workbench 0.8.163__tar.gz → 0.8.165__tar.gz

{workbench-0.8.163 → workbench-0.8.165}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: workbench
-Version: 0.8.163
+Version: 0.8.165
 Summary: Workbench: A Dashboard and Python API for creating and deploying AWS SageMaker Model Pipelines
 Author-email: SuperCowPowers LLC <support@supercowpowers.com>
 License-Expression: MIT

{workbench-0.8.163 → workbench-0.8.165}/applications/aws_dashboard/pages/data_sources/layout.py

@@ -54,7 +54,11 @@ def data_sources_layout(
                 [
                     # Column 1: Data Source Details
                     dbc.Col(
-                        data_source_details,
+                        dcc.Loading(
+                            data_source_details,
+                            type="dot",
+                            color="#33aa33",
+                        ),
                         width=4,
                         className="text-break workbench-container",
                         style={"margin": "20px 0px 0px 0px", "padding": "20px"},
@@ -63,10 +67,12 @@ def data_sources_layout(
                     dbc.Col(
                         [
                             dbc.Row(
-                                violin_plot, className="workbench-container", style={"margin": "20px 0px 10px 20px"}
+                                dcc.Loading(violin_plot, type="graph"),
+                                className="workbench-container",
+                                style={"margin": "20px 0px 10px 20px"},
                             ),
                             dbc.Row(
-                                correlation_matrix,
+                                dcc.Loading(correlation_matrix, type="graph"),
                                 className="workbench-container",
                                 style={"margin": "20px 0px 10px 20px"},
                             ),

{workbench-0.8.163 → workbench-0.8.165}/applications/aws_dashboard/pages/endpoints/layout.py

@@ -47,7 +47,7 @@ def endpoints_layout(
                 [
                     # Column 1: Endpoint Details
                     dbc.Col(
-                        endpoint_details,
+                        dcc.Loading(endpoint_details, type="dot", color="#33aa33"),
                         width=4,
                         className="text-break workbench-container",
                         style={"margin": "20px 0px 0px 0px", "padding": "20px"},
@@ -56,7 +56,7 @@ def endpoints_layout(
                     dbc.Col(
                         [
                             dbc.Row(
-                                endpoint_metrics,
+                                dcc.Loading(endpoint_metrics, type="graph"),
                                 className="workbench-container",
                                 style={"margin": "20px 0px 10px 20px"},
                             ),

{workbench-0.8.163 → workbench-0.8.165}/applications/aws_dashboard/pages/feature_sets/layout.py

@@ -46,7 +46,11 @@ def feature_sets_layout(
                 [
                     # Column 1: Feature Set Details
                     dbc.Col(
-                        feature_set_details,
+                        dcc.Loading(
+                            feature_set_details,
+                            type="dot",
+                            color="#33aa33",
+                        ),
                         width=4,
                         className="text-break workbench-container",
                         style={"margin": "20px 0px 0px 0px", "padding": "20px"},
@@ -55,10 +59,12 @@ def feature_sets_layout(
                     dbc.Col(
                         [
                             dbc.Row(
-                                violin_plot, className="workbench-container", style={"margin": "20px 0px 10px 20px"}
+                                dcc.Loading(violin_plot, type="graph"),
+                                className="workbench-container",
+                                style={"margin": "20px 0px 10px 20px"},
                             ),
                             dbc.Row(
-                                correlation_matrix,
+                                dcc.Loading(correlation_matrix, type="graph"),
                                 className="workbench-container",
                                 style={"margin": "20px 0px 10px 20px"},
                             ),

{workbench-0.8.163 → workbench-0.8.165}/applications/aws_dashboard/pages/models/layout.py

