diff --git a/duplicate_checker.py b/duplicate_checker.py index 8eca0e39..a57a4ad5 100644 --- a/duplicate_checker.py +++ b/duplicate_checker.py @@ -1,4 +1,4 @@ -# duplicate_checker.py (v3.0 - Back to Basics: Optimized Brute-Force) +# duplicate_checker.py (v2.2 - Multi-Key Blocking & optimiertes Scoring) import logging import pandas as pd @@ -6,34 +6,26 @@ from thefuzz import fuzz from config import Config from helpers import normalize_company_name, simple_normalize_url from google_sheet_handler import GoogleSheetHandler -import time +from collections import defaultdict # --- Konfiguration --- CRM_SHEET_NAME = "CRM_Accounts" MATCHING_SHEET_NAME = "Matching_Accounts" -SCORE_THRESHOLD = 85 # Treffer unter diesem Wert werden nicht als "potenzieller Treffer" angezeigt - -# WICHTIG: Logging Setup für detaillierte Ausgaben -logging.basicConfig(level=logging.DEBUG, format='%(asctime)s - %(levelname)-8s - %(name)s - %(message)s') -logger = logging.getLogger(__name__) +SCORE_THRESHOLD = 85 # Etwas höherer Schwellenwert für bessere Präzision +logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s') def calculate_similarity_details(record1, record2): - """ - Berechnet einen gewichteten Ähnlichkeits-Score und gibt die Details zurück. - """ + """Berechnet einen gewichteten Ähnlichkeits-Score und gibt die Details zurück.""" scores = {'name': 0, 'location': 0, 'domain': 0} - # Domain-Match (höchste Priorität, 100 Punkte) if record1.get('normalized_domain') and record1['normalized_domain'] != 'k.a.' and record1['normalized_domain'] == record2.get('normalized_domain'): scores['domain'] = 100 - # Namensähnlichkeit (hohe 85% Gewichtung) + # Höhere Gewichtung für den Namen, da die Website oft fehlt if record1.get('normalized_name') and record2.get('normalized_name'): - # token_set_ratio ist robust gegen zusätzliche Wörter wie "Holding" oder "Gruppe" scores['name'] = round(fuzz.token_set_ratio(record1['normalized_name'], record2['normalized_name']) * 0.85) - # Standort-Bonus (20 Punkte) if record1.get('CRM Ort') and record1['CRM Ort'] == record2.get('CRM Ort'): if record1.get('CRM Land') and record1['CRM Land'] == record2.get('CRM Land'): scores['location'] = 20 @@ -41,59 +33,80 @@ def calculate_similarity_details(record1, record2): total_score = sum(scores.values()) return {'total': total_score, 'details': scores} +def create_blocking_keys(name): + """Erstellt mehrere Blocking Keys für einen Namen, um die Sensitivität zu erhöhen.""" + if not name: + return [] + + words = name.split() + keys = set() + + # 1. Erstes Wort + if len(words) > 0: + keys.add(words[0]) + # 2. Zweites Wort (falls vorhanden) + if len(words) > 1: + keys.add(words[1]) + # 3. Erste 4 Buchstaben des ersten Wortes + if len(words) > 0 and len(words[0]) >= 4: + keys.add(words[0][:4]) + + return list(keys) def main(): - start_time = time.time() - logger.info("Starte den Duplikats-Check (v3.0 - Back to Basics)...") + logging.info("Starte den Duplikats-Check (v2.2 mit Multi-Key Blocking)...") - # ... (Initialisierung und Laden der Daten bleibt gleich) ... try: sheet_handler = GoogleSheetHandler() except Exception as e: - logger.critical(f"FEHLER bei Initialisierung: {e}") + logging.critical(f"FEHLER bei Initialisierung: {e}") return - logger.info(f"Lade Master-Daten aus '{CRM_SHEET_NAME}'...") + logging.info(f"Lade Master-Daten aus '{CRM_SHEET_NAME}'...") crm_df = sheet_handler.get_sheet_as_dataframe(CRM_SHEET_NAME) if crm_df is None or crm_df.empty: return - logger.info(f"Lade zu prüfende Daten aus '{MATCHING_SHEET_NAME}'...") + logging.info(f"Lade zu prüfende Daten aus '{MATCHING_SHEET_NAME}'...") matching_df = sheet_handler.get_sheet_as_dataframe(MATCHING_SHEET_NAME) if matching_df is None or matching_df.empty: return original_matching_df = matching_df.copy() - logger.info("Normalisiere Daten für den Vergleich...") + logging.info("Normalisiere Daten für den Vergleich...") for df in [crm_df, matching_df]: df['normalized_name'] = df['CRM Name'].astype(str).apply(normalize_company_name) df['normalized_domain'] = df['CRM Website'].astype(str).apply(simple_normalize_url) df['CRM Ort'] = df['CRM Ort'].astype(str).str.lower().str.strip() df['CRM Land'] = df['CRM Land'].astype(str).str.lower().str.strip() + df['block_keys'] = df['normalized_name'].apply(create_blocking_keys) - crm_records = crm_df.to_dict('records') - matching_records = matching_df.to_dict('records') + logging.info("Erstelle Index für CRM-Daten zur Beschleunigung...") + crm_index = defaultdict(list) + for record in crm_df.to_dict('records'): + for key in record['block_keys']: + crm_index[key].append(record) - logger.info(f"Starte Matching-Prozess: {len(matching_records)} Einträge werden mit {len(crm_records)} CRM-Einträgen verglichen...") + logging.info("Starte Matching-Prozess...") results = [] - for i, match_record in enumerate(matching_records): - best_score_info = {'total': -1, 'details': {'name': 0, 'location': 0, 'domain': 0}} + for match_record in matching_df.to_dict('records'): + best_score_info = {'total': 0, 'details': {'name': 0, 'location': 0, 'domain': 0}} best_match_name = "" - logger.info(f"--- Prüfe {i + 1}/{len(matching_records)}: '{match_record.get('CRM Name', 'N/A')}' ---") - - # BRUTE-FORCE: Vergleiche mit jedem einzelnen CRM-Eintrag - for crm_record in crm_records: - score_info = calculate_similarity_details(match_record, crm_record) - - # Logge jeden interessanten Vergleich (Score > 60) - if score_info['total'] > 60: - logger.debug(f" - Kandidat: '{crm_record.get('CRM Name', 'N/A')}' -> Score: {score_info['total']} (Details: {score_info['details']})") + logging.info(f"Prüfe: {match_record['CRM Name']}...") + candidate_pool = {} + for key in match_record['block_keys']: + for crm_record in crm_index.get(key, []): + candidate_pool[crm_record['CRM Name']] = crm_record + + if not candidate_pool: + logging.debug(" -> Keine Kandidaten im Index gefunden.") + + for crm_record in candidate_pool.values(): + score_info = calculate_similarity_details(match_record, crm_record) if score_info['total'] > best_score_info['total']: best_score_info = score_info - best_match_name = crm_record.get('CRM Name', 'N/A') - - logger.info(f" --> Bester Treffer: '{best_match_name}' mit Score {best_score_info['total']}") + best_match_name = crm_record['CRM Name'] results.append({ 'Potenzieller Treffer im CRM': best_match_name if best_score_info['total'] >= SCORE_THRESHOLD else "", @@ -116,8 +129,5 @@ def main(): else: logging.error("FEHLER beim Schreiben der Ergebnisse ins Google Sheet.") - end_time = time.time() - logger.info(f"Gesamtdauer des Duplikats-Checks: {end_time - start_time:.2f} Sekunden.") - if __name__ == "__main__": main() \ No newline at end of file