workbench 0.8.192__py3-none-any.whl → 0.8.193__py3-none-any.whl

workbench/core/artifacts/model_core.py

@@ -41,52 +41,39 @@ class ModelType(Enum):
 class ModelImages:
     """Class for retrieving workbench inference images"""
 
-    image_uris = {
-        # US East 1 images
-        ("us-east-1", "training", "0.1", "x86_64"): (
-            "507740646243.dkr.ecr.us-east-1.amazonaws.com/aws-ml-images/py312-general-ml-training:0.1"
-        ),
-        ("us-east-1", "inference", "0.1", "x86_64"): (
-            "507740646243.dkr.ecr.us-east-1.amazonaws.com/aws-ml-images/py312-general-ml-inference:0.1"
-        ),
-        ("us-east-1", "pytorch_training", "0.1", "x86_64"): (
-            "507740646243.dkr.ecr.us-east-1.amazonaws.com/aws-ml-images/py312-pytorch-training:0.1"
-        ),
-        ("us-east-1", "pytorch_inference", "0.1", "x86_64"): (
-            "507740646243.dkr.ecr.us-east-1.amazonaws.com/aws-ml-images/py312-pytorch-inference:0.1"
-        ),
-        # US West 2 images
-        ("us-west-2", "training", "0.1", "x86_64"): (
-            "507740646243.dkr.ecr.us-west-2.amazonaws.com/aws-ml-images/py312-general-ml-training:0.1"
-        ),
-        ("us-west-2", "inference", "0.1", "x86_64"): (
-            "507740646243.dkr.ecr.us-west-2.amazonaws.com/aws-ml-images/py312-general-ml-inference:0.1"
-        ),
-        ("us-west-2", "pytorch_training", "0.1", "x86_64"): (
-            "507740646243.dkr.ecr.us-west-2.amazonaws.com/aws-ml-images/py312-pytorch-training:0.1"
-        ),
-        ("us-west-2", "pytorch_inference", "0.1", "x86_64"): (
-            "507740646243.dkr.ecr.us-west-2.amazonaws.com/aws-ml-images/py312-pytorch-inference:0.1"
-        ),
-        # ARM64 images
-        # Meta Endpoint inference images
-        ("us-east-1", "meta-endpoint", "0.1", "x86_64"): (
-            "507740646243.dkr.ecr.us-east-1.amazonaws.com/aws-ml-images/py312-meta-endpoint:0.1"
-        ),
-        ("us-west-2", "meta-endpoint", "0.1", "x86_64"): (
-            "507740646243.dkr.ecr.us-west-2.amazonaws.com/aws-ml-images/py312-meta-endpoint:0.1"
-        ),
+    # Account ID
+    ACCOUNT_ID = "507740646243"
+
+    # Image name mappings
+    IMAGE_NAMES = {
+        "training": "py312-general-ml-training",
+        "inference": "py312-general-ml-inference",
+        "pytorch_training": "py312-pytorch-training",
+        "pytorch_inference": "py312-pytorch-inference",
+        "meta-endpoint": "py312-meta-endpoint",
     }
 
     @classmethod
     def get_image_uri(cls, region, image_type, version="0.1", architecture="x86_64"):
-        key = (region, image_type, version, architecture)
-        if key in cls.image_uris:
-            return cls.image_uris[key]
-        else:
-            raise ValueError(
-                f"No matching image found for region: {region}, image_type: {image_type}, version: {version}"
-            )
+        """
+        Dynamically construct ECR image URI.
+
+        Args:
+            region: AWS region (e.g., 'us-east-1', 'us-west-2')
+            image_type: Type of image (e.g., 'training', 'inference', 'pytorch_training')
+            version: Image version (e.g., '0.1', '0.2')
+            architecture: CPU architecture (default: 'x86_64', currently unused but kept for compatibility)
+
+        Returns:
+            ECR image URI string
+        """
+        if image_type not in cls.IMAGE_NAMES:
+            raise ValueError(f"Unknown image_type: {image_type}. Valid types: {list(cls.IMAGE_NAMES.keys())}")
+
+        image_name = cls.IMAGE_NAMES[image_type]
+        uri = f"{cls.ACCOUNT_ID}.dkr.ecr.{region}.amazonaws.com/aws-ml-images/{image_name}:{version}"
+
+        return uri
 
 
 class ModelCore(Artifact):

workbench/core/transforms/features_to_model/features_to_model.py

@@ -233,7 +233,7 @@ class FeaturesToModel(Transform):
         source_dir = str(Path(script_path).parent)
 
