def set_artifact_store(self, artifact_store_path: Text):
"""
Updates artifact store to point to path.
Args:
artifact_store_path: new path to artifact store
"""
self.artifact_store = ArtifactStore(artifact_store_path)
self.save()
def from_config(self, config_dict: Dict):
"""
Sets metadata and artifact_store variables
Args:
config_dict (dict): .zenml config object in dict format.
"""
assert METADATA_KEY in config_dict
assert ARTIFACT_STORE_KEY in config_dict
assert PIPELINES_DIR_KEY in config_dict
self.artifact_store = ArtifactStore(config_dict[ARTIFACT_STORE_KEY])
self.metadata_store = ZenMLMetadataStore.from_config(
config=config_dict[METADATA_KEY])
self.pipelines_dir = config_dict[PIPELINES_DIR_KEY]
def from_config(cls, config: Dict):
"""
Convert from pipeline config to ZenML Pipeline object.
All steps are also populated and configuration set to parameters set
in the config file.
Args:
config: a ZenML config in dict-form (probably loaded from YAML).
"""
# start with artifact store
artifact_store = ArtifactStore(config[keys.GlobalKeys.ARTIFACT_STORE])
# metadata store
metadata_store = ZenMLMetadataStore.from_config(
config=config[keys.GlobalKeys.METADATA_STORE])
# orchestration backend
backend = OrchestratorBaseBackend.from_config(
config[keys.GlobalKeys.BACKEND])
# pipeline configuration
p_config = config[keys.GlobalKeys.PIPELINE]
kwargs = p_config[keys.PipelineKeys.ARGS]
pipeline_name = kwargs.pop(keys.PipelineDetailKeys.NAME)
pipeline_source = p_config[keys.PipelineKeys.SOURCE]
# populate steps
steps_dict: Dict = {}
for step_key, step_config in p_config[keys.PipelineKeys.STEPS].items():
steps_dict[step_key] = BaseStep.from_config(step_config)
# datasource
datasource = BaseDatasource.from_config(
config[keys.GlobalKeys.PIPELINE])
class_ = source_utils.load_source_path_class(pipeline_source)
obj = class_(steps_dict=steps_dict,
backend=backend,
artifact_store=artifact_store,
metadata_store=metadata_store,
datasource=datasource,
pipeline_name=pipeline_name,
name=cls.get_name_from_pipeline_name(pipeline_name),
**kwargs)
obj._immutable = True
return obj
training_pipeline.add_evaluator(
TFMAEvaluator(
slices=[['has_diabetes']],
metrics={'has_diabetes': ['binary_crossentropy', 'binary_accuracy']}))
# Add cortex deployer
api_config = {
"name": CORTEX_MODEL_NAME,
"kind": "RealtimeAPI",
"predictor": {
"type": "tensorflow",
# Set signature key of the model as we are using Tensorflow Trainer
"models": {
"signature_key": "serving_default"
}
}
}
training_pipeline.add_deployment(
CortexDeployer(
env=CORTEX_ENV,
api_config=api_config,
predictor=TensorFlowPredictor,
))
# Define the artifact store
artifact_store = ArtifactStore(
os.path.join(GCP_BUCKET, 'cortex/artifact_store'))
# Run the pipeline
training_pipeline.run(artifact_store=artifact_store)
# Add an evaluator
training_pipeline.add_evaluator(
TFMAEvaluator(
slices=[['has_diabetes']],
metrics={'has_diabetes': ['binary_crossentropy', 'binary_accuracy']}))
# Define the metadata store
metadata_store = MySQLMetadataStore(
host=MYSQL_HOST,
port=int(MYSQL_PORT),
database=MYSQL_DB,
username=MYSQL_USER,
password=MYSQL_PWD,
)
# Define the artifact store
artifact_store = ArtifactStore(
os.path.join(GCP_BUCKET, 'gcp_gcaip_training/artifact_store'))
