mirror of
https://github.com/webclinic017/drift.git
synced 2026-08-02 21:57:46 +00:00
Mark Aron Szulyovszky
1cd0119589
* fix(FeatureExtractor): apply log to transform some series to normality * feat(DataLoader): add ability of not returning returns when they're not needed (exogenous data), applied log to certain features * feat(FeatureExtractors): added standard scaling for exogenous data * feat(FeatureSelection): scale data with the passed in scaler before doing feature-selection * fix(Config): sweep config * feat(Models): output probability, store it * feat(Core): added caching to select_features() and load_data() * fix(Dependencies): added diskcache * fix(Training): error when creating results DF * feat(Models): added xgboost, fixed tests * refactor(Cache): moved hashing to a separate function, created wrapper functions to separate business logic and caching * fix(Tests): new syntax * fix(Model): XGboost can't handle -1 class, so we'll use the deprecated label_encoder fornow * fix(Model): XGBoost config * feat(Cache): add run_clear_cache script * fix(Pipeline) accidentally re-instatiating all_predictions for each asset
62 lines
2.5 KiB
Python
62 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
|
|
)
|
|
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 |