mirror of
https://github.com/webclinic017/drift.git
synced 2026-07-28 03:08:01 +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
40 lines
1.2 KiB
Python
40 lines
1.2 KiB
Python
from __future__ import annotations
|
|
from transformations.base import Transformation
|
|
from typing import Optional
|
|
from copy import deepcopy
|
|
from sklearn.decomposition import PCA
|
|
import pandas as pd
|
|
|
|
class PCATransformation(Transformation):
|
|
|
|
pca: PCA
|
|
|
|
def __init__(self, ratio_components_to_keep: float, sliding_window_size: int):
|
|
self.ratio_components_to_keep = ratio_components_to_keep
|
|
self.sliding_window_size = sliding_window_size
|
|
|
|
def fit(self, X: pd.DataFrame, y: Optional[pd.Series] = None) -> None:
|
|
self.pca = PCA(n_components = min(int(len(X.columns) * self.ratio_components_to_keep), self.sliding_window_size))
|
|
self.pca.fit(X, y)
|
|
|
|
def fit_transform(self, X: pd.DataFrame, y: Optional[pd.Series] = None) -> pd.DataFrame:
|
|
self.fit(X, y)
|
|
return self.transform(X)
|
|
|
|
def transform(self, X: pd.DataFrame) -> pd.DataFrame:
|
|
X = pd.DataFrame(self.pca.transform(X), index = X.index)
|
|
X.columns = ['PCA_' + str(i) for i in range(1, len(X.columns)+1)]
|
|
return X
|
|
|
|
def clone(self) -> PCATransformation:
|
|
return deepcopy(self)
|
|
|
|
def get_name(self) -> str:
|
|
return "PCA"
|
|
|
|
|
|
|
|
|
|
|
|
|