@@ -37,7 +37,11 @@ def models_layout(
                 [
                     # Column 1: Model Details
                     dbc.Col(
-                        model_details,
+                        dcc.Loading(
+                            model_details,
+                            type="dot",
+                            color="#33aa33",
+                        ),
                         width=5,
                         className="text-break workbench-container",
                         style={"margin": "20px 0px 0px 0px", "padding": "20px"},
@@ -46,11 +50,15 @@ def models_layout(
                     dbc.Col(
                         [
                             dbc.Row(
-                                model_plot,
+                                dcc.Loading(model_plot, type="graph", style={"height": "400px"}),
                                 className="workbench-container",
-                                style={"margin": "20px 0px 10px 20px", "height": "400px"},
+                                style={"margin": "20px 0px 10px 20px"},
+                            ),
+                            dbc.Row(
+                                dcc.Loading(shap_plot, type="graph"),
+                                className="workbench-container",
+                                style={"margin": "20px 0px 10px 20px"},
                             ),
-                            dbc.Row(shap_plot, className="workbench-container", style={"margin": "20px 0px 10px 20px"}),
                         ],
                         width=7,
                         style={"padding": "0px"},

{workbench-0.8.163 → workbench-0.8.165}/aws_setup/workbench_core/workbench_core/workbench_core_stack.py

@@ -202,6 +202,24 @@ class WorkbenchCoreStack(Stack):
     #####################
     #     Glue Jobs     #
     #####################
+    def glue_job_logs(self) -> iam.PolicyStatement:
+        """Create a policy statement for Glue job CloudWatch logs.
+
+        Returns:
+            iam.PolicyStatement: The policy statement for Glue job log interactions.
+        """
+        return iam.PolicyStatement(
+            actions=[
+                "logs:CreateLogGroup",
+                "logs:CreateLogStream",
+                "logs:PutLogEvents",
+            ],
+            resources=[
+                f"arn:aws:logs:{self.region}:{self.account}:log-group:/aws-glue/*",
+                f"arn:aws:logs:{self.region}:{self.account}:log-group:/aws-glue/*:*",
+            ],
+        )
+
     def glue_pass_role(self) -> iam.PolicyStatement:
         """Allows us to specify the Workbench-Glue role when creating a Glue Job"""
         return iam.PolicyStatement(
@@ -363,8 +381,7 @@ class WorkbenchCoreStack(Stack):
             resources=[f"arn:aws:sagemaker:{self.region}:{self.account}:training-job/*"],
         )
 
-    @staticmethod
-    def model_training_logs() -> iam.PolicyStatement:
+    def model_training_logs(self) -> iam.PolicyStatement:
         """Create a policy statement for log interactions when training SageMaker models.
         Returns:
             iam.PolicyStatement: The policy statement for log interactions when training SageMaker models.
@@ -378,7 +395,10 @@ class WorkbenchCoreStack(Stack):
                 "logs:CreateLogStream",
                 "logs:PutLogEvents",
             ],
-            resources=["arn:aws:logs:*:*:log-group:/aws/sagemaker/*", "arn:aws:logs:*:*:log-group:/aws/sagemaker/*:*"],
+            resources=[
+                f"arn:aws:logs:{self.region}:{self.account}:log-group:/aws/sagemaker/*",
+                f"arn:aws:logs:{self.region}:{self.account}:log-group:/aws/sagemaker/*:*",
+            ],
         )
 
     #####################
@@ -635,6 +655,23 @@ class WorkbenchCoreStack(Stack):
             ],
         )
 
+    def cloudwatch_monitor(self) -> iam.PolicyStatement:
+        """CloudWatch logs monitoring permissions - read and describe operations
+        Returns:
+            iam.PolicyStatement: The policy statement for monitoring WorkbenchLogGroup.
+        """
+        return iam.PolicyStatement(
+            actions=[
+                "logs:DescribeLogStreams",
+                "logs:GetLogEvents",
+                "logs:FilterLogEvents",
+            ],
+            resources=[
+                f"arn:aws:logs:{self.region}:{self.account}:log-group:WorkbenchLogGroup",
+                f"arn:aws:logs:{self.region}:{self.account}:log-group:WorkbenchLogGroup:*",
+            ],
+        )
+
     # For CloudWatch alarm operations
     def cloudwatch_alarms(self) -> iam.PolicyStatement:
         """Create a policy statement for managing CloudWatch alarms.
@@ -934,6 +971,7 @@ class WorkbenchCoreStack(Stack):
         api_execution_role.add_to_policy(self.glue_jobs_full())
         api_execution_role.add_to_policy(self.parameter_store_discover())
         api_execution_role.add_to_policy(self.parameter_store_full())
+        api_execution_role.add_to_policy(self.cloudwatch_monitor())
         api_execution_role.add_managed_policy(self.datasource_policy)
         api_execution_role.add_managed_policy(self.featureset_policy)
         api_execution_role.add_managed_policy(self.model_policy)
@@ -999,6 +1037,7 @@ class WorkbenchCoreStack(Stack):
         )
 
