updated preprocessing file for regression (small)

src/utils.py

+from pathlib import Path
+import pandas as pd
+import os
+
+def load_dataset(filename, folder="raw", base_path=None):
+    """
+    Load a dataset from a specific folder path using pandas.
+
+    Parameters:
+        filename (str): The name of the file (e.g., "data.csv").
+        folder (str): The subfolder inside the data directory (default is "raw").
+        base_path (str or Path): Base path to the data directory. If None, defaults to two levels up from this script.
+
+    Returns:
+        pd.DataFrame: Loaded dataset.
+    """
+    if base_path is None:
+        base_path = Path(__file__).resolve().parents[2] / "data"
+
+    file_path = base_path / folder / filename
+
+    if not file_path.exists():
+        raise FileNotFoundError(f"❌ File not found: {file_path}")
+    
+    try:
+        df = pd.read_csv(file_path)
+        print(f"✅ Loaded dataset from: {file_path}")
+        return df
+    except Exception as e:
+        raise RuntimeError(f"⚠️ Failed to load dataset: {e}")