def i_create_all_ml_resources(step, tag=None, label_separator=None, number_of_labels=None, data=None, training_separator=None, test=None, output=None):
if tag is None or label_separator is None or training_separator is None or number_of_labels is None or data is None or test is None or output is None:
assert False
world.directory = os.path.dirname(output)
world.folders.append(world.directory)
world.number_of_models = int(number_of_labels)
test = res_filename(test)
try:
command = ("bigmler --multi-label --train " + res_filename(data) +
" --label-separator \"" + label_separator +
"\" --training-separator \"" + training_separator +
"\" --test " + test + " --store --output " + output +
" --tag " + tag + " --max-batch-models 1")
command = check_debug(command)
retcode = check_call(command, shell=True)
if retcode < 0:
assert False
else:
world.test_lines = file_number_of_lines(test)
# test file has headers in it, so first line must be ignored
world.test_lines -= 1
world.output = output
assert True
except (OSError, CalledProcessError, IOError) as exc:
assert False, str(exc)
def shell_execute(command, output, test=None, options=None,
data=None, test_split=None):
"""Excute bigmler command in shell
"""
command = check_debug(command)
world.directory = os.path.dirname(output)
world.folders.append(world.directory)
try:
retcode = check_call(command, shell=True)
if retcode < 0:
assert False
else:
if test is not None:
world.test_lines = file_number_of_lines(test)
if options is None or options.find('--prediction-header') == -1:
# test file has headers in it, so first line must be ignored
world.test_lines -= 1
if test_split is not None:
data_lines = file_number_of_lines(data) - 1
world.test_lines = int(data_lines * float(test_split))
world.output = output
assert True
except (OSError, CalledProcessError, IOError) as exc:
assert False, str(exc)
def i_evaluate_ensemble_with_dataset(step, ensemble_dir=None, dataset_dir=None, output=None):
if ensemble_dir is None or dataset_dir is None or output is None:
assert False
world.directory = os.path.dirname(output)
world.folders.append(world.directory)
ensemble_id = read_id_from_file(os.path.join(ensemble_dir, "ensembles"))
dataset_id = read_id_from_file(os.path.join(dataset_dir, "dataset_test"))
command = (
"bigmler --dataset "
+ dataset_id
+ " --ensemble "
+ ensemble_id
+ " --store"
+ " --output "
+ output
+ " --evaluate"
)
command = check_debug(command)
try:
retcode = check_call(command, shell=True)
if retcode < 0:
assert False
else:
world.output = output
assert True
except OSError as exc:
assert False, str(exc)
def i_create_with_split_to_evaluate_ensemble(step, data=None, number_of_models=None, split=None, output=None):
if data is None or split is None or output is None:
assert False
command = (
"bigmler --evaluate --train "
+ res_filename(data)
+ " --test-split "
+ split
+ " --number-of-models "
+ number_of_models
+ " --output "
+ output
)
command = check_debug(command)
try:
retcode = check_call(command, shell=True)
if retcode < 0:
assert False
else:
world.directory = os.path.dirname(output)
world.folders.append(world.directory)
world.output = output
assert True
except OSError as e:
assert False
def i_predict_ml_from_model_tag_with_labels(step,
labels=None,
tag=None,
test=None,
output=None):
if tag is None or labels is None or test is None or output is None:
assert False
world.directory = os.path.dirname(output)
world.folders.append(world.directory)
test = res_filename(test)
try:
command = ("bigmler --multi-label --model-tag " + tag + " --labels " +
labels + " --test " + test + " --store --output " + output +
" --max-batch-models 1")
command = check_debug(command)
retcode = check_call(command, shell=True)
if retcode < 0:
assert False
else:
world.test_lines = file_number_of_lines(test)
# test file has headers in it, so first line must be ignored
world.test_lines -= 1
world.output = output
assert True
except (OSError, CalledProcessError, IOError) as exc:
assert False, str(exc)
def i_create_source_with_project(step,
data=None,
project=None,
output_dir=None):
if data is None:
assert False
world.directory = output_dir
world.folders.append(world.directory)
#Check if the project already exists
previous_projects = world.api.list_projects('name=%s' % project)
while previous_projects['meta']['total_count'] > 0:
print "the project %s already exists, trying with:" % project
project += " " + project
print project
previous_projects = world.api.list_projects('name=%s' % project)
try:
command = (u"bigmler --train " + res_filename(data) +
