workbench 0.8.174__py3-none-any.whl → 0.8.227__py3-none-any.whl

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

workbench/model_scripts/custom_models/proximity/generated_model_script.py

@@ -1,138 +0,0 @@
-# Model: feature_space_proximity
-#
-# Description: The feature_space_proximity model computes nearest neighbors for the given feature space
-#
-
-# Template Placeholders
-TEMPLATE_PARAMS = {
-    "id_column": "udm_mol_bat_id",
-    "features": ['bcut2d_logplow', 'numradicalelectrons', 'smr_vsa5', 'fr_lactam', 'fr_morpholine', 'fr_aldehyde', 'slogp_vsa1', 'fr_amidine', 'bpol', 'fr_ester', 'fr_azo', 'kappa3', 'peoe_vsa5', 'fr_ketone_topliss', 'vsa_estate9', 'estate_vsa9', 'bcut2d_mrhi', 'fr_ndealkylation1', 'numrotatablebonds', 'minestateindex', 'fr_quatn', 'peoe_vsa3', 'fr_epoxide', 'fr_aniline', 'minpartialcharge', 'fr_nitroso', 'fpdensitymorgan2', 'fr_oxime', 'fr_sulfone', 'smr_vsa1', 'kappa1', 'fr_pyridine', 'numaromaticrings', 'vsa_estate6', 'molmr', 'estate_vsa1', 'fr_dihydropyridine', 'vsa_estate10', 'fr_alkyl_halide', 'chi2n', 'fr_thiocyan', 'fpdensitymorgan1', 'fr_unbrch_alkane', 'slogp_vsa9', 'chi4n', 'fr_nitro_arom', 'fr_al_oh', 'fr_furan', 'fr_c_s', 'peoe_vsa8', 'peoe_vsa14', 'numheteroatoms', 'fr_ndealkylation2', 'maxabspartialcharge', 'vsa_estate2', 'peoe_vsa7', 'apol', 'numhacceptors', 'fr_tetrazole', 'vsa_estate1', 'peoe_vsa9', 'naromatom', 'bcut2d_chghi', 'fr_sh', 'fr_halogen', 'slogp_vsa4', 'fr_benzodiazepine', 'molwt', 'fr_isocyan', 'fr_prisulfonamd', 'maxabsestateindex', 'minabsestateindex', 'peoe_vsa11', 'slogp_vsa12', 'estate_vsa5', 'numaliphaticcarbocycles', 'bcut2d_mwlow', 'slogp_vsa7', 'fr_allylic_oxid', 'fr_methoxy', 'fr_nh0', 'fr_coo2', 'fr_phenol', 'nacid', 'nbase', 'chi3v', 'fr_ar_nh', 'fr_nitrile', 'fr_imidazole', 'fr_urea', 'bcut2d_mrlow', 'chi1', 'smr_vsa6', 'fr_aryl_methyl', 'narombond', 'fr_alkyl_carbamate', 'fr_piperzine', 'exactmolwt', 'qed', 'chi0n', 'fr_sulfonamd', 'fr_thiazole', 'numvalenceelectrons', 'fr_phos_acid', 'peoe_vsa12', 'fr_nh1', 'fr_hdrzine', 'fr_c_o_nocoo', 'fr_lactone', 'estate_vsa6', 'bcut2d_logphi', 'vsa_estate7', 'peoe_vsa13', 'numsaturatedcarbocycles', 'fr_nitro', 'fr_phenol_noorthohbond', 'rotratio', 'fr_barbitur', 'fr_isothiocyan', 'balabanj', 'fr_arn', 'fr_imine', 'maxpartialcharge', 'fr_sulfide', 'slogp_vsa11', 'fr_hoccn', 'fr_n_o', 'peoe_vsa1', 'slogp_vsa6', 'heavyatommolwt', 'fractioncsp3', 'estate_vsa8', 'peoe_vsa10', 'numaliphaticrings', 'fr_thiophene', 'maxestateindex', 'smr_vsa10', 'labuteasa', 'smr_vsa2', 'fpdensitymorgan3', 'smr_vsa9', 'slogp_vsa10', 'numaromaticheterocycles', 'fr_nh2', 'fr_diazo', 'chi3n', 'fr_ar_coo', 'slogp_vsa5', 'fr_bicyclic', 'fr_amide', 'estate_vsa10', 'fr_guanido', 'chi1n', 'numsaturatedrings', 'fr_piperdine', 'fr_term_acetylene', 'estate_vsa4', 'slogp_vsa3', 'fr_coo', 'fr_ether', 'estate_vsa7', 'bcut2d_chglo', 'fr_oxazole', 'peoe_vsa6', 'hallkieralpha', 'peoe_vsa2', 'chi2v', 'nocount', 'vsa_estate5', 'fr_nhpyrrole', 'fr_al_coo', 'bertzct', 'estate_vsa11', 'minabspartialcharge', 'slogp_vsa8', 'fr_imide', 'kappa2', 'numaliphaticheterocycles', 'numsaturatedheterocycles', 'fr_hdrzone', 'smr_vsa4', 'fr_ar_n', 'nrot', 'smr_vsa8', 'slogp_vsa2', 'chi4v', 'fr_phos_ester', 'fr_para_hydroxylation', 'smr_vsa3', 'nhohcount', 'estate_vsa2', 'mollogp', 'tpsa', 'fr_azide', 'peoe_vsa4', 'numhdonors', 'fr_al_oh_notert', 'fr_c_o', 'chi0', 'fr_nitro_arom_nonortho', 'vsa_estate3', 'fr_benzene', 'fr_ketone', 'vsa_estate8', 'smr_vsa7', 'fr_ar_oh', 'fr_priamide', 'ringcount', 'estate_vsa3', 'numaromaticcarbocycles', 'bcut2d_mwhi', 'chi1v', 'heavyatomcount', 'vsa_estate4', 'chi0v'],
-    "target": "udm_asy_res_value",
-    "track_columns": None
-}
-
-from io import StringIO
-import json
-import argparse
-import os
-import pandas as pd
-
-# Local Imports
-from proximity import Proximity
-
-
-# Function to check if dataframe is empty
-def check_dataframe(df: pd.DataFrame, df_name: str) -> None:
-    """Check if the DataFrame is empty and raise an error if so."""
-    if df.empty:
-        msg = f"*** The training data {df_name} has 0 rows! ***STOPPING***"
-        print(msg)
-        raise ValueError(msg)
-
-
-# Function to match DataFrame columns to model features (case-insensitive)
-def match_features_case_insensitive(df: pd.DataFrame, model_features: list) -> pd.DataFrame:
-    """Match and rename DataFrame columns to match the model's features, case-insensitively."""
-    # Create a set of exact matches from the DataFrame columns
-    exact_match_set = set(df.columns)
-
-    # Create a case-insensitive map of DataFrame columns
-    column_map = {col.lower(): col for col in df.columns}
-    rename_dict = {}
-
-    # Build a dictionary for renaming columns based on case-insensitive matching
-    for feature in model_features:
-        if feature in exact_match_set:
-            rename_dict[feature] = feature
-        elif feature.lower() in column_map:
-            rename_dict[column_map[feature.lower()]] = feature
-
-    # Rename columns in the DataFrame to match model features
-    return df.rename(columns=rename_dict)
-
-
-# TRAINING SECTION
-#
-# This section (__main__) is where SageMaker will execute the training job
-# and save the model artifacts to the model directory.
