workbench 0.8.187__tar.gz → 0.8.189__tar.gz

{workbench-0.8.187 → workbench-0.8.189}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: workbench
-Version: 0.8.187
+Version: 0.8.189
 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-0.8.187 → workbench-0.8.189}/aws_setup/workbench_compute/workbench_compute/workbench_compute_stack.py

@@ -208,7 +208,7 @@ class WorkbenchComputeStack(Stack):
         # Connect SQS to Lambda
         batch_trigger_lambda.add_event_source(
             lambda_events.SqsEventSource(
-                self.ml_pipeline_queue, batch_size=1, max_concurrency=5  # Limit parallel Batch job submissions
+                self.ml_pipeline_queue, batch_size=1  # One message at a time for precise error handling
             )
         )
         return batch_trigger_lambda

{workbench-0.8.187 → workbench-0.8.189}/docs/api_classes/endpoint.md

@@ -11,19 +11,15 @@
 **Run Inference on an Endpoint**
 
 ```py title="endpoint_inference.py"
-from workbench.api.feature_set import FeatureSet
-from workbench.api.model import Model
-from workbench.api.endpoint import Endpoint
+from workbench.api import Endpoint
+from workbench.utils.endpoint_utils import get_evaluation_data
 
 # Grab an existing Endpoint
 endpoint = Endpoint("abalone-regression-end")
 
 # Workbench has full ML Pipeline provenance, so we can backtrack the inputs,
 # get a DataFrame of data (not used for training) and run inference
-model = Model(endpoint.get_input())
-fs = FeatureSet(model.get_input())
-athena_table = fs.view("training").table
-df = fs.query(f"SELECT * FROM {athena_table} where training = FALSE")
+df = get_evaluation_data(endpoint)
 
 # Run inference/predictions on the Endpoint
 results_df = endpoint.inference(df)

{workbench-0.8.187 → workbench-0.8.189}/docs/api_classes/overview.md

@@ -17,10 +17,7 @@ These classes provide high-level APIs for the Workbench package, they enable you
 ## Example ML Pipline
 
 ```py title="full_ml_pipeline.py"
-from workbench.api.data_source import DataSource
-from workbench.api.feature_set import FeatureSet
-from workbench.api.model import Model, ModelType
-from workbench.api.endpoint import Endpoint
+from workbench.api import DataSource, FeatureSet, Model, ModelType, Endpoint
 
 # Create the abalone_data DataSource
 ds = DataSource("s3://workbench-public-data/common/abalone.csv")
@@ -46,9 +43,7 @@ model.to_endpoint(name="abalone-regression-end", tags=["abalone", "regression"])
 endpoint = Endpoint("abalone-regression-end")
 
 # Run inference on the Endpoint
-athena_table = fs.view("training").table
-df = fs.query(f"SELECT * FROM {athena_table} where training = FALSE")
-results = endpoint.predict(df)
+results = endpoint.auto_inference()
 print(results[["class_number_of_rings", "prediction"]])
 ```
 

{workbench-0.8.187 → workbench-0.8.189}/docs/api_classes/views.md

@@ -49,10 +49,10 @@ from workbench.api.feature_set import FeatureSet
 
 # Grab a FeatureSet View
 fs = FeatureSet("abalone_features")
-t_view = fs.view("training")
+d_view = fs.view("display")
 
 # Make some queries using the Athena backend
-df = t_view(f"select * from {t_view.table} where height > .3")
+df = d_view(f"select * from {d_view.table} where height > .3")
 print(df.head())
 
 df = t_view.query("select * from abalone_features where class_number_of_rings < 3")

{workbench-0.8.187 → workbench-0.8.189}/docs/core_classes/views/overview.md

@@ -57,10 +57,10 @@ from workbench.api.feature_set import FeatureSet
 
 # Grab a FeatureSet View
 fs = FeatureSet("abalone_features")
-t_view = fs.view("training")
+d_view = fs.view("display")
 
