duplicate_checker.py aktualisiert

duplicate_checker.py

@@ -1,4 +1,4 @@
-# duplicate_checker.py (v2.2 - Multi-Key Blocking & optimiertes Scoring)
+# duplicate_checker.py (v2.6 - Final Optimized Brute-Force)
 
 import logging
 import pandas as pd
@@ -6,12 +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 # Etwas höherer Schwellenwert für bessere Präzision
+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')
 
@@ -19,13 +19,16 @@ 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 (höchste Priorität)
     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
+    # Namensähnlichkeit (hohe Gewichtung)
     if record1.get('normalized_name') and record2.get('normalized_name'):
+        # token_set_ratio ist gut bei unterschiedlicher Wortreihenfolge und Zusatzwörtern
         scores['name'] = round(fuzz.token_set_ratio(record1['normalized_name'], record2['normalized_name']) * 0.85)
 
+    # Standort-Bonus
     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
@@ -33,28 +36,9 @@ 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 für einen Namen, um die Sensitivität zu erhöhen."""
-    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)
-
 def main():
-    logging.info("Starte den Duplikats-Check (v2.2 mit Multi-Key Blocking)...")
+    start_time = time.time()
+    logging.info("Starte den Duplikats-Check (v2.6 - Final Optimized Brute-Force)...")
     
     try:
         sheet_handler = GoogleSheetHandler()
@@ -77,36 +61,25 @@ 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)
+    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.get('CRM Name', 'N/A')}...")
         
-        if not candidate_pool:
-            logging.debug("  -> Keine Kandidaten im Index gefunden.")
-        
-        for crm_record in candidate_pool.values():
+        # Brute-Force-Vergleich: Jede Zeile wird mit jeder CRM-Zeile verglichen
+        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
-                best_match_name = crm_record['CRM Name']
+                best_match_name = crm_record.get('CRM Name', 'N/A')
         
         results.append({
             'Potenzieller Treffer im CRM': best_match_name if best_score_info['total'] >= SCORE_THRESHOLD else "",
@@ -129,5 +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()