
if command_args.clusters:
cluster_ids = u.read_resources(command_args.clusters)
command_args.cluster_ids_ = cluster_ids
except AttributeError:
pass
# Retrieve cluster/ids if provided.
try:
if command_args.cluster_tag:
cluster_ids = (cluster_ids +
u.list_ids(api.list_clusters,
"tags__in=%s" %
command_args.cluster_tag))
command_args.cluster_ids_ = cluster_ids
except AttributeError:
pass
association_ids = []
try:
# Parses association/ids if provided.
if command_args.associations:
association_ids = u.read_resources(command_args.associations)
command_args.association_ids_ = association_ids
except AttributeError:
pass
# Retrieve cluster/ids if provided.
try:
if command_args.association_tag:
association_ids = (association_ids +
u.list_ids(api.list_associations,
"tags__in=%s" %
command_args.association_tag))
command_args.association_ids_ = association_ids
except AttributeError:
pass
logistic_regression_ids = []
try:
# Parses logisticregression/ids if provided.
if command_args.logistic_regressions:
logistic_regression_ids = u.read_resources( \
command_args.logistic_regressions)
command_args.logistic_regression_ids_ = logistic_regression_ids
except AttributeError:
pass
# Retrieve logisticregression/ids if provided.
try:
if command_args.logistic_tag:
logistic_regression_ids = (logistic_ids +
u.list_ids(api.list_logistic_regressions,
"tags__in=%s" %
command_args.logistic_tag))
command_args.logistic_regression_ids_ = logistic_regression_ids
except AttributeError:
pass
# Parses cluster names to generate datasets if provided
try:
if command_args.cluster_datasets:
cluster_datasets_arg = [
dataset.strip() for dataset in
command_args.cluster_datasets.split(
command_args.args_separator)]
command_args.cluster_datasets_ = cluster_datasets_arg
else:
command_args.cluster_datasets_ = []
except AttributeError:
pass
# Parses cluster names to generate models if provided
try:
if command_args.cluster_models:
cluster_models_arg = [
model.strip() for model in
command_args.cluster_models.split(
command_args.args_separator)]
command_args.cluster_models_ = cluster_models_arg
else:
command_args.cluster_models_ = []
except AttributeError:
pass
# Parses summary_fields to exclude from the clustering algorithm
try:
if command_args.summary_fields:
summary_fields_arg = [
field.strip() for field in
command_args.summary_fields.split(
command_args.args_separator)]
command_args.summary_fields_ = summary_fields_arg
else:
command_args.summary_fields_ = []
except AttributeError:
pass
anomaly_ids = []
try:
# Parses anomaly/ids if provided.
if command_args.anomalies:
anomaly_ids = u.read_resources(command_args.anomalies)
command_args.anomaly_ids_ = anomaly_ids
except AttributeError:
pass
# Retrieve anomaly/ids if provided.
try:
if command_args.anomaly_tag:
anomaly_ids = (anomaly_ids +
u.list_ids(api.list_anomalies,
"tags__in=%s" %
command_args.anomaly_tag))
command_args.anomaly_ids_ = anomaly_ids
except AttributeError:
pass
sample_ids = []
try:
# Parses sample/ids if provided.
if command_args.samples:
sample_ids = u.read_resources(command_args.samples)
command_args.sample_ids_ = sample_ids
except AttributeError:
pass
# Retrieve sample/ids if provided.
try:
if command_args.sample_tag:
sample_ids = (
sample_ids + u.list_ids(api.list_samples,
"tags__in=%s" %
command_args.sample_tag))
command_args.sample_ids_ = sample_ids
except AttributeError:
pass
# Parses sample row fields
try:
if command_args.row_fields:
row_fields_arg = [field.strip() for field in
command_args.row_fields.split(
command_args.args_separator)]
command_args.row_fields_ = row_fields_arg
else:
command_args.row_fields_ = []
except AttributeError:
pass
# Parses sample stat_fields
try:
if command_args.stat_fields:
stat_fields_arg = [field.strip() for field in
command_args.stat_fields.split(
command_args.args_separator)]
command_args.stat_fields_ = stat_fields_arg
else:
command_args.stat_fields_ = []
except AttributeError:
pass
return {"api": api, "args": command_args}
def main(args=sys.argv[1:]):
"""Main process
"""
train_stdin = False
for i in range(0, len(args)):
if args[i].startswith("--"):
args[i] = args[i].replace("_", "-")
if (args[i] == '--train'
and (i == len(args) - 1 or args[i + 1].startswith("--"))):
train_stdin = True
# If --clear-logs the log files are cleared
if "--clear-logs" in args:
for log_file in LOG_FILES:
try:
open(log_file, 'w', 0).close()
except IOError:
pass
literal_args = args[:]
for i in range(0, len(args)):
if ' ' in args[i]:
literal_args[i] = '"%s"' % args[i]
message = "bigmler %s\n" % " ".join(literal_args)
# Resume calls are not logged
if not "--resume" in args:
with open(COMMAND_LOG, "a", 0) as command_log:
command_log.write(message)
resume = False
parser = create_parser(defaults=get_user_defaults(),
constants={
'NOW': NOW,
'MAX_MODELS': MAX_MODELS,
'PLURALITY': PLURALITY
})
