From 600b977a9f83f2f76f26a3800c6ce4d1695542a7 Mon Sep 17 00:00:00 2001 From: Floke Date: Tue, 5 Aug 2025 15:54:08 +0000 Subject: [PATCH] duplicate_checker.py aktualisiert --- duplicate_checker.py | 93 +++++++++++++++++++++----------------------- 1 file changed, 44 insertions(+), 49 deletions(-) diff --git a/duplicate_checker.py b/duplicate_checker.py index d86874e6..fbc5db42 100644 --- a/duplicate_checker.py +++ b/duplicate_checker.py @@ -28,16 +28,13 @@ log_path = os.path.join(LOG_DIR, LOG_FILENAME) logger = logging.getLogger(__name__) logger.setLevel(logging.DEBUG) - formatter = logging.Formatter('%(asctime)s - %(levelname)-8s - %(name)s - %(message)s') - -# Console Handler +# Console handler console_handler = logging.StreamHandler() console_handler.setLevel(logging.INFO) console_handler.setFormatter(formatter) logger.addHandler(console_handler) - -# File Handler +# File handler try: file_handler = logging.FileHandler(log_path, mode='a', encoding='utf-8') file_handler.setLevel(logging.DEBUG) @@ -57,7 +54,6 @@ def normalize_company_name(name: str) -> str: tokens = [t for t in s.split() if t and t not in stops] return ' '.join(tokens) - def normalize_domain(url: str) -> str: s = str(url).casefold().strip() s = re.sub(r'^https?://', '', s) @@ -68,8 +64,7 @@ def normalize_domain(url: str) -> str: def main(): - logger.info("Starte den Duplikats-Check (v2.0 mit Logging in /log)...") - # GoogleSheetHandler initialisieren + logger.info("Starte den Duplikats-Check (v2.0 mit Kandidaten-Logging)...") try: sheet_handler = GoogleSheetHandler() logger.info("GoogleSheetHandler initialisiert") @@ -77,81 +72,81 @@ def main(): logger.critical(f"FEHLER bei Initialisierung des GoogleSheetHandler: {e}") return - # CRM-Daten laden - logger.info(f"Lade Master-Daten aus '{CRM_SHEET_NAME}'...") + # Daten laden crm_df = sheet_handler.get_sheet_as_dataframe(CRM_SHEET_NAME) - if crm_df is None or crm_df.empty: - logger.critical(f"Konnte keine Daten aus '{CRM_SHEET_NAME}' laden. Abbruch.") - return - logger.info(f"{len(crm_df)} Zeilen aus '{CRM_SHEET_NAME}' geladen") - - # Matching-Daten laden - logger.info(f"Lade zu prüfende 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(f"Konnte keine Daten aus '{MATCHING_SHEET_NAME}' laden. Abbruch.") + if crm_df is None or crm_df.empty or match_df is None or match_df.empty: + logger.critical("CRM- oder Matching-Daten leer. Abbruch.") return - logger.info(f"{len(match_df)} Zeilen aus '{MATCHING_SHEET_NAME}' geladen") + logger.info(f"{len(crm_df)} CRM-Zeilen, {len(match_df)} Matching-Zeilen geladen") # Normalisierung for df, label in [(crm_df, 'CRM'), (match_df, 'Matching')]: df['norm_name'] = df['CRM Name'].fillna('').apply(normalize_company_name) df['norm_domain'] = df['CRM Website'].fillna('').apply(normalize_domain) df['city'] = df['CRM Ort'].fillna('').apply(lambda x: str(x).casefold().strip()) - logger.debug(f"{label}-Daten normalisiert. Erste Zeile: {df.iloc[0].to_dict()}") + logger.debug(f"{label}-Daten normalisiert: Beispiel: {df.iloc[0][['norm_name','norm_domain','city']].to_dict()}") - # Blocking per Domain + # Blocking indexer = recordlinkage.Index() indexer.block('norm_domain') candidate_pairs = indexer.index(crm_df, match_df) - logger.info(f"Blocking abgeschlossen: {len(candidate_pairs)} Kandidatenpaare gefunden") + logger.info(f"Blocking abgeschlossen: {len(candidate_pairs)} Kandidatenpaare") - # Vergleichsregeln definieren + # Compare compare = recordlinkage.Compare() compare.exact('norm_domain', 'norm_domain', label='domain') compare.string('norm_name', 'norm_name', method='jarowinkler', label='name_sim') compare.exact('city', 'city', label='city') features = compare.compute(candidate_pairs, crm_df, match_df) - logger.debug(f"Feature-DataFrame Vorschau:\n{features.head()}") + logger.debug(f"Features berechnet: {features.head()}\n...") - # Score berechnen - features['score'] = ( - WEIGHTS['domain'] * features['domain'] + - WEIGHTS['name'] * features['name_sim'] + - WEIGHTS['city'] * features['city'] - ) + # Score + features['score'] = (WEIGHTS['domain']*features['domain'] + + WEIGHTS['name']*features['name_sim'] + + WEIGHTS['city']*features['city']) logger.info("Scores berechnet") - # Best Match pro neuer Zeile mit detailliertem Logging + # Per Match Logging results = [] + crm_df_idx = crm_df.reset_index() for match_idx, group in features.reset_index().groupby('level_1'): - logger.info(f"--- Prüfe: Zeile {match_idx} ---") - df_block = group.sort_values('score', ascending=False) - logger.debug(f"Kandidaten für Zeile {match_idx}:\n{df_block[['level_0','score','domain','name_sim','city']].to_string(index=False)}") + logger.info(f"--- Prüfe Matching-Zeile {match_idx} ---") + df_block = group.sort_values('score', ascending=False).copy() + # Enrich with CRM fields + df_block['CRM Name'] = df_block['level_0'].map(crm_df_idx.set_index('index')['CRM Name']) + df_block['CRM Website'] = df_block['level_0'].map(crm_df_idx.set_index('index')['CRM Website']) + df_block['CRM Ort'] = df_block['level_0'].map(crm_df_idx.set_index('index')['CRM Ort']) + # Log top candidates + logger.debug("Kandidaten (CRM_Index, Score, Domain, Name_sim, City, CRM Name):") + for _, row in df_block.iterrows(): + logger.debug(f" [{int(row['level_0'])}] score={row['score']:.3f} dom={row['domain']} name_sim={row['name_sim']:.3f} city={row['city']} => {row['CRM Name']}") top = df_block.iloc[0] crm_idx = top['level_0'] if top['score'] >= SCORE_THRESHOLD else None if crm_idx is not None: - logger.info(f" --> Match: CRM-Index {crm_idx} mit Score {top['score']:.2f}") + logger.info(f" --> Match: CRM-Index {int(crm_idx)} ({top['CRM Name']}) mit Score {top['score']:.2f}") else: logger.info(f" --> Kein Match (höchster Score {top['score']:.2f})") results.append((crm_idx, match_idx, top['score'])) - # Ausgabe DataFrame zusammenstellen - crm_df = crm_df.reset_index() - match_df = match_df.reset_index() - output = match_df[['CRM Name','CRM Website','CRM Ort','CRM Land']].copy() - output[['Matched CRM Name','Matched CRM Website','Matched CRM Ort','Matched CRM Land','Score']] = '' - + # Prepare output + match_df_idx = match_df.reset_index() + output = match_df_idx[['CRM Name','CRM Website','CRM Ort','CRM Land']].copy() + output['Matched CRM Name'] = '' + output['Matched CRM Website'] = '' + output['Matched CRM Ort'] = '' + output['Matched CRM Land'] = '' + output['Score'] = 0.0 for crm_idx, match_idx, score in results: if crm_idx is not None: - row_crm = crm_df.loc[crm_df['index']==crm_idx].iloc[0] - output.at[match_idx, 'Matched CRM Name'] = row_crm['CRM Name'] - output.at[match_idx, 'Matched CRM Website'] = row_crm['CRM Website'] - output.at[match_idx, 'Matched CRM Ort'] = row_crm['CRM Ort'] - output.at[match_idx, 'Matched CRM Land'] = row_crm['CRM Land'] - output.at[match_idx, 'Score'] = round(score, 3) + crm_row = crm_df_idx[crm_df_idx['index']==crm_idx].iloc[0] + output.at[match_idx, 'Matched CRM Name'] = crm_row['CRM Name'] + output.at[match_idx, 'Matched CRM Website'] = crm_row['CRM Website'] + output.at[match_idx, 'Matched CRM Ort'] = crm_row['CRM Ort'] + output.at[match_idx, 'Matched CRM Land'] = crm_row['CRM Land'] + output.at[match_idx, 'Score'] = round(score,3) - # Zurückschreiben ins Google Sheet + # Write back data = [output.columns.tolist()] + output.values.tolist() success = sheet_handler.clear_and_write_data(MATCHING_SHEET_NAME, data) if success: