workbench 0.8.203__py3-none-any.whl → 0.8.205__py3-none-any.whl

workbench/core/artifacts/endpoint_core.py

@@ -436,19 +436,14 @@ class EndpointCore(Artifact):
 
             # Normalize targets to a list for iteration
             target_list = targets if isinstance(targets, list) else [targets]
+            primary_target = target_list[0]
 
-            # For multi-target models, use target-specific capture names (e.g., auto_target1, auto_target2)
-            # For single-target models, use the original capture name for backward compatibility
-            for target in target_list:
-                # Determine capture name: use prefix for multi-target, original name for single-target
-                if len(target_list) > 1:
-                    prefix = "auto" if "auto" in capture_name else capture_name
-                    target_capture_name = f"{prefix}_{target}"
-                else:
-                    target_capture_name = capture_name
-
-                description = target_capture_name.replace("_", " ").title()
+            # For auto_inference, use shorter "auto_{target}" naming
+            # Otherwise use "{capture_name}_{target}"
+            prefix = "auto" if capture_name == "auto_inference" else capture_name
 
+            # Save results for each target, plus primary target with original capture_name
+            for target in target_list:
                 # Drop rows with NaN target values for metrics/plots
                 target_df = prediction_df.dropna(subset=[target])
 
@@ -460,6 +455,9 @@ class EndpointCore(Artifact):
                 else:
                     target_metrics = pd.DataFrame()
 
+                # Save as {prefix}_{target}
+                target_capture_name = f"{prefix}_{target}"
+                description = target_capture_name.replace("_", " ").title()
                 self._capture_inference_results(
                     target_capture_name,
                     target_df,
@@ -471,6 +469,19 @@ class EndpointCore(Artifact):
                     id_column,
                 )
 
+                # Also save primary target with original capture_name for backward compatibility
+                if target == primary_target:
+                    self._capture_inference_results(
+                        capture_name,
+                        target_df,
+                        target,
+                        model.model_type,
+                        target_metrics,
+                        capture_name.replace("_", " ").title(),
+                        features,
+                        id_column,
+                    )
+
             # For UQ Models we also capture the uncertainty metrics
             if model.model_type in [ModelType.UQ_REGRESSOR]:
                 metrics = uq_metrics(prediction_df, primary_target)
@@ -561,13 +572,11 @@ class EndpointCore(Artifact):
 
         # Normalize targets to a list for iteration
         target_list = targets if isinstance(targets, list) else [targets]
+        primary_target = target_list[0]
 
-        # For multi-target models, use target-specific capture names (e.g., cv_target1, cv_target2)
-        # For single-target models, use "full_cross_fold" for backward compatibility
+        # Save results for each target as cv_{target}
+        # Also save primary target as "full_cross_fold" for backward compatibility
         for target in target_list:
-            capture_name = f"cv_{target}"
-            description = capture_name.replace("_", " ").title()
-
             # Drop rows with NaN target values for metrics/plots
             target_df = out_of_fold_df.dropna(subset=[target])
 
@@ -579,6 +588,9 @@ class EndpointCore(Artifact):
             else:
                 target_metrics = pd.DataFrame()
 
+            # Save as cv_{target}
+            capture_name = f"cv_{target}"
+            description = capture_name.replace("_", " ").title()
             self._capture_inference_results(
                 capture_name,
                 target_df,
@@ -590,6 +602,19 @@ class EndpointCore(Artifact):
                 id_column=id_column,
             )
 
+            # Also save primary target as "full_cross_fold" for backward compatibility
+            if target == primary_target:
+                self._capture_inference_results(
+                    "full_cross_fold",
+                    target_df,
+                    target,
+                    model_type,
+                    target_metrics,
+                    "Full Cross Fold",
+                    features=additional_columns,
+                    id_column=id_column,
+                )
+
         return out_of_fold_df
 
     def fast_inference(self, eval_df: pd.DataFrame, threads: int = 4) -> pd.DataFrame:
@@ -795,30 +820,6 @@ class EndpointCore(Artifact):
         combined = row_hashes.values.tobytes()
         return hashlib.md5(combined).hexdigest()[:hash_length]
 
-    @staticmethod
-    def _find_prediction_column(df: pd.DataFrame, target_column: str) -> Optional[str]:
-        """Find the prediction column in a DataFrame.
-
-        Looks for 'prediction' column first, then '{target}_pred' pattern.
-
-        Args:
-            df: DataFrame to search
-            target_column: Name of the target column (used for {target}_pred pattern)
-
-        Returns:
-            Name of the prediction column, or None if not found
-        """
-        # Check for 'prediction' column first (legacy/standard format)
-        if "prediction" in df.columns:
-            return "prediction"
-
-        # Check for '{target}_pred' format (multi-target format)
-        target_pred_col = f"{target_column}_pred"
-        if target_pred_col in df.columns:
-            return target_pred_col
-
-        return None
-
     def _capture_inference_results(
         self,
         capture_name: str,
@@ -946,29 +947,23 @@ class EndpointCore(Artifact):
             self.log.warning("No predictions were made. Returning empty DataFrame.")
             return pd.DataFrame()
 
-        # Find the prediction column: "prediction" or "{target}_pred"
-        prediction_col = self._find_prediction_column(prediction_df, target_column)
-        if prediction_col is None:
-            self.log.warning(f"No prediction column found for target '{target_column}'")
+        # Check for prediction column
+        if "prediction" not in prediction_df.columns:
+            self.log.warning("No 'prediction' column found in DataFrame")
             return pd.DataFrame()
 
         # Check for NaN values in target or prediction columns
-        if prediction_df[target_column].isnull().any() or prediction_df[prediction_col].isnull().any():
-            # Compute the number of NaN values in each column
+        if prediction_df[target_column].isnull().any() or prediction_df["prediction"].isnull().any():
             num_nan_target = prediction_df[target_column].isnull().sum()
-            num_nan_prediction = prediction_df[prediction_col].isnull().sum()
-            self.log.warning(
-                f"NaNs Found: {target_column} {num_nan_target} and {prediction_col}: {num_nan_prediction}."
-            )
-            self.log.warning(
-                "NaN values found in target or prediction columns. Dropping NaN rows for metric computation."
-            )
-            prediction_df = prediction_df.dropna(subset=[target_column, prediction_col])
+            num_nan_prediction = prediction_df["prediction"].isnull().sum()
+            self.log.warning(f"NaNs Found: {target_column} {num_nan_target} and prediction: {num_nan_prediction}.")
+            self.log.warning("Dropping NaN rows for metric computation.")
+            prediction_df = prediction_df.dropna(subset=[target_column, "prediction"])
 
         # Compute the metrics
         try:
             y_true = prediction_df[target_column]
-            y_pred = prediction_df[prediction_col]
+            y_pred = prediction_df["prediction"]
 
             mae = mean_absolute_error(y_true, y_pred)
             rmse = np.sqrt(mean_squared_error(y_true, y_pred))
@@ -1000,17 +995,13 @@ class EndpointCore(Artifact):
         Returns:
             pd.DataFrame: DataFrame with two new columns called 'residuals' and 'residuals_abs'
         """
-
-        # Compute the residuals
-        y_true = prediction_df[target_column]
-
-        # Find the prediction column: "prediction" or "{target}_pred"
-        prediction_col = self._find_prediction_column(prediction_df, target_column)
-        if prediction_col is None:
-            self.log.warning(f"No prediction column found for target '{target_column}'. Cannot compute residuals.")
+        # Check for prediction column
+        if "prediction" not in prediction_df.columns:
+            self.log.warning("No 'prediction' column found. Cannot compute residuals.")
             return prediction_df
 
-        y_pred = prediction_df[prediction_col]
+        y_true = prediction_df[target_column]
+        y_pred = prediction_df["prediction"]
 
         # Check for classification scenario
         if not pd.api.types.is_numeric_dtype(y_true) or not pd.api.types.is_numeric_dtype(y_pred):
@@ -1051,14 +1042,13 @@ class EndpointCore(Artifact):
         Returns:
             pd.DataFrame: DataFrame with the performance metrics
         """
-        # Find the prediction column: "prediction" or "{target}_pred"
-        prediction_col = self._find_prediction_column(prediction_df, target_column)
-        if prediction_col is None:
-            self.log.warning(f"No prediction column found for target '{target_column}'")
+        # Check for prediction column
+        if "prediction" not in prediction_df.columns:
+            self.log.warning("No 'prediction' column found in DataFrame")
             return pd.DataFrame()
 
         # Drop rows with NaN predictions (can't compute metrics on missing predictions)
-        nan_mask = prediction_df[prediction_col].isna()
+        nan_mask = prediction_df["prediction"].isna()
         if nan_mask.any():
             n_nan = nan_mask.sum()
             self.log.warning(f"Dropping {n_nan} rows with NaN predictions for metrics calculation")
@@ -1078,7 +1068,7 @@ class EndpointCore(Artifact):
         # Calculate precision, recall, f1, and support, handling zero division
         scores = precision_recall_fscore_support(
             prediction_df[target_column],
-            prediction_df[prediction_col],
+            prediction_df["prediction"],
             average=None,
             labels=class_labels,
             zero_division=0,
@@ -1126,21 +1116,20 @@ class EndpointCore(Artifact):
         Returns:
             pd.DataFrame: DataFrame with the confusion matrix
         """
-        # Find the prediction column: "prediction" or "{target}_pred"
-        prediction_col = self._find_prediction_column(prediction_df, target_column)
-        if prediction_col is None:
-            self.log.warning(f"No prediction column found for target '{target_column}'")
+        # Check for prediction column
+        if "prediction" not in prediction_df.columns:
+            self.log.warning("No 'prediction' column found in DataFrame")
             return pd.DataFrame()
 
         # Drop rows with NaN predictions (can't include in confusion matrix)
-        nan_mask = prediction_df[prediction_col].isna()
+        nan_mask = prediction_df["prediction"].isna()
         if nan_mask.any():
             n_nan = nan_mask.sum()
             self.log.warning(f"Dropping {n_nan} rows with NaN predictions for confusion matrix")
             prediction_df = prediction_df[~nan_mask].copy()
 
         y_true = prediction_df[target_column]
-        y_pred = prediction_df[prediction_col]
+        y_pred = prediction_df["prediction"]
 
