diff --git a/duplicate_checker.py b/duplicate_checker.py index 5c58a74d..6229d691 100644 --- a/duplicate_checker.py +++ b/duplicate_checker.py @@ -1,6 +1,9 @@ import os +import sys import logging import pandas as pd +from datetime import datetime +import tldextract from thefuzz import fuzz from helpers import normalize_company_name, simple_normalize_url from google_sheet_handler import GoogleSheetHandler @@ -8,25 +11,25 @@ from google_sheet_handler import GoogleSheetHandler # --- Konfiguration --- CRM_SHEET_NAME = "CRM_Accounts" MATCHING_SHEET_NAME = "Matching_Accounts" -SCORE_THRESHOLD = 80 # Score ab hier gilt als Match +SCORE_THRESHOLD = 80 # ab hier automatisches Match LOG_DIR = "Log" -LOG_FILE = "duplicate_check.log" -# --- Logging Setup --- +# --- Logging Setup mit Datum im Dateinamen --- if not os.path.exists(LOG_DIR): os.makedirs(LOG_DIR, exist_ok=True) -log_path = os.path.join(LOG_DIR, LOG_FILE) +now = datetime.now().strftime('%Y-%m-%d_%H-%M') +log_path = os.path.join(LOG_DIR, f"{now}_Duplicate.txt") logger = logging.getLogger(__name__) logger.setLevel(logging.DEBUG) -# Console Handler: INFO+ +# Console-Handler (INFO+) ch = logging.StreamHandler() ch.setLevel(logging.INFO) ch.setFormatter(logging.Formatter("%(asctime)s - %(levelname)-8s - %(message)s")) logger.addHandler(ch) -# File Handler: DEBUG+ +# File-Handler (DEBUG+) fh = logging.FileHandler(log_path, mode='a', encoding='utf-8') fh.setLevel(logging.DEBUG) fh.setFormatter(logging.Formatter("%(asctime)s - %(levelname)-8s - %(name)s - %(message)s")) @@ -36,93 +39,90 @@ logger.info(f"Logging in Datei: {log_path}") def calculate_similarity(record1, record2): - """Berechnet gewichteten Ähnlichkeits-Score zwischen zwei Datensätzen.""" - total_score = 0 - # Domain exact match - if record1['normalized_domain'] and record1['normalized_domain'] == record2['normalized_domain']: - total_score += 100 - # Name fuzzy - name_similarity = fuzz.token_set_ratio(record1['normalized_name'], record2['normalized_name']) - total_score += name_similarity * 0.7 - # Ort+Land exact + """Berechnet gewichteten Ähnlichkeits-Score (0–190) zwischen zwei Datensätzen.""" + total = 0 + # Domain-Check über registered domain + url1 = record1.get('CRM Website','') + url2 = record2.get('CRM Website','') + dom1 = tldextract.extract(url1).registered_domain or '' + dom2 = tldextract.extract(url2).registered_domain or '' + if dom1 and dom1 == dom2: + total += 100 + # Name-Fuzzy + name1 = record1['normalized_name'] + name2 = record2['normalized_name'] + if name1 and name2: + total += fuzz.token_set_ratio(name1, name2) * 0.7 + # Ort+Land exakt if record1['CRM Ort'] == record2['CRM Ort'] and record1['CRM Land'] == record2['CRM Land']: - total_score += 20 - return round(total_score) + total += 20 + return round(total) def main(): - logger.info("Starte Duplikats-Check (v2.0 - mit Blocking & relevantem Kandidaten-Log)") + logger.info("Starte Duplikats-Check (v2.0) mit Datum im Lognamen und verbessertem Domain-Match") try: - sheet_handler = GoogleSheetHandler() + sheet = GoogleSheetHandler() logger.info("GoogleSheetHandler initialisiert") except Exception as e: - logger.critical(f"FEHLER Init GoogleSheetHandler: {e}") - return + logger.critical(f"FEHLER beim Init GoogleSheetHandler: {e}") + sys.exit(1) - # Daten laden - crm_df = sheet_handler.get_sheet_as_dataframe(CRM_SHEET_NAME) - match_df = sheet_handler.get_sheet_as_dataframe(MATCHING_SHEET_NAME) - if crm_df is None or crm_df.empty: - logger.critical(f"Keine Daten in '{CRM_SHEET_NAME}'") + # Daten einlesen + crm_df = sheet.get_sheet_as_dataframe(CRM_SHEET_NAME) + match_df = sheet.get_sheet_as_dataframe(MATCHING_SHEET_NAME) + if