u" --no-model --no-dataset --store --output-dir " +
output_dir + u" --project=\"" + project + "\"")
if not PYTHON3:
command = command.encode(SYSTEM_ENCODING)
command = check_debug(command)
retcode = check_call(command, shell=True)
if retcode < 0:
assert False
else:
world.output = output_dir
assert True
except (OSError, CalledProcessError, IOError) as exc:
assert False, str(exc)
def i_predict_ml_from_model_tag_with_labels(step, labels=None, tag=None, test=None, output=None):
if tag is None or labels is None or test is None or output is None:
assert False
world.directory = os.path.dirname(output)
world.folders.append(world.directory)
test = res_filename(test)
try:
command = (
"bigmler --multi-label --model-tag "
+ tag
+ " --labels "
+ labels
+ " --test "
+ test
+ " --store --output "
+ output
+ " --max-batch-models 1"
)
command = check_debug(command)
retcode = check_call(command, shell=True)
if retcode < 0:
assert False
else:
world.test_lines = file_number_of_lines(test)
# test file has headers in it, so first line must be ignored
world.test_lines -= 1
world.output = output
assert True
except (OSError, CalledProcessError, IOError) as exc:
assert False, str(exc)
def i_create_output(step,
output=None,
language=None,
resource_type='source',
add_fields=False):
if output is None and language is None:
assert False
world.directory = os.path.dirname(output)
world.folders.append(world.directory)
resource_id = getattr(world, resource_type)['resource']
try:
command = (u"bigmler reify --id " + resource_id + " --language " +
language + u" --store --output " + output)
if add_fields:
command += u' --add-fields'
command = check_debug(command)
if not PYTHON3:
command.encode(SYSTEM_ENCODING)
retcode = check_call(command, shell=True)
if retcode < 0:
assert False
else:
world.output = world.directory
assert True
except (OSError, CalledProcessError, IOError) as exc:
assert False, str(exc)
def i_create_resources_and_ensembles_from_dataset(step,
multi_label=None,
number_of_models=None,
test=None,
output=None):
if test is None or output is None:
assert False
world.directory = os.path.dirname(output)
world.folders.append(world.directory)
multi_label = "" if multi_label is None else " --multi-label "
test = res_filename(test)
try:
command = ("bigmler " + multi_label + "--dataset " +
world.dataset['resource'] + " --number-of-models " +
str(number_of_models) + " --test " + test +
" --store --output " + output)
command = check_debug(command)
retcode = check_call(command, shell=True)
if retcode < 0:
assert False
else:
world.test_lines = file_number_of_lines(test)
# test file has headers in it, so first line must be ignored
world.test_lines -= 1
world.output = output
assert True
except (OSError, CalledProcessError, IOError) as exc:
assert False, str(exc)
def i_create_all_ml_resources(step,
tag=None,
label_separator=None,
number_of_labels=None,
data=None,
training_separator=None,
test=None,
output=None):
if tag is None or label_separator is None or training_separator is None or number_of_labels is None or data is None or test is None or output is None:
assert False
world.directory = os.path.dirname(output)
world.folders.append(world.directory)
world.number_of_models = int(number_of_labels)
test = res_filename(test)
try:
command = ("bigmler --multi-label --train " + res_filename(data) +
" --label-separator \"" + label_separator +
"\" --training-separator \"" + training_separator +
"\" --test " + test + " --store --output " + output +
" --tag " + tag + " --max-batch-models 1")
command = check_debug(command)
retcode = check_call(command, shell=True)
if retcode < 0:
assert False
else:
world.test_lines = file_number_of_lines(test)
# test file has headers in it, so first line must be ignored
world.test_lines -= 1
world.output = output
assert True
except (OSError, CalledProcessError, IOError) as exc:
assert False, str(exc)
def i_create_source_with_project(step, data=None, project=None, output_dir=None):
ok_(data is not None)
world.directory = output_dir
world.folders.append(world.directory)
#Check if the project already exists
previous_projects = world.api.list_projects('name=%s' % project)
while previous_projects['meta']['total_count'] > 0:
print "the project %s already exists, trying with:" % project
project += " " + project
print project
previous_projects = world.api.list_projects('name=%s' % project)
try:
command = (u"bigmler --train " + res_filename(data) +
u" --no-model --no-dataset --store --output-dir " +
output_dir +
u" --project=\"" + project + "\"")
if not PYTHON3:
