workbench 0.8.217__py3-none-any.whl → 0.8.219__py3-none-any.whl

workbench/utils/chem_utils/fingerprints.py

@@ -1,11 +1,19 @@
-"""Molecular fingerprint computation utilities"""
+"""Molecular fingerprint computation utilities for ADMET modeling.
+
+This module provides Morgan count fingerprints, the standard for ADMET prediction.
+Count fingerprints outperform binary fingerprints for molecular property prediction.
+
+References:
+    - Count vs Binary: https://pubs.acs.org/doi/10.1021/acs.est.3c02198
+    - ECFP/Morgan: https://pubs.acs.org/doi/10.1021/ci100050t
+"""
 
 import logging
-import pandas as pd
 
-# Molecular Descriptor Imports
+import numpy as np
+import pandas as pd
 from rdkit import Chem, RDLogger
-from rdkit.Chem import rdFingerprintGenerator
+from rdkit.Chem import AllChem
 from rdkit.Chem.MolStandardize import rdMolStandardize
 
 # Suppress RDKit warnings (e.g., "not removing hydrogen atom without neighbors")
@@ -16,20 +24,25 @@ RDLogger.DisableLog("rdApp.warning")
 log = logging.getLogger("workbench")
 
 
-def compute_morgan_fingerprints(df: pd.DataFrame, radius=2, n_bits=2048, counts=True) -> pd.DataFrame:
-    """Compute and add Morgan fingerprints to the DataFrame.
+def compute_morgan_fingerprints(df: pd.DataFrame, radius: int = 2, n_bits: int = 2048) -> pd.DataFrame:
+    """Compute Morgan count fingerprints for ADMET modeling.
+
+    Generates true count fingerprints where each bit position contains the
+    number of times that substructure appears in the molecule (clamped to 0-255).
+    This is the recommended approach for ADMET prediction per 2025 research.
 
     Args:
-        df (pd.DataFrame): Input DataFrame containing SMILES strings.
-        radius (int): Radius for the Morgan fingerprint.
-        n_bits (int): Number of bits for the fingerprint.
-        counts (bool): Count simulation for the fingerprint.
+        df: Input DataFrame containing SMILES strings.
+        radius: Radius for the Morgan fingerprint (default 2 = ECFP4 equivalent).
+        n_bits: Number of bits for the fingerprint (default 2048).
 
     Returns:
-        pd.DataFrame: The input DataFrame with the Morgan fingerprints added as bit strings.
+        pd.DataFrame: Input DataFrame with 'fingerprint' column added.
+                      Values are comma-separated uint8 counts.
 
     Note:
-        See: https://greglandrum.github.io/rdkit-blog/posts/2021-07-06-simulating-counts.html
+        Count fingerprints outperform binary for ADMET prediction.
+        See: https://pubs.acs.org/doi/10.1021/acs.est.3c02198
     """
     delete_mol_column = False
 
@@ -43,7 +56,7 @@ def compute_morgan_fingerprints(df: pd.DataFrame, radius=2, n_bits=2048, counts=
         log.warning("Detected serialized molecules in 'molecule' column. Removing...")
         del df["molecule"]
 
-    # Convert SMILES to RDKit molecule objects (vectorized)
+    # Convert SMILES to RDKit molecule objects
     if "molecule" not in df.columns:
         log.info("Converting SMILES to RDKit Molecules...")
         delete_mol_column = True
@@ -59,15 +72,24 @@ def compute_morgan_fingerprints(df: pd.DataFrame, radius=2, n_bits=2048, counts=
         lambda mol: rdMolStandardize.LargestFragmentChooser().choose(mol) if mol else None
     )
 
-    # Create a Morgan fingerprint generator
-    if counts:
-        n_bits *= 4  # Multiply by 4 to simulate counts
-    morgan_generator = rdFingerprintGenerator.GetMorganGenerator(radius=radius, fpSize=n_bits, countSimulation=counts)
+    def mol_to_count_string(mol):
+        """Convert molecule to comma-separated count fingerprint string."""
+        if mol is None:
+            return pd.NA
 
-    # Compute Morgan fingerprints (vectorized)
-    fingerprints = largest_frags.apply(
-        lambda mol: (morgan_generator.GetFingerprint(mol).ToBitString() if mol else pd.NA)
-    )
+        # Get hashed Morgan fingerprint with counts
+        fp = AllChem.GetHashedMorganFingerprint(mol, radius, nBits=n_bits)
+
+        # Initialize array and populate with counts (clamped to uint8 range)
+        counts = np.zeros(n_bits, dtype=np.uint8)
+        for idx, count in fp.GetNonzeroElements().items():
+            counts[idx] = min(count, 255)
+
+        # Return as comma-separated string
+        return ",".join(map(str, counts))
+
+    # Compute Morgan count fingerprints
+    fingerprints = largest_frags.apply(mol_to_count_string)
 
     # Add the fingerprints to the DataFrame
     df["fingerprint"] = fingerprints
@@ -75,59 +97,62 @@ def compute_morgan_fingerprints(df: pd.DataFrame, radius=2, n_bits=2048, counts=
     # Drop the intermediate 'molecule' column if it was added
     if delete_mol_column:
         del df["molecule"]
+
     return df
 
 
 if __name__ == "__main__":
-    print("Running molecular fingerprint tests...")
-    print("Note: This requires molecular_screening module to be available")
+    print("Running Morgan count fingerprint tests...")
 
