How to Find Missing Values in Large Datasets in Python

import pandas as pd
import numpy as np

def find_missing_values_summary(datasets):
    """Analyze missing values across multiple datasets (dict of name: DataFrame)."""
    summary = {}
    for name, df in datasets.items():
        missing_count = df.isnull().sum()
        total_rows = len(df)
        missing_pct = (missing_count / total_rows * 100).round(2)
        
        summary[name] = pd.DataFrame({
            'Column': df.columns,
            'Missing_Count': missing_count.values,
            'Missing_Percentage': missing_pct.values
        })
    return summary

if __name__ == "__main__":
    # Simulate large datasets with missing values
    np.random.seed(42)
    size = 10000
    df1 = pd.DataFrame({'A': np.random.choice([1, np.nan], size=size, p=[0.9, 0.1]),
                        'B': np.random.choice([2, np.nan], size=size, p=[0.8, 0.2])})
    df2 = pd.DataFrame({'X': np.random.choice([10, np.nan], size=size, p=[0.95, 0.05]),
                        'Y': np.random.choice([20, np.nan], size=size, p=[0.85, 0.15])})
    
    datasets = {'sales': df1, 'customers': df2}
    result = find_missing_values_summary(datasets)
    for name, df in result.items():
        print(f"Dataset: {name}")
        print(df.to_string(index=False))
        print()