# Parses command line arguments.
command_args = parser.parse_args(args)
if command_args.cross_validation_rate > 0 and (command_args.test_set
or command_args.evaluate
or command_args.model
or command_args.models
or command_args.model_tag):
parser.error("Non compatible flags: --cross-validation-rate"
" cannot be used with --evaluate, --model,"
" --models or --model-tag. Usage:\n\n"
"bigmler --train data/iris.csv "
"--cross-validation-rate 0.1")
default_output = ('evaluation'
if command_args.evaluate else 'predictions.csv')
if command_args.resume:
debug = command_args.debug
command = u.get_log_reversed(COMMAND_LOG, command_args.stack_level)
args = shlex.split(command)[1:]
try:
position = args.index("--train")
if (position == (len(args) - 1)
or args[position + 1].startswith("--")):
train_stdin = True
except ValueError:
pass
output_dir = u.get_log_reversed(DIRS_LOG, command_args.stack_level)
defaults_file = "%s%s%s" % (output_dir, os.sep, DEFAULTS_FILE)
parser = create_parser(defaults=get_user_defaults(defaults_file),
constants={
'NOW': NOW,
'MAX_MODELS': MAX_MODELS,
'PLURALITY': PLURALITY
})
command_args = parser.parse_args(args)
if command_args.predictions is None:
command_args.predictions = ("%s%s%s" %
(output_dir, os.sep, default_output))
# Logs the issued command and the resumed command
session_file = "%s%s%s" % (output_dir, os.sep, SESSIONS_LOG)
u.log_message(message, log_file=session_file)
message = "\nResuming command:\n%s\n\n" % command
u.log_message(message, log_file=session_file, console=True)
try:
defaults_handler = open(defaults_file, 'r')
contents = defaults_handler.read()
message = "\nUsing the following defaults:\n%s\n\n" % contents
u.log_message(message, log_file=session_file, console=True)
defaults_handler.close()
except IOError:
pass
resume = True
else:
if command_args.predictions is None:
command_args.predictions = ("%s%s%s" %
(NOW, os.sep, default_output))
if len(os.path.dirname(command_args.predictions).strip()) == 0:
command_args.predictions = (
"%s%s%s" % (NOW, os.sep, command_args.predictions))
directory = u.check_dir(command_args.predictions)
session_file = "%s%s%s" % (directory, os.sep, SESSIONS_LOG)
u.log_message(message + "\n", log_file=session_file)
try:
defaults_file = open(DEFAULTS_FILE, 'r')
contents = defaults_file.read()
defaults_file.close()
defaults_copy = open("%s%s%s" % (directory, os.sep, DEFAULTS_FILE),
'w', 0)
defaults_copy.write(contents)
defaults_copy.close()
except IOError:
pass
with open(DIRS_LOG, "a", 0) as directory_log:
directory_log.write("%s\n" % os.path.abspath(directory))
if resume and debug:
command_args.debug = True
if train_stdin:
command_args.training_set = StringIO.StringIO(sys.stdin.read())
api_command_args = {
'username': command_args.username,
'api_key': command_args.api_key,
'dev_mode': command_args.dev_mode,
'debug': command_args.debug
}
if command_args.store:
api_command_args.update({'storage': u.check_dir(session_file)})
api = bigml.api.BigML(**api_command_args)
if (command_args.evaluate
and not (command_args.training_set or command_args.source
or command_args.dataset)
and not (command_args.test_set and
(command_args.model or command_args.models
or command_args.model_tag or command_args.ensemble))):
parser.error("Evaluation wrong syntax.\n"
"\nTry for instance:\n\nbigmler --train data/iris.csv"
" --evaluate\nbigmler --model "
"model/5081d067035d076151000011 --dataset "
"dataset/5081d067035d076151003423 --evaluate\n"
"bigmler --ensemble ensemble/5081d067035d076151003443"
" --evaluate")
if command_args.objective_field:
objective = command_args.objective_field
try:
command_args.objective_field = int(objective)
except ValueError:
pass
output_args = {
"api": api,
"training_set": command_args.training_set,
"test_set": command_args.test_set,
"output": command_args.predictions,
"objective_field": command_args.objective_field,
"name": command_args.name,
"training_set_header": command_args.train_header,
"test_set_header": command_args.test_header,
"args": command_args,
"resume": resume,
}
# Reads description if provided.
if command_args.description:
description_arg = u.read_description(command_args.description)
output_args.update(description=description_arg)
else:
output_args.update(description="Created using BigMLer")
# Parses fields if provided.
if command_args.field_attributes:
field_attributes_arg = (u.read_field_attributes(
command_args.field_attributes))
output_args.update(field_attributes=field_attributes_arg)
# Parses types if provided.
if command_args.types:
types_arg = u.read_types(command_args.types)
output_args.update(types=types_arg)
# Parses dataset fields if provided.
if command_args.dataset_fields:
dataset_fields_arg = map(lambda x: x.strip(),
command_args.dataset_fields.split(','))
output_args.update(dataset_fields=dataset_fields_arg)
# Parses model input fields if provided.
if command_args.model_fields:
model_fields_arg = map(lambda x: x.strip(),
command_args.model_fields.split(','))
output_args.update(model_fields=model_fields_arg)
model_ids = []
# Parses model/ids if provided.
if command_args.models:
model_ids = u.read_models(command_args.models)
output_args.update(model_ids=model_ids)
dataset_id = None
# Parses dataset/id if provided.
if command_args.datasets:
dataset_id = u.read_dataset(command_args.datasets)
command_args.dataset = dataset_id
# Retrieve model/ids if provided.
if command_args.model_tag:
model_ids = (model_ids + u.list_ids(
api.list_models, "tags__in=%s" % command_args.model_tag))
output_args.update(model_ids=model_ids)
# Reads a json filter if provided.
if command_args.json_filter:
json_filter = u.read_json_filter(command_args.json_filter)