-#
-if __name__ == "__main__":
-    # Template Parameters
-    id_column = TEMPLATE_PARAMS["id_column"]
-    features = TEMPLATE_PARAMS["features"]
-    target = TEMPLATE_PARAMS["target"]  # Can be None for unsupervised models
-    track_columns = TEMPLATE_PARAMS["track_columns"]  # Can be None
-
-    # Script arguments for input/output directories
-    parser = argparse.ArgumentParser()
-    parser.add_argument("--model-dir", type=str, default=os.environ.get("SM_MODEL_DIR", "/opt/ml/model"))
-    parser.add_argument("--train", type=str, default=os.environ.get("SM_CHANNEL_TRAIN", "/opt/ml/input/data/train"))
-    parser.add_argument(
-        "--output-data-dir", type=str, default=os.environ.get("SM_OUTPUT_DATA_DIR", "/opt/ml/output/data")
-    )
-    args = parser.parse_args()
-
-    # Load training data from the specified directory
-    training_files = [
-        os.path.join(args.train, file)
-        for file in os.listdir(args.train) if file.endswith(".csv")
-    ]
-    all_df = pd.concat([pd.read_csv(file, engine="python") for file in training_files])
-
-    # Check if the DataFrame is empty
-    check_dataframe(all_df, "training_df")
-
-    # Create the Proximity model
-    model = Proximity(all_df, id_column, features, target, track_columns=track_columns)
-
-    # Now serialize the model
-    model.serialize(args.model_dir)
-
-# Model loading and prediction functions
-def model_fn(model_dir):
-
-    # Deserialize the model
-    model = Proximity.deserialize(model_dir)
-    return model
-
-
-def input_fn(input_data, content_type):
-    """Parse input data and return a DataFrame."""
-    if not input_data:
-        raise ValueError("Empty input data is not supported!")
-
-    # Decode bytes to string if necessary
-    if isinstance(input_data, bytes):
-        input_data = input_data.decode("utf-8")
-
-    if "text/csv" in content_type:
-        return pd.read_csv(StringIO(input_data))
-    elif "application/json" in content_type:
-        return pd.DataFrame(json.loads(input_data))  # Assumes JSON array of records
-    else:
-        raise ValueError(f"{content_type} not supported!")
-
-
-def output_fn(output_df, accept_type):
-    """Supports both CSV and JSON output formats."""
-    use_explicit_na = False
-    if "text/csv" in accept_type:
-        if use_explicit_na:
-            csv_output = output_df.fillna("N/A").to_csv(index=False)  # CSV with N/A for missing values
-        else:
-            csv_output = output_df.to_csv(index=False)
-        return csv_output, "text/csv"
-    elif "application/json" in accept_type:
-        return output_df.to_json(orient="records"), "application/json"  # JSON array of records (NaNs -> null)
-    else:
-        raise RuntimeError(f"{accept_type} accept type is not supported by this script.")
-
-
-# Prediction function
-def predict_fn(df, model):
-    # Match column names before prediction if needed
-    df = match_features_case_insensitive(df, model.features + [model.id_column])
-
-    # Compute Nearest neighbors
-    df = model.neighbors(df)
-    return df

workbench/model_scripts/custom_models/proximity/proximity.py

@@ -1,384 +0,0 @@
-import pandas as pd
-import numpy as np
-from sklearn.preprocessing import StandardScaler
-from sklearn.neighbors import NearestNeighbors
-from typing import List, Dict
-import logging
-import pickle
-import os
-import json
-from pathlib import Path
-from enum import Enum
-
-# Set up logging
-log = logging.getLogger("workbench")
-
-
-# ^Enumerated^ Proximity Types (distance or similarity)
-class ProximityType(Enum):
-    DISTANCE = "distance"
-    SIMILARITY = "similarity"
-
-
-class Proximity:
-    def __init__(
-        self,
-        df: pd.DataFrame,
-        id_column: str,
-        features: List[str],
-        target: str = None,
-        track_columns: List[str] = None,
-        n_neighbors: int = 10,
-    ):
-        """
-        Initialize the Proximity class.
-
-        Args:
-            df (pd.DataFrame): DataFrame containing data for neighbor computations.
-            id_column (str): Name of the column used as the identifier.
-            features (List[str]): List of feature column names to be used for neighbor computations.
-            target (str, optional): Name of the target column. Defaults to None.
-            track_columns (List[str], optional): Additional columns to track in results. Defaults to None.
-            n_neighbors (int): Number of neighbors to compute. Defaults to 10.
-        """
-        self.df = df.dropna(subset=features).copy()
-        self.id_column = id_column
-        self.n_neighbors = min(n_neighbors, len(self.df) - 1)
-        self.target = target
-        self.features = features
-        self.scaler = None
-        self.X = None
-        self.nn = None
-        self.proximity_type = None
-        self.track_columns = track_columns or []
-
-        # Right now we only support numeric features, so remove any columns that are not numeric
-        non_numeric_features = self.df[self.features].select_dtypes(exclude=["number"]).columns.tolist()
-        if non_numeric_features:
-            log.warning(f"Non-numeric features {non_numeric_features} aren't currently supported...")
