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 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)
session_file=session_file, path=path,
log=log, labels=labels, all_labels=all_labels,
objective_field=objective_field)
# If cross_validation_rate is > 0, create remote evaluations and save
# results in json and human-readable format. Then average the results to
# issue a cross_validation measure set.
if args.cross_validation_rate > 0:
args.sample_rate = 1 - args.cross_validation_rate
cross_validate(models, dataset, fields, api, args, resume,
name=name, description=description,
fields_map=fields_map, session_file=session_file,
path=path, log=log)
# Workaround to restore windows console cp850 encoding to print the tree
if sys.platform == "win32" and sys.stdout.isatty():
import locale
data_locale = locale.getlocale()
if not data_locale[0] is None:
locale.setlocale(locale.LC_ALL, (data_locale[0], "850"))
message = (u"\nGenerated files:\n\n" +
unicode(u.print_tree(path, u" "), "utf-8") + u"\n")
else:
message = (u"\nGenerated files:\n\n" +
u.print_tree(path, u" ") + u"\n")
u.log_message(message, log_file=session_file, console=args.verbosity)
if args.reports:
clear_reports(path)
if args.upload:
upload_reports(args.reports, path)
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)
fields_map,
api,
args,
resume,
session_file=session_file,
path=path,
log=log)
# Workaround to restore windows console cp850 encoding to print the tree
if sys.platform == "win32" and sys.stdout.isatty():
import locale
data_locale = locale.getlocale()
if not data_locale[0] is None:
locale.setlocale(locale.LC_ALL, (data_locale[0], "850"))
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=args.verbosity)
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("--"))):
# issue a cross_validation measure set.
if args.cross_validation_rate > 0:
args.sample_rate = 1 - args.cross_validation_rate
cross_validate(models, dataset, fields, api, args, resume,
name=name, description=description,
fields_map=fields_map, session_file=session_file,
path=path, log=log)
# Workaround to restore windows console cp850 encoding to print the tree
if sys.platform == "win32" and sys.stdout.isatty():
import locale
data_locale = locale.getlocale()
if not data_locale[0] is None:
locale.setlocale(locale.LC_ALL, (data_locale[0], "850"))
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=args.verbosity)
def main(args=sys.argv[1:]):
"""Main process
"""
(flags, train_stdin, test_stdin) = a.get_flags(args)
# If --clear-logs the log files are cleared
if "--clear-logs" in args:
for log_file in LOG_FILES:
try:
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 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 compute_output(api, args, training_set, test_set=None, output=None,
objective_field=None,
description=None,
field_attributes=None,
types=None,
dataset_fields=None,
model_fields=None,
name=None, training_set_header=True,
test_set_header=True, model_ids=None,
votes_files=None, resume=False, fields_map=None):
""" Creates one or more models using the `training_set` or uses the ids
of previously created BigML models to make predictions for the `test_set`.
"""
source = None
dataset = None
model = None
models = None
fields = None
path = u.check_dir(output)
session_file = "%s%s%s" % (path, os.sep, SESSIONS_LOG)
csv_properties = {}
# If logging is required, open the file for logging
log = None
if args.log_file:
u.check_dir(args.log_file)
log = args.log_file
# If --clear_logs the log files are cleared
if args.clear_logs:
try:
open(log, 'w', 0).close()
except IOError:
pass
if (training_set or (args.evaluate and test_set)):
if resume:
resume, args.source = u.checkpoint(u.is_source_created, path,
bigml.api, debug=args.debug)
if not resume:
message = u.dated("Source not found. Resuming.\n")
u.log_message(message, log_file=session_file,
console=args.verbosity)
