mirror of
https://github.com/webclinic017/drift.git
synced 2026-07-27 18:57:55 +00:00
Mark Aron Szulyovszky
9d47ee942d
* feat(Project): use 5 minute data, running training in parallel, sped up cusum filter by 10x with numba * fix(WalkForward): inference mini-batch parallelization * fix(WalkForward): don't use the parallel version of any of the functions * feat(CI): download the data required * fix(Project): 5min_crypto folder added * fix(Evaluate): make sure we have numerical stability in returns * feat(Models): use SKLearn models directly to enable composability * feat(Inference): batched inference now working, added forecasting_horizon * fix(Inference): works again * fix(Inference) * chore(Models): remove unused Ensemble model * fix(Labeller): don't just forward shift returns, also take the sum of the data happened until then * Update test.yml
19 lines
734 B
Python
19 lines
734 B
Python
from .types import EventFilter, EventLabeller, EventsDataFrame
|
|
from data_loader.types import ForwardReturnSeries, XDataFrame, ReturnSeries, ySeries
|
|
|
|
def label_data(
|
|
event_filter: EventFilter,
|
|
event_labeller: EventLabeller,
|
|
X: XDataFrame,
|
|
returns: ReturnSeries) -> tuple[EventsDataFrame, XDataFrame, ySeries, ForwardReturnSeries]:
|
|
|
|
event_start_times = event_filter.get_event_start_times(returns)
|
|
print("| Filtered out ", (1 - (len(event_start_times) / len(returns))) * 100, "% of timestamps" )
|
|
|
|
events, forward_returns = event_labeller.label_events(event_start_times, returns)
|
|
|
|
X = X.filter(items = events.index, axis = 0)
|
|
y = events['label']
|
|
forward_returns = events['returns']
|
|
|
|
return events, X, y, forward_returns |