     # Test molecules
     test_molecules = {
         "aspirin": "CC(=O)OC1=CC=CC=C1C(=O)O",
         "caffeine": "CN1C=NC2=C1C(=O)N(C(=O)N2C)C",
         "glucose": "C([C@@H]1[C@H]([C@@H]([C@H](C(O1)O)O)O)O)O",  # With stereochemistry
-        "sodium_acetate": "CC(=O)[O-].[Na+]",  # Salt
+        "sodium_acetate": "CC(=O)[O-].[Na+]",  # Salt (largest fragment used)
         "benzene": "c1ccccc1",
         "butene_e": "C/C=C/C",  # E-butene
         "butene_z": "C/C=C\\C",  # Z-butene
     }
 
-    # Test 1: Morgan Fingerprints
-    print("\n1. Testing Morgan fingerprint generation...")
+    # Test 1: Morgan Count Fingerprints (default parameters)
+    print("\n1. Testing Morgan fingerprint generation (radius=2, n_bits=2048)...")
 
     test_df = pd.DataFrame({"SMILES": list(test_molecules.values()), "name": list(test_molecules.keys())})
-
-    fp_df = compute_morgan_fingerprints(test_df.copy(), radius=2, n_bits=512, counts=False)
+    fp_df = compute_morgan_fingerprints(test_df.copy())
 
     print("   Fingerprint generation results:")
     for _, row in fp_df.iterrows():
         fp = row.get("fingerprint", "N/A")
-        fp_len = len(fp) if fp != "N/A" else 0
-        print(f"   {row['name']:15} → {fp_len} bits")
+        if pd.notna(fp):
+            counts = [int(x) for x in fp.split(",")]
+            non_zero = sum(1 for c in counts if c > 0)
+            max_count = max(counts)
+            print(f"   {row['name']:15} → {len(counts)} features, {non_zero} non-zero, max={max_count}")
+        else:
+            print(f"   {row['name']:15} → N/A")
 
-    # Test 2: Different fingerprint parameters
-    print("\n2. Testing different fingerprint parameters...")
+    # Test 2: Different parameters
+    print("\n2. Testing with different parameters (radius=3, n_bits=1024)...")
 
-    # Test with counts enabled
-    fp_counts_df = compute_morgan_fingerprints(test_df.copy(), radius=3, n_bits=256, counts=True)
+    fp_df_custom = compute_morgan_fingerprints(test_df.copy(), radius=3, n_bits=1024)
 
-    print("   With count simulation (256 bits * 4):")
-    for _, row in fp_counts_df.iterrows():
+    for _, row in fp_df_custom.iterrows():
         fp = row.get("fingerprint", "N/A")
-        fp_len = len(fp) if fp != "N/A" else 0
-        print(f"   {row['name']:15} → {fp_len} bits")
+        if pd.notna(fp):
+            counts = [int(x) for x in fp.split(",")]
+            non_zero = sum(1 for c in counts if c > 0)
+            print(f"   {row['name']:15} → {len(counts)} features, {non_zero} non-zero")
+        else:
+            print(f"   {row['name']:15} → N/A")
 
     # Test 3: Edge cases
     print("\n3. Testing edge cases...")
 
     # Invalid SMILES
     invalid_df = pd.DataFrame({"SMILES": ["INVALID", ""]})
-    try:
-        fp_invalid = compute_morgan_fingerprints(invalid_df.copy())
-        print(f"   ✓ Invalid SMILES handled: {len(fp_invalid)} valid molecules")
-    except Exception as e:
-        print(f"   ✓ Invalid SMILES properly raised error: {type(e).__name__}")
+    fp_invalid = compute_morgan_fingerprints(invalid_df.copy())
+    print(f"   ✓ Invalid SMILES handled: {len(fp_invalid)} rows returned")
 
     # Test with pre-existing molecule column
     mol_df = test_df.copy()
@@ -135,4 +160,16 @@ if __name__ == "__main__":
     fp_with_mol = compute_morgan_fingerprints(mol_df)
     print(f"   ✓ Pre-existing molecule column handled: {len(fp_with_mol)} fingerprints generated")
 
+    # Test 4: Verify count values are reasonable
+    print("\n4. Verifying count distribution...")
+    all_counts = []
+    for _, row in fp_df.iterrows():
+        fp = row.get("fingerprint", "N/A")
+        if pd.notna(fp):
+            counts = [int(x) for x in fp.split(",")]
+            all_counts.extend([c for c in counts if c > 0])
+
+    if all_counts:
+        print(f"   Non-zero counts: min={min(all_counts)}, max={max(all_counts)}, mean={np.mean(all_counts):.2f}")
+
     print("\n✅ All fingerprint tests completed!")

workbench/utils/meta_model_simulator.py

@@ -61,6 +61,13 @@ class MetaModelSimulator:
             df["abs_residual"] = df["residual"].abs()
             self._dfs[name] = df
 
