mirror of
https://github.com/webclinic017/drift.git
synced 2026-07-28 03:08:01 +00:00
Daniel Szemerey
31dc847be1
* feat: Added optional import of models. * fix: Models weren't wrapped into abstract class, fixed it. * chore: Deleted leftover comments. * fix: Same merge commit as on remote. * fix: System wasn't putting in RF because there was no differentiation between RF as regressor and RF as classificator. * fix(Models): use the XGBoostModel wrapper Co-authored-by: Daniel Szemerey <szemereydaniel@gmail.com> Co-authored-by: Mark Aron Szulyovszky <mark.szulyovszky@gmail.com>
36 lines
1.4 KiB
Python
36 lines
1.4 KiB
Python
import pandas as pd
|
|
from operator import itemgetter
|
|
|
|
from utils.helpers import has_enough_samples_to_train
|
|
from feature_selection.dim_reduction import reduce_dimensionality
|
|
from models.model_map import get_model_map
|
|
from feature_selection.feature_selection import select_features
|
|
import warnings
|
|
|
|
|
|
|
|
|
|
|
|
def process_data(X:pd.DataFrame, y:pd.Series, configs: dict) -> tuple[pd.DataFrame,pd.DataFrame]:
|
|
|
|
model_config, training_config, data_config = itemgetter('model_config', 'training_config', 'data_config')(configs)
|
|
_, _, _, default_feature_selector_regression, default_feature_selector_classification = get_model_map(model_config)
|
|
|
|
original_X = X.copy()
|
|
|
|
# 2b. Feature Selection
|
|
print("Feature Selection started")
|
|
# TODO: this needs to be done per model!
|
|
backup_model = default_feature_selector_regression if data_config['method'] == 'regression' else default_feature_selector_classification
|
|
X = select_features(X = X, y = y, model = model_config['primary_models'][0][1], n_features_to_select = training_config['n_features_to_select'], backup_model = backup_model, scaling = training_config['scaler'])
|
|
|
|
return X, original_X
|
|
|
|
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 |