workbench 0.8.177__py3-none-any.whl → 0.8.227__py3-none-any.whl

workbench/model_scripts/custom_models/proximity/feature_space_proximity.py

@@ -0,0 +1,194 @@
+import pandas as pd
+import numpy as np
+from sklearn.preprocessing import StandardScaler
+from sklearn.neighbors import NearestNeighbors
+from typing import List, Optional
+import logging
+
+# Workbench Imports
+from workbench.algorithms.dataframe.proximity import Proximity
+from workbench.algorithms.dataframe.projection_2d import Projection2D
+
+# Set up logging
+log = logging.getLogger("workbench")
+
+
+class FeatureSpaceProximity(Proximity):
+    """Proximity computations for numeric feature spaces using Euclidean distance."""
+
+    def __init__(
+        self,
+        df: pd.DataFrame,
+        id_column: str,
+        features: List[str],
+        target: Optional[str] = None,
+        include_all_columns: bool = False,
+    ):
+        """
+        Initialize the FeatureSpaceProximity class.
+
+        Args:
+            df: DataFrame containing data for neighbor computations.
+            id_column: Name of the column used as the identifier.
+            features: List of feature column names to be used for neighbor computations.
+            target: Name of the target column. Defaults to None.
+            include_all_columns: Include all DataFrame columns in neighbor results. Defaults to False.
+        """
+        # Validate and filter features before calling parent init
+        self._raw_features = features
+        super().__init__(
+            df, id_column=id_column, features=features, target=target, include_all_columns=include_all_columns
+        )
+
+    def _prepare_data(self) -> None:
+        """Filter out non-numeric features and drop NaN rows."""
+        # Validate features
+        self.features = self._validate_features(self.df, self._raw_features)
+
+        # Drop NaN rows for the features we're using
+        self.df = self.df.dropna(subset=self.features).copy()
+
+    def _validate_features(self, df: pd.DataFrame, features: List[str]) -> List[str]:
+        """Remove non-numeric features and log warnings."""
+        non_numeric = [f for f in features if f not in df.select_dtypes(include=["number"]).columns]
+        if non_numeric:
+            log.warning(f"Non-numeric features {non_numeric} aren't currently supported, excluding them")
+        return [f for f in features if f not in non_numeric]
+
+    def _build_model(self) -> None:
+        """Standardize features and fit Nearest Neighbors model."""
+        self.scaler = StandardScaler()
+        X = self.scaler.fit_transform(self.df[self.features])
+        self.nn = NearestNeighbors().fit(X)
+
+    def _transform_features(self, df: pd.DataFrame) -> np.ndarray:
+        """Transform features using the fitted scaler."""
+        return self.scaler.transform(df[self.features])
+
+    def _project_2d(self) -> None:
+        """Project the numeric features to 2D for visualization."""
+        if len(self.features) >= 2:
+            self.df = Projection2D().fit_transform(self.df, features=self.features)
+
+
+# Testing the FeatureSpaceProximity 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 FeatureSpaceProximity class
+    features = ["Feature1", "Feature2", "Feature3"]
+    prox = FeatureSpaceProximity(df, id_column="ID", features=features)
+    print(prox.neighbors(1, n_neighbors=2))
+
+    # Test the neighbors method with radius
+    print(prox.neighbors(1, radius=2.0))
+
+    # Test with Features list
+    prox = FeatureSpaceProximity(df, id_column="ID", features=["Feature1"])
+    print(prox.neighbors(1))
+
+    # Create a sample DataFrame
+    data = {
+        "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 = FeatureSpaceProximity(
+        df,
+        id_column="id",
+        features=["Feature1", "Feature2"],
+        target="target",
+        include_all_columns=True,
+    )
+    print(prox.neighbors(["a", "b"]))
+
+    # Test duplicate IDs
+    data = {
+        "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 = FeatureSpaceProximity(df, id_column="id", features=["Feature1", "Feature2"], target="target")
+    print(df.equals(prox.df))
+
+    # Test on real data from Workbench
+    from workbench.api import FeatureSet, Model
+
+    fs = FeatureSet("aqsol_features")
+    model = Model("aqsol-regression")
+    features = model.features()
+    df = fs.pull_dataframe()
+    prox = FeatureSpaceProximity(df, id_column=fs.id_column, features=model.features(), target=model.target())
+    print("\n" + "=" * 80)
+    print("Testing Neighbors...")
+    print("=" * 80)
+    test_id = df[fs.id_column].tolist()[0]
+    print(f"\nNeighbors for ID {test_id}:")
+    print(prox.neighbors(test_id))
+
+    print("\n" + "=" * 80)
+    print("Testing isolated_compounds...")
+    print("=" * 80)
+
+    # Test isolated data in the top 1%
+    isolated_1pct = prox.isolated(top_percent=1.0)
+    print(f"\nTop 1% most isolated compounds (n={len(isolated_1pct)}):")
+    print(isolated_1pct)
+
+    # Test isolated data in the top 5%
+    isolated_5pct = prox.isolated(top_percent=5.0)
+    print(f"\nTop 5% most isolated compounds (n={len(isolated_5pct)}):")
+    print(isolated_5pct)
+
+    print("\n" + "=" * 80)
+    print("Testing target_gradients...")
+    print("=" * 80)
+
+    # Test with different parameters
+    gradients_1pct = prox.target_gradients(top_percent=1.0, min_delta=1.0)
+    print(f"\nTop 1% target gradients (min_delta=5.0) (n={len(gradients_1pct)}):")
+    print(gradients_1pct)
+
+    gradients_5pct = prox.target_gradients(top_percent=5.0, min_delta=5.0)
+    print(f"\nTop 5% target gradients (min_delta=5.0) (n={len(gradients_5pct)}):")
+    print(gradients_5pct)
+
+    # Test proximity_stats
+    print("\n" + "=" * 80)
+    print("Testing proximity_stats...")
+    print("=" * 80)
+    stats = prox.proximity_stats()
+    print(stats)
+
+    # Plot the distance distribution using pandas
+    print("\n" + "=" * 80)
+    print("Plotting distance distribution...")
+    print("=" * 80)
+    prox.df["nn_distance"].hist(bins=50, figsize=(10, 6), edgecolor="black")
+
+    # Visualize the 2D projection
+    print("\n" + "=" * 80)
+    print("Visualizing 2D Projection...")
+    print("=" * 80)
+    from workbench.web_interface.components.plugin_unit_test import PluginUnitTest
+    from workbench.web_interface.components.plugins.scatter_plot import ScatterPlot
+
+    unit_test = PluginUnitTest(ScatterPlot, input_data=prox.df[:1000], x="x", y="y", color=model.target())
+    unit_test.run()