         # Get model class labels
         model_class_labels = ModelCore(self.model_name).class_labels()

workbench/core/transforms/model_to_endpoint/model_to_endpoint.py

@@ -102,10 +102,21 @@ class ModelToEndpoint(Transform):
         # Is this a serverless deployment?
         serverless_config = None
         if self.serverless:
+            # For PyTorch or ChemProp we need at least 4GB of memory
+            from workbench.api import ModelFramework
+
+            self.log.info(f"Model Framework: {workbench_model.model_framework}")
+            if workbench_model.model_framework in [ModelFramework.PYTORCH_TABULAR, ModelFramework.CHEMPROP]:
+                if mem_size < 4096:
+                    self.log.important(
+                        f"{workbench_model.model_framework} needs at least 4GB of memory (setting to 4GB)"
+                    )
+                    mem_size = 4096
             serverless_config = ServerlessInferenceConfig(
                 memory_size_in_mb=mem_size,
                 max_concurrency=max_concurrency,
             )
+            self.log.important(f"Serverless Config: Memory={mem_size}MB, MaxConcurrency={max_concurrency}")
 
         # Configure data capture if requested (and not serverless)
         data_capture_config = None

workbench/model_scripts/chemprop/chemprop.template

@@ -25,6 +25,7 @@
 # - argparse, file loading, S3 writes
 # =============================
 
+import glob
 import os
 import argparse
 import json
@@ -185,7 +186,7 @@ def build_mpnn_model(
     # Model hyperparameters with defaults
     hidden_dim = hyperparameters.get("hidden_dim", 700)
     depth = hyperparameters.get("depth", 6)
-    dropout = hyperparameters.get("dropout", 0.25)
+    dropout = hyperparameters.get("dropout", 0.15)
     ffn_hidden_dim = hyperparameters.get("ffn_hidden_dim", 2000)
     ffn_num_layers = hyperparameters.get("ffn_num_layers", 2)
 
@@ -468,6 +469,11 @@ def predict_fn(df: pd.DataFrame, model_dict: dict) -> pd.DataFrame:
             df.loc[valid_mask, f"{tc}_pred"] = preds[:, t_idx]
             df.loc[valid_mask, f"{tc}_pred_std"] = preds_std[:, t_idx]
 
+        # Add prediction/prediction_std aliases for first target
+        first_target = target_columns[0]
+        df["prediction"] = df[f"{first_target}_pred"]
+        df["prediction_std"] = df[f"{first_target}_pred_std"]
+
     return df
 
 
@@ -881,6 +887,11 @@ if __name__ == "__main__":
             else:
                 df_val[f"{t_name}_pred_std"] = 0.0
 
+        # Add prediction/prediction_std aliases for first target
+        first_target = target_columns[0]
+        df_val["prediction"] = df_val[f"{first_target}_pred"]
+        df_val["prediction_std"] = df_val[f"{first_target}_pred_std"]
+
     # Save validation predictions to S3
     # Include id_column if it exists in df_val
     output_columns = []
@@ -890,6 +901,7 @@ if __name__ == "__main__":
     output_columns += target_columns
     output_columns += [f"{t}_pred" for t in target_columns]
     output_columns += [f"{t}_pred_std" for t in target_columns]
+    output_columns += ["prediction", "prediction_std"]
     # Add proba columns for classifiers
     output_columns += [col for col in df_val.columns if col.endswith("_proba")]
     # Filter to only columns that exist
@@ -906,6 +918,11 @@ if __name__ == "__main__":
         models.save_model(model_path, ens_model)
         print(f"Saved model {model_idx + 1} to {model_path}")
 
+    # Clean up checkpoint files (not needed for inference, reduces artifact size)
+    for ckpt_file in glob.glob(os.path.join(args.model_dir, "best_model_*.ckpt")):
+        os.remove(ckpt_file)
+        print(f"Removed checkpoint: {ckpt_file}")
+
     # Save ensemble metadata (n_ensemble = number of models for inference)
     n_ensemble = len(ensemble_models)
     ensemble_metadata = {

workbench/model_scripts/chemprop/generated_model_script.py

@@ -25,6 +25,7 @@
 # - argparse, file loading, S3 writes
 # =============================
 
+import glob
 import os
 import argparse
 import json
@@ -53,12 +54,12 @@ from chemprop import data, models, nn
 
 # Template Parameters
 TEMPLATE_PARAMS = {
-    "model_type": "regressor",
-    "targets": ['logd', 'ksol', 'hlm_clint', 'mlm_clint', 'caco_2_papp_a_b', 'caco_2_efflux', 'mppb', 'mbpb', 'mgmb'],  # List of target columns (single or multi-task)
-    "feature_list": ['smiles'],
-    "id_column": "molecule_name",
-    "model_metrics_s3_path": "s3://sandbox-sageworks-artifacts/models/open-admet-chemprop-mt/training",
-    "hyperparameters": {},
+    "model_type": "uq_regressor",
+    "targets": ['udm_asy_res_efflux_ratio'],  # List of target columns (single or multi-task)
+    "feature_list": ['smiles', 'smr_vsa4', 'tpsa', 'nhohcount', 'mollogp', 'peoe_vsa1', 'smr_vsa3', 'nitrogen_span', 'numhdonors', 'minpartialcharge', 'vsa_estate3', 'vsa_estate6', 'tertiary_amine_count', 'hba_hbd_ratio', 'peoe_vsa8', 'estate_vsa4', 'xc_4dv', 'vsa_estate2', 'molmr', 'xp_2dv', 'mi', 'molecular_axis_length', 'vsa_estate4', 'xp_6dv', 'qed', 'estate_vsa8', 'chi1v', 'asphericity', 'axp_1d', 'bcut2d_logphi', 'kappa3', 'axp_7d', 'num_s_centers', 'amphiphilic_moment', 'molecular_asymmetry', 'charge_centroid_distance', 'estate_vsa3', 'vsa_estate8', 'aromatic_interaction_score', 'molecular_volume_3d', 'axp_7dv', 'peoe_vsa3', 'smr_vsa6', 'bcut2d_mrhi', 'radius_of_gyration', 'xpc_4dv', 'minabsestateindex', 'axp_0dv', 'chi4n', 'balabanj', 'bcut2d_mwlow'],
+    "id_column": "udm_mol_bat_id",
+    "model_metrics_s3_path": "s3://ideaya-sageworks-bucket/models/caco2-er-chemprop-reg-hybrid/training",
+    "hyperparameters": {'n_folds': 5, 'hidden_dim': 700, 'depth': 6, 'dropout': 0.15, 'ffn_hidden_dim': 2000, 'ffn_num_layers': 2},
 }
 