# Define the orchestrator backend
orchestrator_backend = OrchestratorGCPBackend(
cloudsql_connection_name=GCP_CLOUD_SQL_INSTANCE_NAME, project=GCP_PROJECT)
# Run the pipeline
training_pipeline.run(
backend=orchestrator_backend,
metadata_store=metadata_store,
artifact_store=artifact_store,
)
metrics={
transformed_label_name('has_diabetes'):
['binary_crossentropy', 'binary_accuracy']
}))
# Define the metadata store
metadata_store = MySQLMetadataStore(
host=MYSQL_HOST,
port=int(MYSQL_PORT),
database=MYSQL_DB,
username=MYSQL_USER,
password=MYSQL_PWD,
)
# Define the artifact store
artifact_store = ArtifactStore(
os.path.join(GCP_BUCKET, 'gcp_orchestrated/artifact_store'))
# Define the orchestrator backend
orchestrator_backend = OrchestratorGCPBackend(
cloudsql_connection_name=CONNECTION_NAME,
project=GCP_PROJECT,
preemptible=True, # reduce costs by using preemptible instances
)
# Run the pipeline
training_pipeline.run(
backend=orchestrator_backend,
metadata_store=metadata_store,
artifact_store=artifact_store,
)
training_pipeline.add_evaluator(
TFMAEvaluator(slices=[['has_diabetes']],
metrics={
transformed_label_name('has_diabetes'):
['binary_crossentropy', 'binary_accuracy']
}))
# Define the metadata store
metadata_store = MySQLMetadataStore(
host=MYSQL_HOST,
port=int(MYSQL_PORT),
database=MYSQL_DB,
username=MYSQL_USER,
password=MYSQL_PWD,
)
# Define the artifact store
artifact_store = ArtifactStore(
os.path.join(GCP_BUCKET, 'kubernetes_orcestrated/artifact_store'))
# Define the orchestrator backend
orchestrator_backend = OrchestratorKubernetesBackend(
kubernetes_config_path=K8S_CONFIG_PATH, image_pull_policy="Always")
# Run the pipeline on a Kubernetes Cluster
training_pipeline.run(
backend=orchestrator_backend,
metadata_store=metadata_store,
artifact_store=artifact_store,
)
epochs=20))
# Add an evaluator
training_pipeline.add_evaluator(
TFMAEvaluator(
slices=[['has_diabetes']],
metrics={'has_diabetes': ['binary_crossentropy', 'binary_accuracy']}))
# Define the metadata store
metadata_store = MySQLMetadataStore(
host=MYSQL_HOST,
port=int(MYSQL_PORT),
database=MYSQL_DB,
username=MYSQL_USER,
password=MYSQL_PWD,
)
# Define the artifact store
artifact_store = ArtifactStore(
os.path.join(S3_BUCKET, 'aws_orchestrated/artifact_store'))
# Define the orchestrator backend
orchestrator_backend = OrchestratorAWSBackend(iam_role=IAM_ROLE)
# Run the pipeline
training_pipeline.run(
backend=orchestrator_backend,
metadata_store=metadata_store,
artifact_store=artifact_store,
)
overwrite={
'has_diabetes': {
'transform': [{
'method': 'no_transform',
'parameters': {}
}]
}
}).with_backend(processing_backend))
# Add a trainer
training_pipeline.add_trainer(
TFFeedForwardTrainer(loss='binary_crossentropy',
last_activation='sigmoid',
output_units=1,
metrics=['accuracy'],
epochs=20))
# Add an evaluator
training_pipeline.add_evaluator(
TFMAEvaluator(slices=[['has_diabetes']],
metrics={
transformed_label_name('has_diabetes'):
['binary_crossentropy', 'binary_accuracy']
}).with_backend(processing_backend))
# Define the artifact store
artifact_store = ArtifactStore(
os.path.join(GCP_BUCKET, 'dataflow_processing/artifact_store'))
# Run the pipeline
training_pipeline.run(artifact_store=artifact_store)