crm_df is None or crm_df.empty or match_df is None or match_df.empty: + logger.critical("CRM- oder Matching-Daten fehlen. Abbruch.") return - if match_df is None or match_df.empty: - logger.critical(f"Keine Daten in '{MATCHING_SHEET_NAME}'") - return - logger.info(f"{len(crm_df)} CRM-Zeilen, {len(match_df)} Matching-Zeilen geladen") + logger.info(f"{len(crm_df)} CRM-Datensätze, {len(match_df)} Matching-Datensätze geladen") - # Normalisierung + # Normalisierung und Blocking-Key for df, label in [(crm_df, 'CRM'), (match_df, 'Matching')]: 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() - # Blocking Key df['block_key'] = df['normalized_name'].apply(lambda x: x.split()[0] if x else None) - logger.debug(f"{label}-Sample nach Norm: {df.iloc[0][['normalized_name','normalized_domain','block_key']].to_dict()}") + logger.debug(f"{label}-Normierung Beispiel: {df.iloc[0][['normalized_name','normalized_domain','block_key']].to_dict()}") - # Blocking Index erstellen + # Blocking-Index crm_index = {} for idx, row in crm_df.iterrows(): key = row['block_key'] - if not key: continue - crm_index.setdefault(key, []).append(row) + if key: + crm_index.setdefault(key, []).append(row) logger.info(f"Blocking-Index erstellt: {len(crm_index)} Keys") # Matching results = [] total = len(match_df) - for i, match_row in match_df.iterrows(): - key = match_row['block_key'] - candidates = crm_index.get(key, []) - logger.info(f"Prüfe {i+1}/{total}: {match_row['CRM Name']} (Key='{key}') -> {len(candidates)} Kandidaten") - - if not candidates: - results.append({'Potenzieller Treffer im CRM': '', 'Ähnlichkeits-Score': 0}) + for i, mrow in match_df.iterrows(): + key = mrow['block_key'] + cands = crm_index.get(key, []) + logger.info(f"Prüfe {i+1}/{total}: '{mrow['CRM Name']}' (Key='{key}') -> {len(cands)} Kandidaten") + if not cands: + results.append({'Match': '', 'Score': 0}) continue - - # Scores für Kandidaten sammeln scored = [] - for crm_row in candidates: - score = calculate_similarity(match_row, crm_row) - scored.append((crm_row['CRM Name'], score)) - # Top 3 loggen - top3 = sorted(scored, key=lambda x: x[1], reverse=True)[:3] - logger.debug(f" Top 3 Kandidaten: {top3}") - - # Besten Treffer wählen + for crow in cands: + score = calculate_similarity(mrow, crow) + scored.append((crow['CRM Name'], score)) + # Log relevante Kandidaten mit Score>=SCORE_THRESHOLD-20 + relevant = [(n,s) for n,s in scored if s >= SCORE_THRESHOLD-20] + logger.debug(f" Relevante Kandidaten (>= {SCORE_THRESHOLD-20}): {relevant}") best_name, best_score = 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}' mit Score {best_score}") + results.append({'Match': best_name, 'Score': best_score}) + logger.info(f" --> Match: '{best_name}' mit Score {best_score}") else: - results.append({'Potenzieller Treffer im CRM': '', 'Ähnlichkeits-Score': best_score}) - logger.info(f" --> Kein Match (höchster Score {best_score})") + results.append({'Match': '', 'Score': best_score}) + logger.info(f" --> Kein Match (höchster Score {best_score})") - # Ergebnisse zurückschreiben - out_df = pd.DataFrame(results) - output = pd.concat([match_df[['CRM Name','CRM Website','CRM Ort','CRM Land']].reset_index(drop=True), out_df], axis=1) + # Ergebnis zurück in Sheet + out = pd.DataFrame(results) + output = pd.concat([match_df[['CRM Name','CRM Website','CRM Ort','CRM Land']].reset_index(drop=True), out], axis=1) data = [output.columns.tolist()] + output.values.tolist() - ok = sheet_handler.clear_and_write_data(MATCHING_SHEET_NAME, data) + ok = sheet.clear_and_write_data(MATCHING_SHEET_NAME, data) if ok: logger.info("Ergebnisse erfolgreich geschrieben") else: