workbench 0.8.186__py3-none-any.whl → 0.8.188__py3-none-any.whl

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/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/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/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/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/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/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/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/scripts/lambda_launcher.py

@@ -0,0 +1,39 @@
+import sys
+import os
+import importlib.util
+
+
+def main():
+    if len(sys.argv) != 2:
+        print("Usage: lambda_launcher <handler_module_name>")
+        sys.exit(1)
+
+    handler_file = sys.argv[1]
+
+    # Add .py if not present
+    if not handler_file.endswith(".py"):
+        handler_file += ".py"
+
+    # Check if file exists
+    if not os.path.exists(handler_file):
+        print(f"Error: File '{handler_file}' not found")
+        sys.exit(1)
+
+    # Load the module dynamically
+    spec = importlib.util.spec_from_file_location("lambda_module", handler_file)
+    lambda_module = importlib.util.module_from_spec(spec)
+    spec.loader.exec_module(lambda_module)
+
+    # Call the lambda_handler
+    print(f"Invoking lambda_handler from {handler_file}...")
+    print("-" * 50)
+
+    result = lambda_module.lambda_handler({}, {})
+
+    print("-" * 50)
+    print("Result:")
+    print(result)
+
+
+if __name__ == "__main__":
+    main()

workbench/scripts/ml_pipeline_sqs.py

@@ -158,9 +158,14 @@ def main():
         action="store_true",
         help="Set DT=True (models and endpoints will have '-dt' suffix)",
     )
+    parser.add_argument(
+        "--promote",
+        action="store_true",
+        help="Set Promote=True (models and endpoints will use promoted naming",
+    )
     args = parser.parse_args()
     try:
-        submit_to_sqs(args.script_file, args.size, realtime=args.realtime, dt=args.dt)
+        submit_to_sqs(args.script_file, args.size, realtime=args.realtime, dt=args.dt, promote=args.promote)
     except Exception as e:
         print(f"\n❌  ERROR: {e}")
         log.error(f"Error: {e}")

workbench/utils/config_manager.py

@@ -4,16 +4,13 @@ import os
 import sys
 import platform
 import logging
-import importlib.resources as resources  # noqa: F401 Python 3.9 compatibility
 from typing import Any, Dict
+from importlib.resources import files, as_file
 
 # Workbench imports
 from workbench.utils.license_manager import LicenseManager
 from workbench_bridges.utils.execution_environment import running_as_service
 
-# Python 3.9 compatibility
-from workbench.utils.resource_utils import get_resource_path
-
 
 class FatalConfigError(Exception):
     """Exception raised for errors in the configuration."""
@@ -172,8 +169,7 @@ class ConfigManager:
         Returns:
             str: The open source API key.
         """
-        # Python 3.9 compatibility
-        with get_resource_path("workbench.resources", "open_source_api.key") as open_source_key_path:
+        with as_file(files("workbench.resources").joinpath("open_source_api.key")) as open_source_key_path:
             with open(open_source_key_path, "r") as key_file:
                 return key_file.read().strip()
 

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/utils/license_manager.py

@@ -6,15 +6,12 @@ import json
 import logging
 import requests
 from typing import Union
-import importlib.resources as resources  # noqa: F401 Python 3.9 compatibility
 from datetime import datetime
 from cryptography.hazmat.primitives import hashes
 from cryptography.hazmat.primitives.asymmetric import padding
 from cryptography.hazmat.primitives import serialization
 from cryptography.hazmat.backends import default_backend
-
-# Python 3.9 compatibility
-from workbench.utils.resource_utils import get_resource_path
+from importlib.resources import files, as_file
 
 
 class FatalLicenseError(Exception):
@@ -140,8 +137,7 @@ class LicenseManager:
         Returns:
             The public key as an object.
         """
-        # Python 3.9 compatibility
-        with get_resource_path("workbench.resources", "signature_verify_pub.pem") as public_key_path:
+        with as_file(files("workbench.resources").joinpath("signature_verify_pub.pem")) as public_key_path:
             with open(public_key_path, "rb") as key_file:
                 public_key_data = key_file.read()
 