         # Create a Sagemaker Model with our script
-        image = ModelImages.get_image_uri(self.sm_session.boto_region_name, self.training_image, "0.1")
+        image = ModelImages.get_image_uri(self.sm_session.boto_region_name, self.training_image, "0.2")
         self.estimator = Estimator(
             entry_point=entry_point,
             source_dir=source_dir,
@@ -306,7 +306,7 @@ class FeaturesToModel(Transform):
 
         # Register our model
         image = ModelImages.get_image_uri(
-            self.sm_session.boto_region_name, self.inference_image, "0.1", self.inference_arch
+            self.sm_session.boto_region_name, self.inference_image, "0.2", self.inference_arch
         )
         self.log.important(f"Registering model {self.output_name} with Inference Image {image}...")
         model = self.estimator.create_model(role=self.workbench_role_arn)

workbench/model_scripts/xgb_model/generated_model_script.py

@@ -0,0 +1,468 @@
+# Imports for XGB Model
+import xgboost as xgb
+import awswrangler as wr
+import numpy as np
+
+# Model Performance Scores
+from sklearn.metrics import (
+    mean_absolute_error,
+    r2_score,
+    root_mean_squared_error,
+    precision_recall_fscore_support,
+    confusion_matrix,
+)
+
+# Classification Encoder
+from sklearn.preprocessing import LabelEncoder
+
+# Scikit Learn Imports
+from sklearn.model_selection import train_test_split
+
+from io import StringIO
+import json
+import argparse
+import joblib
+import os
+import pandas as pd
+from typing import List, Tuple
+
+# Template Parameters
+TEMPLATE_PARAMS = {
+    "model_type": "regressor",
+    "target": "solubility",
+    "features": ['molwt', 'mollogp', 'molmr', 'heavyatomcount', 'numhacceptors', 'numhdonors', 'numheteroatoms', 'numrotatablebonds', 'numvalenceelectrons', 'numaromaticrings', 'numsaturatedrings', 'numaliphaticrings', 'ringcount', 'tpsa', 'labuteasa', 'balabanj', 'bertzct'],
+    "compressed_features": [],
+    "model_metrics_s3_path": "s3://sandbox-sageworks-artifacts/models/aqsol-regression/training",
+    "train_all_data": False,
+    "hyperparameters": {},
+}
+
+
+# Function to check if dataframe is empty
+def check_dataframe(df: pd.DataFrame, df_name: str) -> None:
+    """
+    Check if the provided dataframe is empty and raise an exception if it is.
+
+    Args:
+        df (pd.DataFrame): DataFrame to check
+        df_name (str): Name of the DataFrame
+    """
+    if df.empty:
+        msg = f"*** The training data {df_name} has 0 rows! ***STOPPING***"
+        print(msg)
+        raise ValueError(msg)
+
+
+def expand_proba_column(df: pd.DataFrame, class_labels: List[str]) -> pd.DataFrame:
+    """
+    Expands a column in a DataFrame containing a list of probabilities into separate columns.
+
+    Args:
+        df (pd.DataFrame): DataFrame containing a "pred_proba" column
+        class_labels (List[str]): List of class labels
+
+    Returns:
+        pd.DataFrame: DataFrame with the "pred_proba" expanded into separate columns
+    """
+
+    # Sanity check
+    proba_column = "pred_proba"
+    if proba_column not in df.columns:
+        raise ValueError('DataFrame does not contain a "pred_proba" column')
+
+    # Construct new column names with '_proba' suffix
+    proba_splits = [f"{label}_proba" for label in class_labels]
+
+    # Expand the proba_column into separate columns for each probability
+    proba_df = pd.DataFrame(df[proba_column].tolist(), columns=proba_splits)
+
+    # Drop any proba columns and reset the index in prep for the concat
+    df = df.drop(columns=[proba_column] + proba_splits, errors="ignore")
+    df = df.reset_index(drop=True)
+
+    # Concatenate the new columns with the original DataFrame
+    df = pd.concat([df, proba_df], axis=1)
+    print(df)
+    return df
+
+
+def match_features_case_insensitive(df: pd.DataFrame, model_features: list) -> pd.DataFrame:
+    """
+    Matches and renames DataFrame columns to match model feature names (case-insensitive).
+    Prioritizes exact matches, then case-insensitive matches.
+
