Data pipelines & processing

import pandas as pd
from pathlib import Path

def find_duplicate_records_across_sheets(file_path: str, key_columns: list, sheet_names: list) -> dict:
    """
    Detect duplicate records across multiple Excel sheets based on specified key columns.
    
    Args:
        file_path: Path to the Excel file
        key_co…

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 = (mi…