gavindiaz/drift
1
0
Fork 0
mirror of https://github.com/webclinic017/drift.git synced 2026-08-16 20:38:07 +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
training/meta_labeling.py
+3 -3
View File
@@ -15,7 +15,7 @@ def run_meta_labeling_training(
data_config: dict,
model_config: dict,
training_config: dict
) -> tuple[pd.Series, pd.Series, pd.DataFrame]:
) -> tuple[pd.Series, pd.Series, pd.DataFrame, dict]:
discretize = discretize_threeway_threshold(0.33)
discretized_predictions = input_predictions.apply(discretize)
@@ -29,7 +29,7 @@ def run_meta_labeling_training(
meta_X = pd.concat([meta_selected_features_X, input_predictions, discretized_predictions], axis = 1)
_, meta_preds, meta_probabilities = run_single_asset_trainig(
_, meta_preds, meta_probabilities, all_models_single_asset = run_single_asset_trainig(
ticker_to_predict = "prediction_correct",
original_X = meta_X,
X = meta_X,
@@ -59,4 +59,4 @@ def run_meta_labeling_training(
)
meta_result.rename("model_" + target_asset + "_meta_lvl" + str(2), inplace=True)
return meta_result, avg_predictions_with_sizing, meta_probabilities
return meta_result, avg_predictions_with_sizing, meta_probabilities, all_models_single_asset
training/training.py
+5 -2
View File
@@ -20,12 +20,13 @@ def run_single_asset_trainig(
scaler: ScalerTypes,
no_of_classes: Literal['two', 'three-balanced', 'three-imbalanced'],
level: int
) -> tuple[pd.DataFrame, pd.DataFrame, pd.DataFrame]:
) -> tuple[pd.DataFrame, pd.DataFrame, pd.DataFrame, dict]:
scaler = get_scaler(scaler)
results = pd.DataFrame()
all_models_single_asset = dict()
predictions = pd.DataFrame(index=y.index)
probabilities = pd.DataFrame(index=y.index)
@@ -41,6 +42,7 @@ def run_single_asset_trainig(
retrain_every = retrain_every,
scaler = scaler
)
assert len(preds) == len(y)
result = evaluate_predictions(
model_name = model_name,
@@ -53,6 +55,7 @@ def run_single_asset_trainig(
)
column_name = "model_" + ticker_to_predict + "_" + model_name + "_lvl" + str(level)
results[column_name] = result
all_models_single_asset[model_name] = model_over_time
# column names for model outputs should be different, so we can differentiate between original data and model predictions later, where necessary
predictions[column_name] = preds
probs_column_name = "probs_" + ticker_to_predict + "_" + model_name + "_lvl" + str(level)
@@ -60,4 +63,4 @@ def run_single_asset_trainig(
probabilities = pd.concat([probabilities, probs], axis=1)
return results, predictions, probabilities
return results, predictions, probabilities, all_models_single_asset