command = command.encode(SYSTEM_ENCODING)
command = check_debug(command)
retcode = check_call(command, shell=True)
if retcode < 0:
assert False
else:
world.output = output_dir
except (OSError, CalledProcessError, IOError) as exc:
assert False, str(exc)
def shell_execute(command,
output,
test=None,
options=None,
test_rows=None,
project=True):
"""Excute bigmler command in shell
"""
command = check_debug(command, project=project)
world.directory = os.path.dirname(output)
world.folders.append(world.directory)
try:
retcode = check_call(command, shell=True)
if retcode < 0:
assert False
else:
if test is not None:
world.test_lines = file_number_of_lines(test)
if options is None or \
options.find('--prediction-header') == -1:
# test file has headers in it, so first line must be ignored
world.test_lines -= 1
elif test_rows is not None:
world.test_lines = test_rows
if options is not None and \
options.find('--prediction-header') > -1:
world.test_lines += 1
elif options is not None and \
options.find('--prediction-header') > -1:
world.test_lines += 1
world.output = output
assert True
except (OSError, CalledProcessError, IOError) as exc:
assert False, str(exc)
def i_create_all_resources_to_evaluate_with_model_and_map(step, data=None, fields_map=None, output=None):
if data is None or fields_map is None or output is None:
assert False
command = (
"bigmler --evaluate --test "
+ res_filename(data)
+ " --model "
+ world.model["resource"]
+ " --output "
+ output
+ " --fields-map "
+ res_filename(fields_map)
)
command = check_debug(command)
try:
retcode = check_call(command, shell=True)
if retcode < 0:
assert False
else:
world.directory = os.path.dirname(output)
world.folders.append(world.directory)
world.output = output
assert True
except OSError as e:
assert False
def i_create_filtered_dataset_from_dataset(step, filter_exp=None, output_dir=None):
if filter_exp is None or output_dir is None:
assert False
world.directory = output_dir
world.folders.append(world.directory)
try:
if not sys.platform == 'win32':
filter_exp = u'"%s"' % filter_exp.replace('"', '\\"')
command = (u'echo ' +
filter_exp + u' > ' +
output_dir + u"/filter.lisp")
if not PYTHON3:
command = command.encode(SYSTEM_ENCODING)
retcode = check_call(command, shell=True)
command = ((u"bigmler --dataset %s" % world.dataset['resource']) +
u" --no-model --store --output-dir " + output_dir +
u" --lisp-filter " + output_dir + "/filter.lisp")
command = check_debug(command)
retcode = check_call(command, shell=True)
if retcode < 0:
assert False
else:
world.output = output_dir
assert True
except (OSError, CalledProcessError, IOError) as exc:
assert False, str(exc)
def shell_execute(command,
output,
test=None,
options=None,
data=None,
test_split=None):
"""Excute bigmler command in shell
"""
command = check_debug(command)
world.directory = os.path.dirname(output)
world.folders.append(world.directory)
try:
retcode = check_call(command, shell=True)
if retcode < 0:
assert False
else:
if test is not None:
world.test_lines = file_number_of_lines(test)
world.test_lines -= 1
# prediction file has headers in it,
# so first line must be ignored
world.prediction_header = options is not None and \
options.find('--prediction-header') > -1
if test_split is not None:
data_lines = file_number_of_lines(data) - 1
world.test_lines = int(data_lines * float(test_split))
world.output = output
assert True
except (OSError, CalledProcessError, IOError) as exc:
assert False, str(exc)
def i_create_all_mc_resources_from_source(step,
max_categories=None,
objective=None,
test=None,
output=None):
if max_categories is None or test is None or output is None:
assert False
world.directory = os.path.dirname(output)
world.folders.append(world.directory)
test = res_filename(test)
try:
command = ("bigmler --source " + world.source['resource'] +
" --max-categories " + max_categories + " --objective " +
objective + " --test " + test + " --store --output " +
output)
command = check_debug(command)
retcode = check_call(command, shell=True)
if retcode < 0:
assert False
else:
world.test_lines = file_number_of_lines(test)
# test file has headers in it, so first line must be ignored
world.test_lines -= 1
world.output = output
assert True
except (OSError, CalledProcessError, IOError) as exc:
assert False, str(exc)
def i_create_proportional_to_evaluate(step, test=None):
if test is None:
assert False
test = res_filename(test)
try:
output_dir = world.directory + "_eval/"
output = output_dir + os.path.basename(world.output)
command = (
"bigmler --evaluate --model "