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/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-0.8.186.dist-info → workbench-0.8.188.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: workbench
-Version: 0.8.186
+Version: 0.8.188
 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
@@ -10,6 +10,7 @@ Classifier: Development Status :: 4 - Beta
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
 Classifier: Topic :: Scientific/Engineering
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown

{workbench-0.8.186.dist-info → workbench-0.8.188.dist-info}/RECORD

@@ -54,9 +54,9 @@ workbench/core/artifacts/cached_artifact_mixin.py,sha256=ngqFLZ4cQx_TFouXZgXZQsv
 workbench/core/artifacts/data_capture_core.py,sha256=q8f79rRTYiZ7T4IQRWXl8ZvPpcvZyNxYERwvo8o0OQc,14858
 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/endpoint_core.py,sha256=FUBs8z5l0D3UsVqmQzjlzkVDzN0fhMcqKXTLAAG1gmc,51966
-workbench/core/artifacts/feature_set_core.py,sha256=7b1o_PzxtwaYC-W2zxlkltiO0fYULA8CVGWwHNmqgtI,31457
-workbench/core/artifacts/model_core.py,sha256=x_FloG9bMUTqUBDYdfl68AaakwNMBCl-BcP-1E9ZpuQ,51545
+workbench/core/artifacts/endpoint_core.py,sha256=VH-q-R4pfKyjCOXl2Gq1pxMNf4Ir0YdMw9YIHqd7CVU,51974
+workbench/core/artifacts/feature_set_core.py,sha256=6qOJoJ9_qwtyz4neFY6vMn73Ujjeut7E0dy_e8nYfSE,31462
+workbench/core/artifacts/model_core.py,sha256=w9zWNSYHELztiXNvn04pjrIl2n6xYoiHK4Tg1Ze-ukQ,52287
 workbench/core/artifacts/monitor_core.py,sha256=M307yz7tEzOEHgv-LmtVy9jKjSbM98fHW3ckmNYrwlU,27897
 workbench/core/cloud_platform/cloud_meta.py,sha256=-g4-LTC3D0PXb3VfaXdLR1ERijKuHdffeMK_zhD-koQ,8809
 workbench/core/cloud_platform/aws/README.md,sha256=QT5IQXoUHbIA0qQ2wO6_2P2lYjYQFVYuezc22mWY4i8,97
@@ -102,7 +102,7 @@ workbench/core/transforms/features_to_features/__init__.py,sha256=47DEQpj8HBSa-_
 workbench/core/transforms/features_to_features/heavy/emr/Readme.md,sha256=YtQgCEQeKe0CQXQkhzMTYq9xOtCsCYb5P5LW2BmRKWQ,68
 workbench/core/transforms/features_to_features/heavy/glue/Readme.md,sha256=TuyCatWfoDr99zUwvOcxf-TqMkQzaMqXlj5nmFcRzfo,48
 workbench/core/transforms/features_to_model/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-workbench/core/transforms/features_to_model/features_to_model.py,sha256=ALGH5UmCdMYv4Fs2ebh6qMlwzt34xYkVSMpn4YfPbaA,19773
+workbench/core/transforms/features_to_model/features_to_model.py,sha256=1WFrUpGDZtnVhwefobGwObd1YadUh9IpppV98tqaQ7w,20115
 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/pandas_transforms/__init__.py,sha256=xL4MT8-fZ1SFqDbTLc8XyxjupHtB1YR6Ej0AC2nwd7I,894
@@ -118,9 +118,9 @@ workbench/core/views/create_view.py,sha256=2Ykzb2NvJGoD4PP4k2Bka46GDog9iGG5SWnAc
 workbench/core/views/display_view.py,sha256=9K4O77ZnKOh93aMRhxcQJQ1lqScLhuJnU_tHtYZ_U4E,2598