 # Make some queries using the Athena backend
-df = t_view(f"select * from {t_view.table} where height > .3")
+df = t_view(f"select * from {d_view.table} where height > .3")
 print(df.head())
 
 df = t_view.query("select * from abalone_features where class_number_of_rings < 3")

{workbench-0.8.187 → workbench-0.8.189}/examples/endpoint/endpoint_inference.py

@@ -1,16 +1,12 @@
-from workbench.api.feature_set import FeatureSet
-from workbench.api.model import Model
-from workbench.api.endpoint import Endpoint
+from workbench.api import Endpoint
+from workbench.utils.endpoint_utils import get_evaluation_data
 
 # Grab an existing Endpoint
 endpoint = Endpoint("abalone-regression")
 
 # Workbench has full ML Pipeline provenance, so we can backtrack the inputs,
 # get a DataFrame of data (not used for training) and run inference
-model = Model(endpoint.get_input())
-fs = FeatureSet(model.get_input())
-athena_table = fs.view("training").table
-df = fs.query(f"SELECT * FROM {athena_table} where training = FALSE")
+df = get_evaluation_data(endpoint)
 
 # Run inference/predictions on the Endpoint
 results_df = endpoint.inference(df)

{workbench-0.8.187 → workbench-0.8.189}/examples/full_ml_pipeline.py

@@ -44,7 +44,5 @@ if __name__ == "__main__":
     endpoint = Endpoint("abalone-regression")
 
     # Run inference on the Endpoint
-    athena_table = fs.view("training").table
-    df = fs.query(f"SELECT * FROM {athena_table} where training = FALSE")
-    results = endpoint.inference(df)
+    results = endpoint.auto_inference()
     print(results[["class_number_of_rings", "prediction"]])

{workbench-0.8.187 → workbench-0.8.189}/model_docker_images/ml_pipelines/Dockerfile

@@ -29,7 +29,7 @@ COPY --from=builder /usr/local/lib/python3.12/site-packages /usr/local/lib/pytho
 COPY --from=builder /usr/local/bin /usr/local/bin
 
 # Install workbench only
-RUN pip install --no-cache-dir workbench==0.8.186
+RUN pip install --no-cache-dir workbench==0.8.188
 
 # Add the script runner
 COPY ml_pipeline_runner.py /app/ml_pipeline_runner.py

{workbench-0.8.187 → workbench-0.8.189}/notebooks/Inference_On_Legacy_Models.ipynb

@@ -63,8 +63,8 @@
     "# Grab the evaluation data\n",
     "from workbench.api.feature_set import FeatureSet\n",
     "fs = FeatureSet(\"solubility_featurized_fs\")\n",
-    "training_view = fs.view(\"training\").table\n",
-    "eval_data = fs.query(f\"select * from {training_view} where training=0\")"
+    "table = model.training_view().table\n",
+    "eval_data = fs.query(f\"select * from {table} where training=0\")"
    ]
   },
   {

{workbench-0.8.187 → workbench-0.8.189}/notebooks/ML_Pipeline_with_Workbench_2.ipynb

@@ -316,7 +316,7 @@
    "id": "a12b00ea",
    "metadata": {},
    "source": [
-    "table = fs.view(\"training\").table\n",
+    "table = model.training_view().table\n",
     "test_df = fs.query(f\"select * from {table} where training=0\")\n",
     "test_df.head()"
    ],

{workbench-0.8.187 → workbench-0.8.189}/src/workbench/core/artifacts/endpoint_core.py

@@ -356,7 +356,7 @@ class EndpointCore(Artifact):
             return pd.DataFrame()
 
         # Grab the evaluation data from the FeatureSet
-        table = fs.view("training").table
+        table = model.training_view().table
         eval_df = fs.query(f'SELECT * FROM "{table}" where training = FALSE')
         capture_name = "auto_inference" if capture else None
         return self.inference(eval_df, capture_name, id_column=fs.id_column)
@@ -472,7 +472,7 @@ class EndpointCore(Artifact):
             self.log.important("UQ Regressor detected, running full inference to get uncertainty estimates...")
