def infer_pipeline(info,
pipeline_,
datasource,
orchestration_backend,
orchestration_args,
processing_backend,
processing_args,
force):
"""Initiate a batch inference run of a selected pipeline"""
# Resolving additional args
_, run_id = utils.resolve_pipeline_runs(
info,
pipeline_,
run_type=PipelineRunTypes.training.name)
if datasource is None:
utils.check_datasource_commit(info)
"""Initiate an infer run of a selected pipeline"""
utils.resolve_pipeline_creation(info=info,
pipeline_type=PipelineRunTypes.infer.name,
pipeline_=pipeline_,
datasource=datasource,
orchestration_backend=orchestration_backend,
orchestration_args=orchestration_args,
processing_backend=processing_backend,
processing_args=processing_args,
force=force,
additional_args={'run_id': run_id})
def evaluate(info, pipeline_):
"""Tool for the in-depth evaluation of a pipeline run"""
p_uuid, r_uuid = resolve_pipeline_runs(info, pipeline_)
notice('Downloading evaluation metrics and tensorboard logs for '
'pipeline ID {} and run ID {}. This might take some time if the '
'model resources are significantly large in size.\nYour patience '
'is much appreciated!'.format(format_uuid(p_uuid),
format_uuid(r_uuid)))
log_dir = get_log_dir(p_uuid, r_uuid, info)
eval_dir = get_eval_dir(p_uuid, r_uuid, info)
# generate notebook
nb = nbf.v4.new_notebook()
nb['cells'] = [
nbf.v4.new_code_cell(get_model_block(log_dir)),
nbf.v4.new_code_cell(get_eval_block(eval_dir)),
]
# write notebook
final_out_path = (Path(click.get_app_dir(constants.APP_NAME)) /
constants.EVALUATION_NOTEBOOK)
s = nbf.writes(nb)
if isinstance(s, bytes):
s = s.decode('utf8')
# only import tfx when needed
with open(final_out_path, 'w') as f:
f.write(s)
os.system('jupyter notebook "{}"'.format(final_out_path))
def logs_pipeline(info, source_id):
"""Get link to the logs of a pipeline"""
p_uuid, r_uuid = utils.resolve_pipeline_runs(info, source_id)
utils.notice(
'Generating logs url for the pipeline run ID {}. Please visit the '
'url for all your logs.'.format(utils.format_uuid(r_uuid)))
api = ce_api.PipelinesApi(utils.api_client(info))
logs_url = utils.api_call(
api.get_pipeline_logs_api_v1_pipelines_pipeline_id_runs_pipeline_run_id_logs_get,
pipeline_id=p_uuid,
pipeline_run_id=r_uuid
)
click.echo(logs_url)
def statistics_pipeline(info, pipeline_):
"""Serve the statistics of a pipeline run"""
p_uuid, r_uuid = utils.resolve_pipeline_runs(info,
pipeline_,
run_type=PipelineRunTypes.training.name)
utils.notice('Generating statistics for the pipeline run ID {}. If your '
'browser opens up to a blank window, please refresh '
'the page once.'.format(utils.format_uuid(r_uuid)))
api = ce_api.PipelinesApi(utils.api_client(info))
stat_artifact = utils.api_call(
api.get_pipeline_artifacts_api_v1_pipelines_pipeline_id_runs_pipeline_run_id_artifacts_component_type_get,
pipeline_id=p_uuid,
pipeline_run_id=r_uuid,
component_type=GDPComponent.SplitStatistics.name)
ws_id = info[info[constants.ACTIVE_USER]][constants.ACTIVE_WORKSPACE]
path = Path(click.get_app_dir(constants.APP_NAME),
'statistics',
str(ws_id),
p_uuid,
r_uuid)
utils.download_artifact(artifact_json=stat_artifact[0].to_dict(),
path=path)
import tensorflow as tf
from tensorflow_metadata.proto.v0 import statistics_pb2
import panel as pn
result = {}
for split in os.listdir(path):
stats_path = os.path.join(path, split, 'stats_tfrecord')
serialized_stats = next(tf.compat.v1.io.tf_record_iterator(stats_path))
stats = statistics_pb2.DatasetFeatureStatisticsList()
stats.ParseFromString(serialized_stats)
dataset_list = statistics_pb2.DatasetFeatureStatisticsList()
for i, d in enumerate(stats.datasets):
d.name = split
dataset_list.datasets.append(d)
result[split] = dataset_list
h = utils.get_statistics_html(result)
pn.serve(panels=pn.pane.HTML(h, width=1200), show=True)
def model_pipeline(info, pipeline_, output_path):
"""Download the trained model to a specified location"""
if os.path.exists(output_path) and os.path.isdir(output_path):
if not [f for f in os.listdir(output_path) if
not f.startswith('.')] == []:
utils.error("Output path must be an empty directory!")
if os.path.exists(output_path) and not os.path.isdir(output_path):
utils.error("Output path must be an empty directory!")
if not os.path.exists(output_path):
"Creating directory {}..".format(output_path)
p_uuid, r_uuid = utils.resolve_pipeline_runs(info, pipeline_)
utils.notice('Downloading the trained model from pipeline run '
'ID {}. This might take some time if the model '
'resources are significantly large in size.\nYour patience '
'is much appreciated!'.format(utils.format_uuid(r_uuid)))
api = ce_api.PipelinesApi(utils.api_client(info))
artifact = utils.api_call(
api.get_pipeline_artifacts_api_v1_pipelines_pipeline_id_runs_pipeline_run_id_artifacts_component_type_get,
pipeline_id=p_uuid,
pipeline_run_id=r_uuid,
component_type=GDPComponent.Deployer.name)
spin = utils.Spinner()
spin.start()
if len(artifact) == 1:
utils.download_artifact(artifact_json=artifact[0].to_dict(),
path=output_path)
spin.stop()
else:
utils.error('Something unexpected happened! Please contact '
'[email protected] to get further information.')
utils.declare('Model downloaded to: {}'.format(output_path))
# TODO: [LOW] Make the Tensorflow version more dynamic
utils.declare('Please note that the model is saved as a SavedModel '
'Tensorflow artifact, trained on Tensoflow 2.1.0.')