Update utils/data_cleaning.py

utils/data_cleaning.py

@@ -22,23 +22,24 @@ def handle_missing_values(df, method='Drop rows'):
                 df[col].fillna(df[col].mode()[0], inplace=True)
     return df
 
-def remove_outliers_iqr(df, col):
+def remove_outliers_iqr(df):
     """
-    Remove outliers using the IQR (Interquartile Range) method for a specific column.
+    Remove outliers using the IQR (Interquartile Range) method for all numerical columns.
     
     Parameters:
     - df: The input DataFrame.
-    - col: The specific column to remove outliers from.
     
     Returns:
     - df: The DataFrame after removing outliers.
     """
-    Q1 = df[col].quantile(0.25)
-    Q3 = df[col].quantile(0.75)
-    IQR = Q3 - Q1
-    lower_bound = Q1 - 1.5 * IQR
-    upper_bound = Q3 + 1.5 * IQR
-    df = df[(df[col] >= lower_bound) & (df[col] <= upper_bound)]
+    numerical_cols = df.select_dtypes(include=['int64', 'float64']).columns
+    for col in numerical_cols:
+        Q1 = df[col].quantile(0.25)
+        Q3 = df[col].quantile(0.75)
+        IQR = Q3 - Q1
+        lower_bound = Q1 - 1.5 * IQR
+        upper_bound = Q3 + 1.5 * IQR
+        df = df[(df[col] >= lower_bound) & (df[col] <= upper_bound)]
     return df
 
 def cap_extreme_values(df):