+    Raises ValueError if any model features cannot be matched.
+    """
+    df_columns_lower = {col.lower(): col for col in df.columns}
+    rename_dict = {}
+    missing = []
+    for feature in model_features:
+        if feature in df.columns:
+            continue  # Exact match
+        elif feature.lower() in df_columns_lower:
+            rename_dict[df_columns_lower[feature.lower()]] = feature
+        else:
+            missing.append(feature)
+
+    if missing:
+        raise ValueError(f"Features not found: {missing}")
+
+    # Rename the DataFrame columns to match the model features
+    return df.rename(columns=rename_dict)
+
+
+def convert_categorical_types(df: pd.DataFrame, features: list, category_mappings={}) -> tuple:
+    """
+    Converts appropriate columns to categorical type with consistent mappings.
+
+    Args:
+        df (pd.DataFrame): The DataFrame to process.
+        features (list): List of feature names to consider for conversion.
+        category_mappings (dict, optional): Existing category mappings. If empty dict, we're in
+                                            training mode. If populated, we're in inference mode.
+
+    Returns:
+        tuple: (processed DataFrame, category mappings dictionary)
+    """
+    # Training mode
+    if category_mappings == {}:
+        for col in df.select_dtypes(include=["object", "string"]):
+            if col in features and df[col].nunique() < 20:
+                print(f"Training mode: Converting {col} to category")
+                df[col] = df[col].astype("category")
+                category_mappings[col] = df[col].cat.categories.tolist()  # Store category mappings
+
+    # Inference mode
+    else:
+        for col, categories in category_mappings.items():
+            if col in df.columns:
+                print(f"Inference mode: Applying categorical mapping for {col}")
+                df[col] = pd.Categorical(df[col], categories=categories)  # Apply consistent categorical mapping
+
+    return df, category_mappings
+
+
+def decompress_features(
+    df: pd.DataFrame, features: List[str], compressed_features: List[str]
+) -> Tuple[pd.DataFrame, List[str]]:
+    """Prepare features for the model by decompressing bitstring features
+
+    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.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.")
+            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
+
+
+if __name__ == "__main__":
+    """The main function is for training the XGBoost model"""
+
+    # Harness Template Parameters
+    target = TEMPLATE_PARAMS["target"]
+    features = TEMPLATE_PARAMS["features"]
+    orig_features = features.copy()
+    compressed_features = TEMPLATE_PARAMS["compressed_features"]
+    model_type = TEMPLATE_PARAMS["model_type"]
+    model_metrics_s3_path = TEMPLATE_PARAMS["model_metrics_s3_path"]
+    train_all_data = TEMPLATE_PARAMS["train_all_data"]
+    hyperparameters = TEMPLATE_PARAMS["hyperparameters"]
+    validation_split = 0.2
+
+    # 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()
+
+    # Read the training data into DataFrames
+    training_files = [os.path.join(args.train, file) for file in os.listdir(args.train) if file.endswith(".csv")]
+    print(f"Training Files: {training_files}")
+
+    # Combine files and read them all into a single pandas dataframe
+    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")
+
+    # Features/Target output
+    print(f"Target: {target}")
+    print(f"Features: {str(features)}")
+
+    # Convert any features that might be categorical to 'category' type
+    all_df, category_mappings = convert_categorical_types(all_df, features)
+
+    # If we have compressed features, decompress them
+    if compressed_features:
+        print(f"Decompressing features {compressed_features}...")
+        all_df, features = decompress_features(all_df, features, compressed_features)
+
+    # Do we want to train on all the data?
+    if train_all_data:
+        print("Training on ALL of the data")
+        df_train = all_df.copy()
