mirror of
https://github.com/webclinic017/drift.git
synced 2026-07-28 11:17:47 +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>
24 lines
951 B
Python
24 lines
951 B
Python
from run_pipeline import run_pipeline
|
|
from config.config import get_default_ensemble_config, get_dev_config
|
|
import pandas as pd
|
|
|
|
all_results = []
|
|
all_predictions = []
|
|
for index in range(6):
|
|
_, _, _, results_1, predictions_1, _ = run_pipeline(project_name='price-prediction', with_wandb = False, sweep = False, get_config= get_default_ensemble_config)
|
|
all_results.append(results_1)
|
|
all_predictions.append(predictions_1)
|
|
|
|
correlations = pd.Series()
|
|
|
|
for asset_name in [c for c in all_predictions[0].columns if 'ensemble' in c]:
|
|
|
|
predictions_for_asset = pd.concat([preds[asset_name] for preds in all_predictions], axis=1)
|
|
correlations[asset_name] = predictions_for_asset.corr().mean()[0]
|
|
print("Correlation for asset ", asset_name, ": ", correlations[asset_name])
|
|
|
|
correlations["Overall"] = correlations.mean()
|
|
print("Average correlation across all assests: ", correlations.mean())
|
|
|
|
correlations.to_csv("output/correlations.csv")
|