gavindiaz/drift
1
0
Fork 0
mirror of https://github.com/webclinic017/drift.git synced 2026-08-20 22:38:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat(Data): add option to predict 3 classes (#79)

Browse Source 
* feat(Data): add option to predict 3 classes

* feat(Evaluation): added ability to evaluate 3 class predictions

* chore(Config): set sensible config for regression models

* feat(Data): added option to use balanced or imbalanced three-class data

* feat(Evaluate): correctly track "no_of_samples" now that we have three classes

* chore(Sweep): remove probably not useful scaler values from sweep
This commit is contained in:
Mark Aron Szulyovszky
2021-12-23 13:24:56 +01:00
committed by GitHub
parent b6cd6b14fe
commit 95573eb9dd
8 changed files with 134 additions and 96 deletions
Download Patch File Download Diff File Expand all files Collapse all files
run_pipeline.py
+5 -8
View File
@@ -46,9 +46,7 @@ def pipeline(project_name:str, wandb, sweep:bool, model_config:dict, training_co
sliding_window_size = training_config['sliding_window_size'],
retrain_every = training_config['retrain_every'],
scaler = training_config['scaler'],
wandb = wandb,
project_name=project_name,
sweep=sweep
no_of_classes = data_config['no_of_classes']
)
results = pd.concat([results, current_result], axis=1)
all_predictions = pd.concat([all_predictions, current_predictions], axis=1)
@@ -71,9 +69,7 @@ def pipeline(project_name:str, wandb, sweep:bool, model_config:dict, training_co
sliding_window_size = training_config['sliding_window_size'],
retrain_every = training_config['retrain_every'],
scaler = training_config['scaler'],
wandb = wandb,
project_name=project_name,
sweep=sweep
no_of_classes = data_config['no_of_classes']
)
results = pd.concat([results, ensemble_result], axis=1)
@@ -86,8 +82,9 @@ def pipeline(project_name:str, wandb, sweep:bool, model_config:dict, training_co
level1_columns = results[[column for column in results.columns if 'Ensemble' not in column]]
ensemble_columns = results[[column for column in results.columns if 'Ensemble' in column]]
print("Mean Sharpe ratio for Level-1 models: ", level1_columns.loc['sharpe'].mean())
print("Mean Sharpe ratio for Level-2 (Ensemble) models: ", ensemble_columns.loc['sharpe'].mean())
print("Mean no of samples: ", results.loc['no_of_samples'].mean())
print("Mean Sharpe ratio for Level-1 models: ", round(level1_columns.loc['sharpe'].mean(), 3))
print("Mean Sharpe ratio for Level-2 (Ensemble) models: ", round(ensemble_columns.loc['sharpe'].mean(), 3))
if sweep:
if wandb.run is not None: