def end_task_train(rec: Recorder, experiment_name: str) -> Recorder:
"""
Finish task training with real model fitting and saving.
Args:
rec (Recorder): the recorder will be resumed
experiment_name (str): the name of experiment
Returns:
Recorder: the model recorder
"""
with R.start(experiment_name=experiment_name,
recorder_id=rec.info["id"],
resume=True):
task_config = R.load_object("task")
# model & dataset initiation
model: Model = init_instance_by_config(task_config["model"])
dataset: Dataset = init_instance_by_config(task_config["dataset"])
# model training
model.fit(dataset)
R.save_objects(**{"params.pkl": model})
# this dataset is saved for online inference. So the concrete data should not be dumped
dataset.config(dump_all=False, recursive=True)
R.save_objects(**{"dataset": dataset})
# fill placehorder
placehorder_value = {"<MODEL>": model, "<DATASET>": dataset}
task_config = fill_placeholder(task_config, placehorder_value)
# generate records: prediction, backtest, and analysis
records = task_config.get("record", [])
if isinstance(records, dict): # prevent only one dict
records = [records]
for record in records:
r = init_instance_by_config(record, recorder=rec)
r.generate()
return rec
def end_task_train(rec: Recorder, experiment_name: str) -> Recorder:
"""
Finish task training with real model fitting and saving.
Args:
rec (Recorder): the recorder will be resumed
experiment_name (str): the name of experiment
Returns:
Recorder: the model recorder
"""
with R.start(experiment_name=experiment_name, recorder_id=rec.info["id"], resume=True):
task_config = R.load_object("task")
_exe_task(task_config)
return rec
def end_task_train(rec: Recorder, experiment_name: str) -> Recorder:
"""
Finish task training with real model fitting and saving.
Args:
rec (Recorder): the recorder will be resumed
experiment_name (str): the name of experiment
Returns:
Recorder: the model recorder
"""
with R.start(experiment_name=experiment_name,
recorder_id=rec.info["id"],
resume=True):
task_config = R.load_object("task")
# model & dataset initiation
model: Model = init_instance_by_config(task_config["model"])
dataset: Dataset = init_instance_by_config(task_config["dataset"])
# model training
model.fit(dataset)
R.save_objects(**{"params.pkl": model})
# this dataset is saved for online inference. So the concrete data should not be dumped
dataset.config(dump_all=False, recursive=True)
R.save_objects(**{"dataset": dataset})
# generate records: prediction, backtest, and analysis
records = task_config.get("record", [])
if isinstance(records, dict): # prevent only one dict
records = [records]
for record in records:
cls, kwargs = get_cls_kwargs(
record, default_module="qlib.workflow.record_temp")
if cls is SignalRecord:
rconf = {"model": model, "dataset": dataset, "recorder": rec}
else:
rconf = {"recorder": rec}
r = cls(**kwargs, **rconf)
r.generate()
return rec
def run_exp(
task_config,
dataset,
experiment_name,
recorder_name,
uri,
model_obj_name="model.pkl",
):
model = init_instance_by_config(task_config["model"])
model_fit_kwargs = dict(dataset=dataset)
# Let's start the experiment.
with R.start(
experiment_name=experiment_name,
recorder_name=recorder_name,
uri=uri,
resume=True,
):
# Setup log
recorder_root_dir = R.get_recorder().get_local_dir()
log_file = os.path.join(recorder_root_dir,
"{:}.log".format(experiment_name))
set_log_basic_config(log_file)
logger = get_module_logger("q.run_exp")
logger.info("task_config::\n{:}".format(
pprint.pformat(task_config, indent=2)))
logger.info("[{:}] - [{:}]: {:}".format(experiment_name, recorder_name,
uri))
logger.info("dataset={:}".format(dataset))
# Train model
try:
if hasattr(model, "to"): # Recoverable model
ori_device = model.device
model = R.load_object(model_obj_name)
model.to(ori_device)
else:
model = R.load_object(model_obj_name)
logger.info(
"[Find existing object from {:}]".format(model_obj_name))
except OSError:
R.log_params(**flatten_dict(update_gpu(task_config, None)))
if "save_path" in inspect.getfullargspec(model.fit).args:
model_fit_kwargs["save_path"] = os.path.join(
recorder_root_dir, "model.ckp")
elif "save_dir" in inspect.getfullargspec(model.fit).args:
model_fit_kwargs["save_dir"] = os.path.join(
recorder_root_dir, "model-ckps")
model.fit(**model_fit_kwargs)
# remove model to CPU for saving
if hasattr(model, "to"):
old_device = model.device
model.to("cpu")
R.save_objects(**{model_obj_name: model})
model.to(old_device)
else:
R.save_objects(**{model_obj_name: model})
except Exception as e:
raise ValueError("Something wrong: {:}".format(e))
# Get the recorder
recorder = R.get_recorder()
# Generate records: prediction, backtest, and analysis
for record in task_config["record"]:
record = deepcopy(record)
if record["class"] == "MultiSegRecord":
record["kwargs"] = dict(model=model,
dataset=dataset,
recorder=recorder)
sr = init_instance_by_config(record)
sr.generate(**record["generate_kwargs"])
elif record["class"] == "SignalRecord":
srconf = {
"model": model,
"dataset": dataset,
"recorder": recorder
}
record["kwargs"].update(srconf)
sr = init_instance_by_config(record)
sr.generate()
else:
rconf = {"recorder": recorder}
record["kwargs"].update(rconf)
ar = init_instance_by_config(record)
ar.generate()