 
             # Get the training view dataframe for inference
-            training_df = fs.view("training").pull_dataframe()
+            training_df = model.training_view().pull_dataframe()
 
             # Run inference on the endpoint to get UQ outputs
             uq_df = self.inference(training_df)
@@ -1103,7 +1103,7 @@ class EndpointCore(Artifact):
 if __name__ == "__main__":
     """Exercise the Endpoint Class"""
     from workbench.api import FeatureSet
-    from workbench.utils.endpoint_utils import fs_evaluation_data
+    from workbench.utils.endpoint_utils import get_evaluation_data
     import random
 
     # Grab an EndpointCore object and pull some information from it
@@ -1111,7 +1111,7 @@ if __name__ == "__main__":
 
     # Test various error conditions (set row 42 length to pd.NA)
     # Note: This test should return ALL rows
-    my_eval_df = fs_evaluation_data(my_endpoint)
+    my_eval_df = get_evaluation_data(my_endpoint)
     my_eval_df.at[42, "length"] = pd.NA
     pred_results = my_endpoint.inference(my_eval_df, drop_error_rows=True)
     print(f"Sent rows: {len(my_eval_df)}")
@@ -1182,11 +1182,11 @@ if __name__ == "__main__":
     # Run Inference where we provide the data
     # Note: This dataframe could be from a FeatureSet or any other source
     print("Running Inference...")
-    my_eval_df = fs_evaluation_data(my_endpoint)
+    my_eval_df = get_evaluation_data(my_endpoint)
     pred_results = my_endpoint.inference(my_eval_df)
 
     # Now set capture=True to save inference results and metrics
-    my_eval_df = fs_evaluation_data(my_endpoint)
+    my_eval_df = get_evaluation_data(my_endpoint)
     pred_results = my_endpoint.inference(my_eval_df, capture_name="holdout_xyz")
 
     # Run predictions using the fast_inference method

{workbench-0.8.187 → workbench-0.8.189}/src/workbench/core/artifacts/feature_set_core.py

@@ -194,24 +194,24 @@ class FeatureSetCore(Artifact):
 
         return View(self, view_name)
 
-    def set_display_columns(self, diplay_columns: list[str]):
+    def set_display_columns(self, display_columns: list[str]):
         """Set the display columns for this Data Source
 
         Args:
-            diplay_columns (list[str]): The display columns for this Data Source
+            display_columns (list[str]): The display columns for this Data Source
         """
         # Check mismatch of display columns to computation columns
         c_view = self.view("computation")
         computation_columns = c_view.columns
-        mismatch_columns = [col for col in diplay_columns if col not in computation_columns]
+        mismatch_columns = [col for col in display_columns if col not in computation_columns]
         if mismatch_columns:
             self.log.monitor(f"Display View/Computation mismatch: {mismatch_columns}")
 
-        self.log.important(f"Setting Display Columns...{diplay_columns}")
+        self.log.important(f"Setting Display Columns...{display_columns}")
         from workbench.core.views import DisplayView
 
         # Create a NEW display view
-        DisplayView.create(self, source_table=c_view.table, column_list=diplay_columns)
+        DisplayView.create(self, source_table=c_view.table, column_list=display_columns)
 
     def set_computation_columns(self, computation_columns: list[str], reset_display: bool = True):
         """Set the computation columns for this FeatureSet

{workbench-0.8.187 → workbench-0.8.189}/src/workbench/core/artifacts/model_core.py

@@ -592,6 +592,24 @@ class ModelCore(Artifact):
         # Return the details
         return details
 
+    # Training View for this model
+    def training_view(self):
+        """Get the training view for this model"""
+        from workbench.core.artifacts.feature_set_core import FeatureSetCore
+        from workbench.core.views import View
+
+        # Grab our FeatureSet
+        fs = FeatureSetCore(self.get_input())
+
+        # See if we have a training view for this model
+        my_model_training_view = f"{self.name.replace('-', '_')}_training"
+        view = View(fs, my_model_training_view, auto_create_view=False)
+        if view.exists():
+            return view
+        else:
+            self.log.important(f"No specific training view {my_model_training_view}, returning default training view")
+            return fs.view("training")
+
     # Pipeline for this model
     def get_pipeline(self) -> str:
         """Get the pipeline for this model"""

{workbench-0.8.187 → workbench-0.8.189}/src/workbench/core/transforms/features_to_model/features_to_model.py

@@ -264,6 +264,11 @@ class FeaturesToModel(Transform):
         self.log.important(f"Creating new model {self.output_name}...")