+        df_val = all_df.copy()
+
+    # Does the dataframe have a training column?
+    elif "training" in all_df.columns:
+        print("Found training column, splitting data based on training column")
+        df_train = all_df[all_df["training"]]
+        df_val = all_df[~all_df["training"]]
+    else:
+        # Just do a random training Split
+        print("WARNING: No training column found, splitting data with random state=42")
+        df_train, df_val = train_test_split(all_df, test_size=validation_split, random_state=42)
+    print(f"FIT/TRAIN: {df_train.shape}")
+    print(f"VALIDATION: {df_val.shape}")
+
+    # Use any hyperparameters to set up both the trainer and model configurations
+    print(f"Hyperparameters: {hyperparameters}")
+
+    # Now spin up our XGB Model
+    if model_type == "classifier":
+        xgb_model = xgb.XGBClassifier(enable_categorical=True, **hyperparameters)
+
+        # Encode the target column
+        label_encoder = LabelEncoder()
+        df_train[target] = label_encoder.fit_transform(df_train[target])
+        df_val[target] = label_encoder.transform(df_val[target])
+
+    else:
+        xgb_model = xgb.XGBRegressor(enable_categorical=True, **hyperparameters)
+        label_encoder = None  # We don't need this for regression
+
+    # Grab our Features, Target and Train the Model
+    y_train = df_train[target]
+    X_train = df_train[features]
+    xgb_model.fit(X_train, y_train)
+
+    # Make Predictions on the Validation Set
+    print(f"Making Predictions on Validation Set...")
+    y_validate = df_val[target]
+    X_validate = df_val[features]
+    preds = xgb_model.predict(X_validate)
+    if model_type == "classifier":
+        # Also get the probabilities for each class
+        print("Processing Probabilities...")
+        probs = xgb_model.predict_proba(X_validate)
+        df_val["pred_proba"] = [p.tolist() for p in probs]
+
+        # Expand the pred_proba column into separate columns for each class
+        print(df_val.columns)
+        df_val = expand_proba_column(df_val, label_encoder.classes_)
+        print(df_val.columns)
+
+        # Decode the target and prediction labels
+        y_validate = label_encoder.inverse_transform(y_validate)
+        preds = label_encoder.inverse_transform(preds)
+
+    # Save predictions to S3 (just the target, prediction, and '_proba' columns)
+    df_val["prediction"] = preds
+    output_columns = [target, "prediction"]
+    output_columns += [col for col in df_val.columns if col.endswith("_proba")]
+    wr.s3.to_csv(
+        df_val[output_columns],
+        path=f"{model_metrics_s3_path}/validation_predictions.csv",
+        index=False,
+    )
+
+    # Report Performance Metrics
+    if model_type == "classifier":
+        # Get the label names and their integer mapping
+        label_names = label_encoder.classes_
+
+        # Calculate various model performance metrics
+        scores = precision_recall_fscore_support(y_validate, preds, average=None, labels=label_names)
+
+        # Put the scores into a dataframe
+        score_df = pd.DataFrame(
+            {
+                target: label_names,
+                "precision": scores[0],
+                "recall": scores[1],
+                "fscore": scores[2],
+                "support": scores[3],
+            }
+        )
+
+        # We need to get creative with the Classification Metrics
+        metrics = ["precision", "recall", "fscore", "support"]
+        for t in label_names:
+            for m in metrics:
+                value = score_df.loc[score_df[target] == t, m].iloc[0]
+                print(f"Metrics:{t}:{m} {value}")
+
+        # Compute and output the confusion matrix
+        conf_mtx = confusion_matrix(y_validate, preds, labels=label_names)
+        for i, row_name in enumerate(label_names):
+            for j, col_name in enumerate(label_names):
+                value = conf_mtx[i, j]
+                print(f"ConfusionMatrix:{row_name}:{col_name} {value}")
+
+    else:
+        # Calculate various model performance metrics (regression)