+ world.model["resource"]
+ " --test "
+ test
+ " --missing-strategy proportional --output "
+ output
)
command = check_debug(command)
retcode = check_call(command, shell=True)
if retcode < 0:
assert False
else:
world.directory = output_dir
world.folders.append(world.directory)
world.output = output
assert True
except OSError as e:
assert False
def i_create_resources_and_ensembles_from_dataset(
step, multi_label=None, number_of_models=None, test=None, output=None
):
if test is None or output is None:
assert False
world.directory = os.path.dirname(output)
world.folders.append(world.directory)
multi_label = "" if multi_label is None else " --multi-label "
test = res_filename(test)
try:
command = (
"bigmler "
+ multi_label
+ "--dataset "
+ world.dataset["resource"]
+ " --number-of-models "
+ str(number_of_models)
+ " --test "
+ test
+ " --store --output "
+ output
)
command = check_debug(command)
retcode = check_call(command, shell=True)
if retcode < 0:
assert False
else:
world.test_lines = file_number_of_lines(test)
# test file has headers in it, so first line must be ignored
world.test_lines -= 1
world.output = output
assert True
except (OSError, CalledProcessError, IOError) as exc:
assert False, str(exc)
def i_create_all_mc_resources(step, data, max_categories=None, objective=None, test=None, output=None):
if max_categories is None or test is None or output is None or objective is None:
assert False
world.directory = os.path.dirname(output)
world.folders.append(world.directory)
test = res_filename(test)
try:
command = (
"bigmler --train "
+ res_filename(data)
+ " --max-categories "
+ max_categories
+ " --objective "
+ objective
+ " --test "
+ test
+ " --store --output "
+ output
)
command = check_debug(command)
retcode = check_call(command, shell=True)
if retcode < 0:
assert False
else:
world.test_lines = file_number_of_lines(test)
# test file has headers in it, so first line must be ignored
world.test_lines -= 1
world.output = output
assert True
except (OSError, CalledProcessError, IOError) as exc:
assert False, str(exc)
def i_create_ml_source(step,
label_separator=None,
number_of_labels=None,
data=None,
training_separator=None,
multi_label_fields=None,
objective=None,
output_dir=None):
if label_separator is None or training_separator is None or number_of_labels is None or data is None or multi_label_fields is None or output_dir is None or objective is None:
assert False
world.directory = output_dir
world.folders.append(world.directory)
try:
command = ("bigmler --multi-label --train " + res_filename(data) +
" --label-separator \"" + label_separator +
"\" --training-separator \"" + training_separator +
"\" --multi-label-fields " + multi_label_fields +
" --objective " + objective + " --store --output-dir " +
output_dir +
" --no-dataset --no-model --max-batch-models 1")
command = check_debug(command)
retcode = check_call(command, shell=True)
if retcode < 0:
assert False
else:
world.output = output_dir
assert True
except (OSError, CalledProcessError, IOError) as exc:
assert False, str(exc)
def shell_execute(command, output, test=None, options=None,
test_rows=None, project=True):
"""Excute bigmler command in shell
"""
command = check_debug(command, project=project)
world.directory = os.path.dirname(output)
world.folders.append(world.directory)
try:
retcode = check_call(command, shell=True)
if retcode < 0:
assert False
else:
if test is not None:
world.test_lines = file_number_of_lines(test)
if options is None or \
options.find('--projection-header') == -1:
# test file has headers in it, so first line must be ignored
world.test_lines -= 1
elif test_rows is not None:
world.test_lines = test_rows
if options is not None and \
options.find('--projection-header') > -1:
world.test_lines += 1
elif options is not None and \
options.find('--projection-header') > -1:
world.test_lines += 1
world.output = output
except (OSError, CalledProcessError, IOError) as exc:
assert False, str(exc)
def i_import_fields(step, summary=None):
ok_(summary is not None)
try:
command = ("bigmler --dataset " + world.dataset['resource'] +
" --import-fields " + res_filename(summary) +
" --output-dir " + world.directory + " --no-model")
command = check_debug(command)
retcode = check_call(command, shell=True)
ok_(retcode >= 0)
except (OSError, CalledProcessError, IOError) as exc:
assert False, str(exc)
def i_create_with_split_to_evaluate(step, data=None, split=None, output=None):
if data is None or split is None or output is None:
assert False
command = ("bigmler --evaluate --train " + res_filename(data) +