         # Add a subset of policies for the Glue Role
+        glue_role.add_to_policy(self.glue_job_logs())
         glue_role.add_to_policy(self.parameter_store_full())
         glue_role.add_managed_policy(self.datasource_policy)
         glue_role.add_managed_policy(self.featureset_policy)

{workbench-0.8.163 → workbench-0.8.165}/scripts/admin/redis_reaper.py

@@ -45,6 +45,12 @@ def redis_reaper(host, port, size_limit=512000, expire=7):
                 client.delete(key)
                 keys_deleted += 1
 
+        # Check if the key has the word "Crashed" in its name
+        if b"Crashed" in key:
+            print(f"Deleting key {key} (contains 'Crashed')")
+            client.delete(key)
+            keys_deleted += 1
+
     # Report
     print(f"\nTotal keys: {total_keys}")
     print("\nTop 5 largest keys (by size):")

{workbench-0.8.163 → workbench-0.8.165}/src/workbench/api/endpoint.py

@@ -70,6 +70,17 @@ class Endpoint(EndpointCore):
         """
         return super().fast_inference(eval_df, threads=threads)
 
+    def cross_fold_inference(self, nfolds: int = 5) -> dict:
+        """Run cross-fold inference (only works for XGBoost models)
+
+        Args:
+            nfolds (int): The number of folds to use for cross-validation (default: 5)
+
+        Returns:
+            dict: A dictionary with fold results
+        """
+        return super().cross_fold_inference(nfolds)
+
 
 if __name__ == "__main__":
     """Exercise the Endpoint Class"""

{workbench-0.8.163 → workbench-0.8.165}/src/workbench/core/artifacts/endpoint_core.py

@@ -378,16 +378,17 @@ class EndpointCore(Artifact):
             self.log.important("No model associated with this endpoint, running 'no frills' inference...")
             return self.fast_inference(eval_df)
 
+        # Grab the model features and target column
+        model = ModelCore(self.model_name)
+        features = model.features()
+        target_column = model.target()
+
         # Run predictions on the evaluation data
-        prediction_df = self._predict(eval_df, drop_error_rows)
+        prediction_df = self._predict(eval_df, features, drop_error_rows)
         if prediction_df.empty:
             self.log.warning("No predictions were made. Returning empty DataFrame.")
             return prediction_df
 
-        # Get the target column
-        model = ModelCore(self.model_name)
-        target_column = model.target()
-
         # Sanity Check that the target column is present
         if target_column and (target_column not in prediction_df.columns):
             self.log.important(f"Target Column {target_column} not found in prediction_df!")
@@ -419,12 +420,6 @@ class EndpointCore(Artifact):
                     capture_name, prediction_df, target_column, model_type, metrics, description, features, id_column
                 )
 
-                # Capture CrossFold Inference Results
-                cross_fold_metrics = cross_fold_inference(model)
-                if cross_fold_metrics:
-                    # Now put into the Parameter Store Model Inference Namespace
-                    self.param_store.upsert(f"/workbench/models/{model.name}/inference/cross_fold", cross_fold_metrics)
-
                 # For UQ Models we also capture the uncertainty metrics
                 if model_type in [ModelType.UQ_REGRESSOR]:
                     metrics = uq_metrics(prediction_df, target_column)
@@ -435,6 +430,25 @@ class EndpointCore(Artifact):
         # Return the prediction DataFrame
         return prediction_df
 
+    def cross_fold_inference(self, nfolds: int = 5) -> dict:
+        """Run cross-fold inference (only works for XGBoost models)
+
+        Args:
+            nfolds (int): Number of folds to use for cross-fold (default: 5)
+
+        Returns:
+            dict: Dictionary with the cross-fold inference results
+        """
+
+        # Grab our model
+        model = ModelCore(self.model_name)
+
+        # Compute CrossFold Metrics
+        cross_fold_metrics = cross_fold_inference(model, nfolds=nfolds)
+        if cross_fold_metrics:
+            self.param_store.upsert(f"/workbench/models/{model.name}/inference/cross_fold", cross_fold_metrics)
+        return cross_fold_metrics
+
     def fast_inference(self, eval_df: pd.DataFrame, threads: int = 4) -> pd.DataFrame:
         """Run inference on the Endpoint using the provided DataFrame
 
@@ -450,11 +464,12 @@ class EndpointCore(Artifact):
         """
         return fast_inference(self.name, eval_df, self.sm_session, threads=threads)
 
-    def _predict(self, eval_df: pd.DataFrame, drop_error_rows: bool = False) -> pd.DataFrame:
-        """Internal: Run prediction on the given observations in the given DataFrame
+    def _predict(self, eval_df: pd.DataFrame, features: list[str], drop_error_rows: bool = False) -> pd.DataFrame:
+        """Internal: Run prediction on observations in the given DataFrame
 
         Args:
             eval_df (pd.DataFrame): DataFrame to run predictions on (must have superset of features)
+            features (list[str]): List of feature column names needed for prediction
             drop_error_rows (bool): If True, drop rows that had endpoint errors/issues (default=False)
         Returns:
             pd.DataFrame: Return the DataFrame with additional columns, prediction and any _proba columns
@@ -465,19 +480,12 @@ class EndpointCore(Artifact):
             self.log.warning("Evaluation DataFrame has 0 rows. No predictions to run.")
             return pd.DataFrame(columns=eval_df.columns)  # Return empty DataFrame with same structure
 
-        # Sanity check: Does the Model have Features?
-        features = ModelCore(self.model_name).features()
-        if not features:
-            self.log.warning("Model does not have features defined, using all columns in the DataFrame")
-        else:
-            # Sanity check: Does the DataFrame have the required features?
-            df_columns_lower = set(col.lower() for col in eval_df.columns)
-            features_lower = set(feature.lower() for feature in features)
-
-            # Check if the features are a subset of the DataFrame columns (case-insensitive)
-            if not features_lower.issubset(df_columns_lower):
-                missing_features = features_lower - df_columns_lower
-                raise ValueError(f"DataFrame does not contain required features: {missing_features}")
+        # Sanity check: Does the DataFrame have the required features?
+        df_columns_lower = set(col.lower() for col in eval_df.columns)
+        features_lower = set(feature.lower() for feature in features)
+        if not features_lower.issubset(df_columns_lower):
+            missing_features = features_lower - df_columns_lower
+            raise ValueError(f"DataFrame does not contain required features: {missing_features}")
 
         # Create our Endpoint Predictor Class
         predictor = Predictor(
@@ -713,18 +721,10 @@ class EndpointCore(Artifact):
             # Note: Unlike other dataframes here, we want to write the index (labels) to the CSV
             wr.s3.to_csv(conf_mtx, f"{inference_capture_path}/inference_cm.csv", index=True)
 
-        # Generate SHAP values for our Prediction Dataframe
-        # generate_shap_values(self.endpoint_name, model_type.value, pred_results_df, inference_capture_path)
-
         # Now recompute the details for our Model
-        self.log.important(f"Recomputing Details for {self.model_name} to show latest Inference Results...")
+        self.log.important(f"Loading inference metrics for {self.model_name}...")
         model = ModelCore(self.model_name)
         model._load_inference_metrics(capture_name)
-        model.details()
-
-        # Recompute the details so that inference model metrics are updated
-        self.log.important(f"Recomputing Details for {self.name} to show latest Inference Results...")
-        self.details()
 
     def regression_metrics(self, target_column: str, prediction_df: pd.DataFrame) -> pd.DataFrame:
         """Compute the performance metrics for this Endpoint
@@ -876,9 +876,11 @@ class EndpointCore(Artifact):
 
     def generate_confusion_matrix(self, target_column: str, prediction_df: pd.DataFrame) -> pd.DataFrame:
         """Compute the confusion matrix for this Endpoint
+
         Args:
             target_column (str): Name of the target column
             prediction_df (pd.DataFrame): DataFrame with the prediction results
+
         Returns:
             pd.DataFrame: DataFrame with the confusion matrix
         """
@@ -887,25 +889,20 @@ class EndpointCore(Artifact):
         prediction_col = "prediction" if "prediction" in prediction_df.columns else "predictions"
         y_pred = prediction_df[prediction_col]
 
