workbench 0.8.177__tar.gz → 0.8.217__tar.gz

{workbench-0.8.177 → workbench-0.8.217}/.github/workflows/python-lint.yml

@@ -12,9 +12,9 @@ jobs:
     - uses: actions/checkout@v4
 
     - name: Set up Python
-      uses: actions/setup-python@v4
+      uses: actions/setup-python@v5
       with:
-        python-version: '3.x'
+        python-version: '3.13'
 
     - name: Install dependencies
       run: |
@@ -27,4 +27,3 @@ jobs:
     - name: Run Flake8 (Linting)
       run: |
         flake8 --exclude '*generated*' src/workbench applications tests
-

{workbench-0.8.177 → workbench-0.8.217}/.gitignore

@@ -149,5 +149,5 @@ workbench_lambda_layer_output/
 # Some test datasets
 test_evaluation_data.csv
 
-# This is a copied file
-src/workbench/model_scripts/custom_models/chem_info/chem_utils.py
+# PyTorch checkpoint/tmp directories
+.pt_tmp/ 

workbench-0.8.217/Dockerfile

@@ -0,0 +1,7 @@
+FROM python:3.12-slim
+
+ARG WORKBENCH_VERSION=
+RUN apt-get update && apt-get upgrade -y && \
+    apt-get install -y --no-install-recommends libexpat1 libnghttp2-dev && \
+    apt-get clean && rm -rf /var/lib/apt/lists/* && \
+    pip install --no-cache-dir workbench${WORKBENCH_VERSION:+==$WORKBENCH_VERSION}

{workbench-0.8.177 → workbench-0.8.217}/LICENSE

@@ -1,6 +1,6 @@
 MIT License
 
-Copyright (c) 2021-2024 SuperCowPowers LLC
+Copyright (c) 2021-2026 SuperCowPowers LLC
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

{workbench-0.8.177 → workbench-0.8.217}/PKG-INFO

@@ -1,15 +1,37 @@
 Metadata-Version: 2.4
 Name: workbench
-Version: 0.8.177
+Version: 0.8.217
 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
+License: MIT License
+        
+        Copyright (c) 2021-2026 SuperCowPowers LLC
+        
+        Permission is hereby granted, free of charge, to any person obtaining a copy
+        of this software and associated documentation files (the "Software"), to deal
+        in the Software without restriction, including without limitation the rights
+        to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+        copies of the Software, and to permit persons to whom the Software is
+        furnished to do so, subject to the following conditions:
+        
+        The above copyright notice and this permission notice shall be included in all
+        copies or substantial portions of the Software.
+        
+        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+        IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+        FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+        AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+        LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+        OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+        SOFTWARE.
+        
 Project-URL: Homepage, https://github.com/SuperCowPowers/workbench
 Keywords: SageMaker,Machine Learning,AWS,Python,Utilities
 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
@@ -20,20 +42,21 @@ Requires-Dist: redis>=5.0.1
 Requires-Dist: numpy>=1.26.4
 Requires-Dist: pandas>=2.2.1
 Requires-Dist: awswrangler>=3.4.0
-Requires-Dist: sagemaker>=2.143
+Requires-Dist: sagemaker<3.0,>=2.143
 Requires-Dist: cryptography>=44.0.2
 Requires-Dist: ipython>=8.37.0
 Requires-Dist: pyreadline3; sys_platform == "win32"
 Requires-Dist: scikit-learn>=1.5.2
+Requires-Dist: umap-learn>=0.5.8
 Requires-Dist: xgboost>=3.0.3
 Requires-Dist: joblib>=1.3.2
 Requires-Dist: requests>=2.26.0
 Requires-Dist: rdkit>=2024.9.5
 Requires-Dist: mordredcommunity>=2.0.6
-Requires-Dist: workbench-bridges>=0.1.10
+Requires-Dist: workbench-bridges>=0.1.16
 Provides-Extra: ui
 Requires-Dist: plotly>=6.0.0; extra == "ui"
-Requires-Dist: dash>3.0.0; extra == "ui"
+Requires-Dist: dash>=3.0.0; extra == "ui"
 Requires-Dist: dash-bootstrap-components>=1.6.0; extra == "ui"
 Requires-Dist: dash-bootstrap-templates>=1.3.0; extra == "ui"
 Requires-Dist: dash_ag_grid; extra == "ui"
@@ -48,8 +71,8 @@ Requires-Dist: flake8; extra == "dev"
 Requires-Dist: black; extra == "dev"
 Provides-Extra: all
 Requires-Dist: networkx>=3.2; extra == "all"
-Requires-Dist: plotly>=5.18.0; extra == "all"
-Requires-Dist: dash<3.0.0,>=2.16.1; extra == "all"
+Requires-Dist: plotly>=6.0.0; extra == "all"
+Requires-Dist: dash>=3.0.0; extra == "all"
 Requires-Dist: dash-bootstrap-components>=1.6.0; extra == "all"
 Requires-Dist: dash-bootstrap-templates>=1.3.0; extra == "all"
 Requires-Dist: dash_ag_grid; extra == "all"

{workbench-0.8.177 → workbench-0.8.217}/applications/aws_dashboard/Dockerfile

@@ -7,7 +7,7 @@ EXPOSE 8000
 ENV PYTHONHASHSEED=0
 
 # Define workbench version
-ARG WORKBENCH_VERSION=0.8.165
+ARG WORKBENCH_VERSION=0.8.208
 
 # Install system packages and gunicorn in one layer
 RUN apt-get update && apt-get install -y --no-install-recommends \

{workbench-0.8.177 → workbench-0.8.217}/applications/compound_explorer/requirements.txt

@@ -4,7 +4,7 @@ redis >= 5.0.1
 numpy >= 1.26.4
 pandas >= 2.2.1
 awswrangler >= 3.4.0
-sagemaker >= 2.143
+sagemaker >= 2.143, < 3.0
 cryptography>=44.0.2
 ipython>=8.17.2
 xgboost>=3.0.3

{workbench-0.8.177 → workbench-0.8.217}/aws_setup/aws_identity_check.py

@@ -1,6 +1,5 @@
 """Just a Utility Script that allows people to check which AWS Identity is active"""
 
-import os
 import sys
 import logging
 

{workbench-0.8.177 → workbench-0.8.217}/aws_setup/workbench_compute/workbench_compute/workbench_compute_stack.py

@@ -9,6 +9,7 @@ from aws_cdk import (
     aws_sqs as sqs,
     aws_lambda as lambda_,
     aws_lambda_event_sources as lambda_events,
+    aws_logs as logs,
     Duration,
     Size,
 )
@@ -95,6 +96,7 @@ class WorkbenchComputeStack(Stack):
             compute_environment_name="workbench-compute-env",
             vpc=vpc,
             vpc_subnets=vpc_subnets,
+            maxv_cpus=16,  # Limit to 16 vCPU to minimize AWS Throttling issues
         )
 
     def create_batch_job_queue(self) -> batch.JobQueue:
@@ -118,7 +120,7 @@ class WorkbenchComputeStack(Stack):
                 "MLPipelineRepo",
                 repository_arn=f"arn:aws:ecr:{self.region}:507740646243:repository/aws-ml-images/py312-ml-pipelines",
             ),
-            tag="0.1",
+            tag="0.2",
         )
 
         # Job Definition Tiers
@@ -192,6 +194,7 @@ class WorkbenchComputeStack(Stack):
             handler="index.lambda_handler",
             code=lambda_.Code.from_inline(self._get_lambda_code()),
             timeout=Duration.minutes(5),
+            log_retention=logs.RetentionDays.ONE_WEEK,
             environment={
                 "WORKBENCH_BUCKET": self.workbench_bucket,
                 "JOB_QUEUE": self.batch_job_queue.job_queue_name,
@@ -205,7 +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
@@ -241,8 +244,6 @@ class WorkbenchComputeStack(Stack):
                         script_path = message['script_path']  # s3://bucket/path/to/script.py
                         size = message.get('size', 'small')
                         extra_env = message.get('environment', {})
-                        model_outputs = message.get('MODEL_OUTPUTS', [])
-                        endpoint_outputs = message.get('ENDPOINT_OUTPUTS', [])
 