 
@@ -185,7 +186,7 @@ def build_mpnn_model(
     # Model hyperparameters with defaults
     hidden_dim = hyperparameters.get("hidden_dim", 700)
     depth = hyperparameters.get("depth", 6)
-    dropout = hyperparameters.get("dropout", 0.25)
+    dropout = hyperparameters.get("dropout", 0.15)
     ffn_hidden_dim = hyperparameters.get("ffn_hidden_dim", 2000)
     ffn_num_layers = hyperparameters.get("ffn_num_layers", 2)
 
@@ -468,6 +469,11 @@ def predict_fn(df: pd.DataFrame, model_dict: dict) -> pd.DataFrame:
             df.loc[valid_mask, f"{tc}_pred"] = preds[:, t_idx]
             df.loc[valid_mask, f"{tc}_pred_std"] = preds_std[:, t_idx]
 
+        # Add prediction/prediction_std aliases for first target
+        first_target = target_columns[0]
+        df["prediction"] = df[f"{first_target}_pred"]
+        df["prediction_std"] = df[f"{first_target}_pred_std"]
+
     return df
 
 
@@ -881,6 +887,11 @@ if __name__ == "__main__":
             else:
                 df_val[f"{t_name}_pred_std"] = 0.0
 
+        # Add prediction/prediction_std aliases for first target
+        first_target = target_columns[0]
+        df_val["prediction"] = df_val[f"{first_target}_pred"]
+        df_val["prediction_std"] = df_val[f"{first_target}_pred_std"]
+
     # Save validation predictions to S3
     # Include id_column if it exists in df_val
     output_columns = []
@@ -890,6 +901,7 @@ if __name__ == "__main__":
     output_columns += target_columns
     output_columns += [f"{t}_pred" for t in target_columns]
     output_columns += [f"{t}_pred_std" for t in target_columns]
+    output_columns += ["prediction", "prediction_std"]
     # Add proba columns for classifiers
     output_columns += [col for col in df_val.columns if col.endswith("_proba")]
     # Filter to only columns that exist
@@ -906,6 +918,11 @@ if __name__ == "__main__":
         models.save_model(model_path, ens_model)
         print(f"Saved model {model_idx + 1} to {model_path}")
 
+    # Clean up checkpoint files (not needed for inference, reduces artifact size)
+    for ckpt_file in glob.glob(os.path.join(args.model_dir, "best_model_*.ckpt")):
+        os.remove(ckpt_file)
+        print(f"Removed checkpoint: {ckpt_file}")
+
     # Save ensemble metadata (n_ensemble = number of models for inference)
     n_ensemble = len(ensemble_models)
     ensemble_metadata = {

