fix: add xlrd for .xls support, use explicit engine in read_excel

data_processor.py

@@ -17,8 +17,10 @@ class DataProcessor:
         try:
             if ext == '.csv':
                 data = pd.read_csv(path)
-            elif ext in ['.xls', '.xlsx']:
-                data = pd.read_excel(path)
+            elif ext == '.xls':
+                data = pd.read_excel(path, engine='xlrd')
+            elif ext == '.xlsx':
+                data = pd.read_excel(path, engine='openpyxl')
             else:
                 raise ValueError(f"Unsupported file type: {ext}")
             logging.info(f"Loaded data from {path} with shape {data.shape}")

requirements.txt

@@ -39,6 +39,7 @@ numpy
 openai>=1.0.0
 openpyxl
 optimum
+xlrd>=2.0.1
 packaging
 pandas
 pillow