command_args.json_filter = json_filter
# Reads a lisp filter if provided.
if command_args.lisp_filter:
lisp_filter = u.read_lisp_filter(command_args.lisp_filter)
command_args.lisp_filter = lisp_filter
# Adds default tags unless that it is requested not to do so.
if command_args.no_tag:
command_args.tag.append('BigMLer')
command_args.tag.append('BigMLer_%s' % NOW)
# Checks combined votes method
if (command_args.method
and not command_args.method in COMBINATION_WEIGHTS.keys()):
command_args.method = 0
else:
combiner_methods = dict([[value, key]
for key, value in COMBINER_MAP.items()])
command_args.method = combiner_methods.get(command_args.method, 0)
# Reads votes files in the provided directories.
if command_args.votes_dirs:
dirs = map(lambda x: x.strip(), command_args.votes_dirs.split(','))
votes_path = os.path.dirname(command_args.predictions)
votes_files = u.read_votes_files(dirs, votes_path)
output_args.update(votes_files=votes_files)
# Parses fields map if provided.
if command_args.fields_map:
fields_map_arg = u.read_fields_map(command_args.fields_map)
output_args.update(fields_map=fields_map_arg)
# Parses resources ids if provided.
if command_args.delete:
if command_args.predictions is None:
path = NOW
else:
path = u.check_dir(command_args.predictions)
session_file = "%s%s%s" % (path, os.sep, SESSIONS_LOG)
message = u.dated("Retrieving objects to delete.\n")
u.log_message(message,
log_file=session_file,
console=command_args.verbosity)
delete_list = []
if command_args.delete_list:
delete_list = map(lambda x: x.strip(),
command_args.delete_list.split(','))
if command_args.delete_file:
if not os.path.exists(command_args.delete_file):
raise Exception("File %s not found" % command_args.delete_file)
delete_list.extend(
[line for line in open(command_args.delete_file, "r")])
if command_args.all_tag:
query_string = "tags__in=%s" % command_args.all_tag
delete_list.extend(u.list_ids(api.list_sources, query_string))
delete_list.extend(u.list_ids(api.list_datasets, query_string))
delete_list.extend(u.list_ids(api.list_models, query_string))
delete_list.extend(u.list_ids(api.list_predictions, query_string))
delete_list.extend(u.list_ids(api.list_evaluations, query_string))
# Retrieve sources/ids if provided
if command_args.source_tag:
query_string = "tags__in=%s" % command_args.source_tag
delete_list.extend(u.list_ids(api.list_sources, query_string))
# Retrieve datasets/ids if provided
if command_args.dataset_tag:
query_string = "tags__in=%s" % command_args.dataset_tag
delete_list.extend(u.list_ids(api.list_datasets, query_string))
# Retrieve model/ids if provided
if command_args.model_tag:
query_string = "tags__in=%s" % command_args.model_tag
delete_list.extend(u.list_ids(api.list_models, query_string))
# Retrieve prediction/ids if provided
if command_args.prediction_tag:
query_string = "tags__in=%s" % command_args.prediction_tag
delete_list.extend(u.list_ids(api.list_predictions, query_string))
# Retrieve evaluation/ids if provided
if command_args.evaluation_tag:
query_string = "tags__in=%s" % command_args.evaluation_tag
delete_list.extend(u.list_ids(api.list_evaluations, query_string))
# Retrieve ensembles/ids if provided
if command_args.ensemble_tag:
query_string = "tags__in=%s" % command_args.ensemble_tag
delete_list.extend(u.list_ids(api.list_ensembles, query_string))
message = u.dated("Deleting objects.\n")
u.log_message(message,
log_file=session_file,
console=command_args.verbosity)
message = "\n".join(delete_list)
u.log_message(message, log_file=session_file)
u.delete(api, delete_list)
if sys.platform == "win32" and sys.stdout.isatty():
message = (u"\nGenerated files:\n\n" +
unicode(u.print_tree(path, " "), "utf-8") + u"\n")
else:
message = "\nGenerated files:\n\n" + u.print_tree(path, " ") + "\n"
u.log_message(message,
log_file=session_file,
console=command_args.verbosity)
elif (command_args.training_set or command_args.test_set
or command_args.source or command_args.dataset
or command_args.datasets or command_args.votes_dirs):
compute_output(**output_args)
u.log_message("_" * 80 + "\n", log_file=session_file)
def delete_resources(command_args, api):
"""Deletes the resources selected by the user given options
"""
if command_args.predictions is None:
path = a.NOW
else:
path = u.check_dir(command_args.predictions)
session_file = "%s%s%s" % (path, os.sep, SESSIONS_LOG)
message = u.dated("Retrieving objects to delete.\n")
u.log_message(message,
log_file=session_file,
console=command_args.verbosity)
delete_list = []
if command_args.delete_list:
delete_list = map(str.strip, command_args.delete_list.split(','))
if command_args.delete_file:
if not os.path.exists(command_args.delete_file):
sys.exit("File %s not found" % command_args.delete_file)
delete_list.extend(
[line for line in open(command_args.delete_file, "r")])
resource_selectors = [(command_args.source_tag, api.list_sources),
(command_args.dataset_tag, api.list_datasets),
(command_args.model_tag, api.list_models),
(command_args.prediction_tag, api.list_predictions),
(command_args.evaluation_tag, api.list_evaluations),
(command_args.ensemble_tag, api.list_ensembles),
(command_args.batch_prediction_tag,
api.list_batch_predictions)]
query_string = None
if command_args.older_than:
date_str = get_date(command_args.older_than, api)
if date_str:
query_string = "created__lt=%s" % date_str
else:
sys.exit("The --older-than and --newer-than flags only accept "
"integers (number of days), dates in YYYY-MM-DD format "
" and resource ids. Please, double-check your input.")