" --test-split " + split + " --output " + output)
command = check_debug(command)
try:
retcode = check_call(command, shell=True)
ok_(retcode >= 0)
world.directory = os.path.dirname(output)
world.folders.append(world.directory)
world.output = output
except OSError as e:
assert False
def given_i_create_bigml_resources_using_source_to_evaluate(step, output=None):
if output is None:
assert False
command = ("bigmler --evaluate --source " + world.source['resource'] +
" --output " + output)
command = check_debug(command)
try:
retcode = check_call(command, shell=True)
ok_(retcode >= 0)
world.directory = os.path.dirname(output)
world.folders.append(world.directory)
world.output = output
except OSError as e:
assert False
def i_export_the_dataset(step, filename):
if filename is None:
assert False
try:
command = ("bigmler --dataset " + world.dataset['resource'] +
" --to-csv " + filename +
" --output-dir " + world.directory + " --no-model")
command = check_debug(command)
retcode = check_call(command, shell=True)
if retcode < 0:
assert False
else:
assert True
except (OSError, CalledProcessError, IOError) as exc:
assert False, str(exc)
def i_export_the_dataset(step, filename):
if filename is None:
assert False
try:
command = ("bigmler --dataset " + world.dataset['resource'] +
" --to-csv " + filename +
" --output-dir " + world.directory + " --no-model")
command = check_debug(command)
retcode = check_call(command, shell=True)
if retcode < 0:
assert False
else:
assert True
except (OSError, CalledProcessError, IOError) as exc:
assert False, str(exc)
def i_create_ml_evaluations_from_source(step, output=None):
if output is None:
assert False
world.directory = os.path.dirname(output)
world.folders.append(world.directory)
try:
command = "bigmler --multi-label --source " + world.source['resource'] + " --evaluate --store --output " + output
retcode = check_call(check_debug(command), shell=True)
if retcode < 0:
assert False
else:
world.output = output
assert True
except (OSError, CalledProcessError, IOError) as exc:
assert False, str(exc)
def given_i_create_bigml_resources_using_dataset_to_evaluate(step,
output=None):
if output is None:
assert False
command = ("bigmler --evaluate --dataset " + world.dataset['resource'] +
" --output " + output)
command = check_debug(command)
try:
retcode = check_call(command, shell=True)
ok_(retcode >= 0)
world.directory = os.path.dirname(output)
world.folders.append(world.directory)
world.output = output
except OSError as e:
assert False
def i_create_all_resources_to_evaluate_with_model_and_map( \
step, data=None, fields_map=None, output=None):
if data is None or fields_map is None or output is None:
assert False
command = ("bigmler --evaluate --test " + res_filename(data) +
" --model " + world.model['resource'] + " --output " + output +
" --fields-map " + res_filename(fields_map))
command = check_debug(command)
try:
retcode = check_call(command, shell=True)
ok_(retcode >= 0)
world.directory = os.path.dirname(output)
world.folders.append(world.directory)
world.output = output
except OSError as e:
assert False
def given_i_create_bigml_resources_using_source_to_evaluate(step, output=None):
if output is None:
assert False
command = "bigmler --evaluate --source " + world.source["resource"] + " --output " + output
command = check_debug(command)
try:
retcode = check_call(command, shell=True)
if retcode < 0:
assert False
else:
world.directory = os.path.dirname(output)
world.folders.append(world.directory)
world.output = output
assert True
except OSError as e:
assert False
def i_create_all_ml_resources_for_evaluation(step, tag=None, label_separator=None, number_of_labels=None, data=None, training_separator=None, output=None):
if tag is None or label_separator is None or training_separator is None or number_of_labels is None or data is None or output is None:
assert False
world.directory = os.path.dirname(output)
world.folders.append(world.directory)
world.number_of_models = int(number_of_labels)
try:
command = "bigmler --multi-label --train " + res_filename(data) + " --label-separator \"" + label_separator + "\" --training-separator \"" + training_separator + "\" --store --output " + output + " --tag " + tag + " --max-batch-models 1"
retcode = check_call(check_debug(command), shell=True)
if retcode < 0:
assert False
else:
world.output = output
assert True
except (OSError, CalledProcessError, IOError) as exc:
assert False, str(exc)
def i_update_dataset_new_properties(step, json_file=None):
if json_file is None:
assert False
