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
2025-08-05 14:36:25 +00:00
parent 012e091ed0
commit 7adba270ed
1 changed files with 43 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files

78
duplicate_checker.py
View File

@@ -16,10 +16,8 @@ WEIGHTS = {
} }
# --- Logging Setup --- # --- Logging Setup ---
logging.basicConfig( LOG_FORMAT = '%(asctime)s - %(levelname)-8s - %(name)s - %(message)s'
level=logging.DEBUG, logging.basicConfig(level=logging.DEBUG, format=LOG_FORMAT)
format='%(asctime)s - %(levelname)-8s - %(message)s'
)
logger = logging.getLogger(__name__) logger = logging.getLogger(__name__)
# --- Hilfsfunktionen --- # --- Hilfsfunktionen ---
@@ -43,20 +41,37 @@ def normalize_domain(url: str) -> str:
def main(): def main():
logger.info("Starte Duplikat-Check mit ausführlichem Logging...") logger.info("Starte den Duplikats-Check (v2.0 mit Blocking und Maximum Logging)...")
sheet_handler = GoogleSheetHandler() # GoogleSheetHandler initialisieren
crm_df = sheet_handler.get_sheet_as_dataframe(CRM_SHEET_NAME) try:
match_df = sheet_handler.get_sheet_as_dataframe(MATCHING_SHEET_NAME) sheet_handler = GoogleSheetHandler()
if crm_df is None or crm_df.empty or match_df is None or match_df.empty: logger.info("GoogleSheetHandler initialisiert")
logger.error("Leere Daten in CRM oder Matching Tab. Abbruch.") except Exception as e:
logger.critical(f"FEHLER bei Initialisierung des GoogleSheetHandler: {e}")
return return
# CRM-Daten laden
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"Konnte keine Daten aus '{CRM_SHEET_NAME}' laden. Abbruch.")
return
logger.info(f"{len(crm_df)} Zeilen aus '{CRM_SHEET_NAME}' geladen")
# Matching-Daten laden
logger.info(f"Lade zu prüfende 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"Konnte keine Daten aus '{MATCHING_SHEET_NAME}' laden. Abbruch.")
return
logger.info(f"{len(match_df)} Zeilen aus '{MATCHING_SHEET_NAME}' geladen")
# Normalisierung # Normalisierung
for df, name in [(crm_df, 'CRM'), (match_df, 'Matching')]: for df, label in [(crm_df, 'CRM'), (match_df, 'Matching')]:
df['norm_name'] = df['CRM Name'].fillna('').apply(normalize_company_name) df['norm_name'] = df['CRM Name'].fillna('').apply(normalize_company_name)
df['norm_domain'] = df['CRM Website'].fillna('').apply(normalize_domain) df['norm_domain'] = df['CRM Website'].fillna('').apply(normalize_domain)
df['city'] = df['CRM Ort'].fillna('').apply(lambda x: str(x).casefold().strip()) df['city'] = df['CRM Ort'].fillna('').apply(lambda x: str(x).casefold().strip())
logger.debug(f"{name}-Daten nach Normalisierung. Erste Zeile: {df.iloc[0].to_dict()}") logger.debug(f"{label}-Daten nach Normalisierung. Erste Zeile: {df.iloc[0].to_dict()}")
# Blocking per Domain # Blocking per Domain
indexer = recordlinkage.Index() indexer = recordlinkage.Index()
@@ -64,13 +79,13 @@ def main():
candidate_pairs = indexer.index(crm_df, match_df) candidate_pairs = indexer.index(crm_df, match_df)
logger.info(f"Blocking abgeschlossen: {len(candidate_pairs)} Kandidatenpaare gefunden") logger.info(f"Blocking abgeschlossen: {len(candidate_pairs)} Kandidatenpaare gefunden")
# Vergleichsregeln # Vergleichsregeln definieren
compare = recordlinkage.Compare() compare = recordlinkage.Compare()
compare.exact('norm_domain', 'norm_domain', label='domain') compare.exact('norm_domain', 'norm_domain', label='domain')
compare.string('norm_name', 'norm_name', method='jarowinkler', label='name_sim') compare.string('norm_name', 'norm_name', method='jarowinkler', label='name_sim')
compare.exact('city', 'city', label='city') compare.exact('city', 'city', label='city')
