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 08:31:02 +00:00
parent 9cc291d568
commit 7c9ee2f799
1 changed files with 27 additions and 81 deletions
Download Patch File Download Diff File Expand all files Collapse all files

108
duplicate_checker.py
View File

@@ -1,64 +1,39 @@
# duplicate_checker.py (v2.8 - Vollständiges Logging & Maximum Debugging)
# 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, create_log_filename
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
SCORE_THRESHOLD = 85 # Treffer unter diesem Wert werden nicht als "potenzieller Treffer" angezeigt
# --- WICHTIG: VOLLSTÄNDIGES LOGGING SETUP ---
LOG_LEVEL = logging.DEBUG if Config.DEBUG else logging.INFO
LOG_FORMAT = '%(asctime)s - %(levelname)-8s - %(name)s - %(message)s'
# WICHTIG: Logging Setup für detaillierte Ausgaben
logging.basicConfig(level=logging.DEBUG, format='%(asctime)s - %(levelname)-8s - %(name)s - %(message)s')
logger = logging.getLogger(__name__)
# Root-Logger konfigurieren
root_logger = logging.getLogger()
root_logger.setLevel(LOG_LEVEL)
# Bestehende Handler entfernen, um Dopplung zu vermeiden
for handler in root_logger.handlers[:]:
root_logger.removeHandler(handler)
# Konsole-Handler hinzufügen
stream_handler = logging.StreamHandler()
stream_handler.setFormatter(logging.Formatter(LOG_FORMAT))
root_logger.addHandler(stream_handler)
# File-Handler hinzufügen
log_file_path = create_log_filename("duplicate_check")
if log_file_path:
file_handler = logging.FileHandler(log_file_path, mode='a', encoding='utf-8')
file_handler.setFormatter(logging.Formatter(LOG_FORMAT))
root_logger.addHandler(file_handler)
logger = logging.getLogger(__name__) # Logger für dieses Modul holen
# --- Der eigentliche Code beginnt hier ---
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'
}
def calculate_similarity_details(record1, record2):
"""Berechnet einen gewichteten Ähnlichkeits-Score und gibt die Details zurück."""
"""
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
@@ -66,18 +41,12 @@ def calculate_similarity_details(record1, record2):
total_score = sum(scores.values())
return {'total': total_score, 'details': scores}
def create_blocking_keys(name):
"""Erstellt Blocking Keys aus allen 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)
def main():
start_time = time.time()
logger.info(f"===== Skript gestartet: Modus 'duplicate_check' v2.8 =====")
logger.info(f"Logdatei: {log_file_path}")
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:
@@ -99,54 +68,33 @@ 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)
logger.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)
matching_records = matching_df.to_dict('records')
logger.info("Starte Matching-Prozess...")
logger.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': -1, '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')}]")
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
logger.info(f"--- Prüfe {i + 1}/{len(matching_records)}: '{match_record.get('CRM Name', 'N/A')}' ---")
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 candidate_pool.values():
# BRUTE-FORCE: Vergleiche mit jedem einzelnen CRM-Eintrag
for crm_record in crm_records:
score_info = calculate_similarity_details(match_record, crm_record)
if score_info['total'] > 50: # Logge nur Vergleiche mit einem minimalen Score, um das Log nicht zu überfluten
logger.debug(f" - Kandidat: '{crm_record.get('CRM Name', 'N/A')}' -> Score: {score_info['total']} (Details: {score_info['details']})")
# 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" --> Neuer bester Treffer: '{best_match_name}' mit Score {best_score_info['total']}")
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'],
@@ -170,8 +118,6 @@ def main():
end_time = time.time()
logger.info(f"Gesamtdauer des Duplikats-Checks: {end_time - start_time:.2f} Sekunden.")
logger.info(f"===== Skript beendet: Modus 'duplicate_check' =====")
if __name__ == "__main__":
main()