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 12:50:12 +00:00
parent 4a015844f7
commit 1a84e10c6c
1 changed files with 55 additions and 60 deletions
Download Patch File Download Diff File Expand all files Collapse all files

115
duplicate_checker.py
View File

@@ -7,125 +7,120 @@ from thefuzz import fuzz
from helpers import normalize_company_name, simple_normalize_url from helpers import normalize_company_name, simple_normalize_url
from google_sheet_handler import GoogleSheetHandler from google_sheet_handler import GoogleSheetHandler
# duplicate_checker.py v2.1 (mit erweitertem Logging und Datum im Dateinamen) # duplicate_checker.py v2.2 (Domain-Fallback & Name-Partial-Bonus für bessere Matches)
# Version: 2025-08-06_12-33 # Version: 2025-08-06_15-20
# --- Konfiguration --- # --- Konfiguration ---
CRM_SHEET_NAME = "CRM_Accounts" CRM_SHEET_NAME = "CRM_Accounts"
MATCHING_SHEET_NAME = "Matching_Accounts" MATCHING_SHEET_NAME = "Matching_Accounts"
SCORE_THRESHOLD = 80 # Score ab hier gilt als Match SCORE_THRESHOLD = 80
LOG_DIR = "Log" LOG_DIR = "Log"
# --- Logging Setup mit Datum im Dateinamen --- # --- Logging Setup ---
if not os.path.exists(LOG_DIR): if not os.path.exists(LOG_DIR):
os.makedirs(LOG_DIR, exist_ok=True) os.makedirs(LOG_DIR, exist_ok=True)
now = datetime.now().strftime('%Y-%m-%d_%H-%M') now = datetime.now().strftime('%Y-%m-%d_%H-%M')
log_path = os.path.join(LOG_DIR, f"{now}_Duplicate.log") log_path = os.path.join(LOG_DIR, f"{now}_Duplicate.log")
logger = logging.getLogger(__name__) logger = logging.getLogger(__name__)
logger.setLevel(logging.DEBUG) logger.setLevel(logging.DEBUG)
# Console
# Console-Handler (INFO+)
ch = logging.StreamHandler() ch = logging.StreamHandler()
ch.setLevel(logging.INFO) ch.setLevel(logging.INFO)
ch.setFormatter(logging.Formatter("%(asctime)s - %(levelname)-8s - %(message)s")) ch.setFormatter(logging.Formatter("%(asctime)s - %(levelname)-8s - %(message)s"))
logger.addHandler(ch) logger.addHandler(ch)
# File
# File-Handler (DEBUG+)
fh = logging.FileHandler(log_path, mode='a', encoding='utf-8') fh = logging.FileHandler(log_path, mode='a', encoding='utf-8')
fh.setLevel(logging.DEBUG) fh.setLevel(logging.DEBUG)
fh.setFormatter(logging.Formatter("%(asctime)s - %(levelname)-8s - %(name)s - %(message)s")) fh.setFormatter(logging.Formatter("%(asctime)s - %(levelname)-8s - %(name)s - %(message)s"))
logger.addHandler(fh) logger.addHandler(fh)
logger.info(f"Logging in Datei: {log_path}") logger.info(f"Logging in Datei: {log_path}")
logger.info("Version: duplicate_checker.py v2.2 (Domain-Fallback & Partial-Bonus) | Build: 2025-08-06_15-20")
def calculate_similarity(record1, record2): def calculate_similarity(record1, record2):
"""Berechnet gewichteten Ähnlichkeits-Score zwischen zwei Datensätzen.""" """Gewichteter Score mit Domain-Fallback und Partial-Name-Bonus."""
total = 0 total = 0
# Domain exact match über normalisierte Domain # Domain-Exact
dom1 = record1.get('normalized_domain', '') dom1 = record1.get('normalized_domain','')
dom2 = record2.get('normalized_domain', '') dom2 = record2.get('normalized_domain','')
if dom1 and dom1 == dom2: if dom1 and dom1 == dom2:
total += 100 total += 100
# Name fuzzy (Token-Set Ratio) # Domain-Fallback: Substring
name1 = record1.get('normalized_name', '') elif dom1 and dom2 and (dom1 in dom2 or dom2 in dom1):
name2 = record2.get('normalized_name', '') total += 50
# Name-Fuzzy Token-Set
name1 = record1.get('normalized_name','')
name2 = record2.get('normalized_name','')
if name1 and name2: if name1 and name2:
name_score = fuzz.token_set_ratio(name1, name2) ts = fuzz.token_set_ratio(name1, name2)
total += name_score * 0.7 total += ts * 0.7
# Ort+Land exact # Partial match bonus für kurze/abweichende Namen
pr = fuzz.partial_ratio(name1, name2)
if pr >= 85:
total += 20
# Ort+Land exakt
if record1.get('CRM Ort') == record2.get('CRM Ort') and record1.get('CRM Land') == record2.get('CRM Land'): if record1.get('CRM Ort') == record2.get('CRM Ort') and record1.get('CRM Land') == record2.get('CRM Land'):
total += 20 total += 20
return round(total) return round(total)
def main(): def main():
logger.info("Starte Duplikats-Check (v2.0 mit Kern-Syntax nach Entwurf)") logger.info("Starte Duplikats-Check v2.2 mit Domain-Fallback & Partial-Bonus")
try: try:
sheet = GoogleSheetHandler() sheet = GoogleSheetHandler()
logger.info("GoogleSheetHandler initialisiert") logger.info("GoogleSheetHandler initialisiert")
except Exception as e: except Exception as e:
logger.critical(f"FEHLER beim Init GoogleSheetHandler: {e}") logger.critical(f"FEHLER Init GoogleSheetHandler: {e}")
sys.exit(1) sys.exit(1)
# Daten einlesen
crm_df = sheet.get_sheet_as_dataframe(CRM_SHEET_NAME) crm_df = sheet.get_sheet_as_dataframe(CRM_SHEET_NAME)
match_df = sheet.get_sheet_as_dataframe(MATCHING_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: if crm_df is None or crm_df.empty or match_df is None or match_df.empty:
logger.critical("CRM- oder Matching-Daten fehlen. Abbruch.") logger.critical("Daten fehlen. Abbruch.")
