def load(self, task_index_url=None):
"""
load task_detail (tasks/models etc ...) from task index file.
It'll automatically loaded during `inference` and `evaluation` phases.
Parameters
----------
task_index_url : str
task index file path, default self.task_index_url.
"""
if task_index_url:
self.task_index_url = task_index_url
assert FileOps.exists(self.task_index_url), FileExistsError(
f"Task index miss: {self.task_index_url}")
task_index = FileOps.load(self.task_index_url)
self.extractor = task_index['extractor']
if isinstance(self.extractor, str):
self.extractor = FileOps.load(self.extractor)
self.task_groups = task_index['task_groups']
self.models = [task.model for task in self.task_groups]
def train(self,
train_data,
valid_data=None,
post_process=None,
action="initial",
**kwargs):
"""
fit for update the knowledge based on training data.
Parameters
----------
train_data : BaseDataSource
Train data, see `sedna.datasources.BaseDataSource` for more detail.
valid_data : BaseDataSource
Valid data, BaseDataSource or None.
post_process : function
function or a registered method, callback after `estimator` train.
action : str
`update` or `initial` the knowledge base
kwargs : Dict
parameters for `estimator` training, Like:
`early_stopping_rounds` in Xgboost.XGBClassifier
Returns
-------
train_history : object
"""
callback_func = None
if post_process is not None:
callback_func = ClassFactory.get_cls(ClassType.CALLBACK,
post_process)
res, task_index_url = self.estimator.train(
train_data=train_data, valid_data=valid_data, **kwargs
) # todo: Distinguishing incremental update and fully overwrite
if isinstance(task_index_url, str) and FileOps.exists(task_index_url):
task_index = FileOps.load(task_index_url)
else:
task_index = task_index_url
extractor = task_index['extractor']
task_groups = task_index['task_groups']
model_upload_key = {}
for task in task_groups:
model_file = task.model.model
save_model = FileOps.join_path(self.config.output_url,
os.path.basename(model_file))
if model_file not in model_upload_key:
model_upload_key[model_file] = FileOps.upload(
model_file, save_model)
model_file = model_upload_key[model_file]
try:
model = self.kb_server.upload_file(save_model)
except Exception as err:
self.log.error(
f"Upload task model of {model_file} fail: {err}")
model = set_backend(
estimator=self.estimator.estimator.base_model)
model.load(model_file)
task.model.model = model
for _task in task.tasks:
sample_dir = FileOps.join_path(
self.config.output_url,
f"{_task.samples.data_type}_{_task.entry}.sample")
task.samples.save(sample_dir)
try:
sample_dir = self.kb_server.upload_file(sample_dir)
except Exception as err:
self.log.error(
f"Upload task samples of {_task.entry} fail: {err}")
_task.samples.data_url = sample_dir
save_extractor = FileOps.join_path(
self.config.output_url,
KBResourceConstant.TASK_EXTRACTOR_NAME.value)
extractor = FileOps.dump(extractor, save_extractor)
try:
extractor = self.kb_server.upload_file(extractor)
except Exception as err:
self.log.error(f"Upload task extractor fail: {err}")
task_info = {"task_groups": task_groups, "extractor": extractor}
fd, name = tempfile.mkstemp()
FileOps.dump(task_info, name)
index_file = self.kb_server.update_db(name)
if not index_file:
self.log.error(f"KB update Fail !")
index_file = name
FileOps.upload(index_file, self.config.task_index)
task_info_res = self.estimator.model_info(
self.config.task_index, relpath=self.config.data_path_prefix)
self.report_task_info(None, K8sResourceKindStatus.COMPLETED.value,
task_info_res)
self.log.info(f"Lifelong learning Train task Finished, "
f"KB idnex save in {self.config.task_index}")
return callback_func(self.estimator, res) if callback_func else res
