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
2025-08-06 13:35:25 +00:00
parent 4f6d51df56
commit 63d014b057
1 changed files with 62 additions and 55 deletions
Download Patch File Download Diff File Expand all files Collapse all files

117
duplicate_checker.py
View File

@@ -2,83 +2,86 @@ import os
import sys
import logging
import pandas as pd
from datetime import datetime
from thefuzz import fuzz
from helpers import normalize_company_name, simple_normalize_url
from google_sheet_handler import GoogleSheetHandler
# duplicate_checker.py v2.5 (Original v2.0-Logik + Logging enhancements)
# Version: 2025-08-06_17-00
# Version: 2025-08-06_16-30
# duplicate_checker.py v2.6 (Original v2.0 Kern + Logging)
# Version: 2025-08-06_17-15
# --- Konfiguration ---
CRM_SHEET_NAME = "CRM_Accounts"
MATCHING_SHEET_NAME = "Matching_Accounts"
SCORE_THRESHOLD = 80 # Schwelle für automatisches Match
SCORE_THRESHOLD = 80
LOG_DIR = "Log"
LOG_FILE = "duplicate_check_v2.6.log"
# --- Logging Setup mit Datum im Dateinamen ---
# --- Logging Setup ---
if not os.path.exists(LOG_DIR):
os.makedirs(LOG_DIR, exist_ok=True)
now = datetime.now().strftime('%Y-%m-%d_%H-%M')
log_path = os.path.join(LOG_DIR, f"{now}_Duplicate_v2.4.log")
log_path = os.path.join(LOG_DIR, LOG_FILE)
# Global logging config
logging.basicConfig(
level=logging.DEBUG,
format="%(asctime)s - %(levelname)-8s - %(message)s",
handlers=[
logging.StreamHandler(sys.stdout),
logging.FileHandler(log_path, mode='a', encoding='utf-8')
]
)
logger = logging.getLogger(__name__)
logger.setLevel(logging.DEBUG)
# Console-Handler (INFO+)
ch = logging.StreamHandler()
ch.setLevel(logging.INFO)
ch.setFormatter(logging.Formatter("%(asctime)s - %(levelname)-8s - %(message)s"))
logger.addHandler(ch)
# File-Handler (DEBUG+)
fh = logging.FileHandler(log_path, mode='a', encoding='utf-8')
fh.setLevel(logging.DEBUG)
fh.setFormatter(logging.Formatter("%(asctime)s - %(levelname)-8s - %(name)s - %(message)s"))
logger.addHandler(fh)
logger.info(f"Logging in Datei: {log_path}")
logger.info("Version: duplicate_checker.py v2.4 (root-domain match via tldextract) | Build: 2025-08-06_16-30")
logger.info(f"Starting duplicate_checker.py v2.6 | Log: {log_path}")
def calculate_similarity(record1, record2):
"""Berechnet den v2.0-Score: Domain exact=100, Name*0.7, Ort+Land=20."""
"""Berechnet einen gewichteten Ähnlichkeits-Score (0–190)."""
total_score = 0
# Domain exact match
# Domain-Exact
dom1 = record1.get('normalized_domain', '')
dom2 = record2.get('normalized_domain', '')
if dom1 and dom1 == dom2:
total_score += 100
# Name fuzzy token_set
# Name-Fuzzy
name1 = record1.get('normalized_name', '')
name2 = record2.get('normalized_name', '')
if name1 and name2:
sim = fuzz.token_set_ratio(name1, name2)
total_score += sim * 0.7
name_similarity = fuzz.token_set_ratio(name1, name2)
total_score += name_similarity * 0.7
# Ort+Land exact
if record1.get('CRM Ort') == record2.get('CRM Ort') and record1.get('CRM Land') == record2.get('CRM Land'):
total_score += 20
if record1.get('CRM Ort') and record1.get('CRM Ort') == record2.get('CRM Ort'):
if record1.get('CRM Land') and record1.get('CRM Land') == record2.get('CRM Land'):
total_score += 20
return round(total_score)
def main():
logger.info("Starte Duplikats-Check v2.4 (root-domain match)")
logger.info("Starte Duplikats-Check v2.6 (Original v2.0 Kern mit Logging)")
try:
sheet = GoogleSheetHandler()
sheet_handler = GoogleSheetHandler()
logger.info("GoogleSheetHandler initialisiert")
except Exception as e:
logger.critical(f"FEHLER Init GoogleSheetHandler: {e}")
sys.exit(1)
# Daten laden
crm_df = sheet.get_sheet_as_dataframe(CRM_SHEET_NAME)
match_df = sheet.get_sheet_as_dataframe(MATCHING_SHEET_NAME)
if crm_df is None or crm_df.empty or match_df is None or match_df.empty:
logger.critical("Daten fehlen. Abbruch.")