if command_args.newer_than:
date_str = get_date(command_args.newer_than, api)
if date_str:
if query_string is None:
query_string = ""
else:
query_string += ";"
query_string += "created__gt=%s" % date_str
else:
sys.exit("The --older-than and --newer-than flags only accept "
"integers (number of days), dates in YYYY-MM-DD format "
" and resource ids. Please, double-check your input.")
if (any([selector[0] is not None for selector in resource_selectors])
or command_args.all_tag):
if query_string is None:
query_string = ""
else:
query_string += ";"
for selector, api_call in resource_selectors:
combined_query = query_string
if command_args.all_tag:
combined_query += "tags__in=%s" % command_args.all_tag
delete_list.extend(u.list_ids(api_call, combined_query))
elif selector:
combined_query += "tags__in=%s" % selector
delete_list.extend(u.list_ids(api_call, combined_query))
else:
if query_string:
for selector, api_call in resource_selectors:
delete_list.extend(u.list_ids(api_call, query_string))
message = u.dated("Deleting objects.\n")
u.log_message(message,
log_file=session_file,
console=command_args.verbosity)
message = "\n".join(delete_list)
u.log_message(message, log_file=session_file)
u.delete(api, delete_list)
if sys.platform == "win32" and sys.stdout.isatty():
message = (u"\nGenerated files:\n\n" +
unicode(u.print_tree(path, " "), "utf-8") + u"\n")
else:
message = "\nGenerated files:\n\n" + u.print_tree(path, " ") + "\n"
u.log_message(message,
log_file=session_file,
console=command_args.verbosity)
def models_processing(datasets, models, model_ids, objective_field, fields,
api, args, resume,
name=None, description=None, model_fields=None,
session_file=None, path=None,
log=None, labels=None, multi_label_data=None,
other_label=None):
"""Creates or retrieves models from the input data
"""
ensemble_ids = []
# If we have a dataset but not a model, we create the model if the no_model
# flag hasn't been set up.
if datasets and not (has_models(args) or args.no_model):
dataset = datasets[0]
model_ids = []
models = []
if args.multi_label:
# If --number-of-models is not set or is 1, create one model per
# label. Otherwise, create one ensemble per label with the required
# number of models
if args.number_of_models < 2:
models, model_ids, resume = model_per_label(
labels, datasets, fields,
objective_field, api, args, resume, name, description,
model_fields, multi_label_data, session_file, path, log)
else:
(ensembles, ensemble_ids,
models, model_ids, resume) = ensemble_per_label(
labels, dataset, fields,
objective_field, api, args, resume, name, description,
model_fields, multi_label_data, session_file, path, log)
elif args.number_of_models > 1:
ensembles = []
# Ensemble of models
(ensembles, ensemble_ids,
models, model_ids, resume) = ensemble_processing(
datasets, objective_field, fields, api, args, resume,
name=name, description=description, model_fields=model_fields,
session_file=session_file, path=path, log=log)
ensemble = ensembles[0]
args.ensemble = bigml.api.get_ensemble_id(ensemble)
else:
# Set of partial datasets created setting args.max_categories
if len(datasets) > 1 and args.max_categories:
args.number_of_models = len(datasets)
# Cross-validation case: we create 2 * n models to be validated
# holding out an n% of data
if args.cross_validation_rate > 0:
if args.number_of_evaluations > 0:
args.number_of_models = args.number_of_evaluations
else:
args.number_of_models = int(MONTECARLO_FACTOR *
args.cross_validation_rate)
if resume:
resume, model_ids = c.checkpoint(
c.are_models_created, path, args.number_of_models,
debug=args.debug)
if not resume:
message = u.dated("Found %s models out of %s. Resuming.\n"
% (len(model_ids),
args.number_of_models))
u.log_message(message, log_file=session_file,
console=args.verbosity)
models = model_ids
args.number_of_models -= len(model_ids)
if args.max_categories > 0:
objective_field = None
model_args = r.set_model_args(name, description, args,
objective_field, fields,
model_fields, other_label)
models, model_ids = r.create_models(datasets, models,
model_args, args, api,
path, session_file, log)
# If a model is provided, we use it.
elif args.model:
model_ids = [args.model]
models = model_ids[:]
elif args.models or args.model_tag:
models = model_ids[:]
if args.ensemble:
ensemble = r.get_ensemble(args.ensemble, api, args.verbosity,
session_file)
ensemble_ids = [ensemble]
model_ids = ensemble['object']['models']
models = model_ids[:]
if args.ensembles or args.ensemble_tag:
model_ids = []
ensemble_ids = []
