diff --git a/duplicate_checker.py b/duplicate_checker.py index a57a4ad5..100ed636 100644 --- a/duplicate_checker.py +++ b/duplicate_checker.py @@ -1,4 +1,4 @@ -# duplicate_checker.py (v2.2 - Multi-Key Blocking & optimiertes Scoring) +# duplicate_checker.py (v2.7 - Maximum Logging) import logging import pandas as pd @@ -7,13 +7,23 @@ from config import Config from helpers import normalize_company_name, simple_normalize_url from google_sheet_handler import GoogleSheetHandler from collections import defaultdict +import time # --- Konfiguration --- CRM_SHEET_NAME = "CRM_Accounts" MATCHING_SHEET_NAME = "Matching_Accounts" -SCORE_THRESHOLD = 85 # Etwas höherer Schwellenwert für bessere Präzision +SCORE_THRESHOLD = 85 -logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s') +# WICHTIG: Logging auf DEBUG-Level setzen, um alles zu sehen +logging.basicConfig(level=logging.DEBUG, format='%(asctime)s - %(levelname)-8s - %(name)s - %(message)s') +logger = logging.getLogger(__name__) + +BLOCKING_STOP_WORDS = { + 'gmbh', 'ag', 'co', 'kg', 'se', 'holding', 'gruppe', 'industries', 'systems', + 'technik', 'service', 'services', 'solutions', 'management', 'international', 'und', + 'germany', 'deutschland', 'gbr', 'mbh', 'company', 'limited', 'logistics', + 'construction', 'products', 'group', 'b-v' +} def calculate_similarity_details(record1, record2): """Berechnet einen gewichteten Ähnlichkeits-Score und gibt die Details zurück.""" @@ -22,7 +32,6 @@ def calculate_similarity_details(record1, record2): if record1.get('normalized_domain') and record1['normalized_domain'] != 'k.a.' and record1['normalized_domain'] == record2.get('normalized_domain'): scores['domain'] = 100 - # Höhere Gewichtung für den Namen, da die Website oft fehlt if record1.get('normalized_name') and record2.get('normalized_name'): scores['name'] = round(fuzz.token_set_ratio(record1['normalized_name'], record2['normalized_name']) * 0.85) @@ -34,44 +43,32 @@ def calculate_similarity_details(record1, record2): return {'total': total_score, 'details': scores} def create_blocking_keys(name): - """Erstellt mehrere Blocking Keys für einen Namen, um die Sensitivität zu erhöhen.""" + """Erstellt Blocking Keys aus allen signifikanten Wörtern eines Namens.""" 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) + significant_words = {word for word in name.split() if word not in BLOCKING_STOP_WORDS and len(word) >= 3} + return list(significant_words) def main(): - logging.info("Starte den Duplikats-Check (v2.2 mit Multi-Key Blocking)...") + start_time = time.time() + logger.info("Starte den Duplikats-Check (v2.7 - Maximum Logging)...") try: sheet_handler = GoogleSheetHandler() except Exception as e: - logging.critical(f"FEHLER bei Initialisierung: {e}") + logger.critical(f"FEHLER bei Initialisierung: {e}") return - logging.info(f"Lade Master-Daten aus '{CRM_SHEET_NAME}'...") + logger.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 - logging.info(f"Lade zu prüfende Daten aus '{MATCHING_SHEET_NAME}'...") + logger.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() - logging.info("Normalisiere Daten für den Vergleich...") + logger.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) @@ -79,35 +76,53 @@ def main(): df['CRM Land'] = df['CRM Land'].astype(str).str.lower().str.strip() df['block_keys'] = df['normalized_name'].apply(create_blocking_keys) - logging.info("Erstelle Index für CRM-Daten zur Beschleunigung...") + logger.info("Erstelle Index für CRM-Daten zur Beschleunigung...") crm_index = defaultdict(list) - for record in crm_df.to_dict('records'): + crm_records = crm_df.to_dict('records') + for record in crm_records: for key in record['block_keys']: crm_index[key].append(record) - logging.info("Starte Matching-Prozess...") + logger.info("Starte Matching-Prozess...") results = [] for match_record in matching_df.to_dict('records'): - best_score_info = {'total': 0, 'details': {'name': 0, 'location': 0, 'domain': 0}} + best_score_info = {'total': -1, 'details': {'name': 0, 'location': 0, 'domain': 0}} best_match_name = "" - logging.info(f"Prüfe: {match_record['CRM Name']}...") + logger.info(f"--- Prüfe: '{match_record.get('CRM Name', 'N/A')}' ---") + logger.debug(f" [Normalisiert: '{match_record.get('normalized_name')}', Domain: '{match_record.get('normalized_domain')}', Keys: {match_record.get('block_keys')}]") 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 + candidates_from_key = crm_index.get(key, []) + if candidates_from_key: + logger.debug(f" -> Block-Key '{key}' gefunden. {len(candidates_from_key)} Kandidaten hinzugefügt.") + for crm_record in candidates_from_key: + candidate_pool[crm_record['CRM Name']] = crm_record if not candidate_pool: - logging.debug(" -> Keine Kandidaten im Index gefunden.") + logger.debug(" -> Keine Kandidaten im Index gefunden. Überspringe Vergleich.") + results.append({ + 'Potenzieller Treffer im CRM': "", 'Score (Gesamt)': 0, 'Score (Name)': 0, + 'Bonus (Standort)': 0, 'Bonus (Domain)': 0 + }) + continue + + logger.debug(f" -> Vergleiche mit insgesamt {len(candidate_pool)} einzigartigen Kandidaten.") for crm_record in candidate_pool.values(): score_info = calculate_similarity_details(match_record, crm_record) + + # Logge jeden einzelnen Vergleich, der einen Score > 0 hat + if score_info['total'] > 0: + logger.debug(f" - Kandidat: '{crm_record.get('CRM Name', 'N/A')}' -> Score: {score_info['total']} (Details: {score_info['details']})") + if score_info['total'] > best_score_info['total']: best_score_info = score_info - best_match_name = crm_record['CRM Name'] - + best_match_name = crm_record.get('CRM Name', 'N/A') + logger.info(f" --> Neuer bester Treffer: '{best_match_name}' mit Score {best_score_info['total']}") + results.append({ 'Potenzieller Treffer im CRM': best_match_name if best_score_info['total'] >= SCORE_THRESHOLD else "", 'Score (Gesamt)': best_score_info['total'], @@ -129,5 +144,8 @@ def main(): else: logging.error("FEHLER beim Schreiben der Ergebnisse ins Google Sheet.") + end_time = time.time() + logging.info(f"Gesamtdauer des Duplikats-Checks: {end_time - start_time:.2f} Sekunden.") + if __name__ == "__main__": main() \ No newline at end of file