duplicate_checker.py hinzugefügt

duplicate_checker.py

@@ -0,0 +1,112 @@
+# duplicate_checker.py
+
+import logging
+import pandas as pd
+from thefuzz import fuzz
+from config import Config
+from helpers import normalize_company_name, simple_normalize_url
+from google_sheet_handler import GoogleSheetHandler
+
+# --- Konfiguration ---
+CRM_SHEET_NAME = "CRM_Accounts"
+MATCHING_SHEET_NAME = "Matching_Accounts"
+SCORE_THRESHOLD = 80 # Mindest-Score, um als "wahrscheinlicher Treffer" zu gelten
+
+# --- Logging einrichten ---
+logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
+
+def calculate_similarity(record1, record2):
+    """Berechnet einen gewichteten Ähnlichkeits-Score zwischen zwei Datensätzen."""
+    total_score = 0
+
+    # 1. Website-Domain (stärkstes Signal)
+    if record1['normalized_domain'] and record1['normalized_domain'] == record2['normalized_domain']:
+        total_score += 100
+    
+    # 2. Firmenname (Fuzzy-Signal)
+    if record1['normalized_name'] and record2['normalized_name']:
+        name_similarity = fuzz.token_set_ratio(record1['normalized_name'], record2['normalized_name'])
+        total_score += name_similarity * 0.7 # Gewichtung: 70%
+
+    # 3. Standort (Bestätigungs-Signal)
+    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 # Bonus für vollen Standort-Match
+
+    return round(total_score)
+
+def main():
+    """Hauptfunktion zum Laden, Vergleichen und Schreiben der Daten."""
+    logging.info("Starte den Duplikats-Check...")
+    
+    try:
+        sheet_handler = GoogleSheetHandler()
+    except Exception as e:
+        logging.critical(f"FEHLER bei der Initialisierung des GoogleSheetHandler: {e}")
+        return
+
+    # 1. Daten laden
+    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:
+        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:
+        logging.critical(f"Konnte keine Daten aus '{MATCHING_SHEET_NAME}' laden. Breche ab.")
+        return
+
+    # 2. Daten normalisieren
+    logging.info("Normalisiere Daten für den Vergleich...")
+    crm_df['normalized_name'] = crm_df['CRM Name'].astype(str).apply(normalize_company_name)
+    crm_df['normalized_domain'] = crm_df['CRM Website'].astype(str).apply(simple_normalize_url)
+    crm_df['CRM Ort'] = crm_df['CRM Ort'].astype(str).str.lower().str.strip()
+    crm_df['CRM Land'] = crm_df['CRM Land'].astype(str).str.lower().str.strip()
+
+    matching_df['normalized_name'] = matching_df['CRM Name'].astype(str).apply(normalize_company_name)
+    matching_df['normalized_domain'] = matching_df['CRM Website'].astype(str).apply(simple_normalize_url)
+    matching_df['CRM Ort'] = matching_df['CRM Ort'].astype(str).str.lower().str.strip()
+    matching_df['CRM Land'] = matching_df['CRM Land'].astype(str).str.lower().str.strip()
+
+    # 3. Matching-Prozess
+    logging.info("Starte Matching-Prozess... Dies kann einige Zeit dauern.")
+    results = []
+    
+    for index, match_row in matching_df.iterrows():
+        best_score = 0
+        best_match_name = ""
+        
+        logging.info(f"Prüfe: {match_row['CRM Name']}...")
+
+        for _, crm_row in crm_df.iterrows():
+            score = calculate_similarity(match_row, crm_row)
+            if score > best_score:
+                best_score = score
+                best_match_name = crm_row['CRM Name']
+        
+        if best_score >= SCORE_THRESHOLD:
+            results.append({'Potenzieller Treffer im CRM': best_match_name, 'Ähnlichkeits-Score': best_score})
+        else:
+            results.append({'Potenzieller Treffer im CRM': '', 'Ähnlichkeits-Score': best_score})
+
+    # 4. Ergebnisse zusammenführen und schreiben
+    logging.info("Matching abgeschlossen. Schreibe Ergebnisse zurück ins Sheet...")
+    result_df = pd.DataFrame(results)
+    output_df = pd.concat([matching_df.reset_index(drop=True), result_df], axis=1)
+    
+    # Entferne die temporären normalisierten Spalten für eine saubere Ausgabe
+    output_df = output_df.drop(columns=['normalized_name', 'normalized_domain'])
+    
+    # Konvertiere DataFrame in Liste von Listen für den Upload
+    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 das Tabellenblatt '{MATCHING_SHEET_NAME}' geschrieben.")
+    else:
+        logging.error("FEHLER beim Schreiben der Ergebnisse ins Google Sheet.")
+
+if __name__ == "__main__":
+    main()