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 13:50:38 +00:00
parent 3febe14526
commit e58e493e38
1 changed files with 44 additions and 43 deletions
Download Patch File Download Diff File Expand all files Collapse all files

87
duplicate_checker.py
View File

@@ -6,64 +6,60 @@ from thefuzz import fuzz
from helpers import normalize_company_name, simple_normalize_url
from google_sheet_handler import GoogleSheetHandler
# duplicate_checker.py v2.7 (Logging-Setup Fix)
# Version: 2025-08-06_17-30
# duplicate_checker.py v2.8 (Match-Komponenten im Log)
# Version: 2025-08-06_17-50
# --- Konfiguration ---
CRM_SHEET_NAME = "CRM_Accounts"
MATCHING_SHEET_NAME = "Matching_Accounts"
SCORE_THRESHOLD = 80
LOG_DIR = "Log"
LOG_FILE = "duplicate_check_v2.7.log"
LOG_FILE = "duplicate_check_v2.8.log"
# --- Logging Setup ---
if not os.path.exists(LOG_DIR):
os.makedirs(LOG_DIR, exist_ok=True)
log_path = os.path.join(LOG_DIR, LOG_FILE)
# Clear existing handlers
root_logger = logging.getLogger()
root_logger.setLevel(logging.DEBUG)
for h in list(root_logger.handlers):
root_logger.removeHandler(h)
# Formatter
root = logging.getLogger()
root.setLevel(logging.DEBUG)
# Remove old handlers
for h in list(root.handlers):
root.removeHandler(h)
formatter = logging.Formatter("%(asctime)s - %(levelname)-8s - %(message)s")
# Console Handler - INFO+
# Console
ch = logging.StreamHandler(sys.stdout)
ch.setLevel(logging.INFO)
ch.setFormatter(formatter)
root_logger.addHandler(ch)
# File Handler - DEBUG+
root.addHandler(ch)
# File
fh = logging.FileHandler(log_path, mode='a', encoding='utf-8')
fh.setLevel(logging.DEBUG)
fh.setFormatter(formatter)
root_logger.addHandler(fh)
root.addHandler(fh)
logger = logging.getLogger(__name__)
logger.info(f"Logging to console and file: {log_path}")
logger.info("Starting duplicate_checker.py v2.7 | Version: 2025-08-06_17-30")
logger.info("Starting duplicate_checker.py v2.8 | Version: 2025-08-06_17-50")
def calculate_similarity(record1, record2):
total_score = 0
dom1 = record1.get('normalized_domain', '')
dom2 = record2.get('normalized_domain', '')
if dom1 and dom1 == dom2:
total_score += 100
name1 = record1.get('normalized_name', '')
name2 = record2.get('normalized_name', '')
if name1 and name2:
total_score += fuzz.token_set_ratio(name1, name2) * 0.7
if record1.get('CRM Ort') == record2.get('CRM Ort') and record1.get('CRM Land') == record2.get('CRM Land'):
total_score += 20
return round(total_score)
def calculate_similarity_components(r1, r2):
"""Gibt einzelne Komponenten und Gesamt-Score zurück."""
# Domain
dom1 = r1.get('normalized_domain', '')
dom2 = r2.get('normalized_domain', '')
domain_match = 1 if dom1 and dom1 == dom2 else 0
# Name
name1 = r1.get('normalized_name', '')
name2 = r2.get('normalized_name', '')
name_score = fuzz.token_set_ratio(name1, name2) if name1 and name2 else 0
# Ort+Land
loc_match = 1 if (r1.get('CRM Ort') == r2.get('CRM Ort') and r1.get('CRM Land') == r2.get('CRM Land')) else 0
# Gewichte
total = domain_match * 100 + name_score * 0.7 + loc_match * 20
return round(total), domain_match, round(name_score,1), loc_match
def main():
logger.info("Starte Duplikats-Check v2.7")
logger.info("Starte Duplikats-Check v2.8 (Match-Komponenten im Log)")
try:
sheet_handler = GoogleSheetHandler()
logger.info("GoogleSheetHandler initialisiert")
@@ -71,7 +67,7 @@ def main():
logger.critical(f"Init GoogleSheetHandler fehlgeschlagen: {e}")
sys.exit(1)
# Load data
# Daten laden
logger.info(f"Lade CRM-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:
@@ -86,7 +82,7 @@ def main():
return
logger.info(f"{len(match_df)} Matching-Datensätze geladen")
# Normalize & blocking key
# Normalisierung & Blocking-Key
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)
@@ -113,18 +109,23 @@ def main():
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})
results.append({'Potenzieller Treffer im CRM':'', 'Ähnlichkeits-Score':0})
continue
scored = [(crow['CRM Name'], calculate_similarity(mrow, crow)) for crow in candidates]
scored = []
for crow in candidates:
score, dm, ns, lm = calculate_similarity_components(mrow, crow)
scored.append((crow['CRM Name'], score, dm, ns, lm))
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])
# Log Top3 mit Komponenten
for name, sc, dm, ns, lm in top3:
logger.debug(f" Kandidat: {name}, Score={sc}, Domain={dm}, Name={ns}, Ort={lm}")
best_name, best_score, best_dm, best_ns, best_lm = 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}' Score={best_score}")
results.append({'Potenzieller Treffer im CRM':best_name, 'Ähnlichkeits-Score':best_score})
logger.info(f" --> Match: '{best_name}' Score={best_score} (Dom={best_dm}, Name={best_ns}, Ort={best_lm})")
else:
results.append({'Potenzieller Treffer im CRM': best_name or '', 'Ähnlichkeits-Score': best_score})
logger.info(f" --> Kein Match (Score {best_score})")
results.append({'Potenzieller Treffer im CRM':'', 'Ähnlichkeits-Score':best_score})
logger.info(f" --> Kein Match (Score={best_score}, Dom={best_dm}, Name={best_ns}, Ort={best_lm})")
# Write back
logger.info("Schreibe Ergebnisse zurück ins Sheet...")