-            self.features = [f for f in self.features if f not in non_numeric_features]
-
-        # Build the proximity model
-        self.build_proximity_model()
-
-    def build_proximity_model(self) -> None:
-        """Standardize features and fit Nearest Neighbors model.
-        Note: This method can be overridden in subclasses for custom behavior."""
-        self.proximity_type = ProximityType.DISTANCE
-        self.scaler = StandardScaler()
-        self.X = self.scaler.fit_transform(self.df[self.features])
-        self.nn = NearestNeighbors(n_neighbors=self.n_neighbors + 1).fit(self.X)
-
-    def all_neighbors(self) -> pd.DataFrame:
-        """
-        Compute nearest neighbors for all rows in the dataset.
-
-        Returns:
-            pd.DataFrame: A DataFrame of neighbors and their distances.
-        """
-        distances, indices = self.nn.kneighbors(self.X)
-        results = []
-
-        for i, (dists, nbrs) in enumerate(zip(distances, indices)):
-            query_id = self.df.iloc[i][self.id_column]
-
-            # Process neighbors
-            for neighbor_idx, dist in zip(nbrs, dists):
-                # Skip self (neighbor index == current row index)
-                if neighbor_idx == i:
-                    continue
-                results.append(self._build_neighbor_result(query_id=query_id, neighbor_idx=neighbor_idx, distance=dist))
-
-        return pd.DataFrame(results)
-
-    def neighbors(
-        self,
-        query_df: pd.DataFrame,
-        radius: float = None,
-        include_self: bool = True,
-    ) -> pd.DataFrame:
-        """
-        Return neighbors for rows in a query DataFrame.
-
-        Args:
-            query_df: DataFrame containing query points
-            radius: If provided, find all neighbors within this radius
-            include_self: Whether to include self in results (if present)
-
-        Returns:
-            DataFrame containing neighbors and distances
-
-        Note: The query DataFrame must include the feature columns. The id_column is optional.
-        """
-        # Check if all required features are present
-        missing = set(self.features) - set(query_df.columns)
-        if missing:
-            raise ValueError(f"Query DataFrame is missing required feature columns: {missing}")
-
-        # Check if id_column is present
-        id_column_present = self.id_column in query_df.columns
-
-        # None of the features can be NaNs, so report rows with NaNs and then drop them
-        rows_with_nan = query_df[self.features].isna().any(axis=1)
-
-        # Print the ID column for rows with NaNs
-        if rows_with_nan.any():
-            log.warning(f"Found {rows_with_nan.sum()} rows with NaNs in feature columns:")
-            log.warning(query_df.loc[rows_with_nan, self.id_column])
-
-        # Drop rows with NaNs in feature columns and reassign to query_df
-        query_df = query_df.dropna(subset=self.features)
-
-        # Transform the query features using the model's scaler
-        X_query = self.scaler.transform(query_df[self.features])
-
-        # Get neighbors using either radius or k-nearest neighbors
-        if radius is not None:
-            distances, indices = self.nn.radius_neighbors(X_query, radius=radius)
-        else:
-            distances, indices = self.nn.kneighbors(X_query)
-
-        # Build results
-        all_results = []
-        for i, (dists, nbrs) in enumerate(zip(distances, indices)):
-            # Use the ID from the query DataFrame if available, otherwise use the row index
-            query_id = query_df.iloc[i][self.id_column] if id_column_present else f"query_{i}"
-
-            for neighbor_idx, dist in zip(nbrs, dists):
-                # Skip if the neighbor is the query itself and include_self is False
-                neighbor_id = self.df.iloc[neighbor_idx][self.id_column]
-                if not include_self and neighbor_id == query_id:
-                    continue
-
-                all_results.append(
-                    self._build_neighbor_result(query_id=query_id, neighbor_idx=neighbor_idx, distance=dist)
-                )
-
-        return pd.DataFrame(all_results)
-
-    def _build_neighbor_result(self, query_id, neighbor_idx: int, distance: float) -> Dict:
-        """
-        Internal: Build a result dictionary for a single neighbor.