# Parses ensemble/ids if provided.
if args.ensemble_tag:
ensemble_ids = (ensemble_ids +
u.list_ids(api.list_ensembles,
"tags__in=%s" % args.ensemble_tag))
else:
ensemble_ids = u.read_resources(args.ensembles)
for ensemble_id in ensemble_ids:
ensemble = r.get_ensemble(ensemble_id, api)
if args.ensemble is None:
args.ensemble = ensemble_id
model_ids.extend(ensemble['object']['models'])
models = model_ids[:]
# If we are going to predict we must retrieve the models
if model_ids and args.test_set and not args.evaluate:
models, model_ids = r.get_models(models, args, api, session_file)
return models, model_ids, ensemble_ids, resume
def get_output_args(api, train_stdin, test_stdin, command_args, resume):
"""Returns the output args needed for the main bigmler computation process
"""
if train_stdin:
if test_stdin:
sys.exit("The standard input can't be used both for training and"
" testing. Choose one of them")
command_args.training_set = StringIO.StringIO(sys.stdin.read())
elif test_stdin:
command_args.test_set = StringIO.StringIO(sys.stdin.read())
if command_args.objective_field:
objective = command_args.objective_field
try:
command_args.objective_field = int(objective)
except ValueError:
if not command_args.train_header:
sys.exit("The %s has been set as objective field but"
" the file has not been marked as containing"
" headers.\nPlease set the --train-header flag if"
" the file has headers or use a column number"
" to set the objective field." % objective)
output_args = {
"api": api,
"training_set": command_args.training_set,
"test_set": command_args.test_set,
"output": command_args.predictions,
"objective_field": command_args.objective_field,
"name": command_args.name,
"training_set_header": command_args.train_header,
"test_set_header": command_args.test_header,
"args": command_args,
"resume": resume,
}
# Reads description if provided.
if command_args.description:
description_arg = u.read_description(command_args.description)
output_args.update(description=description_arg)
else:
output_args.update(description="Created using BigMLer")
# Parses fields if provided.
if command_args.field_attributes:
field_attributes_arg = (
u.read_field_attributes(command_args.field_attributes))
output_args.update(field_attributes=field_attributes_arg)
if command_args.test_field_attributes:
field_attributes_arg = (
u.read_field_attributes(command_args.test_field_attributes))
output_args.update(test_field_attributes=field_attributes_arg)
# Parses types if provided.
if command_args.types:
types_arg = u.read_types(command_args.types)
output_args.update(types=types_arg)
if command_args.test_types:
types_arg = u.read_types(command_args.test_types)
output_args.update(test_types=types_arg)
# Parses dataset fields if provided.
if command_args.dataset_fields:
dataset_fields_arg = map(str.strip,
command_args.dataset_fields.split(
command_args.args_separator))
output_args.update(dataset_fields=dataset_fields_arg)
# Parses model input fields if provided.
if command_args.model_fields:
model_fields_arg = map(lambda x: x.strip(),
command_args.model_fields.split(
command_args.args_separator))
output_args.update(model_fields=model_fields_arg)
model_ids = []
# Parses model/ids if provided.
if command_args.models:
model_ids = u.read_resources(command_args.models)
output_args.update(model_ids=model_ids)
# Retrieve model/ids if provided.
if command_args.model_tag:
model_ids = (model_ids +
u.list_ids(api.list_models,
"tags__in=%s" % command_args.model_tag))
output_args.update(model_ids=model_ids)
# Reads votes files in the provided directories.
if command_args.votes_dirs:
dirs = map(str.strip, command_args.votes_dirs.split(
command_args.args_separator))
votes_path = os.path.dirname(command_args.predictions)
votes_files = u.read_votes_files(dirs, votes_path)
output_args.update(votes_files=votes_files)
# Parses fields map if provided.
if command_args.fields_map:
fields_map_arg = u.read_fields_map(command_args.fields_map)
output_args.update(fields_map=fields_map_arg)
return output_args
def transform_args(command_args, flags, api, user_defaults):
"""Transforms the formatted argument strings into structured arguments
"""
# Parses attributes in json format if provided
command_args.json_args = {}
for resource_type in RESOURCE_TYPES:
attributes_file = getattr(command_args,
"%s_attributes" % resource_type, None)
if attributes_file is not None:
command_args.json_args[resource_type] = u.read_json(
attributes_file)
else:
command_args.json_args[resource_type] = {}
# Parses dataset generators in json format if provided
if command_args.new_fields:
json_generators = u.read_json(command_args.new_fields)
command_args.dataset_json_generators = json_generators
else:
command_args.dataset_json_generators = {}
# Parses multi-dataset attributes in json such as field maps
if command_args.multi_dataset_attributes:
multi_dataset_json = u.read_json(command_args.multi_dataset_attributes)
command_args.multi_dataset_json = multi_dataset_json
else:
command_args.multi_dataset_json = {}
dataset_ids = None
command_args.dataset_ids = []
# Parses dataset/id if provided.
if command_args.datasets:
dataset_ids = u.read_datasets(command_args.datasets)
if len(dataset_ids) == 1:
command_args.dataset = dataset_ids[0]
command_args.dataset_ids = dataset_ids
# Reading test dataset ids is delayed till the very moment of use to ensure
# that the newly generated resources files can be used there too
command_args.test_dataset_ids = []
# Retrieve dataset/ids if provided.
if command_args.dataset_tag:
dataset_ids = dataset_ids.extend(
u.list_ids(api.list_datasets,
"tags__in=%s" % command_args.dataset_tag))
if len(dataset_ids) == 1:
command_args.dataset = dataset_ids[0]
command_args.dataset_ids = dataset_ids
# Reads a json filter if provided.
if command_args.json_filter:
json_filter = u.read_json_filter(command_args.json_filter)
command_args.json_filter = json_filter
# Reads a lisp filter if provided.
if command_args.lisp_filter:
lisp_filter = u.read_lisp_filter(command_args.lisp_filter)