return return
logger.info(f"{len(crm_df)} CRM-Datensätze, {len(match_df)} Matching-Datensätze geladen") logger.info(f"{len(crm_df)} CRM-Zeilen, {len(match_df)} Matching-Zeilen geladen")
# Normalisierung und Blocking-Key # Norm & Block-Key
for df, label in [(crm_df, 'CRM'), (match_df, 'Matching')]: for df, label in [(crm_df,'CRM'),(match_df,'Matching')]:
df['normalized_name'] = df['CRM Name'].astype(str).apply(normalize_company_name) df['normalized_name'] = df['CRM Name'].astype(str).apply(normalize_company_name)
df['normalized_domain'] = df['CRM Website'].astype(str).apply(simple_normalize_url) 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 Ort'] = df['CRM Ort'].astype(str).str.lower().str.strip()
df['CRM Land'] = df['CRM Land'].astype(str).str.lower().str.strip() df['CRM Land'] = df['CRM Land'].astype(str).str.lower().str.strip()
df['block_key'] = df['normalized_name'].apply(lambda x: x.split()[0] if x else None) df['block_key'] = df['normalized_name'].apply(lambda x: x.split()[0] if x else None)
logger.debug(f"{label}-Beispiel nach Normalisierung: {df.iloc[0][['normalized_name','normalized_domain','block_key']].to_dict()}") logger.debug(f"{label}-Sample: {df.iloc[0][['normalized_name','normalized_domain','block_key']].to_dict()}")
# Blocking-Index # Build index
crm_index = {} crm_index = {}
for idx, row in crm_df.iterrows(): for idx, row in crm_df.iterrows():
key = row['block_key'] key = row['block_key']
if key: if key:
crm_index.setdefault(key, []).append(row) crm_index.setdefault(key, []).append(row)
logger.info(f"Blocking-Index erstellt: {len(crm_index)} Keys") logger.info(f"Blocking-Index mit {len(crm_index)} Keys erstellt")
# Matching mit Log relevanter Kandidaten
results = [] results = []
total = len(match_df) total = len(match_df)
for i, mrow in match_df.iterrows(): for i, mrow in match_df.iterrows():
key = mrow['block_key'] key = mrow['block_key']
candidates = crm_index.get(key, []) cands = crm_index.get(key, [])
logger.info(f"Prüfe {i+1}/{total}: '{mrow['CRM Name']}' (Key='{key}') -> {len(candidates)} Kandidaten") logger.info(f"Prüfe {i+1}/{total}: '{mrow['CRM Name']}' (Key='{key}') -> {len(cands)} Kandidaten")
if not candidates: if not cands:
results.append({'Match': '', 'Score': 0}) results.append({'Match':'','Score':0}); continue
continue scored = [(crow['CRM Name'], calculate_similarity(mrow,crow)) for crow in cands]
# Scores sammeln top3 = sorted(scored, key=lambda x:x[1], reverse=True)[:3]
scored = [(crow['CRM Name'], calculate_similarity(mrow, crow)) for crow in candidates] logger.debug(f" Top3: {top3}")
# Top 3 relevante Kandidaten loggen best, score = max(scored, key=lambda x:x[1])
top3 = sorted(scored, key=lambda x: x[1], reverse=True)[:3] if score >= SCORE_THRESHOLD:
logger.debug(f" Top 3 Kandidaten: {top3}") results.append({'Match':best,'Score':score})
# Besten Treffer wählen logger.info(f" --> Match: '{best}' ({score})")
best_name, best_score = max(scored, key=lambda x: x[1])
if best_score >= SCORE_THRESHOLD:
results.append({'Match': best_name, 'Score': best_score})
logger.info(f" --> Match: '{best_name}' mit Score {best_score}")
else: else:
results.append({'Match': '', 'Score': best_score}) results.append({'Match':'','Score':score})
logger.info(f" --> Kein Match (höchster Score {best_score})") logger.info(f" --> Kein Match (Score {score})")
# Ergebnisse zurück ins Sheet
out = pd.DataFrame(results) out = pd.DataFrame(results)
output = pd.concat([match_df[['CRM Name','CRM Website','CRM Ort','CRM Land']].reset_index(drop=True), out], axis=1) output = pd.concat([match_df[['CRM Name','CRM Website','CRM Ort','CRM Land']].reset_index(drop=True), out], axis=1)
data = [output.columns.tolist()] + output.values.tolist() data = [output.columns.tolist()] + output.values.tolist()
ok = sheet.clear_and_write_data(MATCHING_SHEET_NAME, data) ok = sheet.clear_and_write_data(MATCHING_SHEET_NAME, data)
if ok: if ok: logger.info("Ergebnisse geschrieben")
logger.info("Ergebnisse erfolgreich geschrieben") else: logger.error("Fehler beim Schreiben ins Sheet")
else:
logger.error("Fehler beim Schreiben ins Google Sheet")
if __name__ == '__main__': if __name__=='__main__':
main() main()