+        # Find common rows across all models
+        id_sets = {name: set(df[self.id_column]) for name, df in self._dfs.items()}
+        common_ids = set.intersection(*id_sets.values())
+        sizes = ", ".join(f"{name}: {len(ids)}" for name, ids in id_sets.items())
+        log.info(f"Row counts before alignment: {sizes} -> common: {len(common_ids)}")
+        self._dfs = {name: df[df[self.id_column].isin(common_ids)] for name, df in self._dfs.items()}
+
         # Align DataFrames by sorting on id column
         self._dfs = {name: df.sort_values(self.id_column).reset_index(drop=True) for name, df in self._dfs.items()}
         log.info(f"Loaded {len(self._dfs)} models, {len(list(self._dfs.values())[0])} samples each")
@@ -372,13 +379,13 @@ class MetaModelSimulator:
         return weight_df
 
     def ensemble_failure_analysis(self) -> dict:
-        """Compare ensemble vs best overall model (not per-row oracle).
+        """Compare best ensemble strategy vs best individual model.
 
         Returns:
             Dict with comparison statistics
         """
         print("\n" + "=" * 60)
-        print("ENSEMBLE VS BEST MODEL COMPARISON")
+        print("BEST ENSEMBLE VS BEST MODEL COMPARISON")
         print("=" * 60)
 
         model_names = list(self._dfs.keys())
@@ -393,35 +400,55 @@ class MetaModelSimulator:
             combined[f"{name}_abs_err"] = df["abs_residual"].values
 
         pred_cols = [f"{name}_pred" for name in model_names]
+        conf_cols = [f"{name}_conf" for name in model_names]
+        pred_arr = combined[pred_cols].values
+        conf_arr = combined[conf_cols].values
 
-        # Calculate ensemble prediction (inverse-MAE weighted)
         mae_scores = {name: self._dfs[name]["abs_residual"].mean() for name in model_names}
         inv_mae_weights = np.array([1.0 / mae_scores[name] for name in model_names])
         inv_mae_weights = inv_mae_weights / inv_mae_weights.sum()
-        pred_arr = combined[pred_cols].values
-        combined["ensemble_pred"] = (pred_arr * inv_mae_weights).sum(axis=1)
-        combined["ensemble_abs_err"] = (combined["ensemble_pred"] - combined["target"]).abs()
 
-        # Find best overall model (lowest MAE)
+        # Compute all ensemble strategies (true ensembles that combine multiple models)
+        ensemble_strategies = {}
+        ensemble_strategies["Simple Mean"] = combined[pred_cols].mean(axis=1)
+        conf_sum = conf_arr.sum(axis=1, keepdims=True) + 1e-8
+        ensemble_strategies["Confidence-Weighted"] = (pred_arr * (conf_arr / conf_sum)).sum(axis=1)
+        ensemble_strategies["Inverse-MAE Weighted"] = (pred_arr * inv_mae_weights).sum(axis=1)
+        scaled_conf = conf_arr * inv_mae_weights
+        scaled_conf_sum = scaled_conf.sum(axis=1, keepdims=True) + 1e-8
+        ensemble_strategies["Scaled Conf-Weighted"] = (pred_arr * (scaled_conf / scaled_conf_sum)).sum(axis=1)
+        worst_model = max(mae_scores, key=mae_scores.get)
+        remaining = [n for n in model_names if n != worst_model]
+        remaining_cols = [f"{n}_pred" for n in remaining]
+        # Only add Drop Worst if it still combines multiple models
+        if len(remaining) > 1:
+            ensemble_strategies[f"Drop Worst ({worst_model})"] = combined[remaining_cols].mean(axis=1)
+
+        # Find best individual model
         best_model = min(mae_scores, key=mae_scores.get)
         combined["best_model_abs_err"] = combined[f"{best_model}_abs_err"]
+        best_model_mae = mae_scores[best_model]
 
-        # Compare ensemble vs best model
+        # Find best true ensemble strategy
+        strategy_maes = {name: (preds - combined["target"]).abs().mean() for name, preds in ensemble_strategies.items()}
+        best_strategy = min(strategy_maes, key=strategy_maes.get)
+        combined["ensemble_pred"] = ensemble_strategies[best_strategy]
+        combined["ensemble_abs_err"] = (combined["ensemble_pred"] - combined["target"]).abs()
+        ensemble_mae = strategy_maes[best_strategy]
+
+        # Compare
         combined["ensemble_better"] = combined["ensemble_abs_err"] < combined["best_model_abs_err"]
         n_better = combined["ensemble_better"].sum()
         n_total = len(combined)
 