         self.create_and_register_model(**kwargs)
 
+        # Make a copy of the training view, to lock-in the training data used for this model
+        model_training_view_name = f"{self.output_name.replace('-', '_')}_training"
+        self.log.important(f"Creating Model Training View: {model_training_view_name}...")
+        feature_set.view("training").copy(f"{model_training_view_name}")
+
     def post_transform(self, **kwargs):
         """Post-Transform: Calling onboard() on the Model"""
         self.log.info("Post-Transform: Calling onboard() on the Model...")

{workbench-0.8.187 → workbench-0.8.189}/src/workbench/core/views/training_view.py

@@ -10,7 +10,11 @@ from workbench.core.views.view_utils import get_column_list
 
 
 class TrainingView(CreateView):
-    """TrainingView Class: A View with an additional training column that marks holdout ids
+    """TrainingView Class: A View with an additional training column (80/20 or holdout ids).
+    The TrainingView class creates a SQL view that includes all columns from the source table
+    along with an additional boolean column named "training". This view can also include
+    a SQL filter expression to filter the rows included in the view.
+
 
     Common Usage:
         ```python
@@ -19,8 +23,9 @@ class TrainingView(CreateView):
         training_view = TrainingView.create(fs)
         df = training_view.pull_dataframe()
 
-        # Create a TrainingView with a specific set of columns
-        training_view = TrainingView.create(fs, column_list=["my_col1", "my_col2"])
+        # Create a TrainingView with a specific filter expression
+        training_view = TrainingView.create(fs, id_column="auto_id", filter_expression="age > 30")
+        df = training_view.pull_dataframe()
 
         # Query the view
         df = training_view.query(f"SELECT * FROM {training_view.table} where training = TRUE")
@@ -31,20 +36,21 @@ class TrainingView(CreateView):
     def create(
         cls,
         feature_set: FeatureSet,
-        source_table: str = None,
+        *,  # Enforce keyword arguments after feature_set
         id_column: str = None,
         holdout_ids: Union[list[str], list[int], None] = None,
         filter_expression: str = None,
+        source_table: str = None,
     ) -> Union[View, None]:
         """Factory method to create and return a TrainingView instance.
 
         Args:
             feature_set (FeatureSet): A FeatureSet object
-            source_table (str, optional): The table/view to create the view from. Defaults to None.
             id_column (str, optional): The name of the id column. Defaults to None.
             holdout_ids (Union[list[str], list[int], None], optional): A list of holdout ids. Defaults to None.
             filter_expression (str, optional): SQL filter expression (e.g., "age > 25 AND status = 'active'").
                                                Defaults to None.
+            source_table (str, optional): The table/view to create the view from. Defaults to None.
