mirror of
https://github.com/webclinic017/drift.git
synced 2026-07-28 11:17:47 +00:00
Mark Aron Szulyovszky
1cd0119589
* fix(FeatureExtractor): apply log to transform some series to normality * feat(DataLoader): add ability of not returning returns when they're not needed (exogenous data), applied log to certain features * feat(FeatureExtractors): added standard scaling for exogenous data * feat(FeatureSelection): scale data with the passed in scaler before doing feature-selection * fix(Config): sweep config * feat(Models): output probability, store it * feat(Core): added caching to select_features() and load_data() * fix(Dependencies): added diskcache * fix(Training): error when creating results DF * feat(Models): added xgboost, fixed tests * refactor(Cache): moved hashing to a separate function, created wrapper functions to separate business logic and caching * fix(Tests): new syntax * fix(Model): XGboost can't handle -1 class, so we'll use the deprecated label_encoder fornow * fix(Model): XGBoost config * feat(Cache): add run_clear_cache script * fix(Pipeline) accidentally re-instatiating all_predictions for each asset
14 lines
443 B
Python
14 lines
443 B
Python
from typing import Callable, Union, Literal
|
|
import pandas as pd
|
|
|
|
Period = int
|
|
IsLogReturn = bool
|
|
FeatureExtractor = Callable[[pd.DataFrame, Period, IsLogReturn], Union[pd.DataFrame, pd.Series]]
|
|
Name = str
|
|
FeatureExtractorConfig = tuple[Name, FeatureExtractor, list[Period]]
|
|
Path = str
|
|
FileName = str
|
|
DataSource = list[tuple[Path, FileName]]
|
|
DataCollection = list[DataSource]
|
|
|
|
ScalerTypes = Literal['normalize', 'minmax', 'standardize', 'none'] |