workbench/model_scripts/uq_models/generated_model_script.py

@@ -19,11 +19,11 @@ from typing import List, Tuple, Optional, Dict
 
 # Template Placeholders
 TEMPLATE_PARAMS = {
-    "target": "mppb",
-    "features": ['chi2v', 'fr_sulfone', 'chi1v', 'bcut2d_logplow', 'fr_piperzine', 'kappa3', 'smr_vsa1', 'slogp_vsa5', 'fr_ketone_topliss', 'fr_sulfonamd', 'fr_imine', 'fr_benzene', 'fr_ester', 'chi2n', 'labuteasa', 'peoe_vsa2', 'smr_vsa6', 'bcut2d_chglo', 'fr_sh', 'peoe_vsa1', 'fr_allylic_oxid', 'chi4n', 'fr_ar_oh', 'fr_nh0', 'fr_term_acetylene', 'slogp_vsa7', 'slogp_vsa4', 'estate_vsa1', 'vsa_estate4', 'numbridgeheadatoms', 'numheterocycles', 'fr_ketone', 'fr_morpholine', 'fr_guanido', 'estate_vsa2', 'numheteroatoms', 'fr_nitro_arom_nonortho', 'fr_piperdine', 'nocount', 'numspiroatoms', 'fr_aniline', 'fr_thiophene', 'slogp_vsa10', 'fr_amide', 'slogp_vsa2', 'fr_epoxide', 'vsa_estate7', 'fr_ar_coo', 'fr_imidazole', 'fr_nitrile', 'fr_oxazole', 'numsaturatedrings', 'fr_pyridine', 'fr_hoccn', 'fr_ndealkylation1', 'numaliphaticheterocycles', 'fr_phenol', 'maxpartialcharge', 'vsa_estate5', 'peoe_vsa13', 'minpartialcharge', 'qed', 'fr_al_oh', 'slogp_vsa11', 'chi0n', 'fr_bicyclic', 'peoe_vsa12', 'fpdensitymorgan1', 'fr_oxime', 'molwt', 'fr_dihydropyridine', 'smr_vsa5', 'peoe_vsa5', 'fr_nitro', 'hallkieralpha', 'heavyatommolwt', 'fr_alkyl_halide', 'peoe_vsa8', 'fr_nhpyrrole', 'fr_isocyan', 'bcut2d_chghi', 'fr_lactam', 'peoe_vsa11', 'smr_vsa9', 'tpsa', 'chi4v', 'slogp_vsa1', 'phi', 'bcut2d_logphi', 'avgipc', 'estate_vsa11', 'fr_coo', 'bcut2d_mwhi', 'numunspecifiedatomstereocenters', 'vsa_estate10', 'estate_vsa8', 'numvalenceelectrons', 'fr_nh2', 'fr_lactone', 'vsa_estate1', 'estate_vsa4', 'numatomstereocenters', 'vsa_estate8', 'fr_para_hydroxylation', 'peoe_vsa3', 'fr_thiazole', 'peoe_vsa10', 'fr_ndealkylation2', 'slogp_vsa12', 'peoe_vsa9', 'maxestateindex', 'fr_quatn', 'smr_vsa7', 'minestateindex', 'numaromaticheterocycles', 'numrotatablebonds', 'fr_ar_nh', 'fr_ether', 'exactmolwt', 'fr_phenol_noorthohbond', 'slogp_vsa3', 'fr_ar_n', 'sps', 'fr_c_o_nocoo', 'bertzct', 'peoe_vsa7', 'slogp_vsa8', 'numradicalelectrons', 'molmr', 'fr_tetrazole', 'numsaturatedcarbocycles', 'bcut2d_mrhi', 'kappa1', 'numamidebonds', 'fpdensitymorgan2', 'smr_vsa8', 'chi1n', 'estate_vsa6', 'fr_barbitur', 'fr_diazo', 'kappa2', 'chi0', 'bcut2d_mrlow', 'balabanj', 'peoe_vsa4', 'numhacceptors', 'fr_sulfide', 'chi3n', 'smr_vsa2', 'fr_al_oh_notert', 'fr_benzodiazepine', 'fr_phos_ester', 'fr_aldehyde', 'fr_coo2', 'estate_vsa5', 'fr_prisulfonamd', 'numaromaticcarbocycles', 'fr_unbrch_alkane', 'fr_urea', 'fr_nitroso', 'smr_vsa10', 'fr_c_s', 'smr_vsa3', 'fr_methoxy', 'maxabspartialcharge', 'slogp_vsa9', 'heavyatomcount', 'fr_azide', 'chi3v', 'smr_vsa4', 'mollogp', 'chi0v', 'fr_aryl_methyl', 'fr_nh1', 'fpdensitymorgan3', 'fr_furan', 'fr_hdrzine', 'fr_arn', 'numaromaticrings', 'vsa_estate3', 'fr_azo', 'fr_halogen', 'estate_vsa9', 'fr_hdrzone', 'numhdonors', 'fr_alkyl_carbamate', 'fr_isothiocyan', 'minabspartialcharge', 'fr_al_coo', 'ringcount', 'chi1', 'estate_vsa7', 'fr_nitro_arom', 'vsa_estate9', 'minabsestateindex', 'maxabsestateindex', 'vsa_estate6', 'estate_vsa10', 'estate_vsa3', 'fr_n_o', 'fr_amidine', 'fr_thiocyan', 'fr_phos_acid', 'fr_c_o', 'fr_imide', 'numaliphaticrings', 'peoe_vsa6', 'vsa_estate2', 'nhohcount', 'numsaturatedheterocycles', 'slogp_vsa6', 'peoe_vsa14', 'fractioncsp3', 'bcut2d_mwlow', 'numaliphaticcarbocycles', 'fr_priamide', 'nacid', 'nbase', 'naromatom', 'narombond', 'sz', 'sm', 'sv', 'sse', 'spe', 'sare', 'sp', 'si', 'mz', 'mm', 'mv', 'mse', 'mpe', 'mare', 'mp', 'mi', 'xch_3d', 'xch_4d', 'xch_5d', 'xch_6d', 'xch_7d', 'xch_3dv', 'xch_4dv', 'xch_5dv', 'xch_6dv', 'xch_7dv', 'xc_3d', 'xc_4d', 'xc_5d', 'xc_6d', 'xc_3dv', 'xc_4dv', 'xc_5dv', 'xc_6dv', 'xpc_4d', 'xpc_5d', 'xpc_6d', 'xpc_4dv', 'xpc_5dv', 'xpc_6dv', 'xp_0d', 'xp_1d', 'xp_2d', 'xp_3d', 'xp_4d', 'xp_5d', 'xp_6d', 'xp_7d', 'axp_0d', 'axp_1d', 'axp_2d', 'axp_3d', 'axp_4d', 'axp_5d', 'axp_6d', 'axp_7d', 'xp_0dv', 'xp_1dv', 'xp_2dv', 'xp_3dv', 'xp_4dv', 'xp_5dv', 'xp_6dv', 'xp_7dv', 'axp_0dv', 'axp_1dv', 'axp_2dv', 'axp_3dv', 'axp_4dv', 'axp_5dv', 'axp_6dv', 'axp_7dv', 'c1sp1', 'c2sp1', 'c1sp2', 'c2sp2', 'c3sp2', 'c1sp3', 'c2sp3', 'c3sp3', 'c4sp3', 'hybratio', 'fcsp3', 'num_stereocenters', 'num_unspecified_stereocenters', 'num_defined_stereocenters', 'num_r_centers', 'num_s_centers', 'num_stereobonds', 'num_e_bonds', 'num_z_bonds', 'stereo_complexity', 'frac_defined_stereo'],