-        ensemble_mae = combined["ensemble_abs_err"].mean()
-        best_model_mae = mae_scores[best_model]
-
         print(f"\nBest individual model: {best_model} (MAE={best_model_mae:.4f})")
-        print(f"Ensemble MAE: {ensemble_mae:.4f}")
+        print(f"Best ensemble strategy: {best_strategy} (MAE={ensemble_mae:.4f})")
         if ensemble_mae < best_model_mae:
             improvement = (best_model_mae - ensemble_mae) / best_model_mae * 100
             print(f"Ensemble improves over best model by {improvement:.1f}%")
         else:
             degradation = (ensemble_mae - best_model_mae) / best_model_mae * 100
-            print(f"Ensemble is worse than best model by {degradation:.1f}%")
+            print(f"No ensemble benefit: best single model outperforms all ensemble strategies by {degradation:.1f}%")
 
         print("\nPer-row comparison:")
         print(f"  Ensemble wins: {n_better}/{n_total} ({100*n_better/n_total:.1f}%)")
@@ -443,6 +470,7 @@ class MetaModelSimulator:
 
         return {
             "ensemble_mae": ensemble_mae,
+            "best_strategy": best_strategy,
             "best_model": best_model,
             "best_model_mae": best_model_mae,
             "ensemble_win_rate": n_better / n_total,

workbench/utils/shap_utils.py

@@ -9,6 +9,7 @@ from typing import Optional, List, Tuple, Dict, Union
 from workbench.utils.xgboost_model_utils import xgboost_model_from_s3
 from workbench.utils.model_utils import load_category_mappings_from_s3
 from workbench.utils.pandas_utils import convert_categorical_types
+from workbench.model_script_utils.model_script_utils import decompress_features
 
 # Set up the log
 log = logging.getLogger("workbench")
@@ -111,61 +112,6 @@ def shap_values_data(
         return result_df, feature_df
 
 
-def decompress_features(
-    df: pd.DataFrame, features: List[str], compressed_features: List[str]
-) -> Tuple[pd.DataFrame, List[str]]:
-    """Prepare features for the XGBoost model
-
-    Args:
-        df (pd.DataFrame): The features DataFrame
-        features (List[str]): Full list of feature names
-        compressed_features (List[str]): List of feature names to decompress (bitstrings)
-
-    Returns:
-        pd.DataFrame: DataFrame with the decompressed features
-        List[str]: Updated list of feature names after decompression
-
-    Raises:
-        ValueError: If any missing values are found in the specified features
-    """
-
-    # Check for any missing values in the required features
-    missing_counts = df[features].isna().sum()
-    if missing_counts.any():
-        missing_features = missing_counts[missing_counts > 0]
-        print(
-            f"WARNING: Found missing values in features: {missing_features.to_dict()}. "
-            "WARNING: You might want to remove/replace all NaN values before processing."
-        )
-
-    # Decompress the specified compressed features
-    decompressed_features = features
-    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.")
-            continue
-
-        # Remove the feature from the list of features to avoid duplication
-        decompressed_features.remove(feature)
-
-        # Handle all compressed features as bitstrings
-        bit_matrix = np.array([list(bitstring) for bitstring in df[feature]], dtype=np.uint8)
-        prefix = feature[:3]
-
-        # Create all new columns at once - avoids fragmentation
-        new_col_names = [f"{prefix}_{i}" for i in range(bit_matrix.shape[1])]
-        new_df = pd.DataFrame(bit_matrix, columns=new_col_names, index=df.index)
-
-        # Add to features list
-        decompressed_features.extend(new_col_names)
-
-        # Drop original column and concatenate new ones
-        df = df.drop(columns=[feature])
-        df = pd.concat([df, new_df], axis=1)
-
-    return df, decompressed_features
-
-
 def _calculate_shap_values(workbench_model, sample_df: pd.DataFrame = None):
     """
     Internal function to calculate SHAP values for Workbench Models.

{workbench-0.8.217.dist-info → workbench-0.8.219.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: workbench
-Version: 0.8.217
+Version: 0.8.219
 Summary: Workbench: A Dashboard and Python API for creating and deploying AWS SageMaker Model Pipelines
 Author-email: SuperCowPowers LLC <support@supercowpowers.com>
 License: MIT License