workbench/model_scripts/custom_models/proximity/feature_space_proximity.template

@@ -8,7 +8,7 @@ TEMPLATE_PARAMS = {
     "id_column": "{{id_column}}",
     "features": "{{feature_list}}",
     "target": "{{target_column}}",
-    "track_columns": "{{track_columns}}"
+    "include_all_columns": "{{include_all_columns}}",
 }
 
 from io import StringIO
@@ -18,7 +18,7 @@ import os
 import pandas as pd
 
 # Local Imports
-from proximity import Proximity
+from feature_space_proximity import FeatureSpaceProximity
 
 
 # Function to check if dataframe is empty
@@ -61,7 +61,7 @@ if __name__ == "__main__":
     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
+    include_all_columns = TEMPLATE_PARAMS["include_all_columns"]  # Defaults to False
 
     # Script arguments for input/output directories
     parser = argparse.ArgumentParser()
@@ -73,26 +73,24 @@ if __name__ == "__main__":
     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")
-    ]
+    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)
+    # Create the FeatureSpaceProximity model
+    model = FeatureSpaceProximity(all_df, id_column=id_column, features=features, target=target, include_all_columns=include_all_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)
+    model = FeatureSpaceProximity.deserialize(model_dir)
     return model
 
 

workbench/model_scripts/custom_models/uq_models/bayesian_ridge.template

@@ -14,7 +14,7 @@ import pandas as pd
 TEMPLATE_PARAMS = {
     "features": "{{feature_list}}",
     "target": "{{target_column}}",
-    "train_all_data": "{{train_all_data}}"
+    "train_all_data": "{{train_all_data}}",
 }
 
 
@@ -37,7 +37,7 @@ def match_features_case_insensitive(df: pd.DataFrame, model_features: list) -> p
     """
     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}
@@ -81,10 +81,7 @@ if __name__ == "__main__":
     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")
-    ]
+    training_files = [os.path.join(args.train, file) for file in os.listdir(args.train) if file.endswith(".csv")]
     df = pd.concat([pd.read_csv(file, engine="python") for file in training_files])
 