+    "target": "udm_asy_res_efflux_ratio",
+    "features": ['smr_vsa4', 'tpsa', 'nhohcount', 'peoe_vsa1', 'mollogp', 'vsa_estate3', 'xc_4dv', 'smr_vsa3', 'tertiary_amine_count', 'peoe_vsa8', 'minpartialcharge', 'nitrogen_span', 'vsa_estate2', 'chi1v', 'hba_hbd_ratio', 'molecular_axis_length', 'molmr', 'vsa_estate4', 'num_s_centers', 'vsa_estate6', 'qed', 'numhdonors', 'mi', 'estate_vsa4', 'axp_7d', 'kappa3', 'asphericity', 'estate_vsa8', 'estate_vsa2', 'estate_vsa3', 'peoe_vsa3', 'xp_6dv', 'bcut2d_logphi', 'vsa_estate8', 'amphiphilic_moment', 'type_ii_pattern_count', 'minestateindex', 'charge_centroid_distance', 'molecular_asymmetry', 'molecular_volume_3d', 'bcut2d_mrlow', 'axp_1d', 'vsa_estate9', 'aromatic_interaction_score', 'xp_7dv', 'bcut2d_mwlow', 'axp_7dv', 'slogp_vsa1', 'maxestateindex', 'fr_al_oh', 'nbase', 'xp_2dv', 'radius_of_gyration', 'sps', 'xch_7d', 'bcut2d_mrhi', 'axp_0dv', 'vsa_estate5', 'hallkieralpha', 'xp_0dv', 'fr_nhpyrrole', 'smr_vsa1', 'smr_vsa6', 'chi2v', 'bcut2d_mwhi', 'estate_vsa6', 'bcut2d_logplow', 'peoe_vsa2', 'fractioncsp3', 'slogp_vsa2', 'c3sp3', 'peoe_vsa7', 'estate_vsa9', 'peoe_vsa9', 'avgipc', 'smr_vsa9', 'xpc_4dv', 'balabanj', 'axp_1dv', 'mv', 'minabsestateindex', 'bcut2d_chglo', 'fpdensitymorgan2', 'axp_4d', 'numsaturatedheterocycles', 'fpdensitymorgan1', 'axp_3dv', 'axp_5d', 'smr_vsa5', 'bcut2d_chghi', 'axp_3d', 'xpc_5dv', 'chi4n', 'peoe_vsa10', 'vsa_estate7', 'peoe_vsa11', 'estate_vsa10', 'xp_7d', 'slogp_vsa5', 'xch_7dv', 'vsa_estate10', 'labuteasa', 'estate_vsa5', 'xp_3d', 'chi1', 'xch_4dv', 'xp_6d', 'estate_vsa1', 'axp_4dv', 'phi', 'xp_3dv', 'xch_6dv', 'smr_vsa10', 'num_r_centers', 'xc_5d', 'maxpartialcharge', 'xc_3d', 'peoe_vsa6', 'fr_imidazole', 'axp_2d', 'slogp_vsa3', 'mz', 'axp_6dv', 'xch_6d', 'mm', 'numatomstereocenters', 'c1sp3', 'chi1n', 'fpdensitymorgan3', 'xp_5dv', 'chi3v', 'slogp_vsa4', 'fr_ether', 'xp_2d', 'chi3n', 'xch_5dv', 'axp_6d', 'xc_5dv', 'numheterocycles', 'mpe', 'fr_hoccn', 'xc_3dv', 'type_i_pattern_count', 'chi0v', 'xch_4d', 'numsaturatedcarbocycles', 'mp', 'xch_5d', 'maxabspartialcharge', 'axp_2dv', 'bertzct', 'sse', 'xpc_6dv', 'sv', 'xpc_4d', 'si', 'chi0n', 'mse', 'xpc_6d', 'peoe_vsa12', 'xpc_5d', 'kappa2', 'axp_5dv', 'kappa1', 'chi2n', 'intramolecular_hbond_potential', 'fr_nh0', 'numaliphaticheterocycles', 'smr_vsa7', 'mare', 'fr_priamide', 'vsa_estate1', 'num_stereocenters', 'fr_nh1', 'estate_vsa7', 'fr_piperzine', 'c1sp2', 'slogp_vsa6', 'xp_5d', 'fr_aryl_methyl', 'molwt', 'chi4v', 'xc_6dv', 'heavyatommolwt', 'xp_4d', 'sp', 'slogp_vsa7', 'numhacceptors', 'c2sp3', 'peoe_vsa4', 'slogp_vsa10', 'fr_morpholine', 'fr_methoxy', 'fr_aniline', 'xp_4dv', 'fr_urea', 'c3sp2', 'fr_pyridine', 'hybratio', 'fr_thiazole', 'minabspartialcharge', 'sm', 'axp_0d', 'numaromaticheterocycles', 'nocount', 'xc_4d', 'peoe_vsa13', 'fr_amide', 'num_defined_stereocenters', 'amide_count', 'xc_6d', 'numrotatablebonds', 'c2sp2', 'fr_piperdine', 'numvalenceelectrons', 'c1sp1', 'fr_nitrile', 'fr_phenol', 'c4sp3', 'spe', 'numheteroatoms', 'estate_vsa11', 'sz', 'chi0', 'smr_vsa2', 'fr_ketone_topliss', 'slogp_vsa11', 'fr_benzene', 'fr_ndealkylation2', 'peoe_vsa5', 'fr_c_o', 'numsaturatedrings', 'exactmolwt', 'sare', 'numaliphaticrings', 'fr_al_oh_notert', 'fr_imine', 'frac_defined_stereo', 'numunspecifiedatomstereocenters', 'fr_ar_n', 'fr_bicyclic', 'fr_c_o_nocoo', 'numspiroatoms', 'fr_sulfone', 'fr_ndealkylation1'],
     "compressed_features": [],
     "train_all_data": True,
-    "hyperparameters": {'objective': 'reg:absoluteerror', 'n_estimators': 300, 'max_depth': 6, 'learning_rate': 0.03, 'subsample': 0.8, 'colsample_bytree': 0.6, 'colsample_bylevel': 0.8, 'min_child_weight': 5, 'gamma': 0.1, 'reg_alpha': 0.3, 'reg_lambda': 1.5, 'random_state': 42},
+    "hyperparameters": {'n_estimators': 500, 'max_depth': 6, 'learning_rate': 0.04},
 }
 