 workbench/core/views/inference_view.py,sha256=9s70M0dFdGq0tWvzMZfgUK7EPKtuvcQhux0uyRZuuLM,3293
 workbench/core/views/pandas_to_view.py,sha256=20uCsnG2iMh-U1VxqVUUtnrWAY98SeuHjmfJK_wcq1I,6422
-workbench/core/views/training_view.py,sha256=UWW8Asxtm_kV7Z8NooitMA4xC5vTc7lSWwTGbLdifqY,5900
-workbench/core/views/view.py,sha256=Ujzw6zLROP9oKfKm3zJwaOyfpyjh5uM9fAu1i3kUOig,11764
-workbench/core/views/view_utils.py,sha256=y0YuPW-90nAfgAD1UW_49-j7Mvncfm7-5rV8I_97CK8,12274
+workbench/core/views/training_view.py,sha256=Wk5fWvnoapngGCHEkqYzRvSNw2f-ZRvhsrzRMYGZfuE,6274
+workbench/core/views/view.py,sha256=QdUSGcrNzpzcwkSkutyptqrlXJZZReWzd2Uc6xQRd8A,13524
+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=dLxVRrvrrI_HQatJRAXta6UEbFFbkgITNvDJllQZyCM,7905
 workbench/model_scripts/custom_models/chem_info/Readme.md,sha256=mH1lxJ4Pb7F5nBnVXaiuxpi8zS_yjUw_LBJepVKXhlA,574
@@ -159,7 +159,7 @@ workbench/model_scripts/scikit_learn/scikit_learn.template,sha256=QQvqx-eX9ZTbYm
 workbench/model_scripts/uq_models/generated_model_script.py,sha256=U4_41APyNISnJ3EHnXiaSIEdb3E1M1JT7ECNjsoX4fI,21197
 workbench/model_scripts/uq_models/mapie.template,sha256=2HIwB_658IsZiLIV1RViIZBIGgXxDsJPZinDUu8SchU,18961
 workbench/model_scripts/uq_models/requirements.txt,sha256=fw7T7t_YJAXK3T6Ysbesxh_Agx_tv0oYx72cEBTqRDY,98
-workbench/model_scripts/xgb_model/generated_model_script.py,sha256=Tbn7EMXxZZO8rDdKQ5fYCbpltACsMXNvuusLL9p-U5c,22319
+workbench/model_scripts/xgb_model/generated_model_script.py,sha256=W3koc4swpjOncpMKWqBHnTGDie0CoDpY9U1oj4OUJrI,17990
 workbench/model_scripts/xgb_model/requirements.txt,sha256=jWlGc7HH7vqyukTm38LN4EyDi8jDUPEay4n45z-30uc,104
 workbench/model_scripts/xgb_model/xgb_model.template,sha256=0uXknIEqgUaIFUfu2gfkxa3WHUr8HBBqBepGUTDvrhQ,17917
 workbench/repl/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -168,8 +168,9 @@ workbench/resources/open_source_api.key,sha256=3S0OTblsmC0msUPdE_dbBmI83xJNmYscu
 workbench/resources/signature_verify_pub.pem,sha256=V3-u-3_z2PH-805ybkKvzDOBwAbvHxcKn0jLBImEtzM,272
 workbench/scripts/check_double_bond_stereo.py,sha256=p5hnL54Weq77ES0HCELq9JeoM-PyUGkvVSeWYF2dKyo,7776
 workbench/scripts/glue_launcher.py,sha256=bIKQvfGxpAhzbeNvTnHfRW_5kQhY-169_868ZnCejJk,10692
+workbench/scripts/lambda_launcher.py,sha256=U5HevvWdwN0SUrN2kpbkf0doY-5Ih_LzjJTH-45LBJ8,925
 workbench/scripts/ml_pipeline_batch.py,sha256=1T5JnLlUJR7bwAGBLHmLPOuj1xFRqVIQX8PsuDhHy8o,4907
-workbench/scripts/ml_pipeline_sqs.py,sha256=LxZyaNKmwt3L7SURyO3lwO64FQ0Y0s4HwKPkkahlhUU,6395
+workbench/scripts/ml_pipeline_sqs.py,sha256=ebe8clE6dMONF43_JiX5Qx1WESPfGlF2-AifvJOde50,6578
 workbench/scripts/monitor_cloud_watch.py,sha256=s7MY4bsHts0nup9G0lWESCvgJZ9Mw1Eo-c8aKRgLjMw,9235