# Load data
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:
logger.critical(f"Keine Daten in '{CRM_SHEET_NAME}'. Abbruch.")
return
logger.info(f"{len(crm_df)} CRM- und {len(match_df)} Matching-Zeilen geladen")
logger.info(f"{len(crm_df)} CRM-Datensätze geladen")
# Normalisierung & Blocking-Key
logger.info(f"Lade Matching-Daten aus '{MATCHING_SHEET_NAME}'...")
match_df = sheet_handler.get_sheet_as_dataframe(MATCHING_SHEET_NAME)
if match_df is None or match_df.empty:
logger.critical(f"Keine Daten in '{MATCHING_SHEET_NAME}'. Abbruch.")
return
logger.info(f"{len(match_df)} Matching-Datensätze geladen")
# Normalize
logger.info("Normalisiere Daten...")
for df, label in [(crm_df, 'CRM'), (match_df, 'Matching')]:
df['normalized_name'] = df['CRM Name'].astype(str).apply(normalize_company_name)
df['normalized_domain'] = df['CRM Website'].astype(str).apply(simple_normalize_url)
@@ -87,42 +90,46 @@ def main():
df['block_key'] = df['normalized_name'].apply(lambda x: x.split()[0] if x else None)
logger.debug(f"{label}-Sample: {df.iloc[0][['normalized_name','normalized_domain','block_key']].to_dict()}")
# Blocking-Index bauen
# Build blocking index
logger.info("Erstelle Blocking-Index...")
crm_index = {}
for idx, row in crm_df.iterrows():
key = row['block_key']
if key:
crm_index.setdefault(key, []).append(row)
logger.info(f"Blocking-Index mit {len(crm_index)} Keys erstellt")
logger.info(f"Blocking-Index erstellt mit {len(crm_index)} Keys")
# Matching mit Top-3-Log
# Matching
logger.info("Starte Matching-Prozess...")
results = []
total = len(match_df)
for i, mrow in match_df.iterrows():
key = mrow['block_key']
cands = crm_index.get(key, [])
logger.info(f"Prüfe {i+1}/{total}: '{mrow['CRM Name']}' (Key='{key}') -> {len(cands)} Kandidaten")
if not cands:
candidates = crm_index.get(key, [])
logger.info(f"Prüfe {i+1}/{total}: '{mrow['CRM Name']}' -> {len(candidates)} Kandidaten")
if not candidates:
results.append({'Potenzieller Treffer im CRM': '', 'Ähnlichkeits-Score': 0})
continue
# Score für Kandidaten
scored = [(crow['CRM Name'], calculate_similarity(mrow, crow)) for crow in cands]
scored = [(crow['CRM Name'], calculate_similarity(mrow, crow)) for crow in candidates]
# Log Top-3 only
top3 = sorted(scored, key=lambda x: x[1], reverse=True)[:3]
logger.debug(f" Top3 Kandidaten: {top3}")
best_name, best_score = max(scored, key=lambda x: x[1])
if best_score >= SCORE_THRESHOLD:
results.append({'Potenzieller Treffer im CRM': best_name, 'Ähnlichkeits-Score': best_score})
logger.info(f" --> Match: '{best_name}' mit Score {best_score}")
logger.info(f" --> Match: '{best_name}' Score={best_score}")
else:
results.append({'Potenzieller Treffer im CRM': '', 'Ähnlichkeits-Score': best_score})
results.append({'Potenzieller Treffer im CRM': best_name if best_name else '', 'Ähnlichkeits-Score': best_score})
logger.info(f" --> Kein Match (höchster Score {best_score})")
# Ergebnisse zurückschreiben
out_df = pd.DataFrame(results)
output = pd.concat([match_df[['CRM Name','CRM Website','CRM Ort','CRM Land']].reset_index(drop=True), out_df], axis=1)
data = [output.columns.tolist()] + output.values.tolist()
ok = sheet.clear_and_write_data(MATCHING_SHEET_NAME, data)
if ok:
# Write back
logger.info("Schreibe Ergebnisse zurück ins Sheet...")
result_df = pd.DataFrame(results)
output_df = match_df[['CRM Name','CRM Website','CRM Ort','CRM Land']].copy()
output_df = pd.concat([output_df.reset_index(drop=True), result_df], axis=1)
data_to_write = [output_df.columns.tolist()] + output_df.values.tolist()
success = sheet_handler.clear_and_write_data(MATCHING_SHEET_NAME, data_to_write)
if success:
logger.info("Ergebnisse erfolgreich geschrieben")
else:
logger.error("Fehler beim Schreiben ins Google Sheet")