# If neither a previous source, dataset or model are provided.
# we create a new one. Also if --evaluate and test data are provided
# we create a new dataset to test with.
data_set = None
if (training_set and not args.source and not args.dataset and
not args.model and not args.models):
data_set = training_set
data_set_header = training_set_header
elif (args.evaluate and test_set and not args.source):
data_set = test_set
data_set_header = test_set_header
if not data_set is None:
source_args = {
"name": name,
"description": description,
"category": args.category,
"tags": args.tag,
"source_parser": {"header": data_set_header}}
message = u.dated("Creating source.\n")
u.log_message(message, log_file=session_file, console=args.verbosity)
source = api.create_source(data_set, source_args,
progress_bar=args.progress_bar)
source = api.check_resource(source, api.get_source)
message = u.dated("Source created: %s\n" % u.get_url(source, api))
u.log_message(message, log_file=session_file, console=args.verbosity)
u.log_message("%s\n" % source['resource'], log_file=log)
fields = Fields(source['object']['fields'],
source['object']['source_parser']['missing_tokens'],
source['object']['source_parser']['locale'])
source_file = open(path + '/source', 'w', 0)
source_file.write("%s\n" % source['resource'])
source_file.write("%s\n" % source['object']['name'])
source_file.flush()
source_file.close()
# If a source is provided, we retrieve it.
elif args.source:
message = u.dated("Retrieving source. %s\n" %
u.get_url(args.source, api))
u.log_message(message, log_file=session_file, console=args.verbosity)
source = api.get_source(args.source)
# If we already have source, we check that is finished and extract the
# fields, and update them if needed.
if source:
if source['object']['status']['code'] != bigml.api.FINISHED:
message = u.dated("Retrieving source. %s\n" %
u.get_url(source, api))
u.log_message(message, log_file=session_file,
console=args.verbosity)
source = api.check_resource(source, api.get_source)
csv_properties = {'missing_tokens':
source['object']['source_parser']['missing_tokens'],
'data_locale':
source['object']['source_parser']['locale']}
fields = Fields(source['object']['fields'], **csv_properties)
update_fields = {}
if field_attributes:
for (column, value) in field_attributes.iteritems():
update_fields.update({
fields.field_id(column): value})
message = u.dated("Updating source. %s\n" %
u.get_url(source, api))
u.log_message(message, log_file=session_file,
console=args.verbosity)
source = api.update_source(source, {"fields": update_fields})
update_fields = {}
if types:
for (column, value) in types.iteritems():
update_fields.update({
fields.field_id(column): {'optype': value}})
message = u.dated("Updating source. %s\n" %
u.get_url(source, api))
u.log_message(message, log_file=session_file,
console=args.verbosity)
source = api.update_source(source, {"fields": update_fields})
if (training_set or args.source or (args.evaluate and test_set)):
if resume:
resume, args.dataset = u.checkpoint(u.is_dataset_created, path,
bigml.api,
debug=args.debug)
if not resume:
message = u.dated("Dataset not found. Resuming.\n")
u.log_message(message, log_file=session_file,
console=args.verbosity)
# If we have a source but not dataset or model has been provided, we
# create a new dataset if the no_dataset option isn't set up. Also
# if evaluate is set and test_set has been provided.
if ((source and not args.dataset and not args.model and not model_ids and
not args.no_dataset) or
(args.evaluate and args.test_set and not args.dataset)):
dataset_args = {
"name": name,
"description": description,
"category": args.category,
"tags": args.tag
}
if args.json_filter:
dataset_args.update(json_filter=args.json_filter)
elif args.lisp_filter:
dataset_args.update(lisp_filter=args.lisp_filter)
input_fields = []
if dataset_fields:
for name in dataset_fields:
input_fields.append(fields.field_id(name))
dataset_args.update(input_fields=input_fields)
message = u.dated("Creating dataset.\n")
u.log_message(message, log_file=session_file, console=args.verbosity)
dataset = api.create_dataset(source, dataset_args)
dataset = api.check_resource(dataset, api.get_dataset)
message = u.dated("Dataset created: %s\n" % u.get_url(dataset, api))
u.log_message(message, log_file=session_file, console=args.verbosity)
u.log_message("%s\n" % dataset['resource'], log_file=log)
dataset_file = open(path + '/dataset', 'w', 0)
dataset_file.write("%s\n" % dataset['resource'])
dataset_file.flush()
dataset_file.close()
# If a dataset is provided, let's retrieve it.
elif args.dataset:
message = u.dated("Retrieving dataset. %s\n" %
u.get_url(args.dataset, api))
u.log_message(message, log_file=session_file, console=args.verbosity)
dataset = api.get_dataset(args.dataset)
# If we already have a dataset, we check the status and get the fields if
# we hadn't them yet.
if dataset:
if dataset['object']['status']['code'] != bigml.api.FINISHED:
message = u.dated("Retrieving dataset. %s\n" %
u.get_url(dataset, api))
u.log_message(message, log_file=session_file,
console=args.verbosity)
dataset = api.check_resource(dataset, api.get_dataset)
if not csv_properties:
csv_properties = {'data_locale':
dataset['object']['locale']}
if args.public_dataset:
if not description:
raise Exception("You should provide a description to publish.")