 

{workbench-0.8.203.dist-info → workbench-0.8.205.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: workbench
-Version: 0.8.203
+Version: 0.8.205
 Summary: Workbench: A Dashboard and Python API for creating and deploying AWS SageMaker Model Pipelines
 Author-email: SuperCowPowers LLC <support@supercowpowers.com>
 License: MIT License

{workbench-0.8.203.dist-info → workbench-0.8.205.dist-info}/RECORD

@@ -55,7 +55,7 @@ workbench/core/artifacts/data_capture_core.py,sha256=q8f79rRTYiZ7T4IQRWXl8ZvPpcv
 workbench/core/artifacts/data_source_abstract.py,sha256=5IRCzFVK-17cd4NXPMRfx99vQAmQ0WHE5jcm5RfsVTg,10619
 workbench/core/artifacts/data_source_factory.py,sha256=YL_tA5fsgubbB3dPF6T4tO0rGgz-6oo3ge4i_YXVC-M,2380
 workbench/core/artifacts/df_store_core.py,sha256=AueNr_JvuLLu_ByE7cb3u-isH9u0Q7cMP-UCgCX-Ctg,3536
-workbench/core/artifacts/endpoint_core.py,sha256=oWWJSXSod5JzI7b4JvoxKWm46lv0FNZZf_FIZR4ZP9Q,60832
+workbench/core/artifacts/endpoint_core.py,sha256=eyjEd8KXMkqUwI7rFuuT0cMZMMrdSBSj3moR-EagS8w,60244
 workbench/core/artifacts/feature_set_core.py,sha256=wZy-02WXWmSBet5t8mWXFRdv9O4MtW3hWqJuVv7Kok0,39330
 workbench/core/artifacts/model_core.py,sha256=QIgV5MJr8aDY63in83thdNc5-bzkWLn5f5vvsS4aNYo,52348
 workbench/core/artifacts/monitor_core.py,sha256=M307yz7tEzOEHgv-LmtVy9jKjSbM98fHW3ckmNYrwlU,27897
@@ -104,7 +104,7 @@ workbench/core/transforms/features_to_features/heavy/glue/Readme.md,sha256=TuyCa
 workbench/core/transforms/features_to_model/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 workbench/core/transforms/features_to_model/features_to_model.py,sha256=JdKKz3eKrKhicA1WxTfmb1IqQNCdHJE0CKDs66bLHYU,21071
 workbench/core/transforms/model_to_endpoint/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-workbench/core/transforms/model_to_endpoint/model_to_endpoint.py,sha256=TIYXvuK0s383PwJ4iS6fCRhuif6oIxsoWb4CpMGJjY4,6358
+workbench/core/transforms/model_to_endpoint/model_to_endpoint.py,sha256=QjfUY_Ay2-W8OszWw2vGtsKfnMY7VjiWQmnjuzLBITk,7020
 workbench/core/transforms/pandas_transforms/__init__.py,sha256=xL4MT8-fZ1SFqDbTLc8XyxjupHtB1YR6Ej0AC2nwd7I,894
 workbench/core/transforms/pandas_transforms/data_to_pandas.py,sha256=sJHPeuNF8Q8aQqgRnkdWkyvur5cbggdUVIwR-xF3Dlo,3621
 workbench/core/transforms/pandas_transforms/features_to_pandas.py,sha256=af6xdPt2V4zhh-SzQa_UYxdmNMzMLXbrbsznV5QoIJg,3441
@@ -123,8 +123,8 @@ workbench/core/views/view.py,sha256=DvmEA1xdvL980GET_cnbmHzqSy6IhlNaZcoQnVTtYis,
 workbench/core/views/view_utils.py,sha256=CwOlpqXpumCr6REi-ey7Qjz5_tpg-s4oWHmlOVu8POQ,12270
 workbench/core/views/storage/mdq_view.py,sha256=qf_ep1KwaXOIfO930laEwNIiCYP7VNOqjE3VdHfopRE,5195
 workbench/model_scripts/script_generation.py,sha256=_AhzM2qzjBuI7pIaXBRZ1YOOs2lwsKQGVM_ovL6T1bo,8135
-workbench/model_scripts/chemprop/chemprop.template,sha256=NR1jMb-IPxBAaQ-KiPR09ylL_gTIC35lZwBpBQPtzig,38109
-workbench/model_scripts/chemprop/generated_model_script.py,sha256=Cxfbu7mNf_HLBCzlsOOXR1u1Y-eHMma63YWM9l8ku44,38206
