Floke/Brancheneinstufung2
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

duplicate_checker.py aktualisiert

Browse Source
This commit is contained in:
Floke
2025-08-03 08:21:36 +00:00
parent c0cade7a21
commit 40de811730
1 changed files with 35 additions and 49 deletions
Download Patch File Download Diff File Expand all files Collapse all files

84
duplicate_checker.py
View File

@@ -1,4 +1,4 @@
# duplicate_checker.py (v2.7 - Maximum Logging)
# duplicate_checker.py (v2.3 - Intelligent Blocking)
import logging
import pandas as pd
@@ -12,19 +12,16 @@ import time
# --- Konfiguration ---
CRM_SHEET_NAME = "CRM_Accounts"
MATCHING_SHEET_NAME = "Matching_Accounts"
SCORE_THRESHOLD = 85
# WICHTIG: Logging auf DEBUG-Level setzen, um alles zu sehen
logging.basicConfig(level=logging.DEBUG, format='%(asctime)s - %(levelname)-8s - %(name)s - %(message)s')
logger = logging.getLogger(__name__)
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', 'und',
'germany', 'deutschland', 'gbr', 'mbh', 'company', 'limited', 'logistics',
'construction', 'products', 'group', 'b-v'
'technik', 'service', 'services', 'solutions', 'management', 'international'
}
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
def calculate_similarity_details(record1, record2):
"""Berechnet einen gewichteten Ähnlichkeits-Score und gibt die Details zurück."""
scores = {'name': 0, 'location': 0, 'domain': 0}
@@ -43,32 +40,43 @@ def calculate_similarity_details(record1, record2):
return {'total': total_score, 'details': scores}
def create_blocking_keys(name):
"""Erstellt Blocking Keys aus allen signifikanten Wörtern eines Namens."""
"""Erstellt mehrere Blocking Keys aus den signifikanten Wörtern eines Namens."""
if not name:
return []
significant_words = {word for word in name.split() if word not in BLOCKING_STOP_WORDS and len(word) >= 3}
return list(significant_words)
# 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():
start_time = time.time()
logger.info("Starte den Duplikats-Check (v2.7 - Maximum Logging)...")
logging.info("Starte den Duplikats-Check (v2.3 mit Intelligent Blocking)...")
# ... (Initialisierung des GoogleSheetHandler bleibt gleich) ...
try:
sheet_handler = GoogleSheetHandler()
except Exception as e:
logger.critical(f"FEHLER bei Initialisierung: {e}")
logging.critical(f"FEHLER bei Initialisierung: {e}")
return
logger.info(f"Lade Master-Daten aus '{CRM_SHEET_NAME}'...")
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
logger.info(f"Lade zu prüfende Daten aus '{MATCHING_SHEET_NAME}'...")
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()
logger.info("Normalisiere Daten für den Vergleich...")
logging.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)
@@ -76,53 +84,33 @@ def main():
df['CRM Land'] = df['CRM Land'].astype(str).str.lower().str.strip()
df['block_keys'] = df['normalized_name'].apply(create_blocking_keys)
logger.info("Erstelle Index für CRM-Daten zur Beschleunigung...")
logging.info("Erstelle Index für CRM-Daten zur Beschleunigung...")
crm_index = defaultdict(list)
crm_records = crm_df.to_dict('records')
for record in crm_records:
for key in record['block_keys']:
crm_index[key].append(record)
logger.info("Starte Matching-Prozess...")
logging.info("Starte Matching-Prozess...")
results = []
for match_record in matching_df.to_dict('records'):
best_score_info = {'total': -1, 'details': {'name': 0, 'location': 0, 'domain': 0}}
best_score_info = {'total': 0, 'details': {'name': 0, 'location': 0, 'domain': 0}}
best_match_name = ""
logger.info(f"--- Prüfe: '{match_record.get('CRM Name', 'N/A')}' ---")
logger.debug(f" [Normalisiert: '{match_record.get('normalized_name')}', Domain: '{match_record.get('normalized_domain')}', Keys: {match_record.get('block_keys')}]")
logging.info(f"Prüfe: {match_record['CRM Name']}...")
candidate_pool = {}
for key in match_record['block_keys']:
candidates_from_key = crm_index.get(key, [])
if candidates_from_key:
logger.debug(f" -> Block-Key '{key}' gefunden. {len(candidates_from_key)} Kandidaten hinzugefügt.")
for crm_record in candidates_from_key:
candidate_pool[crm_record['CRM Name']] = crm_record
if not candidate_pool:
logger.debug(" -> Keine Kandidaten im Index gefunden. Überspringe Vergleich.")
results.append({
'Potenzieller Treffer im CRM': "", 'Score (Gesamt)': 0, 'Score (Name)': 0,
'Bonus (Standort)': 0, 'Bonus (Domain)': 0
})
continue
logger.debug(f" -> Vergleiche mit insgesamt {len(candidate_pool)} einzigartigen Kandidaten.")
for crm_record in crm_index.get(key, []):
candidate_pool[crm_record['CRM Name']] = crm_record
for crm_record in candidate_pool.values():
score_info = calculate_similarity_details(match_record, crm_record)
# Logge jeden einzelnen Vergleich, der einen Score > 0 hat
if score_info['total'] > 0:
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" --> Neuer bester Treffer: '{best_match_name}' mit Score {best_score_info['total']}")
best_match_name = crm_record['CRM Name']
results.append({
'Potenzieller Treffer im CRM': best_match_name if best_score_info['total'] >= SCORE_THRESHOLD else "",
'Score (Gesamt)': best_score_info['total'],
@@ -134,6 +122,7 @@ 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()
@@ -144,8 +133,5 @@ 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()