def prepare_tasks(self, cur_time) -> List[dict]:
"""
Prepare new tasks based on cur_time (None for the latest).
You can find the last online models by OnlineToolR.online_models.
Returns:
List[dict]: a list of new tasks.
"""
latest_records, max_test = self._list_latest(self.tool.online_models())
if max_test is None:
self.logger.warn(f"No latest online recorders, no new tasks.")
return []
calendar_latest = D.calendar(end_time=cur_time)[-1] if cur_time is None else cur_time
self.logger.info(
f"The interval between current time {calendar_latest} and last rolling test begin time {max_test[0]} is {self.ta.cal_interval(calendar_latest, max_test[0])}, the rolling step is {self.rg.step}"
)
if self.ta.cal_interval(calendar_latest, max_test[0]) >= self.rg.step:
old_tasks = []
tasks_tmp = []
for rec in latest_records:
task = rec.load_object("task")
old_tasks.append(deepcopy(task))
test_begin = task["dataset"]["kwargs"]["segments"]["test"][0]
# modify the test segment to generate new tasks
task["dataset"]["kwargs"]["segments"]["test"] = (test_begin, calendar_latest)
tasks_tmp.append(task)
new_tasks_tmp = task_generator(tasks_tmp, self.rg)
new_tasks = [task for task in new_tasks_tmp if task not in old_tasks]
return new_tasks
return []
def task_generating(self):
print("========== task_generating ==========")
tasks = task_generator(
tasks=self.task_config,
generators=self.rolling_gen, # generate different date segments
)
pprint(tasks)
return tasks
def first_tasks(self) -> List[dict]:
"""
Use rolling_gen to generate different tasks based on task_template.
Returns:
List[dict]: a list of tasks
"""
return task_generator(
tasks=self.task_template,
generators=self.rg, # generate different date segment
)
def setup(self, trainer=TrainerR, trainer_kwargs={}):
"""
after running this function `self.data_ic_df` will become set.
Each col represents a data.
Each row represents the Timestamp of performance of that data.
For example,
.. code-block:: python
2021-06-21 2021-06-04 2021-05-21 2021-05-07 2021-04-20 2021-04-06 2021-03-22 2021-03-08 ...
2021-07-02 2021-06-18 2021-06-03 2021-05-20 2021-05-06 2021-04-19 2021-04-02 2021-03-19 ...
datetime ...
2018-01-02 0.079782 0.115975 0.070866 0.028849 -0.081170 0.140380 0.063864 0.110987 ...
2018-01-03 0.123386 0.107789 0.071037 0.045278 -0.060782 0.167446 0.089779 0.124476 ...
2018-01-04 0.140775 0.097206 0.063702 0.042415 -0.078164 0.173218 0.098914 0.114389 ...
2018-01-05 0.030320 -0.037209 -0.044536 -0.047267 -0.081888 0.045648 0.059947 0.047652 ...
2018-01-08 0.107201 0.009219 -0.015995 -0.036594 -0.086633 0.108965 0.122164 0.108508 ...
... ... ... ... ... ... ... ... ... ...
"""
# 1) prepare the prediction of proxy models
perf_task_tpl = deepcopy(
self.task_tpl
) # this task is supposed to contains no complicated objects
trainer = auto_filter_kwargs(trainer)(experiment_name=self.exp_name,
**trainer_kwargs)
# NOTE:
# The handler is initialized for only once.
if not trainer.has_worker():
self.dh = init_task_handler(perf_task_tpl)
else:
self.dh = init_instance_by_config(
perf_task_tpl["dataset"]["kwargs"]["handler"])
seg = perf_task_tpl["dataset"]["kwargs"]["segments"]
# We want to split the training time period into small segments.
perf_task_tpl["dataset"]["kwargs"]["segments"] = {
"train": (DatasetH.get_min_time(seg), DatasetH.get_max_time(seg)),
"test": (None, None),
}
# NOTE:
# we play a trick here
# treat the training segments as test to create the rolling tasks
rg = RollingGen(step=self.step,
test_key="train",
train_key=None,
task_copy_func=deepcopy_basic_type)
gen_task = task_generator(perf_task_tpl, [rg])
recorders = R.list_recorders(experiment_name=self.exp_name)
if len(gen_task) == len(recorders):
get_module_logger("Internal Data").info(
"the data has been initialized")
else:
# train new models
assert 0 == len(
recorders
), "An empty experiment is required for setup `InternalData``"
trainer.train(gen_task)
# 2) extract the similarity matrix
label_df = self.dh.fetch(col_set="label")
# for
recorders = R.list_recorders(experiment_name=self.exp_name)
key_l = []
ic_l = []
for _, rec in tqdm(recorders.items(), desc="calc"):
pred = rec.load_object("pred.pkl")
task = rec.load_object("task")
data_key = task["dataset"]["kwargs"]["segments"]["train"]
key_l.append(data_key)
ic_l.append(
delayed(self._calc_perf)(pred.iloc[:, 0], label_df.iloc[:, 0]))
ic_l = Parallel(n_jobs=-1)(ic_l)
self.data_ic_df = pd.DataFrame(dict(zip(key_l, ic_l)))
self.data_ic_df = self.data_ic_df.sort_index().sort_index(axis=1)
del self.dh # handler is not useful now
def create_rolling_tasks(self):
task = self.basic_task()
task_l = task_generator(
task, RollingGen(step=self.step, trunc_days=self.horizon + 1)
) # the last two days should be truncated to avoid information leakage
return task_l
