mirror of
https://github.com/webclinic017/drift.git
synced 2026-07-27 18:57:55 +00:00
Daniel Szemerey
516c8bcc87
* fix, feat: Fixed inference processing data. Add transformation attribute. * feat: Added transformations step, refractored the loop to make more sense (divided the train and inference loop). * feat: Truncated models over time and transformations over time. Fixed some typing aswell. * fix: Fixed a number of out of array problems. * feat: Inference now works! * fix(Steps): runtime error not checking for None * fix(Steps): preloaded transformers are not optional anymore, sped up training by temporary increasing the retrain_every * fix(CI): disable ray memory monitoring * refactor(Inference): removed truncate_models and replaced it with filling X with NaN until inference should start * feat(Inference): added index_from parameter * fix(Tests): walk_forward test * refactor(Pipeline): only predict one asset * refactor(Inference): removed select_models step, inference code moved to run_inference.py so it matches convention (similar to run_pipeline.py) * fix(Evaluation): adjust transaction costs * fix(Config): adjusted retrain_every Co-authored-by: Daniel Szemerey <szemereydaniel@gmail.com> Co-authored-by: Mark Aron Szulyovszky <mark.szulyovszky@gmail.com>
47 lines
2.3 KiB
Python
47 lines
2.3 KiB
Python
from data_loader.load_data import load_data
|
|
from data_loader.process_data import check_data
|
|
from reporting.saving import load_models
|
|
|
|
from run_pipeline import run_pipeline
|
|
from config.config import get_dev_config, get_default_ensemble_config, get_lightweight_ensemble_config
|
|
|
|
from typing import Callable, Optional
|
|
from reporting.types import Reporting
|
|
from training.training_steps import primary_step, secondary_step
|
|
import warnings
|
|
|
|
def run_inference(preload_models:bool, get_config:Callable):
|
|
if preload_models:
|
|
all_models, data_config, training_config, model_config = load_models(None)
|
|
else:
|
|
all_models, data_config, training_config, model_config, _, _, _ = run_pipeline(project_name='price-prediction', with_wandb = False, sweep = False, get_config=get_config)
|
|
|
|
configs = dict(model_config=model_config, training_config=training_config, data_config=data_config)
|
|
__inference(configs, all_models.primary, all_models.secondary)
|
|
|
|
|
|
def __inference(configs: dict, primary_models: Optional[Reporting.Training_Step], secondary_models: Optional[Reporting.Training_Step]):
|
|
reporting = Reporting()
|
|
asset = configs['data_config']['target_asset']
|
|
|
|
# 1. Load data, check for validity and process data
|
|
X, y, target_returns = load_data(**configs['data_config'])
|
|
assert check_data(X, y, configs['training_config']) == True, "Data is not valid. Cancelling Inference."
|
|
|
|
inference_from = X.index.stop - 2
|
|
# 2. Train a Primary model with optional metalabeling for each asset
|
|
training_step_primary, current_predictions = primary_step(X, y, target_returns, configs, reporting, from_index = inference_from, preloaded_training_step = primary_models)
|
|
|
|
# 3. Train an Ensemble model with optional metalabeling for each asset
|
|
if secondary_models is not None:
|
|
warnings.warn("Secondary models are not specified.")
|
|
training_step_secondary = secondary_step(X, y, current_predictions, target_returns, configs, reporting, from_index = inference_from, preloaded_training_step = secondary_models)
|
|
|
|
# 4. Save the models
|
|
reporting.asset = Reporting.Asset(ticker=asset, primary=training_step_primary, secondary=training_step_secondary)
|
|
|
|
return reporting
|
|
|
|
|
|
if __name__ == '__main__':
|
|
run_inference(preload_models=True, get_config=get_lightweight_ensemble_config) |