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_all_anomaly_resources(step, data=None, test=None, output=None):
if data is None or test is None or output is None:
assert False
test = res_filename(test)
command = ("bigmler anomaly --train " + res_filename(data) + " --test " + test +
" --store --output " + output)
shell_execute(command, output, test=test)
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_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_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_anomaly_resources(step, data=None, test=None, output=None):
if data is None or test is None or output is None:
assert False
test = res_filename(test)
command = ("bigmler anomaly --train " + res_filename(data) + " --test " + test +
" --store --output " + output)
shell_execute(command, output, test=test)
def i_create_all_lr_resources(step, data=None, test=None, output=None):
ok_(data is not None and test is not None and output is not None)
test = res_filename(test)
command = ("bigmler linear-regression --train " + res_filename(data) +
" --test " + test +
" --store --no-bias --default-numeric-value mean --output " + output)
shell_execute(command, output, test=test)
def i_create_all_lr_resources(step, data=None, test=None, output=None):
ok_(data is not None and test is not None and output is not None)
test = res_filename(test)
command = ("bigmler logistic-regression --train " + res_filename(data) +
" --test " + test +
" --store --no-balance-fields --no-bias --output " + output)
shell_execute(command, output, test=test)
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_all_cluster_resources(step, data=None, test=None, output=None):
ok_(data is not None and test is not None and output is not None)
test = res_filename(test)
command = ("bigmler cluster --train " + res_filename(data) + " --test " + test +
" --k 8" +
" --store --output " + output)
shell_execute(command, output, test=test)
def i_create_all_lr_resources(step, data=None, test=None, output=None):
ok_(data is not None and test is not None and output is not None)
test = res_filename(test)
command = ("bigmler linear-regression --train " + res_filename(data) +
" --test " + test +
" --store --no-bias --default-numeric-value mean --output " + output)
shell_execute(command, output, test=test)
def i_create_all_dn_resources(step, data=None, test=None, output=None):
ok_(data is not None and test is not None and output is not None)
test = res_filename(test)
command = ("bigmler deepnet --train " + res_filename(data) +
" --test " + test +
" --store --output " + output)
shell_execute(command, output, test=test)
def i_create_all_resources_to_test_from_stdin(step, data=None, test=None, name=None, output=None):
if data is None or test is None or output is None or name is None:
assert False
test = res_filename(test)
command = ("cat " + test + "|bigmler --train " + res_filename(data) +
" --test --store --output " + output + " --name \"" +
name + "\" --max-batch-models 1")
shell_execute(command, output, test=test)
def i_create_all_pca_resources_with_no_headers(step, data=None, test=None, output=None):
ok_(data is not None and test is not None and output is not None)
test = res_filename(test)
command = ("bigmler pca --train " + res_filename(data) +
" --test " + test +
" --store --output " + output +
" --no-train-header --no-test-header")
shell_execute(command, output, test=test, options="--projection-header")
def i_create_all_cluster_resources_with_mapping(step, data=None, test=None, fields_map=None, output=None):
ok_(data is not None and test is not None and output is not None and fields_map is not None)
test = res_filename(test)
command = ("bigmler cluster --remote --train " + res_filename(data) +
" --test " + test + " --k 8" +
" --fields-map " + res_filename(fields_map) +
" --store --output " + output)
shell_execute(command, output, test=test)
def i_create_all_cluster_resources_to_dataset(step, data=None, test=None, output_dir=None):
ok_(data is not None and test is not None and output_dir is not None)
test = res_filename(test)
command = ("bigmler cluster --remote --train " + res_filename(data) +
" --test " + test + " --k 8" +
" --to-dataset --no-csv " +
" --store --output-dir " + output_dir)
