data_processor.py

import pandas as pd
import numpy as np

class DataProcessor:
    def __init__(self, df):
        self.df = df

    def get_columns_with_missing_values(self):
        return self.df.columns[self.df.isnull().any()].tolist()

    def clean_data(self):
        # Remove rows with any missing values
        df_cleaned = self.df.dropna()
        
        # Remove duplicate rows
        df_cleaned = df_cleaned.drop_duplicates()
        
        # Reset the index
        df_cleaned = df_cleaned.reset_index(drop=True)
        
        return df_cleaned