     # Check if the DataFrame is empty
@@ -109,8 +106,10 @@ if __name__ == "__main__":
     # Create and train the Regression/Confidence model
     # model = BayesianRidge()
     model = BayesianRidge(
-        alpha_1=1e-6, alpha_2=1e-6,  # Noise precision
-        lambda_1=1e-6, lambda_2=1e-6,  # Weight precision
+        alpha_1=1e-6,
+        alpha_2=1e-6,  # Noise precision
+        lambda_1=1e-6,
+        lambda_2=1e-6,  # Weight precision
         fit_intercept=True,
     )
 

workbench/model_scripts/custom_models/uq_models/ensemble_xgb.template

@@ -4,13 +4,10 @@ import awswrangler as wr
 import numpy as np
 
 # Model Performance Scores
-from sklearn.metrics import (
-    mean_absolute_error,
-    r2_score,
-    root_mean_squared_error
-)
+from sklearn.metrics import mean_absolute_error, median_absolute_error, r2_score, root_mean_squared_error
 from sklearn.model_selection import KFold
 from scipy.optimize import minimize
+from scipy.stats import spearmanr
 
 from io import StringIO
 import json
@@ -23,7 +20,7 @@ TEMPLATE_PARAMS = {
     "features": "{{feature_list}}",
     "target": "{{target_column}}",
     "train_all_data": "{{train_all_data}}",
-    "model_metrics_s3_path": "{{model_metrics_s3_path}}"
+    "model_metrics_s3_path": "{{model_metrics_s3_path}}",
 }
 
 
@@ -47,7 +44,7 @@ def match_features_case_insensitive(df: pd.DataFrame, model_features: list) -> p
     """
     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}
@@ -90,10 +87,7 @@ if __name__ == "__main__":
     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")
-    ]
+    training_files = [os.path.join(args.train, file) for file in os.listdir(args.train) if file.endswith(".csv")]
     df = pd.concat([pd.read_csv(file, engine="python") for file in training_files])
 
     # Check if the DataFrame is empty
@@ -172,16 +166,14 @@ if __name__ == "__main__":
     cv_residuals = np.array(cv_residuals)
     cv_uncertainties = np.array(cv_uncertainties)
 
-
     # Optimize calibration parameters: σ_cal = a * σ_uc + b
     def neg_log_likelihood(params):
         a, b = params
         sigma_cal = a * cv_uncertainties + b
         sigma_cal = np.maximum(sigma_cal, 1e-8)  # Prevent division by zero
-        return np.sum(0.5 * np.log(2 * np.pi * sigma_cal ** 2) + 0.5 * (cv_residuals ** 2) / (sigma_cal ** 2))
+        return np.sum(0.5 * np.log(2 * np.pi * sigma_cal**2) + 0.5 * (cv_residuals**2) / (sigma_cal**2))
 
-
-    result = minimize(neg_log_likelihood, x0=[1.0, 0.1], method='Nelder-Mead')
+    result = minimize(neg_log_likelihood, x0=[1.0, 0.1], method="Nelder-Mead")
     cal_a, cal_b = result.x
 
     print(f"Calibration parameters: a={cal_a:.4f}, b={cal_b:.4f}")
@@ -205,7 +197,9 @@ if __name__ == "__main__":
     result_df["prediction"] = result_df[[name for name in result_df.columns if name.startswith("m_")]].mean(axis=1)
 
     # Compute uncalibrated uncertainty
-    result_df["prediction_std_uc"] = result_df[[name for name in result_df.columns if name.startswith("m_")]].std(axis=1)
+    result_df["prediction_std_uc"] = result_df[[name for name in result_df.columns if name.startswith("m_")]].std(
+        axis=1
+    )
 
     # Apply calibration to uncertainty
     result_df["prediction_std"] = cal_a * result_df["prediction_std_uc"] + cal_b
@@ -224,11 +218,16 @@ if __name__ == "__main__":
     # Report Performance Metrics
     rmse = root_mean_squared_error(result_df[target], result_df["prediction"])
     mae = mean_absolute_error(result_df[target], result_df["prediction"])
+    medae = median_absolute_error(result_df[target], result_df["prediction"])
     r2 = r2_score(result_df[target], result_df["prediction"])
-    print(f"RMSE: {rmse:.3f}")
-    print(f"MAE: {mae:.3f}")
-    print(f"R2: {r2:.3f}")
-    print(f"NumRows: {len(result_df)}")
+    spearman_corr = spearmanr(result_df[target], result_df["prediction"]).correlation
+    support = len(result_df)
+    print(f"rmse: {rmse:.3f}")
+    print(f"mae: {mae:.3f}")
+    print(f"medae: {medae:.3f}")
+    print(f"r2: {r2:.3f}")
+    print(f"spearmanr: {spearman_corr:.3f}")
+    print(f"support: {support}")
 
