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
13 lines
388 B
Python
13 lines
388 B
Python
import pandas as pd
|
|
|
|
from utils.helpers import has_enough_samples_to_train
|
|
import warnings
|
|
|
|
def check_data(X:pd.DataFrame, y:pd.Series, training_config:dict):
|
|
""" Returns True if data is valid, else returns False."""
|
|
|
|
if has_enough_samples_to_train(X, y, training_config) == False:
|
|
warnings.warn("Not enough samples to train")
|
|
return False
|
|
|
|
return True |