-
-        Args:
-            query_id: ID of the query point
-            neighbor_idx: Index of the neighbor in the original DataFrame
-            distance: Distance between query and neighbor
-
-        Returns:
-            Dictionary containing neighbor information
-        """
-        neighbor_id = self.df.iloc[neighbor_idx][self.id_column]
-
-        # Basic neighbor info
-        neighbor_info = {
-            self.id_column: query_id,
-            "neighbor_id": neighbor_id,
-            "distance": distance,
-        }
-
-        # Determine which additional columns to include
-        relevant_cols = [self.target, "prediction"] if self.target else []
-        relevant_cols += [c for c in self.df.columns if "_proba" in c or "residual" in c]
-        relevant_cols += ["outlier"]
-
-        # Add user-specified columns
-        relevant_cols += self.track_columns
-
-        # Add values for each relevant column that exists in the dataframe
-        for col in filter(lambda c: c in self.df.columns, relevant_cols):
-            neighbor_info[col] = self.df.iloc[neighbor_idx][col]
-
-        return neighbor_info
-
-    def serialize(self, directory: str) -> None:
-        """
-        Serialize the Proximity model to a directory.
-
-        Args:
-            directory: Directory path to save the model components
-        """
-        # Create directory if it doesn't exist
-        os.makedirs(directory, exist_ok=True)
-
-        # Save metadata
-        metadata = {
-            "id_column": self.id_column,
-            "features": self.features,
-            "target": self.target,
-            "track_columns": self.track_columns,
-            "n_neighbors": self.n_neighbors,
-        }
-
-        with open(os.path.join(directory, "metadata.json"), "w") as f:
-            json.dump(metadata, f)
-
-        # Save the DataFrame
-        self.df.to_pickle(os.path.join(directory, "df.pkl"))
-
-        # Save the scaler and nearest neighbors model
-        with open(os.path.join(directory, "scaler.pkl"), "wb") as f:
-            pickle.dump(self.scaler, f)
-
-        with open(os.path.join(directory, "nn_model.pkl"), "wb") as f:
-            pickle.dump(self.nn, f)
-
-        log.info(f"Proximity model serialized to {directory}")
-
-    @classmethod
-    def deserialize(cls, directory: str) -> "Proximity":
-        """
-        Deserialize a Proximity model from a directory.
-
-        Args:
-            directory: Directory path containing the serialized model components
-
-        Returns:
-            Proximity: A new Proximity instance
-        """
-        directory_path = Path(directory)
-        if not directory_path.exists() or not directory_path.is_dir():
-            raise ValueError(f"Directory {directory} does not exist or is not a directory")
-
-        # Load metadata
-        with open(os.path.join(directory, "metadata.json"), "r") as f:
-            metadata = json.load(f)
-
-        # Load DataFrame
-        df_path = os.path.join(directory, "df.pkl")
-        if not os.path.exists(df_path):
-            raise FileNotFoundError(f"DataFrame file not found at {df_path}")
-        df = pd.read_pickle(df_path)
-
-        # Create instance but skip _prepare_data
-        instance = cls.__new__(cls)
-        instance.df = df
-        instance.id_column = metadata["id_column"]
-        instance.features = metadata["features"]
-        instance.target = metadata["target"]
-        instance.track_columns = metadata["track_columns"]
-        instance.n_neighbors = metadata["n_neighbors"]
-
-        # Load scaler and nn model
-        with open(os.path.join(directory, "scaler.pkl"), "rb") as f:
-            instance.scaler = pickle.load(f)
-
-        with open(os.path.join(directory, "nn_model.pkl"), "rb") as f:
-            instance.nn = pickle.load(f)
-
-        # Load X from scaler transform
-        instance.X = instance.scaler.transform(instance.df[instance.features])
-
-        log.info(f"Proximity model deserialized from {directory}")
-        return instance
-
-
-# Testing the Proximity class
-if __name__ == "__main__":
-
-    pd.set_option("display.max_columns", None)
-    pd.set_option("display.width", 1000)
-
-    # Create a sample DataFrame
-    data = {
-        "ID": [1, 2, 3, 4, 5],
-        "Feature1": [0.1, 0.2, 0.3, 0.4, 0.5],
-        "Feature2": [0.5, 0.4, 0.3, 0.2, 0.1],
-        "Feature3": [2.5, 2.4, 2.3, 2.3, np.nan],
-    }
-    df = pd.DataFrame(data)
-
-    # Test the Proximity class
-    features = ["Feature1", "Feature2", "Feature3"]
-    prox = Proximity(df, id_column="ID", features=features, n_neighbors=3)
-    print(prox.all_neighbors())
-
-    # Test the neighbors method
-    print(prox.neighbors(query_df=df.iloc[[0]]))
-
-    # Test the neighbors method with radius
-    print(prox.neighbors(query_df=df.iloc[0:2], radius=2.0))
-
-    # Test with data that isn't in the 'train' dataframe
-    query_data = {
-        "ID": [6],
-        "Feature1": [0.31],
-        "Feature2": [0.31],
-        "Feature3": [2.31],
-    }
-    query_df = pd.DataFrame(query_data)
-    print(prox.neighbors(query_df=query_df))
-
-    # Test with Features list
-    prox = Proximity(df, id_column="ID", features=["Feature1"], n_neighbors=2)
-    print(prox.all_neighbors())
-
-    # Create a sample DataFrame
-    data = {
-        "foo_id": ["a", "b", "c", "d", "e"],  # Testing string IDs
-        "Feature1": [0.1, 0.2, 0.3, 0.4, 0.5],
-        "Feature2": [0.5, 0.4, 0.3, 0.2, 0.1],
-        "target": [1, 0, 1, 0, 5],
-    }
-    df = pd.DataFrame(data)
-
-    # Test with String Ids
-    prox = Proximity(
-        df,
-        id_column="foo_id",
-        features=["Feature1", "Feature2"],
-        target="target",
-        track_columns=["Feature1", "Feature2"],
-        n_neighbors=3,
-    )
-    print(prox.all_neighbors())
-
-    # Test the neighbors method
-    print(prox.neighbors(query_df=df.iloc[0:2]))
-
-    # Time neighbors with all IDs versus calling all_neighbors
-    import time
-
-    start_time = time.time()
-    prox_df = prox.neighbors(query_df=df, include_self=False)
-    end_time = time.time()
-    print(f"Time taken for neighbors: {end_time - start_time:.4f} seconds")
-    start_time = time.time()
-    prox_df_all = prox.all_neighbors()
-    end_time = time.time()
-    print(f"Time taken for all_neighbors: {end_time - start_time:.4f} seconds")
-
-    # Now compare the two dataframes
-    print("Neighbors DataFrame:")
-    print(prox_df)
-    print("\nAll Neighbors DataFrame:")
-    print(prox_df_all)
-    # Check for any discrepancies
-    if prox_df.equals(prox_df_all):
-        print("The two DataFrames are equal :)")
-    else:
-        print("ERROR: The two DataFrames are not equal!")
-
-    # Test querying without the id_column
-    df_no_id = df.drop(columns=["foo_id"])
-    print(prox.neighbors(query_df=df_no_id, include_self=False))
-
-    # Test duplicate IDs
-    data = {
-        "foo_id": ["a", "b", "c", "d", "d"],  # Duplicate ID (d)
-        "Feature1": [0.1, 0.2, 0.3, 0.4, 0.5],
-        "Feature2": [0.5, 0.4, 0.3, 0.2, 0.1],
-        "target": [1, 0, 1, 0, 5],
-    }
-    df = pd.DataFrame(data)
-    prox = Proximity(df, id_column="foo_id", features=["Feature1", "Feature2"], target="target", n_neighbors=3)
-    print(df.equals(prox.df))
-
-    # Test with a categorical feature
-    from workbench.api import FeatureSet, Model
-
-    fs = FeatureSet("abalone_features")
-    model = Model("abalone-regression")
-    df = fs.pull_dataframe()
-    prox = Proximity(df, id_column=fs.id_column, features=model.features(), target=model.target())
-    print(prox.neighbors(query_df=df[0:2]))