{workbench-0.8.217.dist-info → workbench-0.8.219.dist-info}/RECORD

@@ -26,7 +26,7 @@ workbench/algorithms/sql/__init__.py,sha256=TbOZQwCfx6Tjc3pCCLCiM31wpCX26j5MBNQ6
 workbench/algorithms/sql/column_stats.py,sha256=IwgddvPVITdAvUgxaK_px2IVSEX-jA-8cPIVFoVkbN8,5943
 workbench/algorithms/sql/correlations.py,sha256=0DMgAkzIdR0cApQ_5vs4CxPSRz1qItcAToz7GAOFqzI,3935
 workbench/algorithms/sql/descriptive_stats.py,sha256=VxSR5zQi8NmAWrJvOCO3wrmgVHYrwhenSy5Gl0AOqoo,4075
-workbench/algorithms/sql/outliers.py,sha256=2hoilOk0gaz9pwrnGEBY2y7M-UqFED3KO_mFm_0_3ac,10645
+workbench/algorithms/sql/outliers.py,sha256=LbOYaE3bNR4x-aEIrA2KAX3Aq07ZowRgrW9buCeKisQ,10663
 workbench/algorithms/sql/sample_rows.py,sha256=SRYoGb24QP_iPvOoW9bGZ95yZuseYDtyoNhilfoLu34,2688
 workbench/algorithms/sql/value_counts.py,sha256=F-rZoLTTKv1cHYl2_tDlvWDjczy76uLTr3EMHa-WrEk,3340
 workbench/api/__init__.py,sha256=1JAQKD82biia4h07BRA9ytjxuJUYQqgHvkf8FwpnlVQ,1195
@@ -58,8 +58,8 @@ workbench/core/artifacts/data_capture_core.py,sha256=q8f79rRTYiZ7T4IQRWXl8ZvPpcv
 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/df_store_core.py,sha256=AueNr_JvuLLu_ByE7cb3u-isH9u0Q7cMP-UCgCX-Ctg,3536
-workbench/core/artifacts/endpoint_core.py,sha256=VAEDP4eLl_Obwcb_Tg4tqDsAti4kXa0UzhGON57M4Hs,54071
-workbench/core/artifacts/feature_set_core.py,sha256=EAvFbkNWDaiTnQvsugNJXAt1sgbzOs4tCvSycPB7Ry8,39332
+workbench/core/artifacts/endpoint_core.py,sha256=fLOxgwNmbsrOpKafXN8zLCzazKdpJQZr2zanKJ14KRc,54057
+workbench/core/artifacts/feature_set_core.py,sha256=zR6gia7V6JeUHaKYzQRGQwF1j0Z5DBcM8oqGPS1pox4,39344
 workbench/core/artifacts/model_core.py,sha256=wPkpdRlxnAXMqsDtJGPotGFO146Hm7NCfYbImHwZo9c,52343
 workbench/core/artifacts/monitor_core.py,sha256=M307yz7tEzOEHgv-LmtVy9jKjSbM98fHW3ckmNYrwlU,27897
 workbench/core/artifacts/parameter_store_core.py,sha256=sHvjJMuybM4qdcKhH-Sx6Ur6Yn5ozA3QHwtidsnhyG8,2867
@@ -125,22 +125,21 @@ workbench/core/views/training_view.py,sha256=7HwhbQhDBhT3Zo_gssS-b4eueJ0h9nqqT8Y
 workbench/core/views/view.py,sha256=DvmEA1xdvL980GET_cnbmHzqSy6IhlNaZcoQnVTtYis,13534
 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_script_utils/model_script_utils.py,sha256=9Js8bc57osH-kkreWPq09VtWeIQ7buzMqutgV63u0UI,11479
+workbench/model_script_utils/model_script_utils.py,sha256=rGPdjxmQUPcZNXK_8nKYQWb7IPQ5ietne7UMYRQZpMo,11841
 workbench/model_script_utils/pytorch_utils.py,sha256=vr8ybK45U0H8Jhjb5qx6xbJNozdcl7bVqubknDwh6U0,13704
 workbench/model_script_utils/uq_harness.py,sha256=70b7dI9Wls03ff6zm2TpfKIsboVBKsj7P7fNzmMe6c0,10305
 workbench/model_scripts/script_generation.py,sha256=w3L2VYGnGUvBtd01BWzH38DuHKULtYsc_Xz_3_Eavvo,8258
-workbench/model_scripts/chemprop/chemprop.template,sha256=Vh2DW3E6ryrvM3VizZ2JVlBeFTu247guB_3cPcF2Hgw,29386
-workbench/model_scripts/chemprop/generated_model_script.py,sha256=7h0sVMIlfe53XHUCRdKyVFUoq6lKOJBcxD15BmZhC8c,29408
-workbench/model_scripts/chemprop/model_script_utils.py,sha256=9Js8bc57osH-kkreWPq09VtWeIQ7buzMqutgV63u0UI,11479
+workbench/model_scripts/chemprop/chemprop.template,sha256=EF1otxEJGPKm_iZibbWBUvjWhQY0G8jnPK8d_A7OnS8,29416
+workbench/model_scripts/chemprop/generated_model_script.py,sha256=4WqqqkUlUSf1EEgzZk-OAFSwoif5drjwitEko0rlI38,30093
+workbench/model_scripts/chemprop/model_script_utils.py,sha256=rGPdjxmQUPcZNXK_8nKYQWb7IPQ5ietne7UMYRQZpMo,11841
 workbench/model_scripts/chemprop/requirements.txt,sha256=2IBHZZNYqhX9Ed7AmRVgN06tO3EHeBbN2EM8-tjWZhs,216
 workbench/model_scripts/custom_models/chem_info/Readme.md,sha256=mH1lxJ4Pb7F5nBnVXaiuxpi8zS_yjUw_LBJepVKXhlA,574
-workbench/model_scripts/custom_models/chem_info/fingerprints.py,sha256=XHRxoP6eV5z_k7w6BmfwpPO8rr6PZIF7KW9jwGjnj7o,5449
+workbench/model_scripts/custom_models/chem_info/fingerprints.py,sha256=ECDzjZs4wSx3ZvAQipMl2NEqI2isCWHLYBv7mp0NVgk,6939
 workbench/model_scripts/custom_models/chem_info/mol_descriptors.py,sha256=c8gkHZ-8s3HJaW9zN9pnYGK7YVW8Y0xFqQ1G_ysrF2Y,18789
 workbench/model_scripts/custom_models/chem_info/mol_standardize.py,sha256=qPLCdVMSXMOWN-01O1isg2zq7eQyFAI0SNatHkRq1uw,17524
 workbench/model_scripts/custom_models/chem_info/molecular_descriptors.py,sha256=xljMjdfh4Idi4v1Afq1zZxvF1SDa7pDOLSAhvGBEj88,2891
