mirror of
https://github.com/webclinic017/drift.git
synced 2026-07-28 03:08:01 +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
87 lines
2.7 KiB
Python
87 lines
2.7 KiB
Python
from pydantic import BaseModel, validator
|
|
from typing import Literal, Optional
|
|
from labeling.types import EventFilter
|
|
from models.base import Model
|
|
from data_loader.types import DataCollection, DataSource
|
|
from feature_extractors.types import FeatureExtractor, ScalerTypes
|
|
from labeling.types import EventFilter, EventLabeller
|
|
from sklearn.base import BaseEstimator
|
|
from dataclasses import dataclass
|
|
|
|
# RawConfig is needed to ensure we can declare config presets here with static typing, we then convert it to Config
|
|
class RawConfig(BaseModel):
|
|
directional_models_meta: bool
|
|
dimensionality_reduction: bool
|
|
n_features_to_select: int
|
|
expanding_window_base: bool
|
|
expanding_window_meta: bool
|
|
sliding_window_size_base: int
|
|
sliding_window_size_meta: int
|
|
retrain_every: int
|
|
scaler: Literal['normalize', 'minmax', 'standardize']
|
|
|
|
assets: list[str]
|
|
target_asset: str
|
|
other_assets: list[str]
|
|
exogenous_data: list[str]
|
|
load_non_target_asset: bool
|
|
own_features: list[str]
|
|
other_features: list[str]
|
|
exogenous_features: list[str]
|
|
event_filter: Literal['none', 'cusum_vol', 'cusum_fixed']
|
|
labeling: Literal['two_class', 'three_class_balanced', 'three_class_imbalanced']
|
|
forecasting_horizon: int
|
|
|
|
directional_models: list[str]
|
|
meta_models: list[str]
|
|
|
|
|
|
@dataclass
|
|
class Config:
|
|
directional_models_meta: bool
|
|
dimensionality_reduction: bool
|
|
n_features_to_select: int
|
|
expanding_window_base: bool
|
|
expanding_window_meta: bool
|
|
sliding_window_size_base: int
|
|
sliding_window_size_meta: int
|
|
retrain_every: int
|
|
scaler: Literal['normalize', 'minmax', 'standardize']
|
|
|
|
assets: DataCollection
|
|
target_asset: DataSource
|
|
other_assets: DataCollection
|
|
exogenous_data: DataCollection
|
|
load_non_target_asset: bool
|
|
own_features: list[tuple[str, FeatureExtractor, list[int]]]
|
|
other_features: list[tuple[str, FeatureExtractor, list[int]]]
|
|
exogenous_features: list[tuple[str, FeatureExtractor, list[int]]]
|
|
event_filter: EventFilter
|
|
labeling: EventLabeller
|
|
forecasting_horizon: int
|
|
no_of_classes: Literal['two', 'three-balanced', 'three-imbalanced']
|
|
|
|
mode: Literal['training', 'inference']
|
|
|
|
directional_model: Model
|
|
meta_model: Model
|
|
|
|
@validator('directional_model', 'meta_model')
|
|
def check_model(cls, v):
|
|
assert isinstance(v, BaseEstimator)
|
|
return v
|
|
|
|
@validator('event_filter')
|
|
def check_event_filter(cls, v):
|
|
assert isinstance(v, EventFilter)
|
|
return v
|
|
|
|
@validator('labeling')
|
|
def check_labeling(cls, v):
|
|
assert isinstance(v, EventLabeller)
|
|
return v
|
|
# class Config:
|
|
# arbitrary_types_allowed = True
|
|
|
|
|