     # Now save the models
     for name, model in models.items():
@@ -352,4 +351,4 @@ def predict_fn(df, models) -> pd.DataFrame:
     df = df.reindex(sorted(df.columns), axis=1)
 
     # All done, return the DataFrame
-    return df
+    return df

workbench/model_scripts/custom_models/uq_models/feature_space_proximity.py

@@ -0,0 +1,194 @@
+import pandas as pd
+import numpy as np
+from sklearn.preprocessing import StandardScaler
+from sklearn.neighbors import NearestNeighbors
+from typing import List, Optional
+import logging
+
+# Workbench Imports
+from workbench.algorithms.dataframe.proximity import Proximity
+from workbench.algorithms.dataframe.projection_2d import Projection2D
+
+# Set up logging
+log = logging.getLogger("workbench")
+
+
+class FeatureSpaceProximity(Proximity):
+    """Proximity computations for numeric feature spaces using Euclidean distance."""
+
+    def __init__(
+        self,
+        df: pd.DataFrame,
+        id_column: str,
+        features: List[str],
+        target: Optional[str] = None,
+        include_all_columns: bool = False,
+    ):
+        """
+        Initialize the FeatureSpaceProximity class.
+
+        Args:
+            df: DataFrame containing data for neighbor computations.
+            id_column: Name of the column used as the identifier.
+            features: List of feature column names to be used for neighbor computations.
+            target: Name of the target column. Defaults to None.
+            include_all_columns: Include all DataFrame columns in neighbor results. Defaults to False.
+        """
+        # Validate and filter features before calling parent init
+        self._raw_features = features
+        super().__init__(
+            df, id_column=id_column, features=features, target=target, include_all_columns=include_all_columns
+        )
+
+    def _prepare_data(self) -> None:
+        """Filter out non-numeric features and drop NaN rows."""
+        # Validate features
+        self.features = self._validate_features(self.df, self._raw_features)
+
+        # Drop NaN rows for the features we're using
+        self.df = self.df.dropna(subset=self.features).copy()
+
+    def _validate_features(self, df: pd.DataFrame, features: List[str]) -> List[str]:
+        """Remove non-numeric features and log warnings."""
+        non_numeric = [f for f in features if f not in df.select_dtypes(include=["number"]).columns]
+        if non_numeric:
+            log.warning(f"Non-numeric features {non_numeric} aren't currently supported, excluding them")
+        return [f for f in features if f not in non_numeric]
+
+    def _build_model(self) -> None:
+        """Standardize features and fit Nearest Neighbors model."""
+        self.scaler = StandardScaler()
+        X = self.scaler.fit_transform(self.df[self.features])
+        self.nn = NearestNeighbors().fit(X)
+
+    def _transform_features(self, df: pd.DataFrame) -> np.ndarray:
+        """Transform features using the fitted scaler."""
+        return self.scaler.transform(df[self.features])
+
+    def _project_2d(self) -> None:
+        """Project the numeric features to 2D for visualization."""
+        if len(self.features) >= 2:
+            self.df = Projection2D().fit_transform(self.df, features=self.features)
+
+
+# Testing the FeatureSpaceProximity 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 FeatureSpaceProximity class
+    features = ["Feature1", "Feature2", "Feature3"]
+    prox = FeatureSpaceProximity(df, id_column="ID", features=features)
+    print(prox.neighbors(1, n_neighbors=2))
+
+    # Test the neighbors method with radius
+    print(prox.neighbors(1, radius=2.0))
+
+    # Test with Features list
+    prox = FeatureSpaceProximity(df, id_column="ID", features=["Feature1"])
+    print(prox.neighbors(1))
+
+    # Create a sample DataFrame
+    data = {
+        "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 = FeatureSpaceProximity(
+        df,
+        id_column="id",
+        features=["Feature1", "Feature2"],
+        target="target",
+        include_all_columns=True,
+    )
+    print(prox.neighbors(["a", "b"]))
+
+    # Test duplicate IDs
+    data = {
+        "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 = FeatureSpaceProximity(df, id_column="id", features=["Feature1", "Feature2"], target="target")
+    print(df.equals(prox.df))
+
+    # Test on real data from Workbench
+    from workbench.api import FeatureSet, Model
+
+    fs = FeatureSet("aqsol_features")
+    model = Model("aqsol-regression")
+    features = model.features()
+    df = fs.pull_dataframe()
+    prox = FeatureSpaceProximity(df, id_column=fs.id_column, features=model.features(), target=model.target())
+    print("\n" + "=" * 80)
+    print("Testing Neighbors...")
+    print("=" * 80)
+    test_id = df[fs.id_column].tolist()[0]
+    print(f"\nNeighbors for ID {test_id}:")
+    print(prox.neighbors(test_id))
+
+    print("\n" + "=" * 80)
+    print("Testing isolated_compounds...")
+    print("=" * 80)
+
+    # Test isolated data in the top 1%
+    isolated_1pct = prox.isolated(top_percent=1.0)
+    print(f"\nTop 1% most isolated compounds (n={len(isolated_1pct)}):")
+    print(isolated_1pct)
+
+    # Test isolated data in the top 5%
+    isolated_5pct = prox.isolated(top_percent=5.0)
+    print(f"\nTop 5% most isolated compounds (n={len(isolated_5pct)}):")
+    print(isolated_5pct)
+
+    print("\n" + "=" * 80)
+    print("Testing target_gradients...")
+    print("=" * 80)
+
+    # Test with different parameters
+    gradients_1pct = prox.target_gradients(top_percent=1.0, min_delta=1.0)
+    print(f"\nTop 1% target gradients (min_delta=5.0) (n={len(gradients_1pct)}):")
+    print(gradients_1pct)
+
+    gradients_5pct = prox.target_gradients(top_percent=5.0, min_delta=5.0)
+    print(f"\nTop 5% target gradients (min_delta=5.0) (n={len(gradients_5pct)}):")
+    print(gradients_5pct)
+
+    # Test proximity_stats
+    print("\n" + "=" * 80)
+    print("Testing proximity_stats...")
+    print("=" * 80)
+    stats = prox.proximity_stats()
+    print(stats)
+
+    # Plot the distance distribution using pandas
+    print("\n" + "=" * 80)
+    print("Plotting distance distribution...")
+    print("=" * 80)
+    prox.df["nn_distance"].hist(bins=50, figsize=(10, 6), edgecolor="black")
+
+    # Visualize the 2D projection
+    print("\n" + "=" * 80)
+    print("Visualizing 2D Projection...")
+    print("=" * 80)
+    from workbench.web_interface.components.plugin_unit_test import PluginUnitTest
+    from workbench.web_interface.components.plugins.scatter_plot import ScatterPlot
+
+    unit_test = PluginUnitTest(ScatterPlot, input_data=prox.df[:1000], x="x", y="y", color=model.target())
+    unit_test.run()