command_args.lisp_filter = lisp_filter
# Adds default tags unless that it is requested not to do so.
if command_args.no_tag:
command_args.tag.append('BigMLer')
command_args.tag.append('BigMLer_%s' % NOW)
# Checks combined votes method
try:
if (command_args.method and command_args.method != COMBINATION_LABEL
and not (command_args.method in COMBINATION_WEIGHTS.keys())):
command_args.method = 0
else:
combiner_methods = dict([[value, key]
for key, value in COMBINER_MAP.items()])
combiner_methods[COMBINATION_LABEL] = COMBINATION
command_args.method = combiner_methods.get(command_args.method, 0)
except AttributeError:
pass
# Checks missing_strategy
try:
if (command_args.missing_strategy
and not (command_args.missing_strategy
in MISSING_STRATEGIES.keys())):
command_args.missing_strategy = 0
else:
command_args.missing_strategy = MISSING_STRATEGIES.get(
command_args.missing_strategy, 0)
except AttributeError:
pass
# Adds replacement=True if creating ensemble and nothing is specified
try:
if (command_args.number_of_models > 1 and not command_args.replacement
and not '--no-replacement' in flags
and not 'replacement' in user_defaults
and not '--no-randomize' in flags
and not 'randomize' in user_defaults
and not '--sample-rate' in flags
and not 'sample_rate' in user_defaults):
command_args.replacement = True
except AttributeError:
pass
try:
# Old value for --prediction-info='full data' maps to 'full'
if command_args.prediction_info == 'full data':
print("WARNING: 'full data' is a deprecated value. Use"
" 'full' instead")
command_args.prediction_info = FULL_FORMAT
except AttributeError:
pass
# Parses class, weight pairs for objective weight
try:
if command_args.objective_weights:
objective_weights = (u.read_objective_weights(
command_args.objective_weights))
command_args.objective_weights_json = objective_weights
except AttributeError:
pass
try:
command_args.multi_label_fields_list = []
if command_args.multi_label_fields is not None:
multi_label_fields = command_args.multi_label_fields.strip()
command_args.multi_label_fields_list = multi_label_fields.split(
command_args.args_separator)
except AttributeError:
pass
# Sets shared_flag if --shared or --unshared has been used
if '--shared' in flags or '--unshared' in flags:
command_args.shared_flag = True
else:
command_args.shared_flag = False
# Set remote on if scoring a trainind dataset in bigmler anomaly
try:
if command_args.score:
command_args.remote = True
if not "--prediction-info" in flags:
command_args.prediction_info = FULL_FORMAT
except AttributeError:
pass
command_args.has_models_ = (
(hasattr(command_args, 'model') and command_args.model)
or (hasattr(command_args, 'models') and command_args.models)
or (hasattr(command_args, 'ensemble') and command_args.ensemble)
or (hasattr(command_args, 'ensembles') and command_args.ensembles)
or (hasattr(command_args, 'cluster') and command_args.cluster)
or (hasattr(command_args, 'clusters') and command_args.clusters)
or (hasattr(command_args, 'model_tag') and command_args.model_tag)
or (hasattr(command_args, 'anomaly') and command_args.anomaly)
or (hasattr(command_args, 'anomalies') and command_args.anomalies) or
(hasattr(command_args, 'ensemble_tag') and command_args.ensemble_tag)
or (hasattr(command_args, 'cluster_tag') and command_args.cluster_tag)
or (hasattr(command_args, 'anomaly_tag') and command_args.anomaly_tag))
command_args.has_datasets_ = (
(hasattr(command_args, 'dataset') and command_args.dataset)
or (hasattr(command_args, 'datasets') and command_args.datasets)
or (hasattr(command_args, 'dataset_tag') and command_args.dataset_tag))
command_args.has_test_datasets_ = (
(hasattr(command_args, 'test_dataset') and command_args.test_dataset)
or
(hasattr(command_args, 'test_datasets') and command_args.test_datasets)
or (hasattr(command_args, 'test_dataset_tag')
and command_args.test_dataset_tag))
def main(args=sys.argv[1:]):
"""Main process
"""
train_stdin = False
test_stdin = False
flags = []
for i in range(0, len(args)):
if args[i].startswith("--"):
flag = args[i]
# syntax --flag=value
if "=" in flag:
flag = args[i][0: flag.index("=")]
flag = flag.replace("_", "-")
flags.append(flag)
if (flag == '--train' and
(i == len(args) - 1 or args[i + 1].startswith("--"))):
train_stdin = True
elif (flag == '--test' and
(i == len(args) - 1 or args[i + 1].startswith("--"))):
test_stdin = True
# If --clear-logs the log files are cleared
if "--clear-logs" in args:
for log_file in LOG_FILES:
try:
open(log_file, 'w', 0).close()
except IOError:
pass
literal_args = args[:]
for i in range(0, len(args)):
# quoting literals with blanks: 'petal length'
if ' ' in args[i]:
prefix = ""
literal = args[i]
# literals with blanks after "+" or "-": +'petal length'
if args[i][0] in r.ADD_REMOVE_PREFIX:
prefix = args[i][0]
literal = args[i][1:]
literal_args[i] = '%s"%s"' % (prefix, literal)
message = "bigmler %s\n" % " ".join(literal_args)
# Resume calls are not logged
if not "--resume" in args:
with open(COMMAND_LOG, "a", 0) as command_log:
command_log.write(message)
resume = False
user_defaults = get_user_defaults()
parser = create_parser(defaults=get_user_defaults(),
constants={'NOW': NOW,
'MAX_MODELS': MAX_MODELS, 'PLURALITY': PLURALITY})
# Parses command line arguments.
command_args = parser.parse_args(args)
if command_args.cross_validation_rate > 0 and (
non_compatible(command_args, '--cross-validation-rate')):
parser.error("Non compatible flags: --cross-validation-rate"
" cannot be used with --evaluate, --model,"
" --models or --model-tag. Usage:\n\n"
"bigmler --train data/iris.csv "
"--cross-validation-rate 0.1")
if train_stdin and command_args.multi_label:
parser.error("Reading multi-label training sets from stream "
"is not yet available.")