 
         Returns:
             Union[View, None]: The created View object (or None if failed to create the view)

{workbench-0.8.187 → workbench-0.8.189}/src/workbench/core/views/view.py

@@ -196,12 +196,52 @@ class View:
 
         # The BaseView always exists
         if self.view_name == "base":
-            return True
+            return
 
         # Check the database directly
         if not self._check_database():
             self._auto_create_view()
 
+    def copy(self, dest_view_name: str) -> "View":
+        """Copy this view to a new view with a different name
+
+        Args:
+            dest_view_name (str): The destination view name (e.g. "training_v1")
+
+        Returns:
+            View: A new View object for the destination view
+        """
+        # Can't copy the base view
+        if self.view_name == "base":
+            self.log.error("Cannot copy the base view")
+            return None
+
+        # Get the view definition
+        get_view_query = f"""
+        SELECT view_definition
+        FROM information_schema.views
+        WHERE table_schema = '{self.database}'
+        AND table_name = '{self.table}'
+        """
+        df = self.data_source.query(get_view_query)
+
+        if df.empty:
+            self.log.error(f"View {self.table} not found")
+            return None
+
+        view_definition = df.iloc[0]["view_definition"]
+
+        # Create the new view with the destination name
+        dest_table = f"{self.base_table_name}___{dest_view_name}"
+        create_view_query = f'CREATE OR REPLACE VIEW "{dest_table}" AS {view_definition}'
+
+        self.log.important(f"Copying view {self.table} to {dest_table}...")
+        self.data_source.execute_statement(create_view_query)
+
+        # Return a new View object for the destination
+        artifact = FeatureSet(self.artifact_name) if self.is_feature_set else DataSource(self.artifact_name)
+        return View(artifact, dest_view_name, auto_create_view=False)
+
     def _check_database(self) -> bool:
         """Internal: Check if the view exists in the database
 
@@ -324,3 +364,13 @@ if __name__ == "__main__":
     # Test supplemental data tables deletion
     view = View(fs, "test_view")
     view.delete()
+
+    # Test copying a view
+    fs = FeatureSet("test_features")
+    display_view = View(fs, "display")
+    copied_view = display_view.copy("display_copy")
+    print(copied_view)
+    print(copied_view.pull_dataframe().head())
+
+    # Clean up copied view
+    copied_view.delete()

{workbench-0.8.187 → workbench-0.8.189}/src/workbench/core/views/view_utils.py

@@ -296,15 +296,15 @@ if __name__ == "__main__":
     print("View Details on the FeatureSet Table...")
     print(view_details(my_data_source.table, my_data_source.database, my_data_source.boto3_session))
 
-    print("View Details on the Training View...")
-    training_view = fs.view("training")
+    print("View Details on the Display View...")
+    training_view = fs.view("display")
     print(view_details(training_view.table, training_view.database, my_data_source.boto3_session))
 
     # Test get_column_list
     print(get_column_list(my_data_source))
 
-    # Test get_column_list (with training view)
-    training_table = fs.view("training").table
+    # Test get_column_list (with display view)
+    training_table = fs.view("display").table
     print(get_column_list(my_data_source, training_table))
 
     # Test list_views

{workbench-0.8.187 → workbench-0.8.189}/src/workbench/model_scripts/xgb_model/generated_model_script.py

@@ -29,12 +29,12 @@ from typing import List, Tuple
 # Template Parameters
 TEMPLATE_PARAMS = {
     "model_type": "regressor",
-    "target": "udm_asy_res_value",
-    "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": "class_number_of_rings",
+    "features": ['length', 'diameter', 'height', 'whole_weight', 'shucked_weight', 'viscera_weight', 'shell_weight', 'sex'],
     "compressed_features": [],
-    "model_metrics_s3_path": "s3://ideaya-sageworks-bucket/models/logd-hyper-80/training",
+    "model_metrics_s3_path": "s3://sandbox-sageworks-artifacts/models/abalone-regression/training",
     "train_all_data": False,
-    "hyperparameters": {'n_estimators': 200, 'max_depth': 6, 'learning_rate': 0.05, 'subsample': 0.7, 'colsample_bytree': 0.3, 'colsample_bylevel': 0.5, 'min_child_weight': 5, 'gamma': 0.2, 'reg_alpha': 0.5, 'reg_lambda': 2.0, 'scale_pos_weight': 1},
+    "hyperparameters": {},
 }
 
 
@@ -145,7 +145,7 @@ def convert_categorical_types(df: pd.DataFrame, features: list, category_mapping
 def decompress_features(
     df: pd.DataFrame, features: List[str], compressed_features: List[str]
 ) -> Tuple[pd.DataFrame, List[str]]:
-    """Prepare features for the model
+    """Prepare features for the model by decompressing bitstring features
 
     Args:
         df (pd.DataFrame): The features DataFrame
@@ -170,7 +170,7 @@ def decompress_features(
         )
 
     # Decompress the specified compressed features
-    decompressed_features = features
+    decompressed_features = features.copy()
     for feature in compressed_features:
         if (feature not in df.columns) or (feature not in features):
             print(f"Feature '{feature}' not in the features list, skipping decompression.")