workbench/model_scripts/custom_models/uq_models/gaussian_process.template

@@ -9,7 +9,7 @@ from sklearn.model_selection import train_test_split
 TEMPLATE_PARAMS = {
     "features": "{{feature_list}}",
     "target": "{{target_column}}",
-    "train_all_data": "{{train_all_data}}"
+    "train_all_data": "{{train_all_data}}",
 }
 
 from io import StringIO
@@ -33,7 +33,7 @@ def match_features_case_insensitive(df: pd.DataFrame, model_features: list) -> p
     """
     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}
@@ -46,7 +46,7 @@ def match_features_case_insensitive(df: pd.DataFrame, model_features: list) -> p
             rename_dict[df_columns_lower[feature.lower()]] = feature
         else:
             missing.append(feature)
-    
+
     if missing:
         raise ValueError(f"Features not found: {missing}")
 
@@ -76,10 +76,7 @@ if __name__ == "__main__":
     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")
-    ]
+    training_files = [os.path.join(args.train, file) for file in os.listdir(args.train) if file.endswith(".csv")]
     df = pd.concat([pd.read_csv(file, engine="python") for file in training_files])
 
     # Check if the DataFrame is empty
@@ -112,10 +109,7 @@ if __name__ == "__main__":
     )
 
     # Create a Pipeline with StandardScaler
-    model = Pipeline([
-        ("scaler", StandardScaler()),
-        ("model", model)
-    ])
+    model = Pipeline([("scaler", StandardScaler()), ("model", model)])
 
     # Prepare features and targets for training
     X_train = df_train[features]