-        # Check if our model has class labels, if not we'll use the unique labels in the prediction
-        class_labels = ModelCore(self.model_name).class_labels()
-        if class_labels is None:
-            class_labels = sorted(list(set(y_true) | set(y_pred)))
+        # Get model class labels
+        model_class_labels = ModelCore(self.model_name).class_labels()
 
-        # Compute the confusion matrix (sklearn confusion_matrix)
-        conf_mtx = confusion_matrix(y_true, y_pred, labels=class_labels)
+        # Use model labels if available, otherwise infer from data
+        if model_class_labels:
+            self.log.important("Using model class labels for confusion matrix ordering...")
+            labels = model_class_labels
+        else:
+            labels = sorted(list(set(y_true) | set(y_pred)))
 
-        # Create a DataFrame
-        conf_mtx_df = pd.DataFrame(conf_mtx, index=class_labels, columns=class_labels)
+        # Compute confusion matrix and create DataFrame
+        conf_mtx = confusion_matrix(y_true, y_pred, labels=labels)
+        conf_mtx_df = pd.DataFrame(conf_mtx, index=labels, columns=labels)
         conf_mtx_df.index.name = "labels"
-
-        # Check if our model has class labels. If so make the index and columns ordered
-        model_class_labels = ModelCore(self.model_name).class_labels()
-        if model_class_labels:
-            self.log.important("Reordering the confusion matrix based on model class labels...")
-            conf_mtx_df.index = pd.Categorical(conf_mtx_df.index, categories=model_class_labels, ordered=True)
-            conf_mtx_df.columns = pd.Categorical(conf_mtx_df.columns, categories=model_class_labels, ordered=True)
-            conf_mtx_df = conf_mtx_df.sort_index().sort_index(axis=1)
         return conf_mtx_df
 
     def endpoint_config_name(self) -> str:
@@ -1086,13 +1083,20 @@ if __name__ == "__main__":
     df = fs.pull_dataframe()[:100]
     cap_df = df.copy()
     cap_df.columns = [col.upper() for col in cap_df.columns]
-    my_endpoint._predict(cap_df)
+    my_endpoint.inference(cap_df)
 
     # Boolean Type Test
     df["bool_column"] = [random.choice([True, False]) for _ in range(len(df))]
-    result_df = my_endpoint._predict(df)
+    result_df = my_endpoint.inference(df)
     assert result_df["bool_column"].dtype == bool
 
+    # Missing Feature Test
+    missing_df = df.drop(columns=["length"])
+    try:
+        my_endpoint.inference(missing_df)
+    except ValueError as e:
+        print(f"Expected error for missing feature: {e}")
+
     # Run Auto Inference on the Endpoint (uses the FeatureSet)
     print("Running Auto Inference...")
     my_endpoint.auto_inference()
@@ -1107,6 +1111,9 @@ if __name__ == "__main__":
     my_eval_df = fs_evaluation_data(my_endpoint)
     pred_results = my_endpoint.inference(my_eval_df, capture_name="holdout_xyz")
 
+    # Run predictions using the fast_inference method
+    fast_results = my_endpoint.fast_inference(my_eval_df)
+
     # Run Inference and metrics for a Classification Endpoint
     class_endpoint = EndpointCore("wine-classification")
     auto_predictions = class_endpoint.auto_inference()
@@ -1115,9 +1122,6 @@ if __name__ == "__main__":
     target = "wine_class"
     print(class_endpoint.generate_confusion_matrix(target, auto_predictions))
 
-    # Run predictions using the fast_inference method
-    fast_results = my_endpoint.fast_inference(my_eval_df)
-
     # Test the class method delete (commented out for now)
     # from workbench.api import Model
     # model = Model("abalone-regression")

{workbench-0.8.163 → workbench-0.8.165}/src/workbench/model_scripts/xgb_model/generated_model_script.py

