mirror of
https://github.com/webclinic017/drift.git
synced 2026-07-28 11:17:47 +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
43 lines
1.2 KiB
Python
43 lines
1.2 KiB
Python
from __future__ import annotations
|
|
from transformations.base import Transformation
|
|
from typing import Optional
|
|
from copy import deepcopy
|
|
from sklearn.feature_selection import RFE
|
|
import pandas as pd
|
|
from models.sklearn import SKLearnModel
|
|
|
|
class RFETransformation(Transformation):
|
|
|
|
rfe: RFE
|
|
n_feature_to_select: int
|
|
|
|
def __init__(self, n_feature_to_select: int, model: SKLearnModel, step = 0.1):
|
|
self.n_feature_to_keep = n_feature_to_select
|
|
self.model = model
|
|
self.rfe = RFE(model, n_features_to_select= n_feature_to_select, step=step)
|
|
|
|
def fit(self, X: pd.DataFrame, y: Optional[pd.Series] = None) -> None:
|
|
if self.rfe is None: return
|
|
self.rfe.fit(X, y)
|
|
|
|
def fit_transform(self, X: pd.DataFrame, y: Optional[pd.Series] = None) -> pd.DataFrame:
|
|
if self.rfe is None: return X
|
|
self.fit(X, y)
|
|
return self.transform(X)
|
|
|
|
def transform(self, X: pd.DataFrame) -> pd.DataFrame:
|
|
if self.rfe is None: return X
|
|
return pd.DataFrame(X[X.columns[self.rfe.support_]], index= X.index)
|
|
|
|
def clone(self) -> RFETransformation:
|
|
return deepcopy(self)
|
|
|
|
def get_name(self) -> str:
|
|
return "RFE"
|
|
|
|
|
|
|
|
|
|
|
|
|