mirror of
https://github.com/webclinic017/drift.git
synced 2026-07-28 11:17:47 +00:00
Mark Aron Szulyovszky
6b26643ece
* feat(Transformations): removed feature-selection pre-processing step completely * fix(Core): removed unnecessary `original_X` * fix(Transformations): use the X_expanding_window to transform subsequent data * fix(RFE): should check for model correctly * fix(Config): only re-train the model every 40 timestamp * fix(MetaLabeling): pass in the correct X to meta-labeling step * fix(Transformation): PCA should at least keep as many features as sliding_window_size * feat(Transformations): cache transformations across the same asset * fix(Tests): missing preloaded_transformations arg * chore(Config): got rid of unnecessary 'classification_models' and 'regression_models' dictionary keys
47 lines
1.5 KiB
Python
47 lines
1.5 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.base import Model
|
|
from models.model_map import default_feature_selector_classification
|
|
|
|
class RFETransformation(Transformation):
|
|
|
|
rfe: RFE
|
|
n_feature_to_select: int
|
|
|
|
def __init__(self, n_feature_to_select: int, model: Model, step = 0.1):
|
|
self.n_feature_to_keep = n_feature_to_select
|
|
self.model = model
|
|
if hasattr(self.model, 'model') == False: return
|
|
if hasattr(self.model.model, 'feature_importances_') == False and hasattr(self.model.model, 'coef_') == False:
|
|
model = default_feature_selector_classification
|
|
self.rfe = RFE(model.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"
|
|
|
|
|
|
|
|
|
|
|
|
|