@@ -28,12 +28,12 @@ from typing import List, Tuple
 
 # Template Parameters
 TEMPLATE_PARAMS = {
-    "model_type": "classifier",
-    "target_column": "solubility_class",
-    "features": ['molwt', 'mollogp', 'molmr', 'heavyatomcount', 'numhacceptors', 'numhdonors', 'numheteroatoms', 'numrotatablebonds', 'numvalenceelectrons', 'numaromaticrings', 'numsaturatedrings', 'numaliphaticrings', 'ringcount', 'tpsa', 'labuteasa', 'balabanj', 'bertzct', 'fingerprint'],
-    "compressed_features": ['fingerprint'],
-    "model_metrics_s3_path": "s3://sandbox-sageworks-artifacts/models/aqsol-fingerprints-plus-class/training",
-    "train_all_data": True
+    "model_type": "regressor",
+    "target_column": "solubility",
+    "features": ['molwt', 'mollogp', 'molmr', 'heavyatomcount', 'numhacceptors', 'numhdonors', 'numheteroatoms', 'numrotatablebonds', 'numvalenceelectrons', 'numaromaticrings', 'numsaturatedrings', 'numaliphaticrings', 'ringcount', 'tpsa', 'labuteasa', 'balabanj', 'bertzct', 'apol', 'avgipc', 'bcut2d_chghi', 'bcut2d_chglo', 'bcut2d_logphi', 'bcut2d_logplow', 'bcut2d_mrhi', 'bcut2d_mrlow', 'bcut2d_mwhi', 'bcut2d_mwlow', 'bpol', 'chi0', 'chi0n', 'chi0v', 'chi1', 'chi1n', 'chi1v', 'chi2n', 'chi2v', 'chi3n', 'chi3v', 'chi4n', 'chi4v', 'chiral_centers', 'chiral_fp', 'db_fp', 'db_stereo', 'e_cnt', 'estate_vsa1', 'estate_vsa10', 'estate_vsa11', 'estate_vsa2', 'estate_vsa3', 'estate_vsa4', 'estate_vsa5', 'estate_vsa6', 'estate_vsa7', 'estate_vsa8', 'estate_vsa9', 'exactmolwt', 'fpdensitymorgan1', 'fpdensitymorgan2', 'fpdensitymorgan3', 'fr_al_coo', 'fr_al_oh', 'fr_al_oh_notert', 'fr_aldehyde', 'fr_alkyl_carbamate', 'fr_alkyl_halide', 'fr_allylic_oxid', 'fr_amide', 'fr_amidine', 'fr_aniline', 'fr_ar_coo', 'fr_ar_n', 'fr_ar_nh', 'fr_ar_oh', 'fr_arn', 'fr_aryl_methyl', 'fr_azide', 'fr_azo', 'fr_barbitur', 'fr_benzene', 'fr_benzodiazepine', 'fr_bicyclic', 'fr_c_o', 'fr_c_o_nocoo', 'fr_c_s', 'fr_coo', 'fr_coo2', 'fr_diazo', 'fr_dihydropyridine', 'fr_epoxide', 'fr_ester', 'fr_ether', 'fr_furan', 'fr_guanido', 'fr_halogen', 'fr_hdrzine', 'fr_hdrzone', 'fr_hoccn', 'fr_imidazole', 'fr_imide', 'fr_imine', 'fr_isocyan', 'fr_isothiocyan', 'fr_ketone', 'fr_ketone_topliss', 'fr_lactam', 'fr_lactone', 'fr_methoxy', 'fr_morpholine', 'fr_n_o', 'fr_ndealkylation1', 'fr_ndealkylation2', 'fr_nh0', 'fr_nh1', 'fr_nh2', 'fr_nhpyrrole', 'fr_nitrile', 'fr_nitro', 'fr_nitro_arom', 'fr_nitro_arom_nonortho', 'fr_nitroso', 'fr_oxazole', 'fr_oxime', 'fr_para_hydroxylation', 'fr_phenol', 'fr_phenol_noorthohbond', 'fr_phos_acid', 'fr_phos_ester', 'fr_piperdine', 'fr_piperzine', 'fr_priamide', 'fr_prisulfonamd', 'fr_pyridine', 'fr_quatn', 'fr_sh', 'fr_sulfide', 'fr_sulfonamd', 'fr_sulfone', 'fr_term_acetylene', 'fr_tetrazole', 'fr_thiazole', 'fr_thiocyan', 'fr_thiophene', 'fr_unbrch_alkane', 'fr_urea', 'fractioncsp3', 'hallkieralpha', 'has_stereo', 'heavyatommolwt', 'kappa1', 'kappa2', 'kappa3', 'maxabsestateindex', 'maxabspartialcharge', 'maxestateindex', 'maxpartialcharge', 'minabsestateindex', 'minabspartialcharge', 'minestateindex', 'minpartialcharge', 'nacid', 'naromatom', 'narombond', 'nbase', 'nhohcount', 'nocount', 'nrot', 'numaliphaticcarbocycles', 'numaliphaticheterocycles', 'numamidebonds', 'numaromaticcarbocycles', 'numaromaticheterocycles', 'numatomstereocenters', 'numbridgeheadatoms', 'numheterocycles', 'numradicalelectrons', 'numsaturatedcarbocycles', 'numsaturatedheterocycles', 'numspiroatoms', 'numunspecifiedatomstereocenters', 'peoe_vsa1', 'peoe_vsa10', 'peoe_vsa11', 'peoe_vsa12', 'peoe_vsa13', 'peoe_vsa14', 'peoe_vsa2', 'peoe_vsa3', 'peoe_vsa4', 'peoe_vsa5', 'peoe_vsa6', 'peoe_vsa7', 'peoe_vsa8', 'peoe_vsa9', 'phi', 'qed', 'r_cnt', 's_cnt', 'slogp_vsa1', 'slogp_vsa10', 'slogp_vsa11', 'slogp_vsa12', 'slogp_vsa2', 'slogp_vsa3', 'slogp_vsa4', 'slogp_vsa5', 'slogp_vsa6', 'slogp_vsa7', 'slogp_vsa8', 'slogp_vsa9', 'smr_vsa1', 'smr_vsa10', 'smr_vsa2', 'smr_vsa3', 'smr_vsa4', 'smr_vsa5', 'smr_vsa6', 'smr_vsa7', 'smr_vsa8', 'smr_vsa9', 'sps', 'vsa_estate1', 'vsa_estate10', 'vsa_estate2', 'vsa_estate3', 'vsa_estate4', 'vsa_estate5', 'vsa_estate6', 'vsa_estate7', 'vsa_estate8', 'vsa_estate9', 'z_cnt'],
+    "compressed_features": [],
+    "model_metrics_s3_path": "s3://sandbox-sageworks-artifacts/models/aqsol-mol-regression/training",
+    "train_all_data": False
 }
 