+workbench/model_scripts/chemprop/chemprop.template,sha256=XcRBEz_JYS1Vjv9MI_5BalvrWL9v2vTq1eRlVpLAtPE,38883
+workbench/model_scripts/chemprop/generated_model_script.py,sha256=lSr5qHZljCzttxlq4YwypUYmYbIAl7flo5RT8nXt_vs,39755
 workbench/model_scripts/chemprop/requirements.txt,sha256=PIuUdPAeDUH3I2M_5nIrCnCfs3FL1l9V5kzHqgCcu7s,281
 workbench/model_scripts/custom_models/chem_info/Readme.md,sha256=mH1lxJ4Pb7F5nBnVXaiuxpi8zS_yjUw_LBJepVKXhlA,574
 workbench/model_scripts/custom_models/chem_info/fingerprints.py,sha256=Qvs8jaUwguWUq3Q3j695MY0t0Wk3BvroW-oWBwalMUo,5255
@@ -157,7 +157,7 @@ workbench/model_scripts/pytorch_model/requirements.txt,sha256=ICS5nW0wix44EJO2tJ
 workbench/model_scripts/scikit_learn/generated_model_script.py,sha256=xhQIglpAgPRCH9iwI3wI0N0V6p9AgqW0mVOMuSXzUCk,17187
 workbench/model_scripts/scikit_learn/requirements.txt,sha256=aVvwiJ3LgBUhM_PyFlb2gHXu_kpGPho3ANBzlOkfcvs,107
 workbench/model_scripts/scikit_learn/scikit_learn.template,sha256=QQvqx-eX9ZTbYmyupq6R6vIQwosmsmY_MRBPaHyfjdk,12586
-workbench/model_scripts/uq_models/generated_model_script.py,sha256=caAXcK03XQQcPo2rvFJtZqnwQpLAz7v0CQWBWDO2Dts,27866
+workbench/model_scripts/uq_models/generated_model_script.py,sha256=0HqH1bY3fXgZTQAFLxfnrPfBEQvTmeMus5C2z7HoeyU,26765
 workbench/model_scripts/uq_models/mapie.template,sha256=on3I40D7zyNfvfqBf5k8VXCFtmepcxKmqVWCH5Q9S84,23432
 workbench/model_scripts/uq_models/requirements.txt,sha256=fw7T7t_YJAXK3T6Ysbesxh_Agx_tv0oYx72cEBTqRDY,98
 workbench/model_scripts/xgb_model/generated_model_script.py,sha256=qUGg5R-boaswzXtgKp_J7JPxFzMdRNv51QeF-lMWL-4,19334
@@ -291,9 +291,9 @@ workbench/web_interface/page_views/main_page.py,sha256=X4-KyGTKLAdxR-Zk2niuLJB2Y
 workbench/web_interface/page_views/models_page_view.py,sha256=M0bdC7bAzLyIaE2jviY12FF4abdMFZmg6sFuOY_LaGI,2650
 workbench/web_interface/page_views/page_view.py,sha256=Gh6YnpOGlUejx-bHZAf5pzqoQ1H1R0OSwOpGhOBO06w,455
 workbench/web_interface/page_views/pipelines_page_view.py,sha256=v2pxrIbsHBcYiblfius3JK766NZ7ciD2yPx0t3E5IJo,2656
-workbench-0.8.203.dist-info/licenses/LICENSE,sha256=RTBoTMeEwTgEhS-n8vgQ-VUo5qig0PWVd8xFPKU6Lck,1080
-workbench-0.8.203.dist-info/METADATA,sha256=qC58O-dE5_EMFpEJWDa9fyPSNwRt-n6K7krsrsJP13I,10500
-workbench-0.8.203.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-workbench-0.8.203.dist-info/entry_points.txt,sha256=j02NCuno2Y_BuE4jEvw-IL73WZ9lkTpLwom29uKcLCw,458
-workbench-0.8.203.dist-info/top_level.txt,sha256=Dhy72zTxaA_o_yRkPZx5zw-fwumnjGaeGf0hBN3jc_w,10
-workbench-0.8.203.dist-info/RECORD,,
+workbench-0.8.205.dist-info/licenses/LICENSE,sha256=RTBoTMeEwTgEhS-n8vgQ-VUo5qig0PWVd8xFPKU6Lck,1080
+workbench-0.8.205.dist-info/METADATA,sha256=4fgPE_3_5UQK9Av-WuIaRPZW-nwcIJVekAXYPbyx5hU,10500
+workbench-0.8.205.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+workbench-0.8.205.dist-info/entry_points.txt,sha256=j02NCuno2Y_BuE4jEvw-IL73WZ9lkTpLwom29uKcLCw,458
+workbench-0.8.205.dist-info/top_level.txt,sha256=Dhy72zTxaA_o_yRkPZx5zw-fwumnjGaeGf0hBN3jc_w,10
+workbench-0.8.205.dist-info/RECORD,,