gavindiaz/drift
1
0
Fork 0
mirror of https://github.com/webclinic017/drift.git synced 2026-08-19 05:48:09 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(Selection): dynamic step size for feature selection (#123)

Browse Source 
* fix(Selection): dynamic step size for feature selection

* refactor(Pipeline): type definition

* chore(Cache): renamed clear_cache script

* feat(Config): dynamic feature selection is now a toggleable feature

* fix(Training): not passing in necessary parameter
This commit is contained in:
Mark Aron Szulyovszky
2022-01-07 18:45:03 +01:00
committed by GitHub
parent 34105f7ca1
commit 57f63f1e93
5 changed files with 12 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files
run_pipeline.py
+3 -2
View File
@@ -12,6 +12,7 @@ from feature_selection.dim_reduction import reduce_dimensionality
from training.meta_labeling import run_meta_labeling_training
from training.averaged import average_and_evaluate_predictions
from reporting.reporting import report_results
from typing import Callable, Optional
import ray
ray.init()
@@ -22,7 +23,7 @@ def run_pipeline(project_name:str, with_wandb: bool, sweep: bool, get_config:obj
report_results(results, all_predictions, model_config, wandb, sweep, project_name)
def __setup_pipeline(project_name:str, with_wandb: bool, sweep: bool, get_config:object):
def __setup_pipeline(project_name:str, with_wandb: bool, sweep: bool, get_config: Callable) -> tuple[Optional[object], dict, dict, dict]:
model_config, training_config, data_config = get_config()
wandb = None
if with_wandb:
@@ -66,7 +67,7 @@ def __run_training(model_config:dict, training_config:dict, data_config:dict):
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['level_1_models'][0][1], n_features_to_select = training_config['n_features_to_select'], backup_model = backup_model, scaling = training_config['scaler'], data_config_hash = hash_data_config(data_params))
X = select_features(X = X, y = y, model = model_config['level_1_models'][0][1], n_features_to_select = training_config['n_features_to_select'], backup_model = backup_model, scaling = training_config['scaler'], dynamic_feature_selection = training_config['dynamic_feature_selection'], data_config_hash = hash_data_config(data_params))
# 3. Train Level-1 models
current_result, current_predictions, current_probabilities, all_models_for_single_asset = run_single_asset_trainig(