public_dataset = {"private": False}
if args.dataset_price:
message = u.dated("Updating dataset. %s\n" %
u.get_url(dataset, api))
u.log_message(message, log_file=session_file,
console=args.verbosity)
public_dataset.update(price=args.dataset_price)
message = u.dated("Updating dataset. %s\n" %
u.get_url(dataset, api))
u.log_message(message, log_file=session_file,
console=args.verbosity)
dataset = api.update_dataset(dataset, public_dataset)
fields = Fields(dataset['object']['fields'], **csv_properties)
# If we have a dataset but not a model, we create the model if the no_model
# flag hasn't been set up.
if (dataset and not args.model and not model_ids and not args.no_model):
model_args = {
"name": name,
"description": description,
"category": args.category,
"tags": args.tag
}
if objective_field is not None:
model_args.update({"objective_field":
fields.field_id(objective_field)})
# If evaluate flag is on, we choose a deterministic sampling with 80%
# of the data to create the model
if args.evaluate:
if args.sample_rate == 1:
args.sample_rate = EVALUATE_SAMPLE_RATE
seed = SEED
model_args.update(seed=seed)
input_fields = []
if model_fields:
for name in model_fields:
input_fields.append(fields.field_id(name))
model_args.update(input_fields=input_fields)
if args.pruning and args.pruning != 'smart':
model_args.update(stat_pruning=(args.pruning == 'statistical'))
model_args.update(sample_rate=args.sample_rate,
replacement=args.replacement,
randomize=args.randomize)
model_ids = []
models = []
if resume:
resume, model_ids = u.checkpoint(u.are_models_created, path,
args.number_of_models,
bigml.api, 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_file = open(path + '/models', 'w', 0)
for model_id in model_ids:
model_file.write("%s\n" % model_id)
last_model = None
if args.number_of_models > 0:
message = u.dated("Creating %s.\n" %
u.plural("model", args.number_of_models))
u.log_message(message, log_file=session_file,
console=args.verbosity)
for i in range(1, args.number_of_models + 1):
if i > args.max_parallel_models:
api.check_resource(last_model, api.get_model)
model = api.create_model(dataset, model_args)
u.log_message("%s\n" % model['resource'], log_file=log)
last_model = model
model_ids.append(model['resource'])
models.append(model)
model_file.write("%s\n" % model['resource'])
model_file.flush()
if args.number_of_models < 2 and args.verbosity:
if model['object']['status']['code'] != bigml.api.FINISHED:
model = api.check_resource(model, api.get_model)
models[0] = model
message = u.dated("Model created: %s.\n" %
u.get_url(model, api))
u.log_message(message, log_file=session_file,
console=args.verbosity)
model_file.close()
# If a model is provided, we retrieve it.
elif args.model:
message = u.dated("Retrieving model. %s\n" %
u.get_url(args.model, api))
u.log_message(message, log_file=session_file, console=args.verbosity)
model = api.get_model(args.model)
elif args.models or args.model_tag:
models = model_ids[:]
if model_ids and test_set and not args.evaluate:
model_id = ""
if len(model_ids) == 1:
model_id = model_ids[0]
message = u.dated("Retrieving %s. %s\n" %
(u.plural("model", len(model_ids)),
u.get_url(model_id, api)))
u.log_message(message, log_file=session_file, console=args.verbosity)
if len(model_ids) < args.max_batch_models:
models = []
for model in model_ids:
model = api.check_resource(model, api.get_model)
models.append(model)
model = models[0]
else:
model = api.check_resource(model_ids[0], api.get_model)
models[0] = model
# We check that the model is finished and get the fields if haven't got
# them yet.
if model and not args.evaluate and (test_set or args.black_box
or args.white_box):
if model['object']['status']['code'] != bigml.api.FINISHED:
message = u.dated("Retrieving model. %s\n" %
u.get_url(model, api))
u.log_message(message, log_file=session_file,
console=args.verbosity)
model = api.check_resource(model, api.get_model)
if args.black_box:
if not description:
raise Exception("You should provide a description to publish.")
