gavindiaz/drift
1
0
Fork 0
mirror of https://github.com/webclinic017/drift.git synced 2026-08-20 06:18:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat(Inference): Models are collected and structured. (#120)

Browse Source 
* feat: Added collection of models into a dictionary.

* feat: Models are now saved in a structured way into a dictionary.

* Rename run_model_test.py to run_model_dev.py

* fix(Pipeline): missing variable statement

Co-authored-by: Mark Aron Szulyovszky <mark.szulyovszky@gmail.com>
This commit is contained in:
Daniel Szemerey
2022-01-07 15:33:50 +01:00
committed by GitHub
co-authored by Mark Aron Szulyovszky
parent c8211e90ff
commit 78a7fe028e
6 changed files with 36 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files
run_pipeline.py
+20 -13
View File
@@ -16,14 +16,14 @@ import ray
ray.init()
def run_pipeline(project_name:str, with_wandb: bool, sweep: bool):
wandb, model_config, training_config, data_config = __setup_pipeline(project_name, with_wandb, sweep)
def run_pipeline(project_name:str, with_wandb: bool, sweep: bool, get_config:object):
wandb, model_config, training_config, data_config = __setup_pipeline(project_name, with_wandb, sweep, get_config)
results, all_predictions, all_probabilities = __run_training(model_config, training_config, data_config)
report_results(results, all_predictions, model_config, wandb, sweep, project_name)
def __setup_pipeline(project_name:str, with_wandb: bool, sweep: bool):
model_config, training_config, data_config = get_default_level_2_daily_config()
def __setup_pipeline(project_name:str, with_wandb: bool, sweep: bool, get_config:object):
model_config, training_config, data_config = get_config()
wandb = None
if with_wandb:
wandb = launch_wandb(project_name=project_name, default_config=dict(**model_config, **training_config, **data_config), sweep=sweep)
@@ -37,6 +37,7 @@ def __run_training(model_config:dict, training_config:dict, data_config:dict):
results = pd.DataFrame()
all_predictions = pd.DataFrame()
all_probabilities = pd.DataFrame()
all_models_for_all_assets = dict()
validate_config(model_config, training_config, data_config)
for asset in data_config['assets']:
@@ -68,7 +69,7 @@ def __run_training(model_config:dict, training_config:dict, data_config:dict):
X = select_features(X = X, y = y, model = model_config['level_1_models'][0][1], n_features_to_select = training_config['n_features_to_select'], backup_model = backup_model, scaling = training_config['scaler'], data_config_hash = hash_data_config(data_params))
# 3. Train Level-1 models
current_result, current_predictions, current_probabilities = run_single_asset_trainig(
current_result, current_predictions, current_probabilities, all_models_for_single_asset = run_single_asset_trainig(
ticker_to_predict = asset[1],
original_X = original_X,
X = X,
@@ -84,12 +85,16 @@ def __run_training(model_config:dict, training_config:dict, data_config:dict):
level = 1
)
all_models_for_all_assets[asset[1]] = dict(
name=asset[1],
models=all_models_for_single_asset)
# 4. Train a Meta-Labeling model for each Level-1 model and replace its predictions with the meta-labeling predictions
if training_config['meta_labeling_lvl_1'] == True:
for column in current_result.columns:
lvl1_model_predictions = current_predictions[column]
prev_sharpe = current_result[column]['sharpe']
lvl1_meta_result, lvl1_meta_preds, lvl1_meta_probabilities = run_meta_labeling_training(
for model_name in current_result.columns:
lvl1_model_predictions = current_predictions[model_name]
prev_sharpe = current_result[model_name]['sharpe']
lvl1_meta_result, lvl1_meta_preds, lvl1_meta_probabilities, meta_labeling_models = run_meta_labeling_training(
target_asset=asset[1],
X_pca = X_pca,
input_predictions= lvl1_model_predictions,
@@ -101,9 +106,11 @@ def __run_training(model_config:dict, training_config:dict, data_config:dict):
)
new_sharpe = lvl1_meta_result['sharpe']
print("Improvement in sharpe for the meta model: ", ((new_sharpe / prev_sharpe) - 1) * 100, "%")
current_result[column] = lvl1_meta_result
current_predictions[column] = lvl1_meta_preds
current_result[model_name] = lvl1_meta_result
current_predictions[model_name] = lvl1_meta_preds
all_models_for_all_assets[asset[1]][model_name] = meta_labeling_models
results = pd.concat([results, current_result], axis=1)
# With static models, because of the lag in the indicator, the first prediction is NA, so we fill it with zero.
all_predictions = pd.concat([all_predictions, current_predictions], axis=1).fillna(0.)
@@ -115,7 +122,7 @@ def __run_training(model_config:dict, training_config:dict, data_config:dict):
averaged_predictions, averaged_results = average_and_evaluate_predictions(current_predictions, y, target_returns, data_config)
# 3. Train a Meta-labeling model on the averaged level-1 model predictions
meta_result, avg_predictions_with_sizing, meta_probabilities = run_meta_labeling_training(
meta_result, avg_predictions_with_sizing, meta_probabilities, meta_labeling_models = run_meta_labeling_training(
target_asset=asset[1],
X_pca = X_pca,
input_predictions= averaged_predictions,
@@ -136,4 +143,4 @@ def __run_training(model_config:dict, training_config:dict, data_config:dict):
if __name__ == '__main__':
run_pipeline(project_name='price-prediction', with_wandb = False, sweep = False)
run_pipeline(project_name='price-prediction', with_wandb = False, sweep = False, get_config=get_default_level_2_daily_config)