mirror of
https://github.com/webclinic017/drift.git
synced 2026-07-29 03:37:45 +00:00
Mark Aron Szulyovszky
b1c04afb13
* refactor(Naming): use `primary_models` & `meta_labeling_models` * refactor(Naming): using primary * meta_labeling across config and in pipeline * feat(Pipeline): added back Ensemble models * fix(Pipeline): compiler error * fix(Config): typo * chore(Pipeline): removed unused averaging step * revert the changes in discretizing * chore(Pipeline): remove sharpe improvement logging * fix(Pipeline): ensemble predictions should be a pd.Series instead of a DataFrame * fix(Pipeline): discard unnecessary ensemble_probabilities * fix(Pipeline): fixes regarding various meta-labeling ensemble bugs * fix(Reporting): use the new naming convention * fix(Reporting): use the right variable * feat(Sweep): new sweep for ensemble models * fix(Sweep): config reference * fix(Config): simplified dev config * fix(Models): use the faster LR model * fix(Models): use LGBM in the meta-labeling model for speed * fix(Selection): always use the first model for feature selection, commented out caching from select_features() as it's close to redundant in terms of speed
67 lines
2.7 KiB
Python
67 lines
2.7 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 train_primary_model(
|
|
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: str,
|
|
print_results: bool
|
|
) -> tuple[pd.DataFrame, pd.DataFrame, pd.DataFrame, dict]:
|
|
|
|
scaler = get_scaler(scaler)
|
|
|
|
results = pd.DataFrame()
|
|
all_models_single_asset = dict()
|
|
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,
|
|
print_results = print_results,
|
|
discretize=True
|
|
)
|
|
column_name = "model_" + ticker_to_predict + "_" + model_name + "_" + level
|
|
results[column_name] = result
|
|
all_models_single_asset[model_name] = model_over_time
|
|
# 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 + "_" + level
|
|
probs.columns = [probs_column_name + "_" + c for c in probs.columns]
|
|
probabilities = pd.concat([probabilities, probs], axis=1)
|
|
|
|
|
|
return results, predictions, probabilities, all_models_single_asset |