 workbench/model_scripts/custom_models/chem_info/morgan_fingerprints.py,sha256=LqVh_AHObo0uxHt_uNmeemScTLjM2j9C3I_QFJXdmUI,3232
 workbench/model_scripts/custom_models/chem_info/requirements.txt,sha256=7HBUzvNiM8lOir-UfQabXYlUp3gxdGJ42u18EuSMGjc,39
-workbench/model_scripts/custom_models/meta_endpoints/example.py,sha256=hzOAuLhIGB8vei-555ruNxpsE1GhuByHGjGB0zw8GSs,1726
 workbench/model_scripts/custom_models/network_security/Readme.md,sha256=Z2gtiu0hLHvEJ1x-_oFq3qJZcsK81sceBAGAGltpqQ8,222
 workbench/model_scripts/custom_models/proximity/Readme.md,sha256=RlMFAJZgAT2mCgDk-UwR_R0Y_NbCqeI5-8DUsxsbpWQ,289
 workbench/model_scripts/custom_models/proximity/feature_space_proximity.py,sha256=FYsQd5Lf5CrSWi-1Dcs_NVFN86izifxkWk1-EOvEV54,6950
@@ -151,7 +150,6 @@ workbench/model_scripts/custom_models/uq_models/bayesian_ridge.template,sha256=c
 workbench/model_scripts/custom_models/uq_models/ensemble_xgb.template,sha256=449Enh4-7RrMrxt1oS_SHJHGV8yYcFlWHsLrCVTFQGI,13778
 workbench/model_scripts/custom_models/uq_models/feature_space_proximity.py,sha256=FYsQd5Lf5CrSWi-1Dcs_NVFN86izifxkWk1-EOvEV54,6950
 workbench/model_scripts/custom_models/uq_models/gaussian_process.template,sha256=3nMlCi8nEbc4N-MQTzjfIcljfDQkUmWeLBfmd18m5fg,6632
-workbench/model_scripts/custom_models/uq_models/meta_uq.template,sha256=wLilHll9Hzwyo-y9Vsqx7PjzdMca4xkUt3Ed1zcgOBE,14412
 workbench/model_scripts/custom_models/uq_models/ngboost.template,sha256=_ukYcsL4pnWvFV1oA89_wfVpxWbvoEx6MGwKxc38kSI,8512
 workbench/model_scripts/custom_models/uq_models/requirements.txt,sha256=fw7T7t_YJAXK3T6Ysbesxh_Agx_tv0oYx72cEBTqRDY,98
 workbench/model_scripts/custom_script_example/custom_model_script.py,sha256=T8aydawgRVAdSlDimoWpXxG2YuWWQkbcjBVjAeSG2_0,6408
@@ -160,8 +158,8 @@ workbench/model_scripts/ensemble_xgb/ensemble_xgb.template,sha256=lMEx0IkawcpTI5
 workbench/model_scripts/ensemble_xgb/requirements.txt,sha256=jWlGc7HH7vqyukTm38LN4EyDi8jDUPEay4n45z-30uc,104
 workbench/model_scripts/meta_model/generated_model_script.py,sha256=ncPrHd9-R8l_98vAiuTUJ92C9PKpEgAtpIrmd7TuqSQ,8341
 workbench/model_scripts/meta_model/meta_model.template,sha256=viz-AKVq3YRwOUBt8-rUO1TwdEPFzyP7nnifqcIJurw,8244
-workbench/model_scripts/pytorch_model/generated_model_script.py,sha256=qw5lqFhkRjMGjTWC9SH1lgGETwqEXEmgzk_cdEs2ZFw,24598
-workbench/model_scripts/pytorch_model/model_script_utils.py,sha256=9Js8bc57osH-kkreWPq09VtWeIQ7buzMqutgV63u0UI,11479
+workbench/model_scripts/pytorch_model/generated_model_script.py,sha256=ma2JOiCxCZfq94jvIsDoCa2VQBwKf-trj9QMpaa0VEQ,21108
+workbench/model_scripts/pytorch_model/model_script_utils.py,sha256=rGPdjxmQUPcZNXK_8nKYQWb7IPQ5ietne7UMYRQZpMo,11841
 workbench/model_scripts/pytorch_model/pytorch.template,sha256=KOH7nhq_3u0pHmjGymY5aycF0_ZlwLQ16qmDKUQcE9k,21091
 workbench/model_scripts/pytorch_model/pytorch_utils.py,sha256=vr8ybK45U0H8Jhjb5qx6xbJNozdcl7bVqubknDwh6U0,13704
 workbench/model_scripts/pytorch_model/requirements.txt,sha256=ES7YehHEL4E5oV8FScHm3oNQmkMI4ODgbC1fSbaY7T4,183
@@ -170,8 +168,8 @@ workbench/model_scripts/scikit_learn/generated_model_script.py,sha256=xhQIglpAgP
 workbench/model_scripts/scikit_learn/requirements.txt,sha256=aVvwiJ3LgBUhM_PyFlb2gHXu_kpGPho3ANBzlOkfcvs,107
 workbench/model_scripts/scikit_learn/scikit_learn.template,sha256=QQvqx-eX9ZTbYmyupq6R6vIQwosmsmY_MRBPaHyfjdk,12586
 workbench/model_scripts/uq_models/generated_model_script.py,sha256=kgcIWghY6eazcBWS77MukhQUyYFmfJcS8SQ8RmjM82I,9006
-workbench/model_scripts/xgb_model/generated_model_script.py,sha256=bIue0u9S1y1rBCcTVZ0Aa0PO8-XBphJmAgm0e8ov90k,18585
-workbench/model_scripts/xgb_model/model_script_utils.py,sha256=9Js8bc57osH-kkreWPq09VtWeIQ7buzMqutgV63u0UI,11479
+workbench/model_scripts/xgb_model/generated_model_script.py,sha256=VkgU9jXvWzTjPsq9JoIRJGKYJE-aj3-z7gTOc5f6hH4,18376
+workbench/model_scripts/xgb_model/model_script_utils.py,sha256=rGPdjxmQUPcZNXK_8nKYQWb7IPQ5ietne7UMYRQZpMo,11841
 workbench/model_scripts/xgb_model/requirements.txt,sha256=jWlGc7HH7vqyukTm38LN4EyDi8jDUPEay4n45z-30uc,104
 workbench/model_scripts/xgb_model/uq_harness.py,sha256=70b7dI9Wls03ff6zm2TpfKIsboVBKsj7P7fNzmMe6c0,10305
 workbench/model_scripts/xgb_model/xgb_model.template,sha256=w4-yx82yws-_esObZQIq13S8WKXXnZxqe86ZuyWoP5w,18367
