workbench 0.8.201__py3-none-any.whl → 0.8.204__py3-none-any.whl

workbench/model_scripts/custom_models/uq_models/ensemble_xgb.template

@@ -4,9 +4,10 @@ import awswrangler as wr
 import numpy as np
 
 # Model Performance Scores
-from sklearn.metrics import mean_absolute_error, r2_score, root_mean_squared_error
+from sklearn.metrics import mean_absolute_error, median_absolute_error, r2_score, root_mean_squared_error
 from sklearn.model_selection import KFold
 from scipy.optimize import minimize
+from scipy.stats import spearmanr
 
 from io import StringIO
 import json
@@ -217,11 +218,16 @@ if __name__ == "__main__":
     # Report Performance Metrics
     rmse = root_mean_squared_error(result_df[target], result_df["prediction"])
     mae = mean_absolute_error(result_df[target], result_df["prediction"])
+    medae = median_absolute_error(result_df[target], result_df["prediction"])
     r2 = r2_score(result_df[target], result_df["prediction"])
-    print(f"RMSE: {rmse:.3f}")
-    print(f"MAE: {mae:.3f}")
-    print(f"R2: {r2:.3f}")
-    print(f"NumRows: {len(result_df)}")
+    spearman_corr = spearmanr(result_df[target], result_df["prediction"]).correlation
+    support = len(result_df)
+    print(f"rmse: {rmse:.3f}")
+    print(f"mae: {mae:.3f}")
+    print(f"medae: {medae:.3f}")
+    print(f"r2: {r2:.3f}")
+    print(f"spearmanr: {spearman_corr:.3f}")
+    print(f"support: {support}")
 
     # Now save the models
     for name, model in models.items():

workbench/model_scripts/custom_models/uq_models/meta_uq.template

@@ -5,7 +5,8 @@ from xgboost import XGBRegressor  # Point Estimator
 from sklearn.model_selection import train_test_split
 
 # Model Performance Scores
-from sklearn.metrics import mean_absolute_error, r2_score, root_mean_squared_error
+from sklearn.metrics import mean_absolute_error, median_absolute_error, r2_score, root_mean_squared_error
+from scipy.stats import spearmanr
 
 from io import StringIO
 import json
@@ -238,11 +239,16 @@ if __name__ == "__main__":
     # Calculate various model performance metrics (regression)
     rmse = root_mean_squared_error(y_validate, preds)
     mae = mean_absolute_error(y_validate, preds)
+    medae = median_absolute_error(y_validate, preds)
     r2 = r2_score(y_validate, preds)
-    print(f"RMSE: {rmse:.3f}")
-    print(f"MAE: {mae:.3f}")
-    print(f"R2: {r2:.3f}")
-    print(f"NumRows: {len(df_val)}")
+    spearman_corr = spearmanr(y_validate, preds).correlation
+    support = len(df_val)
+    print(f"rmse: {rmse:.3f}")
+    print(f"mae: {mae:.3f}")
+    print(f"medae: {medae:.3f}")
+    print(f"r2: {r2:.3f}")
+    print(f"spearmanr: {spearman_corr:.3f}")
+    print(f"support: {support}")
 
     # Save the trained XGBoost model
     xgb_model.save_model(os.path.join(args.model_dir, "xgb_model.json"))

workbench/model_scripts/custom_models/uq_models/ngboost.template

@@ -3,7 +3,8 @@ from ngboost import NGBRegressor
 from sklearn.model_selection import train_test_split
 
 # Model Performance Scores
-from sklearn.metrics import mean_absolute_error, r2_score, root_mean_squared_error
+from sklearn.metrics import mean_absolute_error, median_absolute_error, r2_score, root_mean_squared_error
+from scipy.stats import spearmanr
 
 from io import StringIO
 import json
@@ -129,11 +130,16 @@ if __name__ == "__main__":
     # Calculate various model performance metrics (regression)
     rmse = root_mean_squared_error(y_validate, preds)
     mae = mean_absolute_error(y_validate, preds)
+    medae = median_absolute_error(y_validate, preds)
     r2 = r2_score(y_validate, preds)
-    print(f"RMSE: {rmse:.3f}")
-    print(f"MAE: {mae:.3f}")
-    print(f"R2: {r2:.3f}")
-    print(f"NumRows: {len(df_val)}")
+    spearman_corr = spearmanr(y_validate, preds).correlation
+    support = len(df_val)
+    print(f"rmse: {rmse:.3f}")
+    print(f"mae: {mae:.3f}")
+    print(f"medae: {medae:.3f}")
+    print(f"r2: {r2:.3f}")
+    print(f"spearmanr: {spearman_corr:.3f}")
+    print(f"support: {support}")
 
     # Save the trained NGBoost model
     joblib.dump(ngb_model, os.path.join(args.model_dir, "ngb_model.joblib"))

workbench/model_scripts/ensemble_xgb/ensemble_xgb.template

@@ -12,7 +12,8 @@ import awswrangler as wr
 import numpy as np
 
 # Model Performance Scores
-from sklearn.metrics import mean_absolute_error, r2_score, root_mean_squared_error
+from sklearn.metrics import mean_absolute_error, median_absolute_error, r2_score, root_mean_squared_error
+from scipy.stats import spearmanr
 
 from io import StringIO
 import json
@@ -153,11 +154,16 @@ if __name__ == "__main__":
     # Report Performance Metrics
     rmse = root_mean_squared_error(result_df[target], result_df["prediction"])
     mae = mean_absolute_error(result_df[target], result_df["prediction"])
+    medae = median_absolute_error(result_df[target], result_df["prediction"])
     r2 = r2_score(result_df[target], result_df["prediction"])
-    print(f"RMSE: {rmse:.3f}")
-    print(f"MAE: {mae:.3f}")
-    print(f"R2: {r2:.3f}")
-    print(f"NumRows: {len(result_df)}")
+    spearman_corr = spearmanr(result_df[target], result_df["prediction"]).correlation
+    support = len(result_df)
+    print(f"rmse: {rmse:.3f}")
+    print(f"mae: {mae:.3f}")
+    print(f"medae: {medae:.3f}")
+    print(f"r2: {r2:.3f}")
+    print(f"spearmanr: {spearman_corr:.3f}")
+    print(f"support: {support}")
 
     # Now save the models
     for name, model in models.items():