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 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 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 transform_args(command_args, flags, api, user_defaults): """Transforms the formatted argument strings into structured arguments """ attribute_args(command_args) # 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 = {} transform_dataset_options(command_args, api) # 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 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 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 = {} 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 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 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 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)
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 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 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 # 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 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 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) )