From fb8aec2d93b3d0eac0aa75524d50e5143de1bce7 Mon Sep 17 00:00:00 2001 From: Floke Date: Fri, 1 Aug 2025 11:56:56 +0000 Subject: [PATCH] revoce --- duplicate_checker.py | 64 +++++++++++++------------------------------- 1 file changed, 19 insertions(+), 45 deletions(-) diff --git a/duplicate_checker.py b/duplicate_checker.py index 4484b971..5eb1856d 100644 --- a/duplicate_checker.py +++ b/duplicate_checker.py @@ -1,4 +1,4 @@ -# duplicate_checker.py (v2.3 - Intelligent Blocking) +# duplicate_checker.py (v2.4 - Optimized Brute-Force) import logging import pandas as pd @@ -6,18 +6,12 @@ from thefuzz import fuzz 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 # Treffer unter diesem Wert werden nicht angezeigt - -# NEU: Liste von generischen Wörtern, die für das Blocking ignoriert werden -BLOCKING_STOP_WORDS = { - 'gmbh', 'ag', 'co', 'kg', 'se', 'holding', 'gruppe', 'industries', 'systems', - 'technik', 'service', 'services', 'solutions', 'management', 'international' -} +SCORE_THRESHOLD = 85 # Treffer unter diesem Wert werden nicht als "potenzieller Treffer" angezeigt logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s') @@ -25,12 +19,15 @@ def calculate_similarity_details(record1, record2): """Berechnet einen gewichteten Ähnlichkeits-Score und gibt die Details zurück.""" scores = {'name': 0, 'location': 0, 'domain': 0} + # Domain-Match gibt 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 (85% Gewichtung) 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) + # 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 @@ -38,28 +35,10 @@ 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 aus den signifikanten Wörtern eines Namens.""" - if not name: - return [] - - # Filtere Stop-Wörter aus der Wortliste - significant_words = [word for word in name.split() if word not in BLOCKING_STOP_WORDS] - keys = set() - - # 1. Erstes signifikantes Wort - if len(significant_words) > 0: - keys.add(significant_words[0]) - # 2. Zweites signifikantes Wort (falls vorhanden) - if len(significant_words) > 1: - keys.add(significant_words[1]) - - return list(keys) - def main(): - logging.info("Starte den Duplikats-Check (v2.3 mit Intelligent Blocking)...") + start_time = time.time() + logging.info("Starte den Duplikats-Check (v2.4 - Optimized Brute-Force)...") - # ... (Initialisierung des GoogleSheetHandler bleibt gleich) ... try: sheet_handler = GoogleSheetHandler() except Exception as e: @@ -81,29 +60,22 @@ def main(): 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) - 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) + # Konvertiere DataFrames in Listen von Dictionaries für schnelleren Zugriff in der Schleife + crm_records = crm_df.to_dict('records') + matching_records = matching_df.to_dict('records') - logging.info("Starte Matching-Prozess...") + logging.info(f"Starte Matching-Prozess: {len(matching_records)} Einträge werden mit {len(crm_records)} CRM-Einträgen verglichen...") results = [] - for match_record in matching_df.to_dict('records'): + for i, match_record in enumerate(matching_records): best_score_info = {'total': 0, 'details': {'name': 0, 'location': 0, 'domain': 0}} best_match_name = "" - 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 + logging.info(f"Prüfe {i + 1}/{len(matching_records)}: {match_record['CRM Name']}...") - for crm_record in candidate_pool.values(): + # Der Brute-Force-Ansatz: Vergleiche mit jedem einzelnen CRM-Eintrag + for crm_record in crm_records: score_info = calculate_similarity_details(match_record, crm_record) if score_info['total'] > best_score_info['total']: best_score_info = score_info @@ -120,7 +92,6 @@ def main(): logging.info("Matching abgeschlossen. Schreibe Ergebnisse zurück ins Sheet...") result_df = pd.DataFrame(results) - # Originalspalten aus der Kopie nehmen, um saubere Ausgabe zu garantieren output_df = pd.concat([original_matching_df.reset_index(drop=True), result_df], axis=1) data_to_write = [output_df.columns.values.tolist()] + output_df.values.tolist() @@ -131,5 +102,8 @@ 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