+        rmse = root_mean_squared_error(y_validate, preds)
+        mae = mean_absolute_error(y_validate, preds)
+        r2 = r2_score(y_validate, preds)
+        print(f"RMSE: {rmse:.3f}")
+        print(f"MAE: {mae:.3f}")
+        print(f"R2: {r2:.3f}")
+        print(f"NumRows: {len(df_val)}")
+
+    # Now save the model to the standard place/name
+    joblib.dump(xgb_model, os.path.join(args.model_dir, "xgb_model.joblib"))
+
+    # Save the label encoder if we have one
+    if label_encoder:
+        joblib.dump(label_encoder, os.path.join(args.model_dir, "label_encoder.joblib"))
+
+    # Save the features (this will validate input during predictions)
+    with open(os.path.join(args.model_dir, "feature_columns.json"), "w") as fp:
+        json.dump(orig_features, fp)  # We save the original features, not the decompressed ones
+
+    # Save the category mappings
+    with open(os.path.join(args.model_dir, "category_mappings.json"), "w") as fp:
+        json.dump(category_mappings, fp)
+
+
+def model_fn(model_dir):
+    """Deserialize and return fitted XGBoost model"""
+    model_path = os.path.join(model_dir, "xgb_model.joblib")
+    model = joblib.load(model_path)
+    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."""
+    if "text/csv" in accept_type:
+        csv_output = output_df.fillna("N/A").to_csv(index=False)  # CSV with N/A for missing values
+        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.")
+
+
+def predict_fn(df, model) -> pd.DataFrame:
+    """Make Predictions with our XGB Model
+
+    Args:
+        df (pd.DataFrame): The input DataFrame
+        model: The model use for predictions
+
+    Returns:
+        pd.DataFrame: The DataFrame with the predictions added
+    """
+    compressed_features = TEMPLATE_PARAMS["compressed_features"]
+
+    # Grab our feature columns (from training)
+    model_dir = os.environ.get("SM_MODEL_DIR", "/opt/ml/model")
+    with open(os.path.join(model_dir, "feature_columns.json")) as fp:
+        features = json.load(fp)
+    print(f"Model Features: {features}")
+
+    # Load the category mappings (from training)
+    with open(os.path.join(model_dir, "category_mappings.json")) as fp:
+        category_mappings = json.load(fp)
+
+    # Load our Label Encoder if we have one
+    label_encoder = None
+    if os.path.exists(os.path.join(model_dir, "label_encoder.joblib")):
+        label_encoder = joblib.load(os.path.join(model_dir, "label_encoder.joblib"))
+
+    # We're going match features in a case-insensitive manner, accounting for all the permutations
+    # - Model has a feature list that's any case ("Id", "taCos", "cOunT", "likes_tacos")
+    # - Incoming data has columns that are mixed case ("ID", "Tacos", "Count", "Likes_Tacos")
+    matched_df = match_features_case_insensitive(df, features)
+
+    # Detect categorical types in the incoming DataFrame
+    matched_df, _ = convert_categorical_types(matched_df, features, category_mappings)
+
+    # If we have compressed features, decompress them
+    if compressed_features:
+        print("Decompressing features for prediction...")
+        matched_df, features = decompress_features(matched_df, features, compressed_features)
+
+    # Predict the features against our XGB Model
+    X = matched_df[features]
+    predictions = model.predict(X)
+
+    # If we have a label encoder, decode the predictions
+    if label_encoder:
+        predictions = label_encoder.inverse_transform(predictions)
+
+    # Set the predictions on the DataFrame
+    df["prediction"] = predictions
+
+    # Does our model have a 'predict_proba' method? If so we will call it and add the results to the DataFrame
+    if getattr(model, "predict_proba", None):
+        probs = model.predict_proba(matched_df[features])
+        df["pred_proba"] = [p.tolist() for p in probs]
+
+        # Expand the pred_proba column into separate columns for each class
+        df = expand_proba_column(df, label_encoder.classes_)
+
+    # All done, return the DataFrame with new columns for the predictions
+    return df