json_file = res_filename(json_file)
try:
command = ("bigmler --dataset " + world.dataset['resource'] +
" --no-model --store --output-dir " + world.output +
" --dataset-attributes " + json_file)
command = check_debug(command)
retcode = check_call(command, shell=True)
if retcode < 0:
assert False
else:
assert True
except (OSError, CalledProcessError, IOError) as exc:
assert False, str(exc)
def i_update_dataset_new_properties(step, json_file=None):
if json_file is None:
assert False
json_file = res_filename(json_file)
try:
command = ("bigmler --dataset " + world.dataset['resource'] +
" --no-model --store --output-dir " + world.output +
" --dataset-attributes " + json_file)
command = check_debug(command)
retcode = check_call(command, shell=True)
if retcode < 0:
assert False
else:
assert True
except (OSError, CalledProcessError, IOError) as exc:
assert False, str(exc)
def i_create_ml_source(
step,
label_separator=None,
number_of_labels=None,
data=None,
training_separator=None,
multi_label_fields=None,
objective=None,
output_dir=None,
):
if (
label_separator is None
or training_separator is None
or number_of_labels is None
or data is None
or multi_label_fields is None
or output_dir is None
or objective is None
):
assert False
world.directory = output_dir
world.folders.append(world.directory)
try:
command = (
"bigmler --multi-label --train "
+ res_filename(data)
+ ' --label-separator "'
+ label_separator
+ '" --training-separator "'
+ training_separator
+ '" --multi-label-fields '
+ multi_label_fields
+ " --objective "
+ objective
+ " --store --output-dir "
+ output_dir
+ " --no-dataset --no-model --max-batch-models 1"
)
command = check_debug(command)
retcode = check_call(command, shell=True)
if retcode < 0:
assert False
else:
world.output = output_dir
assert True
except (OSError, CalledProcessError, IOError) as exc:
assert False, str(exc)
def i_create_sample(step, options=None, output_dir=None):
if options is None or output_dir is None:
assert False
world.directory = output_dir
world.folders.append(world.directory)
try:
command = (u"bigmler sample --dataset " + world.dataset['resource'] +
u" --store --output-dir " + output_dir + u" " + options)
command = check_debug(command)
retcode = check_call(command.encode(SYSTEM_ENCODING), shell=True)
if retcode < 0:
assert False
else:
world.output = output_dir
assert True
except (OSError, CalledProcessError, IOError) as exc:
assert False, str(exc)
def i_update_project(step, params=None, values=None):
ok_(params is not None and values is not None)
try:
command = (u"bigmler project --project-id " +
world.project['resource'] + u" --store --output-dir " +
world.directory)
for index, param in enumerate(params):
value = values[index]
command += u" --%s %s" % (param, value)
if not PYTHON3:
command = command.encode(BIGML_SYS_ENCODING)
command = check_debug(command)
retcode = check_call(command, shell=True)
assert retcode >= 0
except (OSError, CalledProcessError, IOError) as exc:
assert False, str(exc)
def i_filter_field_from_dataset(step, field=None, output_dir=None):
if field is None or output_dir is None:
assert False
try:
empty_json = res_filename('data/empty.json')
command = ("bigmler --dataset " + world.dataset['resource'] +
" --no-model --store --output-dir " + output_dir +
" --dataset-fields=\"-" + field + "\""+
" --new-fields " + empty_json)
command = check_debug(command)
retcode = check_call(command, shell=True)
if retcode < 0:
assert False
else:
assert True
except (OSError, CalledProcessError, IOError) as exc:
assert False, str(exc)
def i_create_dataset_new_fields(step, json_file=None, model_fields=None):
if json_file is None or model_fields is None:
assert False
json_file = res_filename(json_file)
try:
command = ("bigmler --dataset " + world.dataset['resource'] +
" --model-fields \"" + model_fields + "\" --store" +
" --output-dir " + world.output +
" --new-fields " + json_file)
command = check_debug(command)
retcode = check_call(command, shell=True)
if retcode < 0:
assert False
else:
assert True
except (OSError, CalledProcessError, IOError) as exc:
assert False, str(exc)
def i_create_dataset(step, data=None, output_dir=None):
if data is None or output_dir is None:
assert False
world.directory = output_dir
world.folders.append(world.directory)
try:
command = (u"bigmler --train " + res_filename(data) +
u" --no-model --store --output-dir " + output_dir)
command = check_debug(command)
retcode = check_call(command.encode(SYSTEM_ENCODING), shell=True)
if retcode < 0:
assert False
else:
world.output = output_dir
assert True
