updated the smolagents

Oracle/DataSmolAgent.py

@@ -5,14 +5,30 @@ from transformers import AutoTokenizer, AutoModelForCausalLM
 
 @tool
 def clean_data(df: pd.DataFrame) -> pd.DataFrame:
-    """Clean the input DataFrame (df) by stripping column whitespace and dropping empty rows."""
+    """
+    Cleans the input DataFrame by stripping whitespace from column names and dropping rows that are completely empty.
+
+    Args:
+        df: The input DataFrame containing the raw data.
+
+    Returns:
+         A cleaned DataFrame with stripped column names and without completely empty rows.
+    """
     df.columns = df.columns.str.strip()
     df = df.dropna(how="all")
     return df
 
 @tool
 def extract_features(df: pd.DataFrame) -> pd.DataFrame:
-    """Dynamically extract features from the input DataFrame (df)."""
+    """
+    Dynamically extracts features from the input DataFrame.
+
+    Args:
+        df: The input DataFrame containing the raw data.
+
+    Returns:
+        The DataFrame updated with new dynamically engineered features.
+    """
     # Numeric columns: log transformation
     numeric_cols = df.select_dtypes(include=[np.number]).columns.to_list()
     for col in numeric_cols:
@@ -45,7 +61,16 @@ def extract_features(df: pd.DataFrame) -> pd.DataFrame:
 
 @tool
 def save_to_csv(df: pd.DataFrame, filename: str = "output.csv") -> str:
-    """Save the input DataFrame (df) to a CSV file named 'filename'."""
+    """
+    Saves the input DataFrame to a CSV file and returns the file path.
+
+    Args:
+        df: The DataFrame to save.
+        filename: The name of the output CSV file (default is "output.csv").
+
+    Returns:
+        The file path of the saved CSV.
+    """
     df.to_csv(filename, index=False)
     return filename