                         script_name = Path(script_path).stem
                         job_name = f"workbench_{script_name}_{datetime.now():%Y%m%d_%H%M%S}"
@@ -257,14 +258,7 @@ class WorkbenchComputeStack(Stack):
                             *[{'name': k, 'value': v} for k, v in extra_env.items()]
                         ]
 
-                        # Add MODEL_OUTPUTS as comma-separated list if provided
-                        if model_outputs:
-                            env_vars.append({'name': 'MODEL_OUTPUTS', 'value': ','.join(model_outputs)})
-
-                        # Add ENDPOINT_OUTPUTS as comma-separated list if provided
-                        if endpoint_outputs:
-                            env_vars.append({'name': 'ENDPOINT_OUTPUTS', 'value': ','.join(endpoint_outputs)})
-
+                        # Submit Batch job to the queue
                         response = batch.submit_job(
                             jobName=job_name,
                             jobQueue=JOB_QUEUE,

{workbench-0.8.177 → workbench-0.8.217}/aws_setup/workbench_dashboard_full/app.py

@@ -12,7 +12,7 @@ print(f"Account: {aws_account}")
 print(f"Region: {aws_region}")
 
 # When you want a different docker image change this line
-dashboard_image = "public.ecr.aws/m6i5k1r2/workbench_dashboard:v0_8_165_amd64"
+dashboard_image = "public.ecr.aws/m6i5k1r2/workbench_dashboard:v0_8_208_amd64"
 
 # Workbench Configuration
 try:

{workbench-0.8.177 → workbench-0.8.217}/aws_setup/workbench_dashboard_full/workbench_dashboard_full/workbench_dashboard_stack.py

@@ -8,7 +8,6 @@ from aws_cdk import (
     aws_elasticache as elasticache,
     aws_logs as logs,
 )
-from aws_cdk.aws_ec2 import Subnet
 from aws_cdk.aws_certificatemanager import Certificate
 from aws_cdk.aws_ecs_patterns import ApplicationLoadBalancedFargateService
 from constructs import Construct

{workbench-0.8.177 → workbench-0.8.217}/aws_setup/workbench_dashboard_lite/app.py

@@ -1,4 +1,3 @@
-import os
 import boto3
 import aws_cdk as cdk
 from pprint import pprint
@@ -13,7 +12,7 @@ print(f"Account: {aws_account}")
 print(f"Region: {aws_region}")
 
 # When you want a different docker image change this line
-dashboard_image = "public.ecr.aws/m6i5k1r2/workbench_dashboard:v0_8_165_amd64"
+dashboard_image = "public.ecr.aws/m6i5k1r2/workbench_dashboard:v0_8_208_amd64"
 
 # Workbench Configuration
 try:

{workbench-0.8.177 → workbench-0.8.217}/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)
@@ -32,7 +28,7 @@ results_df = endpoint.inference(df)
 results_df = endpoint.inference(df, capture=True)
 