except (OSError, CalledProcessError, IOError) as exc:
assert False, str(exc)
def i_filter_field_from_dataset(step, field=None, output_dir=None):
if field is None or output_dir is None:
assert False
try:
empty_json = res_filename('data/empty.json')
command = ("bigmler --dataset " + world.dataset['resource'] +
" --no-model --store --output-dir " + output_dir +
" --dataset-fields=\"-" + field + "\""+
" --new-fields " + empty_json)
command = check_debug(command)
retcode = check_call(command, shell=True)
if retcode < 0:
assert False
else:
assert True
except (OSError, CalledProcessError, IOError) as exc:
assert False, str(exc)
def i_create_dataset_new_fields(step, json_file=None, model_fields=None):
if json_file is None or model_fields is None:
assert False
json_file = res_filename(json_file)
try:
command = ("bigmler --dataset " + world.dataset['resource'] +
" --model-fields \"" + model_fields + "\" --store" +
" --output-dir " + world.output +
" --new-fields " + json_file)
command = check_debug(command)
retcode = check_call(command, shell=True)
if retcode < 0:
assert False
else:
assert True
except (OSError, CalledProcessError, IOError) as exc:
assert False, str(exc)
def i_create_project(step, project=None, output_dir=None):
ok_(project is not None)
world.directory = output_dir
world.folders.append(world.directory)
try:
command = (u"bigmler project --name \"" + project +
u"\" --store --output-dir " + output_dir)
if not PYTHON3:
command = command.encode(BIGML_SYS_ENCODING)
command = check_debug(command)
retcode = check_call(command, shell=True)
if retcode < 0:
assert False
else:
world.output = output_dir
except (OSError, CalledProcessError, IOError) as exc:
assert False, str(exc)
def i_create_dataset(step, data=None, output_dir=None):
if data is None or output_dir is None:
assert False
world.directory = output_dir
world.folders.append(world.directory)
try:
command = (u"bigmler --train " + res_filename(data) +
u" --no-model --store --output-dir " + output_dir)
command = check_debug(command)
retcode = check_call(command.encode(SYSTEM_ENCODING), shell=True)
if retcode < 0:
assert False
else:
world.output = output_dir
assert True
except (OSError, CalledProcessError, IOError) as exc:
assert False, str(exc)
def i_create_anomaly_with_params_from_dataset( \
step, params=None, output_dir=None):
ok_(output_dir is not None and params is not None)
world.directory = output_dir
world.folders.append(world.directory)
try:
command = (u"bigmler anomaly --dataset " + world.dataset['resource'] +
u" --store --output-dir " + output_dir + u" " + params)
command = check_debug(command)
retcode = check_call(command, shell=True)
if retcode < 0:
assert False
else:
world.output = output_dir
assert True
except (OSError, CalledProcessError, IOError) as exc:
assert False, str(exc)
def given_i_create_bigml_resources_using_dataset_to_evaluate_with_model(
step, output=None):
if output is None:
assert False
command = ("bigmler --evaluate --dataset " + world.dataset['resource'] +
" --model " + world.model['resource'] + " --output " + output)
command = check_debug(command)
try:
retcode = check_call(command, shell=True)
if retcode < 0:
assert False
else:
world.directory = os.path.dirname(output)
world.folders.append(world.directory)
world.output = output
assert True
except OSError as e:
assert False
def i_create_project_in_org(step, name=None, output_dir=None, organization=None):
ok_(name is not None and organization is not None)
world.directory = output_dir
world.folders.append(world.directory)
try:
command = (u"bigmler project --name \"" + name +
"\" --organization " + organization +
u" --output-dir " + output_dir)
if not PYTHON3:
command = command.encode(SYSTEM_ENCODING)
command = check_debug(command)
retcode = check_call(command, shell=True)
if retcode < 0:
assert False
else:
world.output = output_dir
except (OSError, CalledProcessError, IOError) as exc:
assert False, str(exc)
def i_create_source_with_org_project(step, data=None, output_dir=None):
ok_(data is not None)
world.directory = output_dir
world.folders.append(world.directory)
try:
command = (u"bigmler --train " + res_filename(data) +
u" --no-model --no-dataset --store --output-dir " +
output_dir + u" --org-project " + world.project["resource"])
if not PYTHON3:
command = command.encode(BIGML_SYS_ENCODING)
command = check_debug(command)
retcode = check_call(command, shell=True)
if retcode < 0:
assert False
else:
world.output = output_dir
except (OSError, CalledProcessError, IOError) as exc:
assert False, str(exc)