if test_stdin and command_args.resume:
parser.error("Can't resume when using stream reading test sets.")
default_output = ('evaluation' if command_args.evaluate
else 'predictions.csv')
if command_args.resume:
debug = command_args.debug
command = u.get_log_reversed(COMMAND_LOG,
command_args.stack_level)
args = shlex.split(command)[1:]
try:
position = args.index("--train")
train_stdin = (position == (len(args) - 1) or
args[position + 1].startswith("--"))
except ValueError:
pass
try:
position = args.index("--test")
test_stdin = (position == (len(args) - 1) or
args[position + 1].startswith("--"))
except ValueError:
pass
output_dir = u.get_log_reversed(DIRS_LOG,
command_args.stack_level)
defaults_file = "%s%s%s" % (output_dir, os.sep, DEFAULTS_FILE)
user_defaults = get_user_defaults(defaults_file)
parser = create_parser(defaults=user_defaults,
constants={'NOW': NOW,
'MAX_MODELS': MAX_MODELS,
'PLURALITY': PLURALITY})
command_args = parser.parse_args(args)
if command_args.predictions is None:
command_args.predictions = ("%s%s%s" %
(output_dir, os.sep,
default_output))
# Logs the issued command and the resumed command
session_file = "%s%s%s" % (output_dir, os.sep, SESSIONS_LOG)
u.log_message(message, log_file=session_file)
message = "\nResuming command:\n%s\n\n" % command
u.log_message(message, log_file=session_file, console=True)
try:
defaults_handler = open(defaults_file, 'r')
contents = defaults_handler.read()
message = "\nUsing the following defaults:\n%s\n\n" % contents
u.log_message(message, log_file=session_file, console=True)
defaults_handler.close()
except IOError:
pass
resume = True
else:
if command_args.predictions is None:
command_args.predictions = ("%s%s%s" %
(NOW, os.sep,
default_output))
if len(os.path.dirname(command_args.predictions).strip()) == 0:
command_args.predictions = ("%s%s%s" %
(NOW, os.sep,
command_args.predictions))
directory = u.check_dir(command_args.predictions)
session_file = "%s%s%s" % (directory, os.sep, SESSIONS_LOG)
u.log_message(message + "\n", log_file=session_file)
try:
defaults_file = open(DEFAULTS_FILE, 'r')
contents = defaults_file.read()
defaults_file.close()
defaults_copy = open("%s%s%s" % (directory, os.sep, DEFAULTS_FILE),
'w', 0)
defaults_copy.write(contents)
defaults_copy.close()
except IOError:
pass
with open(DIRS_LOG, "a", 0) as directory_log:
directory_log.write("%s\n" % os.path.abspath(directory))
if resume and debug:
command_args.debug = True
if train_stdin:
if test_stdin:
sys.exit("The standard input can't be used both for training and"
" testing. Choose one of them")
command_args.training_set = StringIO.StringIO(sys.stdin.read())
elif test_stdin:
command_args.test_set = StringIO.StringIO(sys.stdin.read())
api_command_args = {
'username': command_args.username,
'api_key': command_args.api_key,
'dev_mode': command_args.dev_mode,
'debug': command_args.debug}
if command_args.store:
api_command_args.update({'storage': u.check_dir(session_file)})
api = bigml.api.BigML(**api_command_args)
if (command_args.evaluate
and not (command_args.training_set or command_args.source
or command_args.dataset)
and not ((command_args.test_set or command_args.test_split) and
(command_args.model or
command_args.models or command_args.model_tag or
command_args.ensemble or command_args.ensembles or
command_args.ensemble_tag))):
parser.error("Evaluation wrong syntax.\n"
"\nTry for instance:\n\nbigmler --train data/iris.csv"
" --evaluate\nbigmler --model "
"model/5081d067035d076151000011 --dataset "
"dataset/5081d067035d076151003423 --evaluate\n"
"bigmler --ensemble ensemble/5081d067035d076151003443"
" --dataset "
"dataset/5081d067035d076151003423 --evaluate")
if command_args.objective_field:
objective = command_args.objective_field
try:
command_args.objective_field = int(objective)
except ValueError:
if not command_args.train_header:
sys.exit("The %s has been set as objective field but"
" the file has not been marked as containing"
" headers.\nPlease set the --train-header flag if"
" the file has headers or use a column number"
" to set the objective field." % objective)
output_args = {
"api": api,
"training_set": command_args.training_set,
"test_set": command_args.test_set,
"output": command_args.predictions,
"objective_field": command_args.objective_field,
"name": command_args.name,
"training_set_header": command_args.train_header,
"test_set_header": command_args.test_header,
"args": command_args,
"resume": resume,
}
# Reads description if provided.
if command_args.description:
description_arg = u.read_description(command_args.description)
output_args.update(description=description_arg)
else:
output_args.update(description="Created using BigMLer")
# Parses fields if provided.
if command_args.field_attributes:
field_attributes_arg = (
u.read_field_attributes(command_args.field_attributes))
output_args.update(field_attributes=field_attributes_arg)
# Parses types if provided.
if command_args.types:
types_arg = u.read_types(command_args.types)
output_args.update(types=types_arg)
# Parses dataset fields if provided.
if command_args.dataset_fields:
dataset_fields_arg = map(str.strip,
command_args.dataset_fields.split(','))
output_args.update(dataset_fields=dataset_fields_arg)
# Parses model input fields if provided.
if command_args.model_fields:
model_fields_arg = map(str.strip,
command_args.model_fields.split(','))
output_args.update(model_fields=model_fields_arg)
model_ids = []
