From 4cd5dccc6f397e0b93dc745bdb7d708f6f9a003e Mon Sep 17 00:00:00 2001 From: Floke Date: Wed, 6 Aug 2025 14:04:03 +0000 Subject: [PATCH] duplicate_checker.py aktualisiert --- duplicate_checker.py | 138 +++++++++++++++++++++++-------------------- 1 file changed, 74 insertions(+), 64 deletions(-) diff --git a/duplicate_checker.py b/duplicate_checker.py index bbdcacbf..6eceeee0 100644 --- a/duplicate_checker.py +++ b/duplicate_checker.py @@ -6,15 +6,15 @@ from thefuzz import fuzz from helpers import normalize_company_name, simple_normalize_url from google_sheet_handler import GoogleSheetHandler -# duplicate_checker.py v2.8 (Match-Komponenten im Log) -# Version: 2025-08-06_17-50 +# duplicate_checker.py v2.9 (Bulletproof Name-Partial/SORT/SET + Bonus) +# Version: 2025-08-06_18-10 # --- Konfiguration --- CRM_SHEET_NAME = "CRM_Accounts" MATCHING_SHEET_NAME = "Matching_Accounts" -SCORE_THRESHOLD = 80 +SCORE_THRESHOLD = 80 # Score-Schwelle LOG_DIR = "Log" -LOG_FILE = "duplicate_check_v2.8.log" +LOG_FILE = "duplicate_check_v2.9.txt" # --- Logging Setup --- if not os.path.exists(LOG_DIR): @@ -22,46 +22,60 @@ if not os.path.exists(LOG_DIR): log_path = os.path.join(LOG_DIR, LOG_FILE) root = logging.getLogger() root.setLevel(logging.DEBUG) -# Remove old handlers +# Remove existing handlers for h in list(root.handlers): root.removeHandler(h) formatter = logging.Formatter("%(asctime)s - %(levelname)-8s - %(message)s") -# Console +# Console handler (INFO+) ch = logging.StreamHandler(sys.stdout) ch.setLevel(logging.INFO) ch.setFormatter(formatter) root.addHandler(ch) -# File +# File handler (DEBUG+) fh = logging.FileHandler(log_path, mode='a', encoding='utf-8') fh.setLevel(logging.DEBUG) fh.setFormatter(formatter) root.addHandler(fh) logger = logging.getLogger(__name__) logger.info(f"Logging to console and file: {log_path}") -logger.info("Starting duplicate_checker.py v2.8 | Version: 2025-08-06_17-50") +logger.info("Starting duplicate_checker.py v2.9 | Version: 2025-08-06_18-10") +# --- Ähnlichkeitsberechnung --- +def calculate_similarity(record1, record2): + """Berechnet Score-Komponenten: Domain, Name (SET,PARTIAL,SORT), Ort und Bonus.""" + # Domain exact match + dom1 = record1.get('normalized_domain', '') + dom2 = record2.get('normalized_domain', '') + domain_flag = 1 if dom1 and dom1 == dom2 else 0 -def calculate_similarity_components(r1, r2): - """Gibt einzelne Komponenten und Gesamt-Score zurück.""" - # Domain - dom1 = r1.get('normalized_domain', '') - dom2 = r2.get('normalized_domain', '') - domain_match = 1 if dom1 and dom1 == dom2 else 0 - # Name - name1 = r1.get('normalized_name', '') - name2 = r2.get('normalized_name', '') - name_score = fuzz.token_set_ratio(name1, name2) if name1 and name2 else 0 - # Ort+Land - loc_match = 1 if (r1.get('CRM Ort') == r2.get('CRM Ort') and r1.get('CRM Land') == r2.get('CRM Land')) else 0 - # Gewichte - total = domain_match * 100 + name_score * 0.7 + loc_match * 20 - return round(total), domain_match, round(name_score,1), loc_match + # Location exact match + loc_flag = 1 if (record1.get('CRM Ort') == record2.get('CRM Ort') and + record1.get('CRM Land') == record2.get('CRM Land')) else 0 + # Name scores + n1 = record1.get('normalized_name', '') + n2 = record2.get('normalized_name', '') + if n1 and n2: + ts = fuzz.token_set_ratio(n1, n2) + pr = fuzz.partial_ratio(n1, n2) + ss = fuzz.token_sort_ratio(n1, n2) + name_score = max(ts, pr, ss) + else: + name_score = 0 + # Bonus für reine Name-Matches + bonus_flag = 1 if domain_flag == 0 and loc_flag == 0 and name_score >= 85 else 0 + + # Gesamtscore + total = domain_flag * 100 + name_score * 1.0 + loc_flag * 20 + bonus_flag * 20 + return round(total), domain_flag, name_score, loc_flag, bonus_flag + +# --- Hauptfunktion --- def main(): - logger.info("Starte Duplikats-Check v2.8 (Match-Komponenten im Log)") + logger.info("Starte Duplikats-Check v2.9 (Bulletproof)") + # GoogleSheetHandler init try: - sheet_handler = GoogleSheetHandler() + sheet = GoogleSheetHandler() logger.info("GoogleSheetHandler initialisiert") except Exception as e: logger.critical(f"Init GoogleSheetHandler fehlgeschlagen: {e}") @@ -69,18 +83,15 @@ def main(): # Daten laden logger.info(f"Lade CRM-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: - logger.critical("CRM-Tab leer. Abbruch.") - return - logger.info(f"{len(crm_df)} CRM-Datensätze geladen") - + crm_df = sheet.get_sheet_as_dataframe(CRM_SHEET_NAME) + logger.info(f"{0 if crm_df is None else len(crm_df)} CRM-Datensätze geladen") logger.info(f"Lade Matching-Daten aus '{MATCHING_SHEET_NAME}'...") - match_df = sheet_handler.get_sheet_as_dataframe(MATCHING_SHEET_NAME) - if match_df is None or match_df.empty: - logger.critical("Matching-Tab leer. Abbruch.") + match_df = sheet.get_sheet_as_dataframe(MATCHING_SHEET_NAME) + logger.info(f"{0 if match_df is None else len(match_df)} Matching-Datensätze geladen") + + if crm_df is None or crm_df.empty or match_df is None or match_df.empty: + logger.critical("Leere Daten in einem der Sheets. Abbruch.") return - logger.info(f"{len(match_df)} Matching-Datensätze geladen") # Normalisierung & Blocking-Key for df, label in [(crm_df, 'CRM'), (match_df, 'Matching')]: @@ -91,50 +102,49 @@ def main(): df['block_key'] = df['normalized_name'].apply(lambda x: x.split()[0] if x else None) logger.debug(f"{label}-Sample: {df.iloc[0][['normalized_name','normalized_domain','block_key']].to_dict()}") - # Build blocking index - logger.info("Erstelle Blocking-Index...") + # Blocking-Index erzeugen crm_index = {} - for idx, row in crm_df.iterrows(): + for _, row in crm_df.iterrows(): key = row['block_key'] if key: crm_index.setdefault(key, []).append(row) logger.info(f"Blocking-Index mit {len(crm_index)} Keys erstellt") # Matching - logger.info("Starte Matching...") results = [] total = len(match_df) + logger.info("Starte Matching-Prozess...") for i, mrow in match_df.iterrows(): key = mrow['block_key'] - candidates = crm_index.get(key, []) - logger.info(f"Prüfe {i+1}/{total}: '{mrow['CRM Name']}' -> {len(candidates)} Kandidaten") - if not candidates: - results.append({'Potenzieller Treffer im CRM':'', 'Ähnlichkeits-Score':0}) + cands = crm_index.get(key, []) + logger.info(f"Prüfe {i+1}/{total}: '{mrow['CRM Name']}' -> {len(cands)} Kandidaten") + if not cands: + results.append({'Match':'', 'Score':0}) continue - scored = [] - for crow in candidates: - score, dm, ns, lm = calculate_similarity_components(mrow, crow) - scored.append((crow['CRM Name'], score, dm, ns, lm)) - top3 = sorted(scored, key=lambda x: x[1], reverse=True)[:3] - # Log Top3 mit Komponenten - for name, sc, dm, ns, lm in top3: - logger.debug(f" Kandidat: {name}, Score={sc}, Domain={dm}, Name={ns}, Ort={lm}") - best_name, best_score, best_dm, best_ns, best_lm = max(scored, key=lambda x: x[1]) - if best_score >= SCORE_THRESHOLD: - results.append({'Potenzieller Treffer im CRM':best_name, 'Ähnlichkeits-Score':best_score}) - logger.info(f" --> Match: '{best_name}' Score={best_score} (Dom={best_dm}, Name={best_ns}, Ort={best_lm})") - else: - results.append({'Potenzieller Treffer im CRM':'', 'Ähnlichkeits-Score':best_score}) - logger.info(f" --> Kein Match (Score={best_score}, Dom={best_dm}, Name={best_ns}, Ort={best_lm})") - # Write back - logger.info("Schreibe Ergebnisse zurück ins Sheet...") - out_df = pd.DataFrame(results) + scored = [] + for crow in cands: + sc, dm, ns, lm, bf = calculate_similarity(mrow, crow) + scored.append((crow['CRM Name'], sc, dm, ns, lm, bf)) + # Top 3 loggen + for name, sc, dm, ns, lm, bf in sorted(scored, key=lambda x: x[1], reverse=True)[:3]: + logger.debug(f" Kandidat: {name}, Score={sc}, Dom={dm}, Name={ns}, Ort={lm}, Bonus={bf}") + + best_name, best_score, dm, ns, lm, bf = max(scored, key=lambda x: x[1]) + if best_score >= SCORE_THRESHOLD: + results.append({'Match':best_name, 'Score':best_score}) + logger.info(f" --> Match: '{best_name}' ({best_score}) [Dom={dm}, Name={ns}, Ort={lm}, Bonus={bf}]") + else: + results.append({'Match':'', 'Score':best_score}) + logger.info(f" --> Kein Match (Score={best_score}) [Dom={dm}, Name={ns}, Ort={lm}, Bonus={bf}]") + + # Ergebnisse zurückschreiben + logger.info("Schreibe Ergebnisse ins Sheet...") + out = pd.DataFrame(results) output = match_df[['CRM Name','CRM Website','CRM Ort','CRM Land']].copy() - output = pd.concat([output.reset_index(drop=True), out_df], axis=1) + output = pd.concat([output.reset_index(drop=True), out], axis=1) data = [output.columns.tolist()] + output.values.tolist() - success = sheet_handler.clear_and_write_data(MATCHING_SHEET_NAME, data) - if success: + if sheet.clear_and_write_data(MATCHING_SHEET_NAME, data): logger.info("Ergebnisse erfolgreich geschrieben") else: logger.error("Fehler beim Schreiben ins Google Sheet")