workbench 0.8.188__tar.gz → 0.8.190__tar.gz

{workbench-0.8.188 → workbench-0.8.190}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: workbench
-Version: 0.8.188
+Version: 0.8.190
 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-0.8.188 → workbench-0.8.190}/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-0.8.188 → workbench-0.8.190}/src/workbench/core/artifacts/model_core.py

@@ -602,7 +602,7 @@ class ModelCore(Artifact):
         fs = FeatureSetCore(self.get_input())
 
         # See if we have a training view for this model
-        my_model_training_view = f"{self.name.replace("-", "_")}_training"
+        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

{workbench-0.8.188 → workbench-0.8.190}/src/workbench/core/transforms/features_to_model/features_to_model.py

@@ -265,7 +265,7 @@ class FeaturesToModel(Transform):
         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"
+        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}")
 

{workbench-0.8.188 → workbench-0.8.190}/src/workbench/scripts/lambda_launcher.py

@@ -1,11 +1,13 @@
 import sys
 import os
+import json
 import importlib.util
 
 
 def main():
     if len(sys.argv) != 2:
         print("Usage: lambda_launcher <handler_module_name>")
+        print("\nOptional: Create event.json with test event")
         sys.exit(1)
 
     handler_file = sys.argv[1]
@@ -19,6 +21,15 @@ def main():
         print(f"Error: File '{handler_file}' not found")
         sys.exit(1)
 
+    # Load event configuration
+    if os.path.exists("event.json"):
+        print("Loading event from event.json")
+        with open("event.json") as f:
+            event = json.load(f)
+    else:
+        print("No event.json found, using empty event")
+        event = {}
+
     # Load the module dynamically
     spec = importlib.util.spec_from_file_location("lambda_module", handler_file)
     lambda_module = importlib.util.module_from_spec(spec)
@@ -27,12 +38,14 @@ def main():
     # Call the lambda_handler
     print(f"Invoking lambda_handler from {handler_file}...")
     print("-" * 50)
+    print(f"Event: {json.dumps(event, indent=2)}")
+    print("-" * 50)
 
-    result = lambda_module.lambda_handler({}, {})
+    result = lambda_module.lambda_handler(event, {})
 
     print("-" * 50)
     print("Result:")
-    print(result)
+    print(json.dumps(result, indent=2))
 
 
 if __name__ == "__main__":

{workbench-0.8.188 → workbench-0.8.190}/src/workbench/scripts/ml_pipeline_sqs.py

@@ -14,7 +14,12 @@ workbench_bucket = cm.get_config("WORKBENCH_BUCKET")
 
 
 def submit_to_sqs(
-    script_path: str, size: str = "small", realtime: bool = False, dt: bool = False, promote: bool = False
+    script_path: str,
+    size: str = "small",
+    realtime: bool = False,
+    dt: bool = False,
+    promote: bool = False,
+    model_names: str = None,
 ) -> None:
     """
     Upload script to S3 and submit message to SQS queue for processing.
@@ -25,9 +30,10 @@ def submit_to_sqs(
         realtime: If True, sets serverless=False for real-time processing (default: False)
         dt: If True, sets DT=True in environment (default: False)
         promote: If True, sets PROMOTE=True in environment (default: False)
+        model_names: Comma-separated model names (required if dt=True)
 
     Raises:
-        ValueError: If size is invalid or script file not found
+        ValueError: If size is invalid, script file not found, or dt=True without model_names
     """
     print(f"\n{'=' * 60}")
     print("🚀  SUBMITTING ML PIPELINE JOB")
@@ -35,6 +41,11 @@ def submit_to_sqs(
 
     if size not in ["small", "medium", "large"]:
         raise ValueError(f"Invalid size '{size}'. Must be 'small', 'medium', or 'large'")
+
+    # Validate dt requirements
+    if dt and not model_names:
+        raise ValueError("model_names is required when dt=True")
+
     # Validate script exists
     script_file = Path(script_path)
     if not script_file.exists():
@@ -45,6 +56,8 @@ def submit_to_sqs(
     print(f"⚡  Mode: {'Real-time' if realtime else 'Serverless'} (serverless={'False' if realtime else 'True'})")
     print(f"🔄  DynamicTraining: {dt}")
     print(f"🆕  Promote: {promote}")
+    if model_names:
+        print(f"🏷️ Model names: {model_names}")
     print(f"🪣  Bucket: {workbench_bucket}")
     sqs = AWSAccountClamp().boto3_session.client("sqs")
     script_name = script_file.name
@@ -108,6 +121,10 @@ def submit_to_sqs(
         "PROMOTE": str(promote),
     }
 