shell_execute(command, "%s/x.csv" % output_dir, test=test)
def i_create_all_dn_resources_headers(step, data=None, test=None, output=None):
ok_(data is not None and test is not None and output is not None)
test = res_filename(test)
command = ("bigmler deepnet --train " + res_filename(data) +
" --test " + test +
" --store --prediction-header --prediction-info full" +
" --output " + output)
shell_execute(command, output, test=test, options='--prediction-header')
def i_create_all_anomaly_resources_with_mapping(step, data=None, test=None, fields_map=None, output=None):
if data is None or test is None or output is None or fields_map is None:
assert False
test = res_filename(test)
command = ("bigmler anomaly --remote --train " + res_filename(data) + " --test " + test +
" --fields-map " + res_filename(fields_map) +
" --store --output " + output)
shell_execute(command, output, test=test)
def i_create_all_anomaly_resources_with_mapping(step, data=None, test=None, fields_map=None, output=None):
if data is None or test is None or output is None or fields_map is None:
assert False
test = res_filename(test)
command = ("bigmler anomaly --remote --train " + res_filename(data) + " --test " + test +
" --fields-map " + res_filename(fields_map) +
" --store --output " + output)
shell_execute(command, output, test=test)
def i_create_all_cluster_resources_with_prediction_fields(step, data=None, test=None, prediction_fields=None, output=None):
ok_(data is not None and test is not None and output is not None and prediction_fields is not None)
test = res_filename(test)
command = ("bigmler cluster --remote --train " + res_filename(data) +
" --test " + test + " --k 8" +
" --prediction-fields \"" + prediction_fields +
"\" --prediction-info full --prediction-header --store " +
"--output " + output)
shell_execute(command, output, test=test, options='--prediction-header')
def i_create_dn_resources_from_model_remote_with_options(
step, test=None, options_file=None, output=None):
ok_(test is not None and output is not None and options_file is not None)
test = res_filename(test)
options_file = res_filename(options_file)
command = ("bigmler deepnet --deepnet " + world.deepnet['resource'] +
" --test " + test + " --batch-prediction-attributes " +
options_file + " --store --remote --output " + output)
shell_execute(command, output, test=test)
def i_create_all_execution_with_io_resources(step, code_file=None, output_dir=None, inputs_dec=None, outputs_dec=None, inputs=None):
ok_(code_file is not None and output_dir is not None and
inputs_dec is not None and outputs_dec is not None and
inputs is not None)
command = ("bigmler execute --code-file " + res_filename(code_file) +
" --store --declare-inputs " + res_filename(inputs_dec) +
" --declare-outputs "+ res_filename(outputs_dec) +
" --inputs " + res_filename(inputs) + " --output-dir " + output_dir)
shell_execute(command, "%s/xx.txt" % output_dir)
def i_create_all_cluster_resources_to_dataset(step,
data=None,
test=None,
output_dir=None):
ok_(data is not None and test is not None and output_dir is not None)
test = res_filename(test)
command = ("bigmler cluster --remote --train " + res_filename(data) +
" --test " + test + " --k 8" + " --to-dataset --no-csv " +
" --store --output-dir " + output_dir)
shell_execute(command, "%s/x.csv" % output_dir, test=test)
def i_create_dn_resources_from_model_remote_with_options(step, test=None, options_file=None, output=None):
ok_(test is not None and output is not None and options_file is not None)
test = res_filename(test)
options_file = res_filename(options_file)
command = ("bigmler deepnet --deepnet " +
world.deepnet['resource'] + " --test " + test +
" --batch-prediction-attributes " + options_file +
" --store --remote --output " +
output)
shell_execute(command, output, test=test)
def i_create_resources_from_model_with_op_remote(step, operating_point=None,
test=None, output=None):
ok_(operating_point is not None and
test is not None and output is not None)
test = res_filename(test)
operating_point = res_filename(operating_point)
command = ("bigmler --model " + world.model['resource'] + " --test " +
test + " --operating-point " + operating_point +
" --store --remote --output " + output +
" --max-batch-models 1")
