mirror of
https://github.com/webclinic017/drift.git
synced 2026-07-29 03:37:45 +00:00
Mark Aron Szulyovszky
9488e92597
* feature(MetaLabeling): added hacky prototype * fix(MetaLabeling): drop index until first valid X & y * fix(MetaLabeling): transform both X & y before feature selection * fix(MetaLabeling): got feature selection to work * fix(MetaLabeling): correct values for meta_y * feat(MetaLabeling): created predictions multiplied by bet sizes * feat(Pipeline): print out averaged result * fix(Evaluation): correctly deal with non-discretized data * fix(Pipeline): use the right column names * refactor(Pipeline): move out meta-labeling * refactor(Pipeline): complete refactoring * feat(CI): post results to PR * fix(Pipeline): use the correct filename * chore(Config): removed now redundant feature_selection flag * feat(Models): added SVC * fix(Pipeline): accidentally switched two return values * feat(Sweep): prepared sweep_meta.yaml, moved report_results() into a separate file * fix(Pipeline): wrong function name * fix(Sweep): yaml + run_sweep * fix(Sweep): typo in name * fix(Reporting): only save averaged results * feat(MetaLabeling): use optional meta-labeling step for every lvl1 models, before averaging * feat(Reporting): print out sharpe improvement in meta-labeling step * fix(Sweep): adjusted config, defaulted to good defaults * fix(Sweep): adjusted sweep
25 lines
1010 B
Python
25 lines
1010 B
Python
|
|
import pandas as pd
|
|
from utils.evaluate import evaluate_predictions
|
|
|
|
def average_and_evaluate_predictions(predictions: pd.DataFrame, y: pd.Series, target_returns: pd.Series, data_config: dict) -> tuple[pd.Series, pd.DataFrame]:
|
|
averaged_predictions = predictions.mean(axis = 1)
|
|
non_discretized_result = evaluate_predictions(
|
|
model_name = 'Averaged - Non-discrete',
|
|
target_returns = target_returns,
|
|
y_pred = averaged_predictions,
|
|
y_true = y,
|
|
method = 'classification',
|
|
no_of_classes = data_config['no_of_classes'],
|
|
discretize=False
|
|
)
|
|
discretized_result = evaluate_predictions(
|
|
model_name = 'Averaged - Discrete',
|
|
target_returns = target_returns,
|
|
y_pred = averaged_predictions,
|
|
y_true = y,
|
|
method = 'classification',
|
|
no_of_classes = data_config['no_of_classes'],
|
|
discretize=True
|
|
)
|
|
return averaged_predictions, pd.concat([non_discretized_result, discretized_result], axis = 1) |