+    # Add MODEL_NAMES if provided
+    if model_names:
+        message["environment"]["MODEL_NAMES"] = model_names
+
     # Send the message to SQS
     try:
         print("\n📨  Sending message to SQS...")
@@ -132,6 +149,8 @@ def submit_to_sqs(
     print(f"⚡  Mode: {'Real-time' if realtime else 'Serverless'} (SERVERLESS={'False' if realtime else 'True'})")
     print(f"🔄  DynamicTraining: {dt}")
     print(f"🆕  Promote: {promote}")
+    if model_names:
+        print(f"🏷️ Model names: {model_names}")
     print(f"🆔  Message ID: {message_id}")
     print("\n🔍  MONITORING LOCATIONS:")
     print(f"   • SQS Queue: AWS Console → SQS → {queue_name}")
@@ -163,9 +182,20 @@ def main():
         action="store_true",
         help="Set Promote=True (models and endpoints will use promoted naming",
     )
+    parser.add_argument(
+        "--model-names",
+        help="Comma-separated model names (required if --dt is set)",
+    )
     args = parser.parse_args()
     try:
-        submit_to_sqs(args.script_file, args.size, realtime=args.realtime, dt=args.dt, promote=args.promote)
+        submit_to_sqs(
+            args.script_file,
+            args.size,
+            realtime=args.realtime,
+            dt=args.dt,
+            promote=args.promote,
+            model_names=args.model_names,
+        )
     except Exception as e:
         print(f"\n❌  ERROR: {e}")
         log.error(f"Error: {e}")

{workbench-0.8.188 → workbench-0.8.190}/src/workbench.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: workbench
-Version: 0.8.188
+Version: 0.8.190
 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-0.8.188 → workbench-0.8.190}/src/workbench.egg-info/SOURCES.txt

@@ -560,14 +560,12 @@ src/workbench/model_scripts/custom_models/meta_endpoints/example.py
 src/workbench/model_scripts/custom_models/network_security/Readme.md
 src/workbench/model_scripts/custom_models/proximity/Readme.md
 src/workbench/model_scripts/custom_models/proximity/feature_space_proximity.template
-src/workbench/model_scripts/custom_models/proximity/generated_model_script.py
 src/workbench/model_scripts/custom_models/proximity/proximity.py
 src/workbench/model_scripts/custom_models/proximity/requirements.txt
 src/workbench/model_scripts/custom_models/uq_models/Readme.md
 src/workbench/model_scripts/custom_models/uq_models/bayesian_ridge.template
 src/workbench/model_scripts/custom_models/uq_models/ensemble_xgb.template
 src/workbench/model_scripts/custom_models/uq_models/gaussian_process.template
-src/workbench/model_scripts/custom_models/uq_models/generated_model_script.py
 src/workbench/model_scripts/custom_models/uq_models/meta_uq.template
 src/workbench/model_scripts/custom_models/uq_models/ngboost.template
 src/workbench/model_scripts/custom_models/uq_models/proximity.py
@@ -575,18 +573,13 @@ src/workbench/model_scripts/custom_models/uq_models/requirements.txt
 src/workbench/model_scripts/custom_script_example/custom_model_script.py
 src/workbench/model_scripts/custom_script_example/requirements.txt
 src/workbench/model_scripts/ensemble_xgb/ensemble_xgb.template
-src/workbench/model_scripts/ensemble_xgb/generated_model_script.py
 src/workbench/model_scripts/ensemble_xgb/requirements.txt
-src/workbench/model_scripts/pytorch_model/generated_model_script.py
 src/workbench/model_scripts/pytorch_model/pytorch.template
 src/workbench/model_scripts/pytorch_model/requirements.txt
-src/workbench/model_scripts/scikit_learn/generated_model_script.py
 src/workbench/model_scripts/scikit_learn/requirements.txt
 src/workbench/model_scripts/scikit_learn/scikit_learn.template
-src/workbench/model_scripts/uq_models/generated_model_script.py
 src/workbench/model_scripts/uq_models/mapie.template
 src/workbench/model_scripts/uq_models/requirements.txt
-src/workbench/model_scripts/xgb_model/generated_model_script.py
 src/workbench/model_scripts/xgb_model/requirements.txt
 src/workbench/model_scripts/xgb_model/xgb_model.template
 src/workbench/repl/__init__.py

workbench-0.8.188/src/workbench/model_scripts/custom_models/proximity/generated_model_script.py