{workbench-0.8.187 → workbench-0.8.189}/src/workbench/utils/endpoint_utils.py

@@ -7,9 +7,7 @@ from typing import Union, Optional
 import pandas as pd
 
 # Workbench Imports
-from workbench.api.feature_set import FeatureSet
-from workbench.api.model import Model
-from workbench.api.endpoint import Endpoint
+from workbench.api import FeatureSet, Model, Endpoint
 
 # Set up the log
 log = logging.getLogger("workbench")
@@ -77,7 +75,7 @@ def internal_model_data_url(endpoint_config_name: str, session: boto3.Session) -
         return None
 
 
-def fs_training_data(end: Endpoint) -> pd.DataFrame:
+def get_training_data(end: Endpoint) -> pd.DataFrame:
     """Code to get the training data from the FeatureSet used to train the Model
 
     Args:
@@ -100,7 +98,7 @@ def fs_training_data(end: Endpoint) -> pd.DataFrame:
     return train_df
 
 
-def fs_evaluation_data(end: Endpoint) -> pd.DataFrame:
+def get_evaluation_data(end: Endpoint) -> pd.DataFrame:
     """Code to get the evaluation data from the FeatureSet NOT used for training
 
     Args:
@@ -178,11 +176,11 @@ if __name__ == "__main__":
     print(model_data_url)
 
     # Get the training data
-    my_train_df = fs_training_data(my_endpoint)
+    my_train_df = get_training_data(my_endpoint)
     print(my_train_df)
 
     # Get the evaluation data
-    my_eval_df = fs_evaluation_data(my_endpoint)
+    my_eval_df = get_evaluation_data(my_endpoint)
     print(my_eval_df)
 
     # Backtrack to the FeatureSet

{workbench-0.8.187 → workbench-0.8.189}/src/workbench/utils/model_utils.py

@@ -93,12 +93,11 @@ def get_custom_script_path(package: str, script_name: str) -> Path:
     return script_path
 
 
-def proximity_model_local(model: "Model", filtered: bool = True):
+def proximity_model_local(model: "Model"):
     """Create a Proximity Model for this Model
 
     Args:
-        model (Model): The model to create the proximity model from
-        filtered (bool, optional): Use filtered training data for the Proximity Model (default: True)
+        model (Model): The Model/FeatureSet used to create the proximity model
 
     Returns:
         Proximity: The proximity model
@@ -110,13 +109,12 @@ def proximity_model_local(model: "Model", filtered: bool = True):
     features = model.features()
     target = model.target()
 
-    # Create the Proximity Model from our FeatureSet
+    # Backtrack our FeatureSet to get the ID column
     fs = FeatureSet(model.get_input())
-    if filtered:
-        df = fs.view("training").pull_dataframe()
-    else:
-        df = fs.pull_dataframe()
     id_column = fs.id_column
+
+    # Create the Proximity Model from our Training Data
+    df = model.training_view().pull_dataframe()
     return Proximity(df, id_column, features, target, track_columns=features)
 
 

{workbench-0.8.187 → workbench-0.8.189}/src/workbench/utils/xgboost_model_utils.py

@@ -298,7 +298,7 @@ def cross_fold_inference(workbench_model: Any, nfolds: int = 5) -> Tuple[Dict[st
 
     # Prepare data
     fs = FeatureSet(workbench_model.get_input())
-    df = fs.view("training").pull_dataframe()
+    df = workbench_model.training_view().pull_dataframe()
 