shell_execute(command, output, test=test)
def i_create_fs_resources_from_model_remote_with_options(
step, test=None, output=None, options_file=None):
ok_(test is not None and output is not None and options_file is not None)
test = res_filename(test)
options_file = res_filename(options_file)
models = [world.model["resource"], world.deepnet["resource"]]
command = ("bigmler fusion --fusion-models " + ",".join(models) +
" --test \"" + test + "\" --batch-prediction-attributes " +
options_file + " --store --remote --output " + output)
shell_execute(command, output, test=test)
def i_create_all_resources_to_model_with_source_attrs( \
self, data=None, source_attributes=None, output=None):
ok_(data is not None and source_attributes is not None
and output is not None)
if source_attributes != "":
source_attributes = " --source-attributes " + \
res_filename(source_attributes)
command = ("bigmler --train " + res_filename(data) +
" --output " + output + source_attributes +
" --store --max-batch-models 1 --no-fast")
shell_execute(command, output)
def i_create_all_cluster_resources_with_prediction_fields(
step, data=None, test=None, prediction_fields=None, output=None):
ok_(data is not None and test is not None and output is not None
and prediction_fields is not None)
test = res_filename(test)
command = ("bigmler cluster --remote --train " + res_filename(data) +
" --test " + test + " --k 8" + " --prediction-fields \"" +
prediction_fields +
"\" --prediction-info full --prediction-header --store " +
"--output " + output)
shell_execute(command, output, test=test, options='--prediction-header')
def i_create_resources_from_model_with_op_remote(step, operating_point=None,
test=None, output=None):
ok_(operating_point is not None and
test is not None and output is not None)
test = res_filename(test)
operating_point = res_filename(operating_point)
command = ("bigmler --model " + world.model['resource'] + " --test " +
test + " --operating-point " + operating_point +
" --store --remote --output " + output +
" --max-batch-models 1")
shell_execute(command, output, test=test)
def i_create_all_resources_to_model_with_source_attrs( \
self, data=None, source_attributes=None, output=None):
ok_(data is not None and source_attributes is not None
and output is not None)
if source_attributes != "":
source_attributes = " --source-attributes " + \
res_filename(source_attributes)
command = ("bigmler --train " + res_filename(data) + " --output " +
output + source_attributes +
" --store --max-batch-models 1 --no-fast")
shell_execute(command, output)
def i_create_fs_resources_from_model_remote_with_options(step, test=None, output=None, options_file=None):
ok_(test is not None and output is not None and options_file is not None)
test = res_filename(test)
options_file = res_filename(options_file)
models = [world.model["resource"], world.deepnet["resource"]]
command = ("bigmler fusion --fusion-models " +
",".join(models) + " --test \"" + test +
"\" --batch-prediction-attributes " + options_file +
" --store --remote --output " +
output)
shell_execute(command, output, test=test)
def i_create_all_resources_to_test_from_stdin(step, data=None, test=None, name=None, output=None):
if data is None or test is None or output is None or name is None:
assert False
test = res_filename(test)
if not PYTHON3:
name = name.decode("utf-8")
command = (CAT + test + u"|bigmler --train " + res_filename(data) +
u" --test --store --output " + output + u" --name \"" +
name + u"\" --max-batch-models 1")
shell_execute(command, output, test=test)
def i_create_lr_resources_from_model_with_op(step, test=None, output=None,
operating_point=None):
ok_(test is not None and output is not None and \
operating_point is not None)
test = res_filename(test)
operating_point = res_filename(operating_point)
command = ("bigmler logistic-regression --logistic-regression " +
world.logistic_regression['resource'] + " --test " + test +
" --operating-point " + operating_point +
" --store --no-balance-fields --no-bias --output " +
output)
shell_execute(command, output, test=test)
def i_create_all_cluster_resources_with_mapping(step,
data=None,
test=None,
fields_map=None,
output=None):
ok_(data is not None and test is not None and output is not None
and fields_map is not None)