features = compare.compute(candidate_pairs, crm_df, match_df) features = compare.compute(candidate_pairs, crm_df, match_df)
logger.debug(f"Feature-DataFrame Vorschau:\n{features.head()}" ) logger.debug(f"Feature-DataFrame Vorschau:\n{features.head()}")
# Score berechnen # Score berechnen
features['score'] = ( features['score'] = (
@@ -80,36 +95,29 @@ def main():
) )
logger.info("Scores berechnet") logger.info("Scores berechnet")
# Best Match pro neuer Zeile mit Logging der Kandidaten # Best Match pro neuer Zeile mit detailliertem Logging
results = [] results = []
crm_idx_col = []
match_idx_col = []
for match_idx, group in features.reset_index().groupby('level_1'): for match_idx, group in features.reset_index().groupby('level_1'):
crm_idx_col.append(match_idx) logger.info(f"--- Prüfe: Zeile {match_idx} ---")
# sortiere Kandidaten nach Score df_block = group.sort_values('score', ascending=False)
sorted_group = group.sort_values('score', ascending=False) logger.debug(f" Kandidaten für Zeile {match_idx}:\n{df_block[['level_0','score','domain','name_sim','city']].to_string(index=False)}")
logger.debug(f"Matching-Index {match_idx}: untersuchte Kandidaten:\n{sorted_group[['level_0','score','domain','name_sim','city']]}" ) top = df_block.iloc[0]
top = sorted_group.iloc[0] crm_idx = top['level_0'] if top['score'] >= SCORE_THRESHOLD else None
if top['score'] >= SCORE_THRESHOLD: if crm_idx is not None:
results.append((top['level_0'], match_idx, top['score'])) logger.info(f" --> Match: CRM-Index {crm_idx} mit Score {top['score']:.2f}")
logger.info(f"Zeile {match_idx}: Match mit CRM-Index {top['level_0']} Score {top['score']:.2f}")
else: else:
results.append((None, match_idx, top['score'])) logger.info(f" --> Kein Match (höchster Score {top['score']:.2f})")
logger.info(f"Zeile {match_idx}: Kein ausreichender Score (top {top['score']:.2f})") results.append((crm_idx, match_idx, top['score']))
# Ausgabe DataFrame # Ausgabe DataFrame zusammenstellen
crm_df = crm_df.reset_index() crm_df = crm_df.reset_index()
match_df = match_df.reset_index() match_df = match_df.reset_index()
output = match_df[['CRM Name','CRM Website','CRM Ort','CRM Land']].copy() output = match_df[['CRM Name','CRM Website','CRM Ort','CRM Land']].copy()
output['Matched CRM Name'] = '' output[['Matched CRM Name','Matched CRM Website','Matched CRM Ort','Matched CRM Land','Score']] = ''
output['Matched CRM Website'] = ''
output['Matched CRM Ort'] = ''
output['Matched CRM Land'] = ''
output['Score'] = 0.0
for crm_idx, match_idx, score in results: for crm_idx, match_idx, score in results:
if crm_idx is not None: if crm_idx is not None:
row_crm = crm_df.loc[crm_df['index'] == crm_idx].iloc[0] row_crm = crm_df.loc[crm_df['index']==crm_idx].iloc[0]
output.at[match_idx, 'Matched CRM Name'] = row_crm['CRM Name'] output.at[match_idx, 'Matched CRM Name'] = row_crm['CRM Name']
output.at[match_idx, 'Matched CRM Website'] = row_crm['CRM Website'] output.at[match_idx, 'Matched CRM Website'] = row_crm['CRM Website']
output.at[match_idx, 'Matched CRM Ort'] = row_crm['CRM Ort'] output.at[match_idx, 'Matched CRM Ort'] = row_crm['CRM Ort']
@@ -120,7 +128,7 @@ def main():
data = [output.columns.tolist()] + output.values.tolist() data = [output.columns.tolist()] + output.values.tolist()
success = sheet_handler.clear_and_write_data(MATCHING_SHEET_NAME, data) success = sheet_handler.clear_and_write_data(MATCHING_SHEET_NAME, data)
if success: if success:
logger.info("Erfolgreich geschrieben ins Google Sheet") logger.info(f"Erfolgreich geschrieben: {len([r for r in results if r[0] is not None])} Matches")
else: else:
logger.error("Fehler beim Schreiben ins Google Sheet.") logger.error("Fehler beim Schreiben ins Google Sheet.")