 workbench/scripts/redis_expire.py,sha256=DxI_RKSNlrW2BsJZXcsSbaWGBgPZdPhtzHjV9SUtElE,1120
 workbench/scripts/redis_report.py,sha256=iaJSuGPyLCs6e0TMcZDoT0YyJ43xJ1u74YD8FLnnUg4,990
@@ -202,24 +203,24 @@ workbench/utils/cache.py,sha256=0R5RXYEz_XHARK3anmQC4VRMawMks_cJ8S4vwC2roAE,5524
 workbench/utils/cloudwatch_handler.py,sha256=t0L280Qa1nMq95dwnf8lB5g8FHrQAyGY5S4JwP3yIa8,5165
 workbench/utils/cloudwatch_utils.py,sha256=wXSqKcJlSnHyC0D6d4RsH8wwmx_0CsffcetUgXlZ_78,4828
 workbench/utils/color_utils.py,sha256=TmDGLK44t975lkfjt_1O-ee02QxrKfke7vPuXb-V-Uo,11779
-workbench/utils/config_manager.py,sha256=SBBmO1RGCQ_Zyh91tDxL1HOm5B0v38ImlLnOsEKzXPU,17649
+workbench/utils/config_manager.py,sha256=UPP9SHTLfPyPKEfsgH2YXp9WlImmVZ5zqFft4BxRdlo,17499
 workbench/utils/dashboard_metrics.py,sha256=cNFI0GIAjd_IiDzM1oebsJ2QkRZuW068W_66ZC3J100,7398
 workbench/utils/datetime_utils.py,sha256=r3G_KB2euu26lwVbDXYXPJEpJCZwin2Iph7BiBIoybg,4454
 workbench/utils/deprecated_utils.py,sha256=qniHVpDGuwOnhxn65LofDQ_EA2OhSUcZLPxAXtx7FgA,3540
 workbench/utils/df_to_endpoint.py,sha256=bIb1CDko8_BClX5wcQuBbmcGH79n3oHUcb_1jdUX_7s,5292
 workbench/utils/ecs_info.py,sha256=Gs9jNb4vcj2pziufIOI4BVIH1J-3XBMtWm1phVh8oRY,2873
 workbench/utils/endpoint_metrics.py,sha256=_4WVU6cLLuV0t_i0PSvhi0EoA5ss5aDFe7ZDpumx2R8,7822
-workbench/utils/endpoint_utils.py,sha256=3-njrhMSAIOaEEiH7qMA9vgD3I7J2S9iUAcqXKx3OBo,7104
+workbench/utils/endpoint_utils.py,sha256=1zVy78H2OCE9tSRlS-AdIuF3uePTMq2mW2rnmwLmDv4,7031
 workbench/utils/extract_model_artifact.py,sha256=sFwkJd5mfJ1PU37pIHVmUIQS-taIUJdqi3D9-qRmy8g,7870
 workbench/utils/glue_utils.py,sha256=dslfXQcJ4C-mGmsD6LqeK8vsXBez570t3fZBVZLV7HA,2039
 workbench/utils/graph_utils.py,sha256=T4aslYVbzPmFe0_qKCQP6PZnaw1KATNXQNVO-yDGBxY,10839
 workbench/utils/ipython_utils.py,sha256=skbdbBwUT-iuY3FZwy3ACS7-FWSe9M2qVXfLlQWnikE,700
 workbench/utils/json_utils.py,sha256=FSxzcD88TbIEJDw0FHue5-ZGny94wm5NeLs4zYlLLpU,4881
 workbench/utils/lambda_utils.py,sha256=7GhGRPyXn9o-toWb9HBGSnI8-DhK9YRkwhCSk_mNKMI,1893
-workbench/utils/license_manager.py,sha256=sDuhk1mZZqUbFmnuFXehyGnui_ALxrmYBg7gYwoo7ho,6975
+workbench/utils/license_manager.py,sha256=lNE9zZIglmX3zqqCKBdN1xqTgHCEZgJDxavF6pdG7fc,6825
 workbench/utils/log_utils.py,sha256=7n1NJXO_jUX82e6LWAQug6oPo3wiPDBYsqk9gsYab_A,3167
 workbench/utils/markdown_utils.py,sha256=4lEqzgG4EVmLcvvKKNUwNxVCySLQKJTJmWDiaDroI1w,8306
-workbench/utils/model_utils.py,sha256=5z4E_F_uDUhuz5_0ZNqNXvretImF1c49LX158RP6yfI,13588
+workbench/utils/model_utils.py,sha256=YKqvDbSv1qV8nvA7s-xGIxRMj4NT7Lp0zz8aXg3WdtI,13468
 workbench/utils/monitor_utils.py,sha256=kVaJ7BgUXs3VPMFYfLC03wkIV4Dq-pEhoXS0wkJFxCc,7858
 workbench/utils/pandas_utils.py,sha256=uTUx-d1KYfjbS9PMQp2_9FogCV7xVZR6XLzU5YAGmfs,39371
