gavindiaz/drift
1
0
Fork 0
mirror of https://github.com/webclinic017/drift.git synced 2026-08-21 14:58:11 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat(Inference): pipeline wired up (#171)

Browse Source 
* feat: Basic pipeline extended.

* feat: Added conversion of model list to existing structure (model_name, model_in_time). Fixed loading of previous models and dicts.

* fix: Had an unfinished function.

* fix: Inference wasn't getting model_over_time. Now transformations are not getting it either yet.

Co-authored-by: Daniel Szemerey <szemereydaniel@gmail.com>
This commit is contained in:
Mark Aron Szulyovszky
2022-01-14 10:34:28 +01:00
committed by GitHub
co-authored by Daniel Szemerey
parent 4aefba33ea
commit 797d45d036
9 changed files with 89 additions and 77 deletions
Download Patch File Download Diff File Expand all files Collapse all files
run_pipeline.py
+4 -4
View File
@@ -20,14 +20,14 @@ import ray
ray.init()
def run_pipeline(project_name:str, with_wandb: bool, sweep: bool, get_config: Callable) -> tuple[list[Reporting.Asset], dict, dict, pd.DataFrame, pd.DataFrame, pd.DataFrame]:
def run_pipeline(project_name:str, with_wandb: bool, sweep: bool, get_config: Callable) -> tuple[list[Reporting.Asset], dict, dict, dict, pd.DataFrame, pd.DataFrame, pd.DataFrame]:
wandb, model_config, training_config, data_config = __setup_config(project_name, with_wandb, sweep, get_config)
reporting = __run_training(model_config, training_config, data_config)
results, all_predictions, all_probabilities, all_models_all_assets = reporting.get_results()
report_results(results, all_predictions, model_config, wandb, sweep, project_name)
save_models(all_models_all_assets, data_config, training_config)
save_models(all_models_all_assets, data_config, training_config, model_config)
return all_models_all_assets, data_config, training_config, results, all_predictions, all_probabilities
return all_models_all_assets, data_config, training_config, model_config, results, all_predictions, all_probabilities
def __setup_config(project_name:str, with_wandb: bool, sweep: bool, get_config: Callable) -> tuple[Optional[object], dict, dict, dict]:
@@ -55,7 +55,7 @@ def __run_training(model_config:dict, training_config:dict, data_config:dict):
# 1. Load data, check for validity and process data (feature selection, dimensionality reduction, etc.)
X, y, target_returns = load_data(**configs['data_config'])
if check_data(X, y, training_config) is False: continue
if check_data(X, y, configs['training_config']) is False: continue
X, original_X = process_data(X, y, configs)
# 2. Train a Primary model with optional metalabeling for each asset