test = res_filename(test)
command = ("bigmler cluster --remote --train " + res_filename(data) +
" --test " + test + " --k 8" + " --fields-map " +
res_filename(fields_map) + " --store --output " + output)
shell_execute(command, output, test=test)
def i_create_all_execution_with_io_resources(step,
code_file=None,
output_dir=None,
inputs_dec=None,
outputs_dec=None,
inputs=None):
ok_(code_file is not None and output_dir is not None
and inputs_dec is not None and outputs_dec is not None
and inputs is not None)
command = ("bigmler execute --code-file " + res_filename(code_file) +
" --store --declare-inputs " + res_filename(inputs_dec) +
" --declare-outputs " + res_filename(outputs_dec) +
" --inputs " + res_filename(inputs) + " --output-dir " +
output_dir)
shell_execute(command, "%s/xx.txt" % output_dir)
def create_dataset_from_batch_anomaly(filename, output=None, args=None):
source = world.api.create_source(res_filename(filename))
world.source = source
world.directory = os.path.dirname(output)
world.output = output
world.api.ok(world.source)
world.sources.append(source['resource'])
world.dataset = world.api.create_dataset(source)
world.api.ok(world.dataset)
world.datasets.append(world.dataset['resource'])
world.anomaly = world.api.create_anomaly(world.dataset, {
"seed": "bigml",
"anomaly_seed": "bigml"
})
world.api.ok(world.anomaly)
world.anomalies.append(world.anomaly['resource'])
world.batch_anomaly_score = world.api.create_batch_anomaly_score( \
world.anomaly, world.dataset, {"output_dataset": True})
world.api.ok(world.batch_anomaly_score)
world.batch_anomaly_scores.append(world.batch_anomaly_score['resource'])
world.batch_anomaly_score_dataset = world.api.get_dataset(
world.batch_anomaly_score['object']['output_dataset_resource'])
world.api.ok(world.batch_anomaly_score_dataset)
world.batch_anomaly_score_dataset = world.api.update_dataset( \
world.batch_anomaly_score_dataset, args)
world.api.ok(world.batch_anomaly_score_dataset)
world.datasets.append(world.batch_anomaly_score_dataset['resource'])
def create_evaluation_split(filename, output=None, args=None):
source = world.api.create_source( \
res_filename(filename), {"project": world.project_id})
world.source = source
world.directory = os.path.dirname(output)
world.output = output
world.api.ok(world.source)
world.sources.append(source['resource'])
world.dataset = world.api.create_dataset(source)
world.api.ok(world.dataset)
world.datasets.append(world.dataset['resource'])
world.dataset_train = world.api.create_dataset(world.dataset, { \
'sample_rate': 0.7, 'seed': 'BigML'})
world.api.ok(world.dataset_train)
world.datasets.append(world.dataset_train['resource'])
world.dataset_test = world.api.create_dataset(world.dataset, { \
'sample_rate': 0.7, 'seed': 'BigML', 'out_of_bag': True})
world.api.ok(world.dataset_test)
world.datasets.append(world.dataset_test['resource'])
world.model = world.api.create_model(world.dataset_train)
world.api.ok(world.model)
world.models.append(world.model['resource'])
world.evaluation = world.api.create_evaluation( \
world.model, world.dataset_test, args)
world.api.ok(world.evaluation)
world.evaluations.append(world.evaluation['resource'])
def i_create_pca_resources_from_source( \
step, test=None, output=None):
ok_(test is not None and output is not None)
test = res_filename(test)
command = ("bigmler pca --source " + world.source['resource']
+ " --test " + test + " --store --output " + output)
shell_execute(command, output, test=test)
def i_create_source_from_stdin(step, data=None, output_dir=None):
if data is None or output_dir is None:
assert False
command = (CAT + res_filename(data) + u"|bigmler --train " +
u"--store --no-dataset --no-model --output-dir " +
output_dir + u" --max-batch-models 1")
shell_execute(command, output_dir + "/test", test=None)
def i_check_anomaly_scores(step, check_file):
check_file = res_filename(check_file)
predictions_file = world.output
try:
predictions_file = csv.reader(open(predictions_file, "U"), lineterminator="\n")
check_file = csv.reader(open(check_file, "U"), lineterminator="\n")
for row in predictions_file:
check_row = check_file.next()
if len(check_row) != len(row):
assert False
for index in range(len(row)):
dot = row[index].find(".")