     # Get id column - assuming FeatureSet has an id_column attribute or similar
     id_col = fs.id_column
@@ -423,7 +423,7 @@ def leave_one_out_inference(workbench_model: Any) -> pd.DataFrame:
 
     # Load and prepare data
     fs = FeatureSet(workbench_model.get_input())
-    df = fs.view("training").pull_dataframe()
+    df = workbench_model.training_view().pull_dataframe()
     id_col = fs.id_column
     target_col = workbench_model.target()
     feature_cols = workbench_model.features()

{workbench-0.8.187 → workbench-0.8.189}/src/workbench.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: workbench
-Version: 0.8.187
+Version: 0.8.189
 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-0.8.187 → workbench-0.8.189}/tests/artifacts/endpoint_tests.py

@@ -4,7 +4,7 @@ import pandas as pd
 
 # Workbench Imports
 from workbench.api import FeatureSet, Endpoint
-from workbench.utils.endpoint_utils import fs_evaluation_data
+from workbench.utils.endpoint_utils import get_evaluation_data
 
 reg_endpoint = Endpoint("abalone-regression")
 class_endpoint = Endpoint("wine-classification")
@@ -37,7 +37,7 @@ def test_classification_auto_inference():
 
 
 def test_classification_inference_with_subset_of_labels():
-    eval_data_df = fs_evaluation_data(class_endpoint)[:50]
+    eval_data_df = get_evaluation_data(class_endpoint)[:50]
 
     # Subset the rows to only include the first 2 classes
     print("Using only TypeA and TypeB classes")
@@ -64,7 +64,7 @@ def test_classification_inference_with_subset_of_labels():
 def test_classification_roc_auc():
 
     # Compute performance metrics for our test predictions
-    eval_data_df = fs_evaluation_data(class_endpoint)[:50]
+    eval_data_df = get_evaluation_data(class_endpoint)[:50]
     pred_df = class_endpoint.inference(eval_data_df)
 
     # Normal test ROCAUC should 1 (or close to 1)
@@ -94,7 +94,7 @@ def test_classification_roc_auc():
 
 
 def test_manual_inference():
-    eval_data_df = fs_evaluation_data(reg_endpoint)[:50]
+    eval_data_df = get_evaluation_data(reg_endpoint)[:50]
     pred_df = reg_endpoint.inference(eval_data_df)
     print(pred_df)
 
@@ -102,7 +102,7 @@ def test_manual_inference():
 def test_regression_metrics():
     # Compute performance metrics for our test predictions
     target_column = "class_number_of_rings"
-    eval_data_df = fs_evaluation_data(reg_endpoint)[:50]
+    eval_data_df = get_evaluation_data(reg_endpoint)[:50]
     pred_df = reg_endpoint.inference(eval_data_df)
     metrics = reg_endpoint.regression_metrics(target_column, pred_df)
     print(metrics)
@@ -113,7 +113,7 @@ def test_regression_metrics():
 
 
 def test_classification_metrics():
-    eval_data_df = fs_evaluation_data(class_endpoint)[:50]
+    eval_data_df = get_evaluation_data(class_endpoint)[:50]
     pred_df = class_endpoint.inference(eval_data_df)
     print(pred_df)
 
@@ -132,7 +132,7 @@ def test_classification_metrics():
 
 
 def test_fast_inference():
-    eval_data_df = fs_evaluation_data(class_endpoint)[:50]
+    eval_data_df = get_evaluation_data(class_endpoint)[:50]
     pred_df = class_endpoint.fast_inference(eval_data_df)
     print(pred_df)