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
36 lines
1.0 KiB
Python
36 lines
1.0 KiB
Python
from __future__ import annotations
|
|
from typing import Literal
|
|
from models.base import Model
|
|
import numpy as np
|
|
from sklearn.base import clone
|
|
|
|
|
|
class SKLearnModel(Model):
|
|
|
|
method: Literal["regression", "classification"]
|
|
data_transformation = 'transformed'
|
|
only_column = None
|
|
model_type = 'ml'
|
|
predict_window_size = 'single_timestamp'
|
|
|
|
def __init__(self, model, method: Literal['regression', 'classification']):
|
|
self.model = model
|
|
self.method = method
|
|
|
|
def fit(self, X: np.ndarray, y: np.ndarray) -> None:
|
|
self.model.fit(X, y)
|
|
|
|
def predict(self, X) -> tuple[float, np.ndarray]:
|
|
pred = self.model.predict(X).item()
|
|
probability = self.model.predict_proba(X).squeeze()
|
|
return (pred, probability)
|
|
|
|
def clone(self) -> SKLearnModel:
|
|
return SKLearnModel(clone(self.model), self.method)
|
|
|
|
def get_name(self) -> str:
|
|
return self.model.__class__.__name__
|
|
|
|
def initialize_network(self, input_dim:int, output_dim:int):
|
|
pass
|
|
|