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
29 lines
756 B
Python
29 lines
756 B
Python
from data_loader.types import ReturnSeries, ForwardReturnSeries
|
|
from abc import ABC, abstractmethod
|
|
import pandas as pd
|
|
import pandera as pa
|
|
from pandera.typing import DataFrame, Series
|
|
|
|
class EventFilter(ABC):
|
|
|
|
@abstractmethod
|
|
def get_event_start_times(self, returns: ReturnSeries) -> pd.DatetimeIndex:
|
|
raise NotImplementedError
|
|
|
|
|
|
class EventSchema(pa.SchemaModel):
|
|
start: Series[pd.Timestamp]
|
|
end: Series[pd.Timestamp]
|
|
label: Series[int]
|
|
returns: Series[float]
|
|
|
|
EventsDataFrame = DataFrame[EventSchema]
|
|
|
|
|
|
class EventLabeller(ABC):
|
|
|
|
@abstractmethod
|
|
def label_events(self, event_start_times: pd.DatetimeIndex, returns: ReturnSeries) -> tuple[EventsDataFrame, ForwardReturnSeries]:
|
|
raise NotImplementedError
|
|
|