revoce

duplicate_checker.py

@@ -1,4 +1,4 @@
-# duplicate_checker.py (v1.1 - Lauf 1 Logik + Match-Grund)
+# duplicate_checker.py (v2.0 - mit Blocking-Strategie)
 
 import logging
 import pandas as pd
@@ -6,65 +6,48 @@ from thefuzz import fuzz
 from config import Config
 from helpers import normalize_company_name, simple_normalize_url
 from google_sheet_handler import GoogleSheetHandler
-import time
 
 # --- Konfiguration ---
 CRM_SHEET_NAME = "CRM_Accounts"
 MATCHING_SHEET_NAME = "Matching_Accounts"
-SCORE_THRESHOLD = 80 # Treffer unter diesem Wert werden nicht als "potenzieller Treffer" angezeigt
+SCORE_THRESHOLD = 80
 
 logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
 
-def calculate_similarity_with_details(record1, record2):
-    """
-    Berechnet einen gewichteten Ähnlichkeits-Score und gibt den Score und den Grund zurück.
-    Dies ist die originale Scoring-Logik von Lauf 1.
-    """
-    scores = {'name': 0, 'location': 0, 'domain': 0}
-    
-    # Domain-Match (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 (70% Gewichtung)
-    if record1.get('normalized_name') and record2.get('normalized_name'):
+def calculate_similarity(record1, record2):
+    """Berechnet einen gewichteten Ähnlichkeits-Score zwischen zwei Datensätzen."""
+    total_score = 0
+    if record1['normalized_domain'] and record1['normalized_domain'] == record2['normalized_domain']:
+        total_score += 100
+    if record1['normalized_name'] and record2['normalized_name']:
         name_similarity = fuzz.token_set_ratio(record1['normalized_name'], record2['normalized_name'])
-        scores['name'] = round(name_similarity * 0.7)
-
-    # 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
-            
-    total_score = sum(scores.values())
-    
-    # Erstelle den Begründungstext
-    reasons = []
-    if scores['domain'] > 0: reasons.append(f"Domain({scores['domain']})")
-    if scores['name'] > 0: reasons.append(f"Name({scores['name']})")
-    if scores['location'] > 0: reasons.append(f"Ort({scores['location']})")
-    reason_text = " + ".join(reasons) if reasons else "Keine Übereinstimmung"
-
-    return round(total_score), reason_text
+        total_score += name_similarity * 0.7
+    if record1['CRM Ort'] and record1['CRM Ort'] == record2['CRM Ort']:
+        if record1['CRM Land'] and record1['CRM Land'] == record2['CRM Land']:
+            total_score += 20
+    return round(total_score)
 
 def main():
-    start_time = time.time()
-    logging.info("Starte den Duplikats-Check (v1.1 - Brute-Force mit Match-Grund)...")
+    """Hauptfunktion zum Laden, Vergleichen und Schreiben der Daten."""
+    logging.info("Starte den Duplikats-Check (v2.0 mit Blocking)...")
     
     try:
         sheet_handler = GoogleSheetHandler()
     except Exception as e:
-        logging.critical(f"FEHLER bei Initialisierung: {e}")
+        logging.critical(f"FEHLER bei Initialisierung des GoogleSheetHandler: {e}")
         return
 
     logging.info(f"Lade Master-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: return
+    if crm_df is None or crm_df.empty:
+        logging.critical(f"Konnte keine Daten aus '{CRM_SHEET_NAME}' laden. Breche ab.")
+        return
 
     logging.info(f"Lade zu prüfende Daten aus '{MATCHING_SHEET_NAME}'...")
     matching_df = sheet_handler.get_sheet_as_dataframe(MATCHING_SHEET_NAME)
-    if matching_df is None or matching_df.empty: return
-    original_matching_df = matching_df.copy()
+    if matching_df is None or matching_df.empty:
+        logging.critical(f"Konnte keine Daten aus '{MATCHING_SHEET_NAME}' laden. Breche ab.")
+        return
 
     logging.info("Normalisiere Daten für den Vergleich...")
     for df in [crm_df, matching_df]:
@@ -72,49 +55,60 @@ 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()
+        # Blocking Key: Das erste Wort des normalisierten Namens
+        df['block_key'] = df['normalized_name'].apply(lambda x: x.split()[0] if x else None)
 