@@ -183,6 +181,7 @@ workbench/scripts/check_double_bond_stereo.py,sha256=p5hnL54Weq77ES0HCELq9JeoM-P
 workbench/scripts/endpoint_test.py,sha256=RV52DZZTOD_ou-ywZjaxQ2_wqnSJqvlnHQZbvf4iM6I,5339
 workbench/scripts/glue_launcher.py,sha256=bIKQvfGxpAhzbeNvTnHfRW_5kQhY-169_868ZnCejJk,10692
 workbench/scripts/lambda_test.py,sha256=SLAPIXeGQn82neQ6-Hif3VS3LWLwT0-dGw8yWw2aXRQ,2077
+workbench/scripts/meta_model_sim.py,sha256=6iGpInA-nH6DSjk0z63fcoL8P7icqnZmKLE5Sqyrh7E,1026
 workbench/scripts/ml_pipeline_batch.py,sha256=1T5JnLlUJR7bwAGBLHmLPOuj1xFRqVIQX8PsuDhHy8o,4907
 workbench/scripts/ml_pipeline_sqs.py,sha256=5c8qX-SoV4htOUcSXk4OzD7BQskCnaA7cLMiF4Et24c,6666
 workbench/scripts/monitor_cloud_watch.py,sha256=s7MY4bsHts0nup9G0lWESCvgJZ9Mw1Eo-c8aKRgLjMw,9235
@@ -236,7 +235,7 @@ workbench/utils/lambda_utils.py,sha256=7GhGRPyXn9o-toWb9HBGSnI8-DhK9YRkwhCSk_mNK
 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/meta_model_simulator.py,sha256=E8O8z4sbSDhKd22_nbuFLUcPNbPGzMacznBdL2H4trU,18755
+workbench/utils/meta_model_simulator.py,sha256=fMKZoLi_VEJohNVvbZSMvZWNdUbIpGlB6Bg6mJQW33s,20630
 workbench/utils/metrics_utils.py,sha256=iAoKrAM4iRX8wFSjSJhfNKbbW1BqB3eI_U3wvdhUdhE,9496
 workbench/utils/model_utils.py,sha256=jiybuv6gGE-p2i2JEQcyAY-ffigtuzZFNvp_rHKCi3A,19284
 workbench/utils/monitor_utils.py,sha256=kVaJ7BgUXs3VPMFYfLC03wkIV4Dq-pEhoXS0wkJFxCc,7858
@@ -250,7 +249,7 @@ workbench/utils/pytorch_utils.py,sha256=RoltE9-fOX2UixzaEmnxN6oJtBEKQ9Jklu0LRzYK
 workbench/utils/redis_cache.py,sha256=39LFSWmOlNNcah02D3sBnmibc-DPeKC3SNq71K4HaB4,12893
 workbench/utils/repl_utils.py,sha256=rWOMv2HiEIp8ZL6Ps6DlwiJlGr-pOhv9OZQhm3aR-1A,4668
 workbench/utils/s3_utils.py,sha256=Xme_o_cftC_jWnw6R9YKS6-6C11zaCBAoQDlY3dZb5o,7337
-workbench/utils/shap_utils.py,sha256=dtjSIwSyvYSaQjjvIp5A9LGS7pr-5Vt907rvVKOrqNY,12651
+workbench/utils/shap_utils.py,sha256=FeFNRH5mJTbuHlpHyFJgjHcU5BU7UthJL1Gb5Gl8_zw,10590
 workbench/utils/shapley_values.py,sha256=3DvQz4HIPnxW42idgtuQ5vtzU-oF4_lToaWzLRjU-E4,3673
 workbench/utils/symbols.py,sha256=PioF1yAQyOabw7kLg8nhvaZBPFe7ABkpfpPPE0qz_2k,1265
 workbench/utils/test_data_generator.py,sha256=gqRXL7IUKG4wVfO1onflY3wg7vLkgx402_Zy3iqY7NU,11921
@@ -264,7 +263,7 @@ workbench/utils/workbench_sqs.py,sha256=RwM80z7YWwdtMaCKh7KWF8v38f7eBRU7kyC7ZhTR
 workbench/utils/xgboost_local_crossfold.py,sha256=GY61F6-avQDiteIb1LAgvkHvAKvLg6H85xBDvfgCVDM,10718
 workbench/utils/xgboost_model_utils.py,sha256=qEnB1viCIXMYLW0LJuyCioKMSilbmKTMuppaxBZqwhc,12967
 workbench/utils/chem_utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-workbench/utils/chem_utils/fingerprints.py,sha256=XHRxoP6eV5z_k7w6BmfwpPO8rr6PZIF7KW9jwGjnj7o,5449
+workbench/utils/chem_utils/fingerprints.py,sha256=ECDzjZs4wSx3ZvAQipMl2NEqI2isCWHLYBv7mp0NVgk,6939
 workbench/utils/chem_utils/misc.py,sha256=Nevf8_opu-uIPrv_1_0ubuFVVo2_fGUkMoLAHB3XAeo,7372
 workbench/utils/chem_utils/mol_descriptors.py,sha256=c8gkHZ-8s3HJaW9zN9pnYGK7YVW8Y0xFqQ1G_ysrF2Y,18789
 workbench/utils/chem_utils/mol_standardize.py,sha256=qPLCdVMSXMOWN-01O1isg2zq7eQyFAI0SNatHkRq1uw,17524
@@ -307,9 +306,9 @@ 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-0.8.217.dist-info/licenses/LICENSE,sha256=RTBoTMeEwTgEhS-n8vgQ-VUo5qig0PWVd8xFPKU6Lck,1080
-workbench-0.8.217.dist-info/METADATA,sha256=7aIfI1eWuhBsh22ymfAboL7MK6l3z-8FlA1AXQ5xzMg,10525
-workbench-0.8.217.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-workbench-0.8.217.dist-info/entry_points.txt,sha256=viJ6aXRj63sBIs7avj4kFbCO2J2E7jTCrIk8U1SIc3I,511
-workbench-0.8.217.dist-info/top_level.txt,sha256=Dhy72zTxaA_o_yRkPZx5zw-fwumnjGaeGf0hBN3jc_w,10
-workbench-0.8.217.dist-info/RECORD,,
+workbench-0.8.219.dist-info/licenses/LICENSE,sha256=RTBoTMeEwTgEhS-n8vgQ-VUo5qig0PWVd8xFPKU6Lck,1080
+workbench-0.8.219.dist-info/METADATA,sha256=1Sks6KYtjjg1QqIH6p4Q8d9Dazr3EfuQdcvv0wgsXgE,10525
+workbench-0.8.219.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+workbench-0.8.219.dist-info/entry_points.txt,sha256=t_9tY7iYku9z96qFZZtUgbWDh_nHtehXxLPLBSpAzeM,566
+workbench-0.8.219.dist-info/top_level.txt,sha256=Dhy72zTxaA_o_yRkPZx5zw-fwumnjGaeGf0hBN3jc_w,10
+workbench-0.8.219.dist-info/RECORD,,

