Update preprocessing.py

Change standardization function

preprocessing.py

@@ -16,26 +16,36 @@ def data_quality(df: pd.DataFrame):
 
 def standardize_data_types(df: pd.DataFrame) -> pd.DataFrame:
     for col in df.columns:
+        # Skip boolean columns
         if df[col].isin([True, False]).all():
             continue
-        if df[col].dtype == 'object' and df[col].str.replace('.', '', 1).str.isnumeric().all():
-            df[col] = pd.to_numeric(df[col], errors='ignore')
+
+        # Attempt numeric conversion
+        if df[col].dtype == 'object':
+            try:
+                df[col] = pd.to_numeric(df[col], errors='coerce')
+            except Exception:
+                pass
+
+        # Attempt datetime conversion
         try:
-            df[col] = pd.to_datetime(df[col], errors='coerce')
-            if df[col].notna().sum() == 0:
-                df[col] = df[col].astype(str)
+            temp_col = pd.to_datetime(df[col], errors='coerce')
+            if temp_col.notna().sum() > 0:
+                df[col] = temp_col
         except Exception:
             pass
+
+        # JSON list/dict conversion
         try:
             if df[col].apply(lambda x: isinstance(x, str) and x.startswith("[") and x.endswith("]")).all():
                 df[col] = df[col].apply(json.loads)
         except Exception:
             pass
-        if df[col].dtype == 'object' and df[col].dropna().isin(["TRUE", "FALSE"]).all():
+
+        # Boolean string to actual bool
+        if df[col].dropna().isin(["TRUE", "FALSE"]).all():
             df[col] = df[col].map({"TRUE": True, "FALSE": False})
-        if df[col].dtype == 'object':
-            df[col] = df[col].astype(str)
-    df.fillna("", inplace=True)
+
     return df
 
 def handle_missing_data(df: pd.DataFrame) -> pd.DataFrame: