123 lines
5.4 KiB
Python
123 lines
5.4 KiB
Python
# duplicate_checker.py (v3.0 - Back to Basics: Optimized Brute-Force)
|
|
|
|
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
|
|
import time
|
|
|
|
# --- Konfiguration ---
|
|
CRM_SHEET_NAME = "CRM_Accounts"
|
|
MATCHING_SHEET_NAME = "Matching_Accounts"
|
|
SCORE_THRESHOLD = 85 # Treffer unter diesem Wert werden nicht als "potenzieller Treffer" angezeigt
|
|
|
|
# WICHTIG: Logging Setup für detaillierte Ausgaben
|
|
logging.basicConfig(level=logging.DEBUG, format='%(asctime)s - %(levelname)-8s - %(name)s - %(message)s')
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
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, 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 (hohe 85% Gewichtung)
|
|
if record1.get('normalized_name') and record2.get('normalized_name'):
|
|
# token_set_ratio ist robust gegen zusätzliche Wörter wie "Holding" oder "Gruppe"
|
|
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
|
|
|
|
total_score = sum(scores.values())
|
|
return {'total': total_score, 'details': scores}
|
|
|
|
|
|
def main():
|
|
start_time = time.time()
|
|
logger.info("Starte den Duplikats-Check (v3.0 - Back to Basics)...")
|
|
|
|
# ... (Initialisierung und Laden der Daten bleibt gleich) ...
|
|
try:
|
|
sheet_handler = GoogleSheetHandler()
|
|
except Exception as e:
|
|
logger.critical(f"FEHLER bei Initialisierung: {e}")
|
|
return
|
|
|
|
logger.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
|
|
|
|
logger.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()
|
|
|
|
logger.info("Normalisiere Daten für den Vergleich...")
|
|
for df in [crm_df, matching_df]:
|
|
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()
|
|
|
|
crm_records = crm_df.to_dict('records')
|
|
matching_records = matching_df.to_dict('records')
|
|
|
|
logger.info(f"Starte Matching-Prozess: {len(matching_records)} Einträge werden mit {len(crm_records)} CRM-Einträgen verglichen...")
|
|
results = []
|
|
|
|
for i, match_record in enumerate(matching_records):
|
|
best_score_info = {'total': -1, 'details': {'name': 0, 'location': 0, 'domain': 0}}
|
|
best_match_name = ""
|
|
|
|
logger.info(f"--- Prüfe {i + 1}/{len(matching_records)}: '{match_record.get('CRM Name', 'N/A')}' ---")
|
|
|
|
# BRUTE-FORCE: Vergleiche mit jedem einzelnen CRM-Eintrag
|
|
for crm_record in crm_records:
|
|
score_info = calculate_similarity_details(match_record, crm_record)
|
|
|
|
# Logge jeden interessanten Vergleich (Score > 60)
|
|
if score_info['total'] > 60:
|
|
logger.debug(f" - Kandidat: '{crm_record.get('CRM Name', 'N/A')}' -> Score: {score_info['total']} (Details: {score_info['details']})")
|
|
|
|
if score_info['total'] > best_score_info['total']:
|
|
best_score_info = score_info
|
|
best_match_name = crm_record.get('CRM Name', 'N/A')
|
|
|
|
logger.info(f" --> Bester Treffer: '{best_match_name}' mit Score {best_score_info['total']}")
|
|
|
|
results.append({
|
|
'Potenzieller Treffer im CRM': best_match_name if best_score_info['total'] >= SCORE_THRESHOLD else "",
|
|
'Score (Gesamt)': best_score_info['total'],
|
|
'Score (Name)': best_score_info['details']['name'],
|
|
'Bonus (Standort)': best_score_info['details']['location'],
|
|
'Bonus (Domain)': best_score_info['details']['domain']
|
|
})
|
|
|
|
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)
|
|
|
|
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.")
|
|
else:
|
|
logging.error("FEHLER beim Schreiben der Ergebnisse ins Google Sheet.")
|
|
|
|
end_time = time.time()
|
|
logger.info(f"Gesamtdauer des Duplikats-Checks: {end_time - start_time:.2f} Sekunden.")
|
|
|
|
if __name__ == "__main__":
|
|
main() |