def i_create_dataset_from_source(step, output_dir=None):
if output_dir is None:
assert False
world.directory = output_dir
world.folders.append(world.directory)
try:
command = ((u"bigmler --source %s" % world.source['resource']) +
u" --no-model --store --output-dir " + output_dir)
command = check_debug(command)
retcode = check_call(command, shell=True)
if retcode < 0:
assert False
else:
world.output = output_dir
assert True
except (OSError, CalledProcessError, IOError) as exc:
assert False, str(exc)
def i_create_project_in_org(step, name=None, output_dir=None, organization=None):
ok_(name is not None and organization is not None)
world.directory = output_dir
world.folders.append(world.directory)
try:
command = (u"bigmler project --name \"" + name +
"\" --organization " + organization +
u" --output-dir " + output_dir)
if not PYTHON3:
command = command.encode(SYSTEM_ENCODING)
command = check_debug(command)
retcode = check_call(command, shell=True)
if retcode < 0:
assert False
else:
world.output = output_dir
except (OSError, CalledProcessError, IOError) as exc:
assert False, str(exc)
def i_evaluate_ensemble_with_dataset( \
step, ensemble_dir=None, dataset_dir=None, output=None):
if ensemble_dir is None or dataset_dir is None or output is None:
assert False
world.directory = os.path.dirname(output)
world.folders.append(world.directory)
ensemble_id = read_id_from_file(os.path.join(ensemble_dir, "ensembles"))
dataset_id = read_id_from_file(os.path.join(dataset_dir, "dataset_test"))
command = ("bigmler --dataset " + dataset_id +
" --ensemble " + ensemble_id + " --store" +
" --output " + output + " --evaluate")
command = check_debug(command)
try:
retcode = check_call(command, shell=True)
ok_(retcode >= 0)
world.output = output
except OSError as exc:
assert False, str(exc)
def i_update_project(step, params=None, values=None):
ok_(params is not None and values is not None)
try:
command = (u"bigmler project --project-id " +
world.project['resource'] +
u" --store --output-dir " +
world.directory)
for index, param in enumerate(params):
value = values[index]
command += u" --%s %s" % (param, value)
if not PYTHON3:
command = command.encode(SYSTEM_ENCODING)
command = check_debug(command)
retcode = check_call(command, shell=True)
assert retcode >= 0
except (OSError, CalledProcessError, IOError) as exc:
assert False, str(exc)
def i_create_dataset_from_source(step, output_dir=None):
if output_dir is None:
assert False
world.directory = output_dir
world.folders.append(world.directory)
try:
command = ((u"bigmler --source %s" % world.source['resource']) +
u" --no-model --store --output-dir " + output_dir)
command = check_debug(command)
retcode = check_call(command.encode(SYSTEM_ENCODING), shell=True)
if retcode < 0:
assert False
else:
world.output = output_dir
assert True
except (OSError, CalledProcessError, IOError) as exc:
assert False, str(exc)
def i_create_source_with_org_project(step, data=None, output_dir=None):
ok_(data is not None)
world.directory = output_dir
world.folders.append(world.directory)
try:
command = (u"bigmler --train " + res_filename(data) +
u" --no-model --no-dataset --store --output-dir " +
output_dir +
u" --org-project " + world.project["resource"])
if not PYTHON3:
command = command.encode(SYSTEM_ENCODING)
command = check_debug(command)
retcode = check_call(command, shell=True)
if retcode < 0:
assert False
else:
world.output = output_dir
except (OSError, CalledProcessError, IOError) as exc:
assert False, str(exc)
def i_create_project(step, project=None, output_dir=None):
ok_(project is not None)
world.directory = output_dir
world.folders.append(world.directory)
try:
command = (u"bigmler project --name \"" + project +
u"\" --store --output-dir " +
output_dir)
if not PYTHON3:
command = command.encode(SYSTEM_ENCODING)
command = check_debug(command)
retcode = check_call(command, shell=True)
if retcode < 0:
assert False
else:
world.output = output_dir
assert True
except (OSError, CalledProcessError, IOError) as exc:
assert False, str(exc)
def i_create_multi_dataset(step, output_dir):
if output_dir is None:
assert False
world.folders.append(output_dir)
datasets_file = "%s%sdataset" % (world.directory, os.sep)
try:
command = ("bigmler --datasets " + datasets_file +
" --multi-dataset --no-model --store --output-dir " +
output_dir)
command = check_debug(command)
retcode = check_call(command, shell=True)
if retcode < 0:
assert False
else:
world.directory = output_dir
world.output = output_dir
assert True
except (OSError, CalledProcessError, IOError) as exc:
assert False, str(exc)