# Parses model/ids if provided.
if command_args.models:
model_ids = u.read_resources(command_args.models)
output_args.update(model_ids=model_ids)
dataset_id = None
# Parses dataset/id if provided.
if command_args.datasets:
dataset_id = u.read_dataset(command_args.datasets)
command_args.dataset = dataset_id
# Retrieve model/ids if provided.
if command_args.model_tag:
model_ids = (model_ids +
u.list_ids(api.list_models,
"tags__in=%s" % command_args.model_tag))
output_args.update(model_ids=model_ids)
# Reads a json filter if provided.
if command_args.json_filter:
json_filter = u.read_json_filter(command_args.json_filter)
command_args.json_filter = json_filter
# Reads a lisp filter if provided.
if command_args.lisp_filter:
lisp_filter = u.read_lisp_filter(command_args.lisp_filter)
command_args.lisp_filter = lisp_filter
# Adds default tags unless that it is requested not to do so.
if command_args.no_tag:
command_args.tag.append('BigMLer')
command_args.tag.append('BigMLer_%s' % NOW)
# Checks combined votes method
if (command_args.method and
not command_args.method in COMBINATION_WEIGHTS.keys()):
command_args.method = 0
else:
combiner_methods = dict([[value, key]
for key, value in COMBINER_MAP.items()])
command_args.method = combiner_methods.get(command_args.method, 0)
# Adds replacement=True if creating ensemble and nothing is specified
if (command_args.number_of_models > 1 and
not command_args.replacement and
not '--no-replacement' in flags and
not 'replacement' in user_defaults and
not '--no-randomize' in flags and
not 'randomize' in user_defaults and
not '--sample-rate' in flags and
not 'sample_rate' in user_defaults):
command_args.replacement = True
# Reads votes files in the provided directories.
if command_args.votes_dirs:
dirs = map(str.strip, command_args.votes_dirs.split(','))
votes_path = os.path.dirname(command_args.predictions)
votes_files = u.read_votes_files(dirs, votes_path)
output_args.update(votes_files=votes_files)
# Parses fields map if provided.
if command_args.fields_map:
fields_map_arg = u.read_fields_map(command_args.fields_map)
output_args.update(fields_map=fields_map_arg)
# Old value for --prediction-info='full data' maps to 'full'
if command_args.prediction_info == 'full data':
print "WARNING: 'full data' is a deprecated value. Use 'full' instead"
command_args.prediction_info = FULL_FORMAT
# Parses resources ids if provided.
if command_args.delete:
if command_args.predictions is None:
path = NOW
else:
path = u.check_dir(command_args.predictions)
session_file = "%s%s%s" % (path, os.sep, SESSIONS_LOG)
message = u.dated("Retrieving objects to delete.\n")
u.log_message(message, log_file=session_file,
console=command_args.verbosity)
delete_list = []
if command_args.delete_list:
delete_list = map(str.strip,
command_args.delete_list.split(','))
if command_args.delete_file:
if not os.path.exists(command_args.delete_file):
sys.exit("File %s not found" % command_args.delete_file)
delete_list.extend([line for line
in open(command_args.delete_file, "r")])
if command_args.all_tag:
query_string = "tags__in=%s" % command_args.all_tag
delete_list.extend(u.list_ids(api.list_sources, query_string))
delete_list.extend(u.list_ids(api.list_datasets, query_string))
delete_list.extend(u.list_ids(api.list_models, query_string))
delete_list.extend(u.list_ids(api.list_predictions, query_string))
delete_list.extend(u.list_ids(api.list_evaluations, query_string))
# Retrieve sources/ids if provided
if command_args.source_tag:
query_string = "tags__in=%s" % command_args.source_tag
delete_list.extend(u.list_ids(api.list_sources, query_string))
# Retrieve datasets/ids if provided
if command_args.dataset_tag:
query_string = "tags__in=%s" % command_args.dataset_tag
delete_list.extend(u.list_ids(api.list_datasets, query_string))
# Retrieve model/ids if provided
if command_args.model_tag:
query_string = "tags__in=%s" % command_args.model_tag
delete_list.extend(u.list_ids(api.list_models, query_string))
# Retrieve prediction/ids if provided
if command_args.prediction_tag:
query_string = "tags__in=%s" % command_args.prediction_tag
delete_list.extend(u.list_ids(api.list_predictions, query_string))
# Retrieve evaluation/ids if provided
if command_args.evaluation_tag:
query_string = "tags__in=%s" % command_args.evaluation_tag
delete_list.extend(u.list_ids(api.list_evaluations, query_string))
# Retrieve ensembles/ids if provided
if command_args.ensemble_tag:
query_string = "tags__in=%s" % command_args.ensemble_tag
delete_list.extend(u.list_ids(api.list_ensembles, query_string))
message = u.dated("Deleting objects.\n")
u.log_message(message, log_file=session_file,
console=command_args.verbosity)
message = "\n".join(delete_list)
u.log_message(message, log_file=session_file)
u.delete(api, delete_list)
if sys.platform == "win32" and sys.stdout.isatty():
message = (u"\nGenerated files:\n\n" +
unicode(u.print_tree(path, " "), "utf-8") + u"\n")
else:
message = "\nGenerated files:\n\n" + u.print_tree(path, " ") + "\n"
u.log_message(message, log_file=session_file,
console=command_args.verbosity)
elif (command_args.training_set or command_args.test_set
or command_args.source or command_args.dataset
or command_args.datasets or command_args.votes_dirs):
compute_output(**output_args)
u.log_message("_" * 80 + "\n", log_file=session_file)