 # Run inference/predictions using the FeatureSet evaluation data
-results_df = endpoint.auto_inference(capture=True)
+results_df = endpoint.auto_inference()
 ```
 
 **Output**

{workbench-0.8.177 → workbench-0.8.217}/docs/api_classes/meta.md

@@ -86,7 +86,7 @@ wine-classification
 	Description: Wine Classification Model
 	Tags: wine::classification
 	Performance Metrics:
-		[{'wine_class': 'TypeA', 'precision': 1.0, 'recall': 1.0, 'fscore': 1.0, 'roc_auc': 1.0, 'support': 12}, {'wine_class': 'TypeB', 'precision': 1.0, 'recall': 1.0, 'fscore': 1.0, 'roc_auc': 1.0, 'support': 14}, {'wine_class': 'TypeC', 'precision': 1.0, 'recall': 1.0, 'fscore': 1.0, 'roc_auc': 1.0, 'support': 9}]
+		[{'wine_class': 'TypeA', 'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'roc_auc': 1.0, 'support': 12}, {'wine_class': 'TypeB', 'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'roc_auc': 1.0, 'support': 14}, {'wine_class': 'TypeC', 'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'roc_auc': 1.0, 'support': 9}]
 
 abalone-regression
 	ARN: arn:aws:sagemaker:us-west-2:507740646243:model-package-group/abalone-regression

{workbench-0.8.177 → workbench-0.8.217}/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-0.8.177 → workbench-0.8.217}/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-0.8.177 → workbench-0.8.217}/docs/cached/cached_meta.md

@@ -86,7 +86,7 @@ wine-classification
 	Description: Wine Classification Model
 	Tags: wine::classification
 	Performance Metrics:
-		[{'wine_class': 'TypeA', 'precision': 1.0, 'recall': 1.0, 'fscore': 1.0, 'roc_auc': 1.0, 'support': 12}, {'wine_class': 'TypeB', 'precision': 1.0, 'recall': 1.0, 'fscore': 1.0, 'roc_auc': 1.0, 'support': 14}, {'wine_class': 'TypeC', 'precision': 1.0, 'recall': 1.0, 'fscore': 1.0, 'roc_auc': 1.0, 'support': 9}]
+		[{'wine_class': 'TypeA', 'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'roc_auc': 1.0, 'support': 12}, {'wine_class': 'TypeB', 'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'roc_auc': 1.0, 'support': 14}, {'wine_class': 'TypeC', 'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'roc_auc': 1.0, 'support': 9}]
 
 abalone-regression
 	ARN: arn:aws:sagemaker:us-west-2:507740646243:model-package-group/abalone-regression

{workbench-0.8.177 → workbench-0.8.217}/docs/core_classes/transforms/features_to_model.md

@@ -116,7 +116,7 @@ model = Model("my-custom-model")
 end = model.to_endpoint()   # Note: This takes a while
 
 # Now run inference on my custom model :)
-end.auto_inference(capture=True)
+end.auto_inference()
 
 # Run inference with my own dataframe
 df = fs.pull_dataframe()  # Or whatever dataframe

{workbench-0.8.177 → workbench-0.8.217}/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-0.8.177 → workbench-0.8.217}/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)
@@ -19,4 +15,4 @@ results_df = endpoint.inference(df)
 results_df = endpoint.inference(df, capture_name="test_inference")
 
 # Run inference/predictions using the FeatureSet evaluation data
-results_df = endpoint.auto_inference(capture=True)
+results_df = endpoint.auto_inference()

{workbench-0.8.177 → workbench-0.8.217}/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-0.8.177 → workbench-0.8.217}/examples/glue_jobs/glue_example_1.py

@@ -13,7 +13,7 @@ cm = ConfigManager()
 cm.set_config("WORKBENCH_BUCKET", glue_args["workbench-bucket"])
 
 # Important Note: This import needs to happen after the WORKBENCH_BUCKET is set
-from workbench.api import DataSource
+from workbench.api import DataSource  # noqa: E402
 
 # Grab a test DataSource
 ds = DataSource("abalone_data")

{workbench-0.8.177 → workbench-0.8.217}/examples/glue_jobs/glue_example_2.py

@@ -13,7 +13,7 @@ cm = ConfigManager()
 cm.set_config("WORKBENCH_BUCKET", glue_args["workbench-bucket"])
 
 # Important Note: This import needs to happen after the WORKBENCH_BUCKET is set
-from workbench.api import Meta
+from workbench.api import Meta  # noqa: E402
 
 # List all the models in AWS
 meta = Meta()

{workbench-0.8.177 → workbench-0.8.217}/examples/glue_jobs/glue_example_3.py

@@ -13,7 +13,7 @@ cm = ConfigManager()
 cm.set_config("WORKBENCH_BUCKET", glue_args["workbench-bucket"])
 
