# 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, '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,
)
training_pipeline.add_evaluator(
TFMAEvaluator(
slices=[['has_diabetes']],
metrics={'has_diabetes': ['binary_crossentropy', 'binary_accuracy']}))
# Important details:
artifact_store_bucket = 'gs://rndm-strg/zenml-k8s-test/'
mysql_host = 'cloudsql'
mysql_port = 3306
mysql_db = 'zenml'
mysql_user = USERNAME
mysql_pw = PASSWORD
# Path to your kubernetes config:
k8s_config_path = os.path.join(os.environ["HOME"], '.kube/config')
# Run the pipeline on a Kubernetes Cluster
training_pipeline.run(backends=[
OrchestratorKubernetesBackend(kubernetes_config_path=k8s_config_path,
image_pull_policy="Always")
],
metadata_store=MySQLMetadataStore(
host=mysql_host,
port=mysql_port,
database=mysql_db,
username=mysql_user,
password=mysql_pw,
),
artifact_store=ArtifactStore(artifact_store_bucket))
features=['times_pregnant', 'pgc', 'dbp', 'tst', 'insulin', 'bmi',
'pedigree', 'age'],
labels=['has_diabetes'],
overwrite={'has_diabetes': {
'transform': [{'method': 'no_transform', 'parameters': {}}]}}
).with_backend(processing_backend)
)
# Add a trainer
training_pipeline.add_trainer(FeedForwardTrainer(
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={'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)
# Add a split
training_pipeline.add_split(RandomSplit(split_map={'eval': 0.3, 'train': 0.7}))
# Add a preprocessing unit
training_pipeline.add_preprocesser(
StandardPreprocesser(features=[
'times_pregnant', 'pgc', 'dbp', 'tst', 'insulin', 'bmi', 'pedigree',
'age'
],
labels=['has_diabetes'],
overwrite={
'has_diabetes': {
'transform': [{
'method': 'no_transform',
'parameters': {}
}]
}
}))
# Add a trainer
training_pipeline.add_trainer(
FeedForwardTrainer(loss='binary_crossentropy',
last_activation='sigmoid',
output_units=1,
metrics=['accuracy'],
epoch=100))
# Run the pipeline locally
training_pipeline.run()