 workbench/utils/performance_utils.py,sha256=WDNvz-bOdC99cDuXl0urAV4DJ7alk_V3yzKPwvqgST4,1329
@@ -229,7 +230,6 @@ workbench/utils/plugin_manager.py,sha256=JWfyFHQih_J_MMtAT1cgjGVnNVPk9bM917LkfH8
 workbench/utils/prox_utils.py,sha256=V0YSxI6lboZl8Bed1GUobFqfMhfpehn2FtgqHpkuhDQ,6170
 workbench/utils/redis_cache.py,sha256=39LFSWmOlNNcah02D3sBnmibc-DPeKC3SNq71K4HaB4,12893
 workbench/utils/repl_utils.py,sha256=rWOMv2HiEIp8ZL6Ps6DlwiJlGr-pOhv9OZQhm3aR-1A,4668
-workbench/utils/resource_utils.py,sha256=EM4SrMmRUQnG80aR5M7hmzw86hYdP_S7fRPuqhpDSVo,1435
 workbench/utils/s3_utils.py,sha256=Xme_o_cftC_jWnw6R9YKS6-6C11zaCBAoQDlY3dZb5o,7337
 workbench/utils/shap_utils.py,sha256=dtjSIwSyvYSaQjjvIp5A9LGS7pr-5Vt907rvVKOrqNY,12651
 workbench/utils/shapley_values.py,sha256=3DvQz4HIPnxW42idgtuQ5vtzU-oF4_lToaWzLRjU-E4,3673
@@ -242,7 +242,7 @@ workbench/utils/workbench_cache.py,sha256=IQchxB81iR4eVggHBxUJdXxUCRkqWz1jKe5gxN
 workbench/utils/workbench_event_bridge.py,sha256=z1GmXOB-Qs7VOgC6Hjnp2DI9nSEWepaSXejACxTIR7o,4150
 workbench/utils/workbench_logging.py,sha256=WCuMWhQwibrvcGAyj96h2wowh6dH7zNlDJ7sWUzdCeI,10263
 workbench/utils/workbench_sqs.py,sha256=RwM80z7YWwdtMaCKh7KWF8v38f7eBRU7kyC7ZhTRuI0,2072
-workbench/utils/xgboost_model_utils.py,sha256=rPfbl5sCZOttkilAHSmYU_u9JIDeYsGi2JrEs-zzcwI,21597
+workbench/utils/xgboost_model_utils.py,sha256=Si2VB-YW-Mjb6hCby_m4KWWajoRzH8e2NwBZSe98tsM,21621
 workbench/utils/chem_utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 workbench/utils/chem_utils/fingerprints.py,sha256=Qvs8jaUwguWUq3Q3j695MY0t0Wk3BvroW-oWBwalMUo,5255
 workbench/utils/chem_utils/misc.py,sha256=Nevf8_opu-uIPrv_1_0ubuFVVo2_fGUkMoLAHB3XAeo,7372
@@ -287,9 +287,9 @@ 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-0.8.186.dist-info/licenses/LICENSE,sha256=z4QMMPlLJkZjU8VOKqJkZiQZCEZ--saIU2Z8-p3aVc0,1080
-workbench-0.8.186.dist-info/METADATA,sha256=r5n70ah6hgyfQfE3oM0gseinKWI4n6DCpvB7ZJXFLNM,9210
-workbench-0.8.186.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-workbench-0.8.186.dist-info/entry_points.txt,sha256=zPFPruY9uayk8-wsKrhfnIyIB6jvZOW_ibyllEIsLWo,356
-workbench-0.8.186.dist-info/top_level.txt,sha256=Dhy72zTxaA_o_yRkPZx5zw-fwumnjGaeGf0hBN3jc_w,10
-workbench-0.8.186.dist-info/RECORD,,
+workbench-0.8.188.dist-info/licenses/LICENSE,sha256=z4QMMPlLJkZjU8VOKqJkZiQZCEZ--saIU2Z8-p3aVc0,1080
+workbench-0.8.188.dist-info/METADATA,sha256=E6u7eeASQ5dzeL4IMVmaOUmuxp6Vr3vPWeq4oVBvAl4,9261
+workbench-0.8.188.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+workbench-0.8.188.dist-info/entry_points.txt,sha256=o7ohD4D2oygnHp7i9-C0LfcHDuPW5Tv0JXGAg97DpGk,413
+workbench-0.8.188.dist-info/top_level.txt,sha256=Dhy72zTxaA_o_yRkPZx5zw-fwumnjGaeGf0hBN3jc_w,10
+workbench-0.8.188.dist-info/RECORD,,

