Fuzzy Match & Deduplicate Messy Vendor/Customer Names in Accounting CSVs (Python)

import pandas as pd
import re
from difflib import SequenceMatcher

def normalize_entity_name(name: str) -> str:
    s = re.sub(r'[^A-Z0-9 ]', ' ', str(name).upper())
    s = re.sub(r'\b(PVT|PRIVATE|LTD|LIMITED|INC|LLP|CO|CORP)\b', '', s)
    return ' '.join(s.split())

def find_duplicate_vendors(vendor_list, threshold=0.88):
    cleaned = [(v, normalize_entity_name(v)) for v in vendor_list]
    matches = []
    for i in range(len(cleaned)):
        for j in range(i + 1, len(cleaned)):
            sim = SequenceMatcher(None, cleaned[i][1], cleaned[j][1]).ratio()
            if sim >= threshold:
                matches.append({'Vendor_A': cleaned[i][0], 'Vendor_B': cleaned[j][0], 'Similarity': round(sim, 3)})
    return pd.DataFrame(matches)