-    crm_records = crm_df.to_dict('records')
-    matching_records = matching_df.to_dict('records')
+    # --- NEUE, SCHNELLE BLOCKING-STRATEGIE ---
+    logging.info("Erstelle Index für CRM-Daten zur Beschleunigung...")
+    crm_index = {}
+    for index, row in crm_df.iterrows():
+        key = row['block_key']
+        if key:
+            if key not in crm_index:
+                crm_index[key] = []
+            crm_index[key].append(row)
     
-    logging.info(f"Starte Matching-Prozess: {len(matching_records)} Einträge werden mit {len(crm_records)} CRM-Einträgen verglichen...")
+    logging.info("Starte Matching-Prozess...")
     results = []
+    total_matches = len(matching_df)
     
-    for i, match_record in enumerate(matching_records):
-        best_score = -1
+    for index, match_row in matching_df.iterrows():
+        best_score = 0
         best_match_name = ""
-        best_reason = ""
         
-        logging.info(f"Prüfe {i + 1}/{len(matching_records)}: {match_record.get('CRM Name', 'N/A')}...")
+        logging.info(f"Prüfe {index + 1}/{total_matches}: {match_row['CRM Name']}...")
+
+        # Finde den Block von Kandidaten
+        block_key = match_row['block_key']
+        candidates = crm_index.get(block_key, [])
         
-        # Brute-Force-Vergleich: Jede Zeile wird mit jeder CRM-Zeile verglichen
-        for crm_record in crm_records:
-            score, reason = calculate_similarity_with_details(match_record, crm_record)
+        # Führe den teuren Vergleich nur für die Kandidaten in diesem Block durch
+        for crm_row in candidates:
+            score = calculate_similarity(match_row, crm_row)
             if score > best_score:
                 best_score = score
-                best_match_name = crm_record.get('CRM Name', 'N/A')
-                best_reason = reason
+                best_match_name = crm_row['CRM Name']
         
-        results.append({
-            'Potenzieller Treffer im CRM': best_match_name if best_score >= SCORE_THRESHOLD else "",
-            'Ähnlichkeits-Score': best_score,
-            'Matching-Grund': best_reason
-        })
+        if best_score >= SCORE_THRESHOLD:
+            results.append({'Potenzieller Treffer im CRM': best_match_name, 'Ähnlichkeits-Score': best_score})
+        else:
+            # Wenn nichts im Block gefunden wurde, trotzdem den besten Treffer (kann 0 sein) anzeigen
+            results.append({'Potenzieller Treffer im CRM': '' if not best_match_name else best_match_name, 'Ähnlichkeits-Score': best_score})
 
     logging.info("Matching abgeschlossen. Schreibe Ergebnisse zurück ins Sheet...")
     result_df = pd.DataFrame(results)
     
-    output_df = pd.concat([original_matching_df.reset_index(drop=True), result_df], axis=1)
+    # Die ursprünglichen Spalten aus matching_df für die Ausgabe nehmen
+    output_df = matching_df[['CRM Name', 'CRM Website', 'CRM Ort', 'CRM Land']].copy()
+    output_df = pd.concat([output_df.reset_index(drop=True), result_df], axis=1)
     
     data_to_write = [output_df.columns.values.tolist()] + output_df.values.tolist()
     
     success = sheet_handler.clear_and_write_data(MATCHING_SHEET_NAME, data_to_write)
     if success:
-        logging.info(f"Ergebnisse erfolgreich in '{MATCHING_SHEET_NAME}' geschrieben.")
+        logging.info(f"Ergebnisse erfolgreich in das Tabellenblatt '{MATCHING_SHEET_NAME}' geschrieben.")
     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()