if dot > 0 or (check_row[index].find(".") > 0
and check_row[index].endswith(".0")):
try:
decimal_places = min(len(row[index]), len(check_row[index])) - dot - 1
row[index] = round(float(row[index]), decimal_places)
check_row[index] = round(float(check_row[index]), decimal_places)
except ValueError:
pass
if check_row[index] != row[index]:
print row, check_row
assert False
assert True
except Exception, exc:
assert False, str(exc)
def i_create_all_anomaly_resources_with_test_split(step, data=None, test_split=None, output=None):
if data is None or output is None or test_split is None:
assert False
data = res_filename(data)
command = ("bigmler anomaly --remote --train " + data + " --test-split " + test_split +
" --store --output " + output)
shell_execute(command, output, data=data, test_split=test_split)
def i_create_cluster_resources_from_clusters_file(step, clusters_file=None, test=None, output=None):
ok_(test is not None and output is not None and clusters_file is not None)
test = res_filename(test)
command = ("bigmler cluster --clusters " +
clusters_file + " --test " + test +
" --store --output " + output)
shell_execute(command, output, test=test)
def i_create_cluster_resources_from_cluster(step, test=None, output=None):
ok_(test is not None and output is not None)
test = res_filename(test)
command = ("bigmler cluster --cluster " +
world.cluster['resource'] + " --test " + test + " --k 8" +
" --store --output " + output)
shell_execute(command, output, test=test)
def i_create_anomaly_resources_with_options(step, data=None, options=None, output_dir=None):
if data is None or output_dir is None or options is None:
assert False
command = ("bigmler anomaly --train " + res_filename(data) + " " +
options +
" --anomalies-dataset in --store --output-dir " + output_dir)
shell_execute(command, "%s/x.csv" % output_dir, data=data)
def create_dataset_from_batch_anomaly(filename, output=None, args=None):
source = world.api.create_source(res_filename(filename))
world.source = source
world.directory = os.path.dirname(output)
world.output = output
world.api.ok(world.source)
world.sources.append(source['resource'])
world.dataset = world.api.create_dataset(source)
world.api.ok(world.dataset)
world.datasets.append(world.dataset['resource'])
world.anomaly = world.api.create_anomaly(world.dataset,
{"seed": "bigml",
"anomaly_seed": "bigml"})
world.api.ok(world.anomaly)
world.anomalies.append(world.anomaly['resource'])
world.batch_anomaly_score = world.api.create_batch_anomaly_score( \
world.anomaly, world.dataset, {"output_dataset": True})
world.api.ok(world.batch_anomaly_score)
world.batch_anomaly_scores.append(world.batch_anomaly_score['resource'])
world.batch_anomaly_score_dataset = world.api.get_dataset(
world.batch_anomaly_score['object']['output_dataset_resource'])
world.api.ok(world.batch_anomaly_score_dataset)
world.batch_anomaly_score_dataset = world.api.update_dataset( \
world.batch_anomaly_score_dataset, args)
world.api.ok(world.batch_anomaly_score_dataset)
world.datasets.append(world.batch_anomaly_score_dataset['resource'])
def create_dataset_from_dataset_from_batch_centroid(filename,
output=None,
args=None):
source = world.api.create_source(res_filename(filename))
world.source = source
world.directory = os.path.dirname(output)
world.output = output
world.api.ok(world.source)
world.sources.append(source['resource'])
world.dataset = world.api.create_dataset(source)
world.api.ok(world.dataset)
world.datasets.append(world.dataset['resource'])
world.cluster = world.api.create_cluster( \
world.dataset, {"cluster_seed": "bigml"})
world.api.ok(world.cluster)
world.clusters.append(world.cluster['resource'])
world.batch_centroid = world.api.create_batch_centroid( \
world.cluster, world.dataset, {"output_dataset": True})
world.api.ok(world.batch_centroid)
world.batch_centroids.append(world.batch_centroid['resource'])
world.batch_centroid_dataset = world.api.get_dataset(
world.batch_centroid['object']['output_dataset_resource'])
world.api.ok(world.batch_centroid_dataset)
world.datasets.append(world.batch_centroid_dataset['resource'])
world.dataset = world.api.create_dataset( \
world.batch_centroid_dataset['resource'], args)
world.api.ok(world.dataset)
world.datasets.append(world.dataset['resource'])
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_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 i_create_anomaly_resources_with_options(step, data=None, options=None, output_dir=None):
if data is None or output_dir is None or options is None:
assert False
command = ("bigmler anomaly --train " + res_filename(data) + " " +
options +
" --anomalies-dataset in --store --output-dir " + output_dir)
shell_execute(command, "%s/x.csv" % output_dir, data=data)
def i_check_anomaly_scores(step, check_file):
check_file = res_filename(check_file)
predictions_file = world.output
try:
predictions_file = csv.reader(open(predictions_file, "U"), lineterminator="\n")
check_file = csv.reader(open(check_file, "U"), lineterminator="\n")
for row in predictions_file:
check_row = check_file.next()
if len(check_row) != len(row):
assert False
for index in range(len(row)):
dot = row[index].find(".")
