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
2025-08-01 12:03:57 +00:00
parent 89ccd86f83
commit 77852b8af1
1 changed files with 28 additions and 51 deletions
Download Patch File Download Diff File Expand all files Collapse all files

79
duplicate_checker.py
View File

@@ -1,4 +1,4 @@
# duplicate_checker.py (v2.2 - Multi-Key Blocking & optimiertes Scoring)
# duplicate_checker.py (v2.1 - mit Match-Basis-Anzeige)
import logging
import pandas as pd
@@ -6,60 +6,44 @@ from thefuzz import fuzz
from config import Config
from helpers import normalize_company_name, simple_normalize_url
from google_sheet_handler import GoogleSheetHandler
from collections import defaultdict
# --- Konfiguration ---
CRM_SHEET_NAME = "CRM_Accounts"
MATCHING_SHEET_NAME = "Matching_Accounts"
SCORE_THRESHOLD = 85 # Etwas höherer Schwellenwert für bessere Präzision
SCORE_THRESHOLD = 80 # Wird jetzt nur noch zur Hervorhebung genutzt, angezeigt werden alle
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."""
"""
Berechnet einen gewichteten Ähnlichkeits-Score und gibt die Details zurück.
"""
scores = {'name': 0, 'location': 0, 'domain': 0}
if record1.get('normalized_domain') and record1['normalized_domain'] != 'k.a.' and record1['normalized_domain'] == record2.get('normalized_domain'):
# 1. Website-Domain (stärkstes Signal)
if record1['normalized_domain'] and record1['normalized_domain'] != 'k.a.' and record1['normalized_domain'] == record2['normalized_domain']:
scores['domain'] = 100
# Höhere Gewichtung für den Namen, da die Website oft fehlt
if record1.get('normalized_name') and record2.get('normalized_name'):
scores['name'] = round(fuzz.token_set_ratio(record1['normalized_name'], record2['normalized_name']) * 0.85)
# 2. Firmenname (Fuzzy-Signal)
if record1['normalized_name'] and record2['normalized_name']:
scores['name'] = round(fuzz.token_set_ratio(record1['normalized_name'], record2['normalized_name']) * 0.7)
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'):
# 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']:
scores['location'] = 20
total_score = sum(scores.values())
return {'total': total_score, 'details': scores}
def create_blocking_keys(name):
"""Erstellt mehrere Blocking Keys für einen Namen, um die Sensitivität zu erhöhen."""
if not name:
return []
words = name.split()
keys = set()
# 1. Erstes Wort
if len(words) > 0:
keys.add(words[0])
# 2. Zweites Wort (falls vorhanden)
if len(words) > 1:
keys.add(words[1])
# 3. Erste 4 Buchstaben des ersten Wortes
if len(words) > 0 and len(words[0]) >= 4:
keys.add(words[0][:4])
return list(keys)
def main():
logging.info("Starte den Duplikats-Check (v2.2 mit Multi-Key Blocking)...")
"""Hauptfunktion zum Laden, Vergleichen und Schreiben der Daten."""
logging.info("Starte den Duplikats-Check (v2.1 mit Match-Basis)...")
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}'...")
@@ -69,7 +53,6 @@ def main():
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()
logging.info("Normalisiere Daten für den Vergleich...")
for df in [crm_df, matching_df]:
@@ -77,36 +60,28 @@ 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)
df['block_key'] = df['normalized_name'].apply(lambda x: x.split()[0] if x else None)
logging.info("Erstelle Index für CRM-Daten zur Beschleunigung...")
crm_index = defaultdict(list)
for record in crm_df.to_dict('records'):
for key in record['block_keys']:
crm_index[key].append(record)
crm_index = crm_df.groupby('block_key').apply(lambda x: x.to_dict('records')).to_dict()
logging.info("Starte Matching-Prozess...")
results = []
for match_record in matching_df.to_dict('records'):
for index, match_row in matching_df.iterrows():
best_score_info = {'total': 0, 'details': {'name': 0, 'location': 0, 'domain': 0}}
best_match_name = ""
logging.info(f"Prüfe: {match_record['CRM Name']}...")
logging.info(f"Prüfe {index + 1}/{len(matching_df)}: {match_row['CRM Name']}...")
candidate_pool = {}
for key in match_record['block_keys']:
for crm_record in crm_index.get(key, []):
candidate_pool[crm_record['CRM Name']] = crm_record
block_key = match_row['block_key']
candidates = crm_index.get(block_key, [])
if not candidate_pool:
logging.debug(" -> Keine Kandidaten im Index gefunden.")
for crm_record in candidate_pool.values():
score_info = calculate_similarity_details(match_record, crm_record)
for crm_row in candidates:
score_info = calculate_similarity_details(match_row, crm_row)
if score_info['total'] > best_score_info['total']:
best_score_info = score_info
best_match_name = crm_record['CRM Name']
best_match_name = crm_row['CRM Name']
results.append({
'Potenzieller Treffer im CRM': best_match_name if best_score_info['total'] >= SCORE_THRESHOLD else "",
@@ -119,7 +94,9 @@ def main():
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)
# Originale Spalten aus matching_df für die Ausgabe nehmen
original_cols = [col for col in ['CRM Name', 'CRM Website', 'CRM Ort', 'CRM Land'] if col in matching_df.columns]
output_df = pd.concat([matching_df[original_cols].reset_index(drop=True), result_df], axis=1)
data_to_write = [output_df.columns.values.tolist()] + output_df.values.tolist()