{workbench-0.8.217.dist-info → workbench-0.8.219.dist-info}/entry_points.txt

@@ -3,6 +3,7 @@ cloud_watch = workbench.scripts.monitor_cloud_watch:main
 endpoint_test = workbench.scripts.endpoint_test:main
 glue_launcher = workbench.scripts.glue_launcher:main
 lambda_test = workbench.scripts.lambda_test:main
+meta_model_sim = workbench.scripts.meta_model_sim:main
 ml_pipeline_batch = workbench.scripts.ml_pipeline_batch:main
 ml_pipeline_sqs = workbench.scripts.ml_pipeline_sqs:main
 training_test = workbench.scripts.training_test:main

workbench/model_scripts/custom_models/meta_endpoints/example.py

@@ -1,53 +0,0 @@
-# Model: Meta Endpoint Example
-# This script is a template for creating a custom meta endpoint in AWS Workbench.
-from io import StringIO
-import pandas as pd
-import json
-
-# Workbench Bridges imports
-try:
-    from workbench_bridges.endpoints.fast_inference import fast_inference
-except ImportError:
-    print("workbench_bridges not found, this is fine for training...")
-
-
-# Not Used: We need to define this function for SageMaker
-def model_fn(model_dir):
-    return None
-
-
-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")
-
-    # Support CSV and JSON input formats
-    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."""
-    if "text/csv" in accept_type:
-        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):
-
-    # Call inference on an endpoint
-    df = fast_inference("abalone-regression", df)
-    return df