@@ -1,136 +0,0 @@
-# Model: feature_space_proximity
-#
-# Description: The feature_space_proximity model computes nearest neighbors for the given feature space
-#
-
-# Template Placeholders
-TEMPLATE_PARAMS = {
-    "id_column": "udm_mol_bat_id",
-    "features": ['chi2v', 'fr_sulfone', 'chi1v', 'bcut2d_logplow', 'fr_piperzine', 'kappa3', 'smr_vsa1', 'slogp_vsa5', 'fr_ketone_topliss', 'fr_sulfonamd', 'fr_imine', 'fr_benzene', 'fr_ester', 'chi2n', 'labuteasa', 'peoe_vsa2', 'smr_vsa6', 'bcut2d_chglo', 'fr_sh', 'peoe_vsa1', 'fr_allylic_oxid', 'chi4n', 'fr_ar_oh', 'fr_nh0', 'fr_term_acetylene', 'slogp_vsa7', 'slogp_vsa4', 'estate_vsa1', 'vsa_estate4', 'numbridgeheadatoms', 'numheterocycles', 'fr_ketone', 'fr_morpholine', 'fr_guanido', 'estate_vsa2', 'numheteroatoms', 'fr_nitro_arom_nonortho', 'fr_piperdine', 'nocount', 'numspiroatoms', 'fr_aniline', 'fr_thiophene', 'slogp_vsa10', 'fr_amide', 'slogp_vsa2', 'fr_epoxide', 'vsa_estate7', 'fr_ar_coo', 'fr_imidazole', 'fr_nitrile', 'fr_oxazole', 'numsaturatedrings', 'fr_pyridine', 'fr_hoccn', 'fr_ndealkylation1', 'numaliphaticheterocycles', 'fr_phenol', 'maxpartialcharge', 'vsa_estate5', 'peoe_vsa13', 'minpartialcharge', 'qed', 'fr_al_oh', 'slogp_vsa11', 'chi0n', 'fr_bicyclic', 'peoe_vsa12', 'fpdensitymorgan1', 'fr_oxime', 'molwt', 'fr_dihydropyridine', 'smr_vsa5', 'peoe_vsa5', 'fr_nitro', 'hallkieralpha', 'heavyatommolwt', 'fr_alkyl_halide', 'peoe_vsa8', 'fr_nhpyrrole', 'fr_isocyan', 'bcut2d_chghi', 'fr_lactam', 'peoe_vsa11', 'smr_vsa9', 'tpsa', 'chi4v', 'slogp_vsa1', 'phi', 'bcut2d_logphi', 'avgipc', 'estate_vsa11', 'fr_coo', 'bcut2d_mwhi', 'numunspecifiedatomstereocenters', 'vsa_estate10', 'estate_vsa8', 'numvalenceelectrons', 'fr_nh2', 'fr_lactone', 'vsa_estate1', 'estate_vsa4', 'numatomstereocenters', 'vsa_estate8', 'fr_para_hydroxylation', 'peoe_vsa3', 'fr_thiazole', 'peoe_vsa10', 'fr_ndealkylation2', 'slogp_vsa12', 'peoe_vsa9', 'maxestateindex', 'fr_quatn', 'smr_vsa7', 'minestateindex', 'numaromaticheterocycles', 'numrotatablebonds', 'fr_ar_nh', 'fr_ether', 'exactmolwt', 'fr_phenol_noorthohbond', 'slogp_vsa3', 'fr_ar_n', 'sps', 'fr_c_o_nocoo', 'bertzct', 'peoe_vsa7', 'slogp_vsa8', 'numradicalelectrons', 'molmr', 'fr_tetrazole', 'numsaturatedcarbocycles', 'bcut2d_mrhi', 'kappa1', 'numamidebonds', 'fpdensitymorgan2', 'smr_vsa8', 'chi1n', 'estate_vsa6', 'fr_barbitur', 'fr_diazo', 'kappa2', 'chi0', 'bcut2d_mrlow', 'balabanj', 'peoe_vsa4', 'numhacceptors', 'fr_sulfide', 'chi3n', 'smr_vsa2', 'fr_al_oh_notert', 'fr_benzodiazepine', 'fr_phos_ester', 'fr_aldehyde', 'fr_coo2', 'estate_vsa5', 'fr_prisulfonamd', 'numaromaticcarbocycles', 'fr_unbrch_alkane', 'fr_urea', 'fr_nitroso', 'smr_vsa10', 'fr_c_s', 'smr_vsa3', 'fr_methoxy', 'maxabspartialcharge', 'slogp_vsa9', 'heavyatomcount', 'fr_azide', 'chi3v', 'smr_vsa4', 'mollogp', 'chi0v', 'fr_aryl_methyl', 'fr_nh1', 'fpdensitymorgan3', 'fr_furan', 'fr_hdrzine', 'fr_arn', 'numaromaticrings', 'vsa_estate3', 'fr_azo', 'fr_halogen', 'estate_vsa9', 'fr_hdrzone', 'numhdonors', 'fr_alkyl_carbamate', 'fr_isothiocyan', 'minabspartialcharge', 