 # Function to check if dataframe is empty

{workbench-0.8.163 → workbench-0.8.165}/src/workbench/utils/workbench_logging.py

@@ -181,9 +181,6 @@ def logging_setup(color_logs=True):
         log.debug("Debugging enabled via WORKBENCH_DEBUG environment variable.")
     else:
         log.setLevel(logging.INFO)
-        # Note: Not using the ThrottlingFilter for now
-        # throttle_filter = ThrottlingFilter(rate_seconds=5)
-        # handler.addFilter(throttle_filter)
 
     # Suppress specific logger
     logging.getLogger("sagemaker.config").setLevel(logging.WARNING)

{workbench-0.8.163 → workbench-0.8.165}/src/workbench.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: workbench
-Version: 0.8.163
+Version: 0.8.165
 Summary: Workbench: A Dashboard and Python API for creating and deploying AWS SageMaker Model Pipelines
 Author-email: SuperCowPowers LLC <support@supercowpowers.com>
 License-Expression: MIT

{workbench-0.8.163 → workbench-0.8.165}/tests/create_test_artifacts/create_wine_artifacts.py

@@ -44,6 +44,7 @@ if __name__ == "__main__":
             description="Wine Classification Model",
         )
         m.set_owner("test")
+        m.set_class_labels(["TypeA", "TypeB", "TypeC"])
 
     # Create the wine classification Endpoint
     if recreate or not Endpoint("wine-classification").exists():