if dot > 0 or (check_row[index].find(".") > 0
and check_row[index].endswith(".0")):
try:
decimal_places = min(len(row[index]), len(check_row[index])) - dot - 1
row[index] = round(float(row[index]), decimal_places)
check_row[index] = round(float(check_row[index]), decimal_places)
except ValueError:
pass
if check_row[index] != row[index]:
print row, check_row
assert False
assert True
except Exception, exc:
assert False, str(exc)
def i_create_source_from_file(step, data=None, output_dir=None):
ok_(data is not None and output_dir is not None)
command = ("bigmler --train " + res_filename(data) + " --store --output-dir " +
output_dir +
" --no-dataset --no-model --store")
shell_execute(command, os.path.join(output_dir, "p.csv"), test=None,
project=False)
def i_create_all_anomaly_resources_with_test_split(step, data=None, test_split=None, output=None):
if data is None or output is None or test_split is None:
assert False
data = res_filename(data)
command = ("bigmler anomaly --remote --train " + data + " --test-split " + test_split +
" --store --output " + output)
shell_execute(command, output, data=data, test_split=test_split)
def i_check_topic_distributions(step, check_file):
check_file = res_filename(check_file)
predictions_file = world.output
import traceback
try:
with UnicodeReader(predictions_file) as predictions_file:
with UnicodeReader(check_file) as check_file:
for row in predictions_file:
check_row = check_file.next()
assert len(check_row) == len(row)
for index in range(len(row)):
dot = row[index].find(".")
decimal_places = 1
if dot > 0 or (check_row[index].find(".") > 0
and check_row[index].endswith(".0")):
try:
decimal_places = min( \
len(row[index]),
len(check_row[index])) - dot - 1
row[index] = round(float(row[index]),
decimal_places)
check_row[index] = round(
float(check_row[index]), decimal_places)
except ValueError:
decimal_places = 1
assert_almost_equal(check_row[index],
row[index],
places=(decimal_places - 1))
else:
assert_equal(check_row[index], row[index])
except Exception, exc:
assert False, traceback.format_exc()
def create_dataset_from_dataset_from_batch_centroid(filename, output=None, args=None):
source = world.api.create_source(res_filename(filename))
world.source = source
world.directory = os.path.dirname(output)
world.output = output
world.api.ok(world.source)
world.sources.append(source['resource'])
world.dataset = world.api.create_dataset(source)
world.api.ok(world.dataset)
world.datasets.append(world.dataset['resource'])
world.cluster = world.api.create_cluster( \
world.dataset, {"cluster_seed": "bigml"})
world.api.ok(world.cluster)
world.clusters.append(world.cluster['resource'])
world.batch_centroid = world.api.create_batch_centroid( \
world.cluster, world.dataset, {"output_dataset": True})
world.api.ok(world.batch_centroid)
world.batch_centroids.append(world.batch_centroid['resource'])
world.batch_centroid_dataset = world.api.get_dataset(
world.batch_centroid['object']['output_dataset_resource'])
world.api.ok(world.batch_centroid_dataset)
world.datasets.append(world.batch_centroid_dataset['resource'])
world.dataset = world.api.create_dataset( \
world.batch_centroid_dataset['resource'], args)
world.api.ok(world.dataset)
world.datasets.append(world.dataset['resource'])
def i_check_topic_distributions(step, check_file):
check_file = res_filename(check_file)
predictions_file = world.output
import traceback
try:
with UnicodeReader(predictions_file) as predictions_file:
with UnicodeReader(check_file) as check_file:
for row in predictions_file:
check_row = check_file.next()
assert len(check_row) == len(row)
for index in range(len(row)):
dot = row[index].find(".")
decimal_places = 1
if dot > 0 or (check_row[index].find(".") > 0
and check_row[index].endswith(".0")):
try:
decimal_places = min( \
len(row[index]),
len(check_row[index])) - dot - 1
row[index] = round(float(row[index]),
decimal_places)
check_row[index] = round(
float(check_row[index]), decimal_places)
except ValueError:
decimal_places = 1
assert_almost_equal(check_row[index], row[index],
places=(decimal_places - 1))
else:
assert_equal(check_row[index], row[index])
except Exception, exc:
assert False, traceback.format_exc()