 # Important Note: This import needs to happen after the WORKBENCH_BUCKET is set
-from workbench.api import Endpoint
+from workbench.api import Endpoint  # noqa: E402
 
 # Run Inference on a particular model (using its endpoint)
 end = Endpoint("abalone-regression")

{workbench-0.8.177 → workbench-0.8.217}/examples/ml_pipelines/list_models.py

@@ -1,4 +1,3 @@
-import time
 import logging
 from workbench.api import Meta
 

{workbench-0.8.177 → workbench-0.8.217}/examples/ml_pipelines/wine_classifier.py

@@ -10,7 +10,7 @@ Endpoints:
     - wine-classification-end
 """
 
-from workbench.api import DataSource, FeatureSet, Model, ModelType, Endpoint
+from workbench.api import DataSource, FeatureSet, Model, ModelType
 
 
 if __name__ == "__main__":
@@ -37,5 +37,5 @@ if __name__ == "__main__":
     end = m.to_endpoint("wine-classification", tags=["wine", "classification"])
 
     # Run inference on the endpoint
-    end.auto_inference(capture=True)
+    end.auto_inference()
     end.set_owner("test")

workbench-0.8.217/examples/models/chemprop.py

@@ -0,0 +1,140 @@
+from workbench.api import FeatureSet, Model, ModelType, ModelFramework, Endpoint
+
+# Recreate Flag in case you want to recreate the artifacts
+recreate = False
+
+# =============================================================================
+# Single-Target Chemprop Regression Model
+# =============================================================================
+if recreate or not Model("open-admet-chemprop-logd").exists():
+    feature_set = FeatureSet("open_admet_all")
+    m = feature_set.to_model(
+        name="open-admet-chemprop-logd",
+        model_type=ModelType.UQ_REGRESSOR,
+        model_framework=ModelFramework.CHEMPROP,
+        target_column="logd",  # Single target (string)
+        feature_list=["smiles"],
+        description="Single-target Chemprop Regression Model for LogD",
+        tags=["chemprop", "open_admet"],
+    )
+    m.set_owner("BW")
+
+# Create an Endpoint for the Regression Model
+if recreate or not Endpoint("open-admet-chemprop-logd").exists():
+    m = Model("open-admet-chemprop-logd")
+    end = m.to_endpoint(tags=["chemprop", "open_admet"])
+    end.set_owner("BW")
+    end.auto_inference()
+    end.cross_fold_inference()
+
+# =============================================================================
+# Hybrid ChemProp Model (SMILES + Molecular Descriptors)
+# =============================================================================
+# This example shows how to combine ChemProp's learned molecular representations
+# with pre-computed molecular descriptors (RDKit/Mordred features).
+# The extra features are concatenated with the MPNN output before the FFN.
+
+# Top 10 SHAP features from LogD XGBoost model (provides complementary information to MPNN)
+TOP_LOGD_SHAP_FEATURES = [
+    "mollogp",
+    "fr_halogen",
+    "peoe_vsa6",
+    "nbase",
+    "peoe_vsa7",
+    "peoe_vsa9",
+    "peoe_vsa1",
+    "mi",
+    "bcut2d_mrlow",
+    "slogp_vsa1",
+]
+
+if recreate or not Model("open-admet-chemprop-logd-hybrid").exists():
+    feature_set = FeatureSet("open_admet_logd")
+
+    # Hybrid mode: SMILES + top molecular descriptors
+    # The template auto-detects extra features beyond the SMILES column
+    hybrid_features = ["smiles"] + TOP_LOGD_SHAP_FEATURES
+
+    m = feature_set.to_model(
+        name="open-admet-chemprop-logd-hybrid",
+        model_type=ModelType.UQ_REGRESSOR,
+        model_framework=ModelFramework.CHEMPROP,
+        target_column="logd",
+        feature_list=hybrid_features,
+        description="Hybrid ChemProp model combining D-MPNN with top SHAP molecular descriptors",
+        tags=["chemprop", "open_admet", "hybrid"],
+    )
+    m.set_owner("BW")
+
+# Create an Endpoint for the Hybrid Model
+if recreate or not Endpoint("open-admet-chemprop-logd-hybrid").exists():
+    m = Model("open-admet-chemprop-logd-hybrid")
+    end = m.to_endpoint(tags=["chemprop", "open_admet", "hybrid"])
+    end.set_owner("BW")
+    end.auto_inference()
+    end.cross_fold_inference()
+
+# =============================================================================
+# Chemprop Classification Model
+# =============================================================================
+if recreate or not Model("aqsol-class-chemprop").exists():