model = api.update_model(model, {"private": False})
if args.white_box:
if not description:
raise Exception("You should provide a description to publish.")
public_model = {"private": False, "white_box": True}
if args.model_price:
message = u.dated("Updating model. %s\n" %
u.get_url(model, api))
u.log_message(message, log_file=session_file,
console=args.verbosity)
public_model.update(price=args.model_price)
if args.cpp:
message = u.dated("Updating model. %s\n" %
u.get_url(model, api))
u.log_message(message, log_file=session_file,
console=args.verbosity)
public_model.update(credits_per_prediction=args.cpp)
model = api.update_model(model, public_model)
if not csv_properties:
csv_properties = {'data_locale':
model['object']['locale']}
csv_properties.update(verbose=True)
if args.user_locale:
csv_properties.update(data_locale=args.user_locale)
fields = Fields(model['object']['model']['fields'], **csv_properties)
if model and not models:
models = [model]
if models and test_set and not args.evaluate:
objective_field = models[0]['object']['objective_fields']
if isinstance(objective_field, list):
objective_field = objective_field[0]
predict(test_set, test_set_header, models, fields, output,
objective_field, args.remote, api, log,
args.max_batch_models, args.method, resume, args.tag,
args.verbosity, session_file, args.debug)
# When combine_votes flag is used, retrieve the predictions files saved
# in the comma separated list of directories and combine them
if votes_files:
model_id = re.sub(r'.*(model_[a-f0-9]{24})__predictions\.csv$',
r'\1', votes_files[0]).replace("_", "/")
model = api.check_resource(model_id, api.get_model)
local_model = Model(model)
message = u.dated("Combining votes.\n")
u.log_message(message, log_file=session_file,
console=args.verbosity)
u.combine_votes(votes_files, local_model.to_prediction,
output, args.method)
# If evaluate flag is on, create remote evaluation and save results in
# json and human-readable format.
if args.evaluate:
if resume:
resume, evaluation = u.checkpoint(u.is_evaluation_created, path,
bigml.api,
debug=args.debug)
if not resume:
message = u.dated("Evaluation not found. Resuming.\n")
u.log_message(message, log_file=session_file,
console=args.verbosity)
if not resume:
evaluation_file = open(path + '/evaluation', 'w', 0)
evaluation_args = {
"name": name,
"description": description,
"tags": args.tag
}
if not fields_map is None:
update_map = {}
for (dataset_column, model_column) in fields_map.iteritems():
update_map.update({
fields.field_id(dataset_column):
fields.field_id(model_column)})
evaluation_args.update({"fields_map": update_map})
if not ((args.dataset or args.test_set)
and (args.model or args.models or args.model_tag)):
evaluation_args.update(out_of_bag=True, seed=SEED,
sample_rate=args.sample_rate)
message = u.dated("Creating evaluation.\n")
u.log_message(message, log_file=session_file,
console=args.verbosity)
evaluation = api.create_evaluation(model, dataset, evaluation_args)
u.log_message("%s\n" % evaluation['resource'], log_file=log)
evaluation_file.write("%s\n" % evaluation['resource'])
evaluation_file.flush()
evaluation_file.close()
message = u.dated("Retrieving evaluation. %s\n" %
u.get_url(evaluation, api))
u.log_message(message, log_file=session_file, console=args.verbosity)
evaluation = api.check_resource(evaluation, api.get_evaluation)
evaluation_json = open(output + '.json', 'w', 0)
evaluation_json.write(json.dumps(evaluation['object']['result']))
evaluation_json.flush()
evaluation_json.close()
evaluation_txt = open(output + '.txt', 'w', 0)
api.pprint(evaluation['object']['result'],
evaluation_txt)
evaluation_txt.flush()
evaluation_txt.close()
# Workaround to restore windows console cp850 encoding to print the tree
if sys.platform == "win32" and sys.stdout.isatty():
import locale
data_locale = locale.getlocale()
if not data_locale[0] is None:
locale.setlocale(locale.LC_ALL, (data_locale[0], "850"))
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=args.verbosity)
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)
