mirror of
https://github.com/webclinic017/drift.git
synced 2026-08-01 21:27:46 +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
63 lines
2.5 KiB
Python
63 lines
2.5 KiB
Python
import pandas as pd
|
|
from typing import Literal
|
|
from training.walk_forward import walk_forward_train_test
|
|
from utils.evaluate import evaluate_predictions
|
|
from models.base import Model
|
|
from utils.scaler import get_scaler
|
|
from utils.types import ScalerTypes
|
|
|
|
def run_single_asset_trainig(
|
|
ticker_to_predict: str,
|
|
original_X: pd.DataFrame,
|
|
X: pd.DataFrame,
|
|
y: pd.Series,
|
|
target_returns: pd.Series,
|
|
models: list[tuple[str, Model]],
|
|
method: Literal['regression', 'classification'],
|
|
expanding_window: bool,
|
|
sliding_window_size: int,
|
|
retrain_every: int,
|
|
scaler: ScalerTypes,
|
|
no_of_classes: Literal['two', 'three-balanced', 'three-imbalanced'],
|
|
level: int
|
|
) -> tuple[pd.DataFrame, pd.DataFrame, pd.DataFrame]:
|
|
|
|
|
|
scaler = get_scaler(scaler)
|
|
|
|
results = pd.DataFrame()
|
|
predictions = pd.DataFrame(index=y.index)
|
|
probabilities = pd.DataFrame(index=y.index)
|
|
|
|
for model_name, model in models:
|
|
model_over_time, preds, probs = walk_forward_train_test(
|
|
model_name=model_name,
|
|
model = model,
|
|
X = X if model.feature_selection == 'on' else original_X,
|
|
y = y,
|
|
target_returns = target_returns,
|
|
expanding_window = expanding_window,
|
|
window_size = sliding_window_size,
|
|
retrain_every = retrain_every,
|
|
scaler = scaler
|
|
)
|
|
assert len(preds) == len(y)
|
|
result = evaluate_predictions(
|
|
model_name = model_name,
|
|
target_returns = target_returns,
|
|
y_pred = preds,
|
|
y_true = y,
|
|
method = method,
|
|
no_of_classes=no_of_classes,
|
|
discretize=True
|
|
)
|
|
column_name = "model_" + ticker_to_predict + "_" + model_name + "_lvl" + str(level)
|
|
results[column_name] = result
|
|
# column names for model outputs should be different, so we can differentiate between original data and model predictions later, where necessary
|
|
predictions[column_name] = preds
|
|
probs_column_name = "probs_" + ticker_to_predict + "_" + model_name + "_lvl" + str(level)
|
|
probs.columns = [probs_column_name + "_" + c for c in probs.columns]
|
|
probabilities = pd.concat([probabilities, probs], axis=1)
|
|
|
|
|
|
return results, predictions, probabilities |