'fr_al_coo', 'ringcount', 'chi1', 'estate_vsa7', 'fr_nitro_arom', 'vsa_estate9', 'minabsestateindex', 'maxabsestateindex', 'vsa_estate6', 'estate_vsa10', 'estate_vsa3', 'fr_n_o', 'fr_amidine', 'fr_thiocyan', 'fr_phos_acid', 'fr_c_o', 'fr_imide', 'numaliphaticrings', 'peoe_vsa6', 'vsa_estate2', 'nhohcount', 'numsaturatedheterocycles', 'slogp_vsa6', 'peoe_vsa14', 'fractioncsp3', 'bcut2d_mwlow', 'numaliphaticcarbocycles', 'fr_priamide', 'nacid', 'nbase', 'naromatom', 'narombond', 'sz', 'sm', 'sv', 'sse', 'spe', 'sare', 'sp', 'si', 'mz', 'mm', 'mv', 'mse', 'mpe', 'mare', 'mp', 'mi', 'xch_3d', 'xch_4d', 'xch_5d', 'xch_6d', 'xch_7d', 'xch_3dv', 'xch_4dv', 'xch_5dv', 'xch_6dv', 'xch_7dv', 'xc_3d', 'xc_4d', 'xc_5d', 'xc_6d', 'xc_3dv', 'xc_4dv', 'xc_5dv', 'xc_6dv', 'xpc_4d', 'xpc_5d', 'xpc_6d', 'xpc_4dv', 'xpc_5dv', 'xpc_6dv', 'xp_0d', 'xp_1d', 'xp_2d', 'xp_3d', 'xp_4d', 'xp_5d', 'xp_6d', 'xp_7d', 'axp_0d', 'axp_1d', 'axp_2d', 'axp_3d', 'axp_4d', 'axp_5d', 'axp_6d', 'axp_7d', 'xp_0dv', 'xp_1dv', 'xp_2dv', 'xp_3dv', 'xp_4dv', 'xp_5dv', 'xp_6dv', 'xp_7dv', 'axp_0dv', 'axp_1dv', 'axp_2dv', 'axp_3dv', 'axp_4dv', 'axp_5dv', 'axp_6dv', 'axp_7dv', 'c1sp1', 'c2sp1', 'c1sp2', 'c2sp2', 'c3sp2', 'c1sp3', 'c2sp3', 'c3sp3', 'c4sp3', 'hybratio', 'fcsp3', 'num_stereocenters', 'num_unspecified_stereocenters', 'num_defined_stereocenters', 'num_r_centers', 'num_s_centers', 'num_stereobonds', 'num_e_bonds', 'num_z_bonds', 'stereo_complexity', 'frac_defined_stereo'],
-    "target": "udm_asy_res_free_percent",
-    "track_columns": None,
-}
-
-from io import StringIO
-import json
-import argparse
-import os
-import pandas as pd
-
-# Local Imports
-from proximity import Proximity
-
-
-# Function to check if dataframe is empty
-def check_dataframe(df: pd.DataFrame, df_name: str) -> None:
-    """Check if the DataFrame is empty and raise an error if so."""
-    if df.empty:
-        msg = f"*** The training data {df_name} has 0 rows! ***STOPPING***"
-        print(msg)
-        raise ValueError(msg)
-
-
-# Function to match DataFrame columns to model features (case-insensitive)
-def match_features_case_insensitive(df: pd.DataFrame, model_features: list) -> pd.DataFrame:
-    """Match and rename DataFrame columns to match the model's features, case-insensitively."""
-    # Create a set of exact matches from the DataFrame columns
-    exact_match_set = set(df.columns)
-
-    # Create a case-insensitive map of DataFrame columns
-    column_map = {col.lower(): col for col in df.columns}
-    rename_dict = {}
-
-    # Build a dictionary for renaming columns based on case-insensitive matching
-    for feature in model_features:
-        if feature in exact_match_set:
-            rename_dict[feature] = feature
-        elif feature.lower() in column_map:
-            rename_dict[column_map[feature.lower()]] = feature
-
-    # Rename columns in the DataFrame to match model features
-    return df.rename(columns=rename_dict)
-
-
-# TRAINING SECTION
-#
-# This section (__main__) is where SageMaker will execute the training job
