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 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_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_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_all_resources_with_options(step, data=None, test=None, output=None, options=""):
if data is None or test is None or output is None:
assert False
world.directory = os.path.dirname(output)
world.folders.append(world.directory)
try:
command = (
"bigmler --train "
+ data
+ " --test "
+ test
+ " --store --output "
+ output
+ " --max-batch-models 1 "
+ options
)
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
if 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_find_predictions_files(step, directory1=None, directory2=None, output=None, method=None):
if directory1 is None or directory2 is None or output is None or method is None:
assert False
world.directory = os.path.dirname(output)
world.folders.append(world.directory)
try:
retcode = check_call(
"bigmler --combine-votes "
+ directory1
+ ","
+ directory2
+ " --store --output "
+ output
+ " --method "
+ method,
shell=True,
)
if retcode < 0:
assert False
else:
world.test_lines = file_number_of_lines("%s%spredictions.csv" % (directory1, os.sep))
world.output = output
assert True
except (OSError, CalledProcessError, IOError) as exc:
assert False, str(exc)
def i_create_resources_from_ensemble_generic(step, number_of_models=None, no_replacement="", test=None, output=None):
if number_of_models is None or test is None or output is None:
assert False
world.directory = os.path.dirname(output)
world.folders.append(world.directory)
try:
retcode = check_call(
"bigmler --dataset "
+ world.dataset["resource"]
+ " --test "
+ test
+ " --number-of-models "
+ str(number_of_models)
+ " --tag my_ensemble --store --output "
+ output
+ no_replacement,
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
world.number_of_models = int(number_of_models)
assert True
except (OSError, CalledProcessError, IOError) as exc:
assert False, str(exc)
def i_create_resources_from_ensemble_generic(step,
number_of_models=None,
no_replacement="",
test=None,
output=None):
if number_of_models is None or test is None or output is None:
assert False
world.directory = os.path.dirname(output)
world.folders.append(world.directory)
try:
command = ("bigmler --dataset " + world.dataset['resource'] +
" --test " + test + " --number-of-models " +
str(number_of_models) + " --tag my_ensemble --store" +
" --output " + output + no_replacement)
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
world.number_of_models = int(number_of_models)
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_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 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_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 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_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_resources_from_model(step, 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)
try:
retcode = check_call(
"bigmler --model "
+ world.model["resource"]
+ " --test "
+ test
+ " --store --output "
+ output
+ " --max-batch-models 1",
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_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 number_of_rows(self):
"""Returns the number of rows in the test file
"""
rows = file_number_of_lines(self.training_set)
if self.training_set_header:
rows -= 1
return rows
def number_of_tests(self):
"""Returns the number of tests in the test file
"""
tests = file_number_of_lines(self.test_set)
if self.test_set_header:
tests -= 1
return tests
def number_of_rows(self):
"""Returns the number of rows in the test file
"""
rows = file_number_of_lines(self.training_set)
if self.training_set_header:
rows -= 1
return rows
def number_of_tests(self):
"""Returns the number of tests in the test file
"""
tests = file_number_of_lines(self.test_set)
if self.test_set_header:
tests -= 1
return tests
def i_create_resources_from_models_file(step, multi_label=None, models_file=None, test=None, output=None):
if models_file is None or 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 "
try:
retcode = check_call(
"bigmler " + multi_label + "--models " + models_file + " --test " + test + " --store --output " + output,
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_from_models(step, models_file=None, test=None, output=None):
if models_file is None or test is None or output is None:
assert False
world.directory = os.path.dirname(output)
world.folders.append(world.directory)
try:
command = ("bigmler --models " + models_file +
" --method combined --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_find_predictions_files(step,
directory1=None,
directory2=None,
output=None):
if directory1 is None or directory2 is None or output is None:
assert False
world.directory = os.path.dirname(output)
world.folders.append(world.directory)
try:
command = ("bigmler --combine-votes " + directory1 + "," + directory2 +
" --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("%s%spredictions.csv" %
(directory1, os.sep))
world.output = output
assert True
except (OSError, CalledProcessError, IOError) as exc:
assert False, str(exc)
