mirror of
https://github.com/webclinic017/drift.git
synced 2026-07-28 11:17:47 +00:00
Mark Aron Szulyovszky
3eb3ea94e3
* refactor(Training): added InferenceResult & TrainedModel types * refactor(Pipeline): introduced TrainingOutcome, BetSizingWithMetaOutcome, etc. * fix(Pipeline): getting it to compile * refactor(WalkForward): separate preprocessing step * feat(Pipeline): separate out transformations processing step * refactor(Pipeline): use the Directional model terminology, put bet_sizing into pipeline instead of hiding it in a step * refactor(WalkForward): moved functions to separate folder * fix(WalkForward): use sparse array to store models, process transformations in parallel (lot faster) * fix(Tests): and evaluation * fix(Tests): for realz * fix(Inference): preloading everything now, renamed primary models to directional models * fix(BetSizing): was running transformations on the wrong data, oops * fix(BetSizing): concatenated on the wrong axis accidentally * fix(Reporting): able to use the new Stats type * fix(BetSizing): renamed int column names * fix(Portfolio): name the column properly * fix(Reporting): rename the correct Series, lol * fix(Inference): walk_forwad_inference() can deal with models not being aligned with the starting index * fix(WalkForward): accidentally using the wrong index * fix(WalkForward): use the correct indicies to fetch last model/transformations * fix(CI): changed the name of the results
85 lines
3.3 KiB
Python
85 lines
3.3 KiB
Python
import pandas as pd
|
|
from typing import Literal, Optional
|
|
from training.walk_forward import walk_forward_train, walk_forward_inference
|
|
from utils.evaluate import evaluate_predictions
|
|
from models.base import Model
|
|
from .types import ModelOverTime, TransformationsOverTime, TrainingOutcome
|
|
|
|
def train_models(
|
|
ticker_to_predict: str,
|
|
X: pd.DataFrame,
|
|
y: pd.Series,
|
|
forward_returns: pd.Series,
|
|
models: list[Model],
|
|
expanding_window: bool,
|
|
sliding_window_size: int,
|
|
retrain_every: int,
|
|
from_index: Optional[pd.Timestamp],
|
|
no_of_classes: Literal['two', 'three-balanced', 'three-imbalanced'],
|
|
level: str,
|
|
print_results: bool,
|
|
transformations_over_time: TransformationsOverTime,
|
|
models_over_time: Optional[list[ModelOverTime]]
|
|
) -> list[TrainingOutcome]:
|
|
return [train_model(ticker_to_predict, X, y, forward_returns, model, expanding_window, sliding_window_size, retrain_every, from_index, no_of_classes, level, print_results, transformations_over_time, models_over_time[index] if models_over_time else None) for index, model in enumerate(models)]
|
|
|
|
|
|
def train_model(
|
|
ticker_to_predict: str,
|
|
X: pd.DataFrame,
|
|
y: pd.Series,
|
|
forward_returns: pd.Series,
|
|
model: Model,
|
|
expanding_window: bool,
|
|
sliding_window_size: int,
|
|
retrain_every: int,
|
|
from_index: Optional[pd.Timestamp],
|
|
no_of_classes: Literal['two', 'three-balanced', 'three-imbalanced'],
|
|
level: str,
|
|
print_results: bool,
|
|
transformations_over_time: TransformationsOverTime,
|
|
model_over_time: Optional[ModelOverTime]
|
|
) -> TrainingOutcome:
|
|
|
|
if model_over_time is None:
|
|
print("Train model")
|
|
model_over_time = walk_forward_train(
|
|
model = model,
|
|
X = X,
|
|
y = y,
|
|
forward_returns = forward_returns,
|
|
expanding_window = expanding_window,
|
|
window_size = sliding_window_size,
|
|
retrain_every = retrain_every,
|
|
from_index = from_index,
|
|
transformations_over_time = transformations_over_time,
|
|
)
|
|
|
|
levelname = ("_" + level) if level == 'meta' else ""
|
|
if model_over_time is None:
|
|
model_id = "model_" + model.name + "_" + ticker_to_predict + levelname
|
|
else:
|
|
model_id = model_over_time.name
|
|
|
|
predictions, probabilities = walk_forward_inference(
|
|
model_name = model_id,
|
|
model_over_time= model_over_time,
|
|
transformations_over_time = transformations_over_time,
|
|
X = X,
|
|
expanding_window = expanding_window,
|
|
window_size = sliding_window_size,
|
|
retrain_every = retrain_every,
|
|
from_index = from_index,
|
|
)
|
|
|
|
assert len(predictions) == len(y)
|
|
stats = evaluate_predictions(
|
|
forward_returns = forward_returns,
|
|
y_pred = predictions,
|
|
y_true = y,
|
|
no_of_classes=no_of_classes,
|
|
print_results = print_results,
|
|
discretize=True
|
|
)
|
|
|
|
return TrainingOutcome(model_id, predictions, probabilities, stats, model_over_time) |