tods/primitive_tests/build_ABOD_pipline.py

from d3m import index
from d3m.metadata.base import ArgumentType
from d3m.metadata.pipeline import Pipeline, PrimitiveStep


# Creating pipeline
pipeline_description = Pipeline()
pipeline_description.add_input(name='inputs')

# Step 0: dataset_to_dataframe
step_0 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.tods.data_processing.dataset_to_dataframe'))
step_0.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='inputs.0')
step_0.add_output('produce')
pipeline_description.add_step(step_0)

# Step 1: column_parser
step_1 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.tods.data_processing.column_parser'))
step_1.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='steps.0.produce')
step_1.add_output('produce')
pipeline_description.add_step(step_1)

# Step 2: extract_columns_by_semantic_types(attributes)
step_2 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.tods.data_processing.extract_columns_by_semantic_types'))
step_2.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='steps.1.produce')
step_2.add_output('produce')
step_2.add_hyperparameter(name='semantic_types', argument_type=ArgumentType.VALUE,
                                  data=['https://metadata.datadrivendiscovery.org/types/Attribute'])
pipeline_description.add_step(step_2)

# Step 3: extract_columns_by_semantic_types(targets)
step_3 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.tods.data_processing.extract_columns_by_semantic_types'))
step_3.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='steps.0.produce')
step_3.add_output('produce')
step_3.add_hyperparameter(name='semantic_types', argument_type=ArgumentType.VALUE,
                                  data=['https://metadata.datadrivendiscovery.org/types/TrueTarget'])
pipeline_description.add_step(step_3)

attributes = 'steps.2.produce'
targets = 'steps.3.produce'

# Step 4: imputer
step_4 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.tods.data_processing.impute_missing'))
step_4.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference=attributes)
step_4.add_output('produce')
pipeline_description.add_step(step_4)

# Step 5: ABOD
step_5 = PrimitiveStep(primitive=index.get_primitive('d3m.primitives.tods.detection_algorithm.pyod_abod'))
step_5.add_argument(name='inputs', argument_type=ArgumentType.CONTAINER, data_reference='steps.4.produce')

step_5.add_hyperparameter(name='use_semantic_types', argument_type=ArgumentType.VALUE, data=True)
step_5.add_hyperparameter(name='contamination', argument_type=ArgumentType.VALUE, data=0.1)
step_5.add_hyperparameter(name='use_columns', argument_type=ArgumentType.VALUE, data=(2, 4,))
step_5.add_hyperparameter(name='return_result', argument_type=ArgumentType.VALUE, data='replace')

step_5.add_output('produce')
pipeline_description.add_step(step_5)

# Final Output
pipeline_description.add_output(name='output predictions', data_reference='steps.5.produce')

# Output to YAML
yaml = pipeline_description.to_yaml()
with open('pipeline.yml', 'w') as f:
    f.write(yaml)
print(yaml)

# Or you can output json
#data = pipline_description.to_json()