-# and save the model artifacts to the model directory.
-#
-if __name__ == "__main__":
-    # Template Parameters
-    id_column = TEMPLATE_PARAMS["id_column"]
-    features = TEMPLATE_PARAMS["features"]
-    target = TEMPLATE_PARAMS["target"]  # Can be None for unsupervised models
-    track_columns = TEMPLATE_PARAMS["track_columns"]  # Can be None
-
-    # Script arguments for input/output directories
-    parser = argparse.ArgumentParser()
-    parser.add_argument("--model-dir", type=str, default=os.environ.get("SM_MODEL_DIR", "/opt/ml/model"))
-    parser.add_argument("--train", type=str, default=os.environ.get("SM_CHANNEL_TRAIN", "/opt/ml/input/data/train"))
-    parser.add_argument(
-        "--output-data-dir", type=str, default=os.environ.get("SM_OUTPUT_DATA_DIR", "/opt/ml/output/data")
-    )
-    args = parser.parse_args()
-
-    # Load training data from the specified directory
-    training_files = [os.path.join(args.train, file) for file in os.listdir(args.train) if file.endswith(".csv")]
-    all_df = pd.concat([pd.read_csv(file, engine="python") for file in training_files])
-
-    # Check if the DataFrame is empty
-    check_dataframe(all_df, "training_df")
-
-    # Create the Proximity model
-    model = Proximity(all_df, id_column, features, target, track_columns=track_columns)
-
-    # Now serialize the model
-    model.serialize(args.model_dir)
-
-
-# Model loading and prediction functions
-def model_fn(model_dir):
-
-    # Deserialize the model
-    model = Proximity.deserialize(model_dir)
-    return model
-
-
-def input_fn(input_data, content_type):
-    """Parse input data and return a DataFrame."""
-    if not input_data:
-        raise ValueError("Empty input data is not supported!")
-
-    # Decode bytes to string if necessary
-    if isinstance(input_data, bytes):
-        input_data = input_data.decode("utf-8")
-
-    if "text/csv" in content_type:
-        return pd.read_csv(StringIO(input_data))
-    elif "application/json" in content_type:
-        return pd.DataFrame(json.loads(input_data))  # Assumes JSON array of records
-    else:
-        raise ValueError(f"{content_type} not supported!")
-
-
-def output_fn(output_df, accept_type):
-    """Supports both CSV and JSON output formats."""
-    use_explicit_na = False
-    if "text/csv" in accept_type:
-        if use_explicit_na:
-            csv_output = output_df.fillna("N/A").to_csv(index=False)  # CSV with N/A for missing values
-        else:
-            csv_output = output_df.to_csv(index=False)
-        return csv_output, "text/csv"
-    elif "application/json" in accept_type:
-        return output_df.to_json(orient="records"), "application/json"  # JSON array of records (NaNs -> null)
-    else:
-        raise RuntimeError(f"{accept_type} accept type is not supported by this script.")
-
-
-# Prediction function
-def predict_fn(df, model):
-    # Match column names before prediction if needed
-    df = match_features_case_insensitive(df, model.features + [model.id_column])
-
-    # Compute Nearest neighbors
-    df = model.neighbors(df)
-    return df