+    feature_set = FeatureSet("aqsol_features")
+    m = feature_set.to_model(
+        name="aqsol-class-chemprop",
+        model_type=ModelType.CLASSIFIER,
+        model_framework=ModelFramework.CHEMPROP,
+        target_column="solubility_class",
+        feature_list=["smiles"],
+        description="Classification ChemProp model AQSol solubility classes",
+        tags=["chemprop", "aqsol", "class"],
+    )
+    m.set_owner("BW")
+    m.set_class_labels(["low", "medium", "high"])
+
+# Create an Endpoint for the Multi-Task Regression Model
+if recreate or not Endpoint("aqsol-class-chemprop").exists():
+    m = Model("aqsol-class-chemprop")
+    end = m.to_endpoint(tags=["chemprop", "aqsol", "class"])
+    end.set_owner("BW")
+    end.auto_inference()
+    end.cross_fold_inference()
+
+# =============================================================================
+# Multi-Target Chemprop Regression Model (Open ADMET)
+# =============================================================================
+# This example shows how to train a multi-task model predicting all 9 ADMET endpoints
+# from the Open ADMET challenge: logd, ksol, hlm_clint, mlm_clint, caco_2_papp_a_b,
+# caco_2_efflux, mppb, mbpb, mgmb
+
+ADMET_TARGETS = [
+    "logd",
+    "ksol",
+    "hlm_clint",
+    "mlm_clint",
+    "caco_2_papp_a_b",
+    "caco_2_efflux",
+    "mppb",
+    "mbpb",
+    "mgmb",
+]
+
+if recreate or not Model("open-admet-chemprop-mt").exists():
+    feature_set = FeatureSet("open_admet_all")
+    m = feature_set.to_model(
+        name="open-admet-chemprop-mt",
+        model_type=ModelType.REGRESSOR,
+        model_framework=ModelFramework.CHEMPROP,
+        target_column=ADMET_TARGETS,  # Multi-task: list of 9 targets
+        feature_list=["smiles"],
+        description="Multi-task ChemProp model for 9 ADMET endpoints",
+        tags=["chemprop", "open_admet", "multitask"],
+    )
+    m.set_owner("BW")
+
+# Create an Endpoint for the Multi-Task Regression Model
+if recreate or not Endpoint("open-admet-chemprop-mt").exists():
+    m = Model("open-admet-chemprop-mt")
+    end = m.to_endpoint(tags=["chemprop", "open_admet", "multitask"])
+    end.set_owner("BW")
+    end.auto_inference()
+    end.cross_fold_inference()

{workbench-0.8.177 → workbench-0.8.217}/examples/models/custom_model.py

@@ -21,4 +21,4 @@ my_model = Model("smiles-to-taut-md-stereo-v0")
 endpoint = my_model.to_endpoint(name="smiles-to-taut-md-stereo-v0", tags=["smiles", "molecular descriptors"])
 
 # Run auto-inference on the Endpoint
-endpoint.auto_inference(capture=True)
+endpoint.auto_inference()

{workbench-0.8.177 → workbench-0.8.217}/examples/models/dbscan.py

@@ -24,4 +24,4 @@ my_model = Model("abalone-clusters")
 endpoint = my_model.to_endpoint(name="abalone-clusters", tags=["abalone", "clusters"])
 
 # Run auto-inference on the Endpoint
-endpoint.auto_inference(capture=True)
+endpoint.auto_inference()

workbench-0.8.217/examples/models/meta_model.py

@@ -0,0 +1,34 @@
+from workbench.api import MetaModel, Endpoint
+
+# Recreate Flag in case you want to recreate the artifacts
+recreate = True
+
+# =============================================================================
+# Meta Model: Ensemble of XGBoost, PyTorch, and ChemProp for LogD
+# =============================================================================
+# This meta model aggregates predictions from different model architectures,
+# using model-weighted voting to combine their outputs.
+
+# Child endpoints that this meta model will call
+CHILD_ENDPOINTS = [
+    "logd-reg-pytorch",
+    "logd-reg-chemprop",
+]
+
+if recreate or not MetaModel("logd-meta").exists():
+    m = MetaModel.create(
+        name="logd-meta",
+        child_endpoints=CHILD_ENDPOINTS,
+        target_column="logd",
+        description="Meta model combining XGBoost, PyTorch, and ChemProp for LogD prediction",
+        tags=["meta", "open_admet", "logd"],
+    )
+    m.set_owner("BW")
+
+# Create an Endpoint for the Meta Model
+if recreate or not Endpoint("logd-meta").exists():
+    m = MetaModel("logd-meta")
+    end = m.to_endpoint(tags=["meta", "open_admet", "logd"])
+    end.set_owner("BW")
+    end.auto_inference()
+    end.full_inference()