{workbench-0.8.186.dist-info → workbench-0.8.188.dist-info}/entry_points.txt

@@ -1,6 +1,7 @@
 [console_scripts]
 cloud_watch = workbench.scripts.monitor_cloud_watch:main
 glue_launcher = workbench.scripts.glue_launcher:main
+lambda_launcher = workbench.scripts.lambda_launcher:main
 ml_pipeline_batch = workbench.scripts.ml_pipeline_batch:main
 ml_pipeline_sqs = workbench.scripts.ml_pipeline_sqs:main
 workbench = workbench.repl.workbench_shell:launch_shell

workbench/utils/resource_utils.py

@@ -1,39 +0,0 @@
-"""Resource utilities for Workbench"""
-
-import sys
-import importlib.resources as resources
-import pathlib
-import pkg_resources
-
-
-def get_resource_path(package: str, resource: str) -> pathlib.Path:
-    """Get the path to a resource file, compatible with Python 3.9 and higher.
-
-    Args:
-        package (str): The package where the resource is located.
-        resource (str): The name of the resource file.
-
-    Returns:
-        pathlib.Path: The path to the resource file.
-    """
-    if sys.version_info >= (3, 10):
-        # Python 3.10 and higher: use importlib.resources.path
-        with resources.path(package, resource) as path:
-            return path
-    else:
-        # Python 3.9 and lower: manually construct the path based on package location
-        # Get the location of the installed package
-        package_location = pathlib.Path(pkg_resources.get_distribution(package.split(".")[0]).location)
-        resource_path = package_location / package.replace(".", "/") / resource
-
-        if resource_path.exists():
-            return resource_path
-        else:
-            raise FileNotFoundError(f"Resource '{resource}' not found in package '{package}'.")
-
-
-if __name__ == "__main__":
-    # Test the resource utilities
-    with get_resource_path("workbench.resources", "open_source_api.key") as open_source_key_path:
-        with open(open_source_key_path, "r") as key_file:
-            print(key_file.read().strip())