def load_pipeline(pipeline):
with open(pipeline) as _pipeline:
if pipeline.endswith('.json'):
pipeline = Pipeline.from_json(_pipeline)
else:
pipeline = Pipeline.from_yaml(_pipeline)
return pipeline
def generate_template(pipeline_file: str) -> dict:
with open(pipeline_file) as f:
pipeline = Pipeline.from_json(f)
steps = []
for i, step in enumerate(pipeline.steps):
if not isinstance(step, PrimitiveStep):
raise ValueError('Can only handle PrimitiveSteps')
step_name = f'steps.{i}'
hyperparameters = {}
for name, value in step.hyperparams.items():
if value['type'] == ArgumentType.VALUE:
hyperparameters[name] = value['data']
else:
raise ValueError(
f'Do not know how to parse hyperparam: {str(value)}')
arguments = []
argument_keys = set(step.arguments.keys())
for argument_name in ['inputs', 'outputs', 'reference']:
if argument_name in argument_keys:
argument_keys.remove(argument_name)
if step.arguments[argument_name][
'type'] == ArgumentType.CONTAINER:
if step.arguments[argument_name]['data'] == 'inputs.0':
arguments.append('template_input')
elif step.arguments[argument_name]['data'].startswith(
'steps.') and step.arguments['inputs'][
'data'].endswith('.produce'):
arguments.append(
step.arguments[argument_name]['data'][:-8])
else:
raise ValueError(
f"Do not know how to parse argument: {step.arguments['inputs']['data']}"
)
else:
raise ValueError(
f"Do not know how to parse argument type: {step.arguments['inputs']['type']}"
)
if len(argument_keys) > 0:
for argument_name in argument_keys:
print(argument_name, step.arguments[argument_name])
raise ValueError(f"Unused arguments: {argument_keys}")
primitive = OrderedDict()
primitive['primitive'] = str(step.primitive)
primitive['hyperparameters'] = hyperparameters
step = OrderedDict()
step['name'] = step_name
step['primitives'] = [primitive]
step['inputs'] = arguments
steps.append(step)
template = OrderedDict()
template['name'] = pipeline.id if pipeline.name is None else pipeline.name
template['taskType'] = {'TaskType'}
template['taskSubtype'] = {'TaskSubtype'}
template['inputType'] = {'table'}
template['output'] = step_name
template['steps'] = steps
return template
def DescribeSolution(self, request, context):
solution_id = request.solution_id
info_dict = self.get_from_stage_outputs("GetSearchSolutionsResults",
solution_id)
# Serialize the pipeline
pipeline_json = info_dict["pipeline_json"]
allowed_value_types = info_dict["allowed_value_types"]
pipeline = Pipeline.from_json(pipeline_json)
pipeline_description = ta3ta2utils.encode_pipeline_description(
pipeline, allowed_value_types, "/tmp")
return core_pb2.DescribeSolutionResponse(pipeline=pipeline_description)
def generate_pipeline(pipeline_path: str,
dataset_path: str,
problem_doc_path: str,
resolver: Resolver = None) -> Runtime:
"""
Simplified interface that fit a pipeline with a dataset
Paramters
---------
pipeline_path
Path to the pipeline description
dataset_path:
Path to the datasetDoc.json
problem_doc_path:
Path to the problemDoc.json
resolver : Resolver
Resolver to use.
"""
# Pipeline description
pipeline_description = None
if '.json' in pipeline_path:
with open(pipeline_path) as pipeline_file:
pipeline_description = Pipeline.from_json(
string_or_file=pipeline_file, resolver=resolver)
else:
with open(pipeline_path) as pipeline_file:
pipeline_description = Pipeline.from_yaml(
string_or_file=pipeline_file, resolver=resolver)
# Problem Doc
problem_doc = load_problem_doc(problem_doc_path)
# Dataset
if 'file:' not in dataset_path:
dataset_path = 'file://{dataset_path}'.format(
dataset_path=os.path.abspath(dataset_path))
dataset = D3MDatasetLoader().load(dataset_uri=dataset_path)
# Adding Metadata to Dataset
dataset = add_target_columns_metadata(dataset, problem_doc)
# Pipeline
pipeline_runtime = Runtime(pipeline_description)
# Fitting Pipeline
pipeline_runtime.fit(inputs=[dataset])
return pipeline_runtime
def fitproduce(self, input_item):
problem_doc, pipeline_json, dataset_train, dataset_test = input_item[
1:]
# Run pipeline
pipeline = Pipeline.from_json(pipeline_json)
pipeline_runtime = Runtime(pipeline, context=Context.TESTING)
pipeline_runtime.fit(inputs=[dataset_train],
return_values=['outputs.0'])
score_predictions = pipeline_runtime.produce(
inputs=[dataset_test], return_values=['outputs.0'])
score_predictions = score_predictions.values['outputs.0']
# Write predictions to output path
path = self.get_predictions_save_path()
utils.utils.write_predictions_to_file(score_predictions, path,
problem_doc)
path_uri = "file://%s" % path
return path_uri
def score(self, input_item):
problem_doc, metric, pipeline_json, dataset_train, dataset_test = input_item[
1:]
# Run pipeline
pipeline = Pipeline.from_json(pipeline_json)
pipeline_runtime = Runtime(pipeline, context=Context.TESTING)
pipeline_runtime.fit(inputs=[dataset_train],
return_values=['outputs.0'])
score_predictions = pipeline_runtime.produce(
inputs=[dataset_test], return_values=['outputs.0'])
score_predictions = score_predictions.values['outputs.0']
# Evaluate scores on score dir
achieved_score = utils.train_utils.score(score_predictions,
dataset_test,
problem_doc,
override_metric_key=metric)
return achieved_score
import utils.utils
import utils.train_utils
if __name__ == "__main__":
# Get args
try:
path_to_pipeline_json = sys.argv[1]
inputdir = sys.argv[2]
# Load datasets
problem_doc, dataset = utils.utils.load_data_from_dir(inputdir)
# Create pipeline
with open(path_to_pipeline_json, "r") as f:
pipeline = Pipeline.from_json(f.read())
pipeline_runtime = Runtime(pipeline, context=Context.TESTING)
pipeline_runtime.fit(inputs=[dataset], return_values=['outputs.0'])
problem_doc_score, dataset_score = utils.utils.load_data_from_dir(inputdir, mode="score")
score_predictions = pipeline_runtime.produce(inputs=[dataset_score], return_values=['outputs.0'])
score_predictions = score_predictions.values['outputs.0']
# Evaluate scores on score dir
achieved_score = utils.train_utils.score(score_predictions, dataset_score, problem_doc_score)
print(achieved_score)
except:
print("N/A")
def load_pipeline(pipeline_json):
return Pipeline.from_json(pipeline_json)
def load_pipeline(pipeline_path):
with open(pipeline_path, 'r') as pipeline_file:
if pipeline_path.endswith('.json'):
return Pipeline.from_json(pipeline_file)
else:
return Pipeline.from_yaml(pipeline_file)