workbench/utils/model_utils.py

@@ -188,6 +188,20 @@ def uq_model(model: "Model", uq_model_name: str, train_all_data: bool = False) -
     return uq_model
 
 
+def safe_extract_tarfile(tar_path: str, extract_path: str) -> None:
+    """
+    Extract a tarball safely, using data filter if available.
+
+    The filter parameter was backported to Python 3.8+, 3.9+, 3.10.13+, 3.11+
+    as a security patch, but may not be present in older patch versions.
+    """
+    with tarfile.open(tar_path, "r:gz") as tar:
+        if hasattr(tarfile, "data_filter"):
+            tar.extractall(path=extract_path, filter="data")
+        else:
+            tar.extractall(path=extract_path)
+
+
 def load_category_mappings_from_s3(model_artifact_uri: str) -> Optional[dict]:
     """
     Download and extract category mappings from a model artifact in S3.
@@ -206,9 +220,7 @@ def load_category_mappings_from_s3(model_artifact_uri: str) -> Optional[dict]:
         wr.s3.download(path=model_artifact_uri, local_file=local_tar_path)
 
         # Extract tarball
-        with tarfile.open(local_tar_path, "r:gz") as tar:
-            # Note: For 3.12+, can use filter="data" argument
-            tar.extractall(path=tmpdir)
+        safe_extract_tarfile(local_tar_path, tmpdir)
 
         # Look for category mappings in base directory only
         mappings_path = os.path.join(tmpdir, "category_mappings.json")

workbench/utils/xgboost_model_utils.py

@@ -3,7 +3,6 @@
 import logging
 import os
 import tempfile
-import tarfile
 import joblib
 import pickle
 import glob
@@ -26,7 +25,7 @@ from scipy.stats import spearmanr
 from sklearn.preprocessing import LabelEncoder
 
 # Workbench Imports
-from workbench.utils.model_utils import load_category_mappings_from_s3
+from workbench.utils.model_utils import load_category_mappings_from_s3, safe_extract_tarfile
 from workbench.utils.pandas_utils import convert_categorical_types
 
 # Set up the log
@@ -50,9 +49,7 @@ def xgboost_model_from_s3(model_artifact_uri: str):
         wr.s3.download(path=model_artifact_uri, local_file=local_tar_path)
 
         # Extract tarball
-        with tarfile.open(local_tar_path, "r:gz") as tar:
-            # Note: For 3.12+, can use filter="data" argument
-            tar.extractall(path=tmpdir)
+        safe_extract_tarfile(local_tar_path, tmpdir)
 
         # Define model file patterns to search for (in order of preference)
         patterns = [
@@ -285,8 +282,18 @@ def cross_fold_inference(workbench_model: Any, nfolds: int = 5) -> Tuple[Dict[st
 
     # Check if we got a full sklearn model or need to create one
     if isinstance(loaded_model, (xgb.XGBClassifier, xgb.XGBRegressor)):
-        xgb_model = loaded_model
-        is_classifier = isinstance(xgb_model, xgb.XGBClassifier)
+        is_classifier = isinstance(loaded_model, xgb.XGBClassifier)
+
+        # Get the model's hyperparameters and ensure enable_categorical=True
+        params = loaded_model.get_params()
+        params["enable_categorical"] = True
+
+        # Create new model with same params but enable_categorical=True
+        if is_classifier:
+            xgb_model = xgb.XGBClassifier(**params)
+        else:
+            xgb_model = xgb.XGBRegressor(**params)
+
     elif isinstance(loaded_model, xgb.Booster):
         # Legacy: got a booster, need to wrap it
         log.warning("Deprecated: Loaded model is a Booster, wrapping in sklearn model.")
@@ -308,10 +315,12 @@ def cross_fold_inference(workbench_model: Any, nfolds: int = 5) -> Tuple[Dict[st
     target_col = workbench_model.target()
     feature_cols = workbench_model.features()
 
-    # Convert string features to categorical
+    # Convert string[python] to object, then to category for XGBoost compatibility
+    # This avoids XGBoost's issue with pandas 2.x string[python] dtype in categorical categories
     for col in feature_cols:
-        if df[col].dtype in ["object", "string"]:
-            df[col] = df[col].astype("category")
+        if pd.api.types.is_string_dtype(df[col]):
+            # Double conversion: string[python] -> object -> category
+            df[col] = df[col].astype("object").astype("category")
 
     X = df[feature_cols]
     y = df[target_col]
@@ -440,10 +449,12 @@ def leave_one_out_inference(workbench_model: Any) -> pd.DataFrame:
     target_col = workbench_model.target()
     feature_cols = workbench_model.features()
 
-    # Convert string features to categorical
+    # Convert string[python] to object, then to category for XGBoost compatibility
+    # This avoids XGBoost's issue with pandas 2.x string[python] dtype in categorical categories
     for col in feature_cols:
-        if df[col].dtype in ["object", "string"]:
-            df[col] = df[col].astype("category")
+        if pd.api.types.is_string_dtype(df[col]):
+            # Double conversion: string[python] -> object -> category
+            df[col] = df[col].astype("object").astype("category")
 
     # Determine which samples to run LOO on
     if len(df) > 1000:

workbench/web_interface/components/model_plot.py

@@ -39,7 +39,13 @@ class ModelPlot(ComponentInterface):
             # Calculate the distance from the diagonal for each point
             target = model.target()
             df["error"] = abs(df["prediction"] - df[target])
-            return ScatterPlot().update_properties(df, color="error", regression_line=True)[0]
+            return ScatterPlot().update_properties(
+                df,
+                color="error",
+                regression_line=True,
+                x=target,
+                y="prediction",
+            )[0]
         else:
             return self.display_text(f"Model Type: {model.model_type}\n\n Awesome Plot Coming Soon!")
 

workbench/web_interface/components/plugins/model_details.py

@@ -249,8 +249,13 @@ class ModelDetails(PluginInterface):
         if not inference_runs:
             return [], None
 
-        # Set "auto_inference" as the default, if that doesn't exist, set the first
-        default_inference_run = "auto_inference" if "auto_inference" in inference_runs else inference_runs[0]
+        # Default inference run (full_cross_fold if it exists, then auto_inference, then first)
+        if "full_cross_fold" in inference_runs:
+            default_inference_run = "full_cross_fold"
+        elif "auto_inference" in inference_runs:
+            default_inference_run = "auto_inference"
+        else:
+            default_inference_run = inference_runs[0]
 
         # Return the options for the dropdown and the selected value
         return inference_runs, default_inference_run

{workbench-0.8.192.dist-info → workbench-0.8.193.dist-info}/METADATA

@@ -1,9 +1,30 @@
 Metadata-Version: 2.4
 Name: workbench
-Version: 0.8.192
+Version: 0.8.193
 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

{workbench-0.8.192.dist-info → workbench-0.8.193.dist-info}/RECORD

@@ -56,7 +56,7 @@ workbench/core/artifacts/data_source_abstract.py,sha256=5IRCzFVK-17cd4NXPMRfx99v
 workbench/core/artifacts/data_source_factory.py,sha256=YL_tA5fsgubbB3dPF6T4tO0rGgz-6oo3ge4i_YXVC-M,2380
 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=vVERAD7cmYW8Y9tG8FmT7GMCWiudj8rJ4wfmucWrHUI,52287
+workbench/core/artifacts/model_core.py,sha256=hY-2w_N4HtCO-vnfVQP22_PYYsnoAQfZzSS3vrP1wYY,51281
 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=qdE7sKMWPERpmDBsBOAAkZ94FzNZftDmUMNu0Mjq6ns,20115
+workbench/core/transforms/features_to_model/features_to_model.py,sha256=MHJQbKpzBQzW-ZXVfmYQ_1yvAHVPHsw81udBWotxiac,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
@@ -153,6 +153,7 @@ workbench/model_scripts/scikit_learn/requirements.txt,sha256=aVvwiJ3LgBUhM_PyFlb
 workbench/model_scripts/scikit_learn/scikit_learn.template,sha256=QQvqx-eX9ZTbYmyupq6R6vIQwosmsmY_MRBPaHyfjdk,12586
 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=0S2WYCcgguGJ3vqiZe9y5CLuhrpHwIOoKVJBIphxQSQ,18129
 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
@@ -213,7 +214,7 @@ 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/model_utils.py,sha256=THs0GXkZdJLkk-sMxEo_wu7-ouGrJZdlN99yDUzO5xk,13515
+workbench/utils/model_utils.py,sha256=_Gjr318BkMT7hv9M3g7eBYsFluYVPzMjWjMrpNpqx3A,13921
 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
@@ -235,7 +236,7 @@ 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=K0lbeb6LpS5oyN8cmK5Mfzz89n9q3p6ikvN39U9rvQw,22090
+workbench/utils/xgboost_model_utils.py,sha256=lm6XYnPImi3RyHyiJgl2o4HLJ63EghEdSbmwVRMctXg,22786
 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
@@ -251,7 +252,7 @@ workbench/web_interface/components/component_interface.py,sha256=QCPWqiZLkVsAEzQ
 workbench/web_interface/components/correlation_matrix.py,sha256=Lv4vRta5-TdxBsu0G8Ea7hyyR3XyPes-k5AfL6qZWEc,6376
 workbench/web_interface/components/data_details_markdown.py,sha256=axDs6eXniglBmvFwIKjpJ5oyT-3D4FO9IcfA_cl-EJ8,9706
 workbench/web_interface/components/endpoint_metric_plots.py,sha256=H0cXuj9UQrrh_2JvRHtq7O8pMXFXKs7o9XpzySENylw,3441
-workbench/web_interface/components/model_plot.py,sha256=fgmOOxdrRkXN2-uNhY3K-pOsY34I-wcfy2MAnhr9ehY,2415
+workbench/web_interface/components/model_plot.py,sha256=Rojx_ZED4P9gvgeEsUm6xnwMNPoeOyn0evw45BWTITc,2536
 workbench/web_interface/components/plugin_interface.py,sha256=jGRq4igUTVXUT4sDqqsKKI2yjilV0ORNBQq6CjEWE84,9563
 workbench/web_interface/components/plugin_unit_test.py,sha256=UBZtGztLk2oJMDXfExfxkhHdmXr6ayv4NS0RpwGc8ro,7704
 workbench/web_interface/components/regression_plot.py,sha256=k18Bd0fcH7ig6kL5GqC_dINci3_YLle_fSEM32zXtzY,3342
@@ -266,7 +267,7 @@ workbench/web_interface/components/plugins/endpoint_details.py,sha256=0A7g_Lx5-3
 workbench/web_interface/components/plugins/generated_compounds.py,sha256=A6JGlkl7buZUugPK21YgufVFDRoGlHJowaqf8PAmz_s,8056
 workbench/web_interface/components/plugins/graph_plot.py,sha256=JFzuSH_CkEmlaLAgFpzmiEpS3sXov0ycnCfP0VLsK2g,14502
 workbench/web_interface/components/plugins/license_details.py,sha256=UyMSBGxEgdp3m9szDkDUAl_Ua8C5a4RNMdYpYCx354M,5497
-workbench/web_interface/components/plugins/model_details.py,sha256=BBvT3zdGHpRWz4V9SpNO0AFMPaExWMbNAE1_onfCGRI,10294
+workbench/web_interface/components/plugins/model_details.py,sha256=S5J7LmN39F-oWbPQjndv0T3XKEKLDm6pz3JY4274O2M,10468
 workbench/web_interface/components/plugins/molecule_panel.py,sha256=xGCEI5af8F5lNId5eKUpetdQs_ahnIPdW6U7wKvbz2o,3515
 workbench/web_interface/components/plugins/molecule_viewer.py,sha256=xavixcu4RNzh6Nj_-3-XlK09DgpNx5jGmo3wEPNftiE,4529
 workbench/web_interface/components/plugins/pipeline_details.py,sha256=caiFIakHk-1dGGNW7wlio2X7iAm2_tCNbSjDzoRWGEk,5534
@@ -280,9 +281,9 @@ 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-0.8.192.dist-info/licenses/LICENSE,sha256=z4QMMPlLJkZjU8VOKqJkZiQZCEZ--saIU2Z8-p3aVc0,1080
-workbench-0.8.192.dist-info/METADATA,sha256=dlskxjoY82E7I0Z-JwO802MdU6hTmk5eWD5hwn1ahq8,9261
-workbench-0.8.192.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-workbench-0.8.192.dist-info/entry_points.txt,sha256=o7ohD4D2oygnHp7i9-C0LfcHDuPW5Tv0JXGAg97DpGk,413
-workbench-0.8.192.dist-info/top_level.txt,sha256=Dhy72zTxaA_o_yRkPZx5zw-fwumnjGaeGf0hBN3jc_w,10
-workbench-0.8.192.dist-info/RECORD,,
+workbench-0.8.193.dist-info/licenses/LICENSE,sha256=RTBoTMeEwTgEhS-n8vgQ-VUo5qig0PWVd8xFPKU6Lck,1080
+workbench-0.8.193.dist-info/METADATA,sha256=vW41RDdu0YekBKST6qabwNkGWXpcDgXaqPhk0YvolRU,10495
+workbench-0.8.193.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+workbench-0.8.193.dist-info/entry_points.txt,sha256=o7ohD4D2oygnHp7i9-C0LfcHDuPW5Tv0JXGAg97DpGk,413
+workbench-0.8.193.dist-info/top_level.txt,sha256=Dhy72zTxaA_o_yRkPZx5zw-fwumnjGaeGf0hBN3jc_w,10
+workbench-0.8.193.dist-info/RECORD,,

{workbench-0.8.192.dist-info → workbench-0.8.193.dist-info}/licenses/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