mirror of
https://github.com/webclinic017/drift.git
synced 2026-08-01 21:27:46 +00:00
Daniel Szemerey
55f083638f
* feat: Basic scaffolding up for inference process after training. * feat: Saving and loading models works. Inference works nearly. * feat: Added inference pipeline. * feat: Saving model now accoring to date and time; loading models now selects from latest file. Fixed the creation of dictionary of models. * feat: Added lightweight asset config, but full pipeline. * feat: Added new naming for dictionary. * fix: Fixed dictionary naming convention. * fix: Fixed naming again, now the model structure is good * fix: Changed the output path and the return values from run_pipeline. * feat: Added function to make sure folder exists for output models. Co-authored-by: Daniel Szemerey <szemereydaniel@gmail.com>
71 lines
2.9 KiB
Python
71 lines
2.9 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
|
|
)
|
|
levelname=("_" + level) if level=='metalabeling' else ""
|
|
column_name = "model_" + model_name + "_" + ticker_to_predict + levelname
|
|
results[column_name] = result
|
|
all_models_single_asset[column_name]=dict()
|
|
all_models_single_asset[column_name][level] = model_over_time.tolist()
|
|
# all_models_single_asset[model_name]=dict()
|
|
# all_models_single_asset[model_name][level] = model_over_time.tolist()
|
|
# 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 |