From 4a41ffb0fadca7d7f3e66981b6c6f9dc26670730 Mon Sep 17 00:00:00 2001 From: Floke Date: Wed, 6 Aug 2025 05:45:15 +0000 Subject: [PATCH] duplicate_checker.py aktualisiert --- duplicate_checker.py | 74 +++++++++++++++++++++++--------------------- 1 file changed, 38 insertions(+), 36 deletions(-) diff --git a/duplicate_checker.py b/duplicate_checker.py index fbc5db42..5b9adefd 100644 --- a/duplicate_checker.py +++ b/duplicate_checker.py @@ -2,6 +2,7 @@ import os import re import logging import pandas as pd +import numpy as np import recordlinkage from rapidfuzz import fuzz from google_sheet_handler import GoogleSheetHandler @@ -64,7 +65,8 @@ def normalize_domain(url: str) -> str: def main(): - logger.info("Starte den Duplikats-Check (v2.0 mit Kandidaten-Logging)...") + logger.info("Starte den Duplikats-Check (v2.0 mit korrekten Missing-Werten)...") + # Initialize GoogleSheetHandler try: sheet_handler = GoogleSheetHandler() logger.info("GoogleSheetHandler initialisiert") @@ -72,7 +74,7 @@ def main(): logger.critical(f"FEHLER bei Initialisierung des GoogleSheetHandler: {e}") return - # Daten laden + # Load data crm_df = sheet_handler.get_sheet_as_dataframe(CRM_SHEET_NAME) match_df = sheet_handler.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: @@ -80,73 +82,73 @@ def main(): return logger.info(f"{len(crm_df)} CRM-Zeilen, {len(match_df)} Matching-Zeilen geladen") - # Normalisierung + # Normalize fields 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['city'] = df['CRM Ort'].fillna('').apply(lambda x: str(x).casefold().strip()) - logger.debug(f"{label}-Daten normalisiert: Beispiel: {df.iloc[0][['norm_name','norm_domain','city']].to_dict()}") + df['city'] = df['CRM Ort'].fillna('').apply(lambda x: str(x).casefold().strip()) + # Replace empty strings with NaN so they aren't considered matches + df['norm_domain'].replace('', np.nan, inplace=True) + df['city'].replace('', np.nan, inplace=True) + logger.debug(f"{label}-Daten normalisiert: Beispiel: {{'norm_name': df.iloc[0]['norm_name'], 'norm_domain': df.iloc[0]['norm_domain'], 'city': df.iloc[0]['city']}}") - # Blocking + # Blocking per Domain indexer = recordlinkage.Index() indexer.block('norm_domain') candidate_pairs = indexer.index(crm_df, match_df) logger.info(f"Blocking abgeschlossen: {len(candidate_pairs)} Kandidatenpaare") - # Compare + # Vergleichsregeln definieren compare = recordlinkage.Compare() - compare.exact('norm_domain', 'norm_domain', label='domain') + compare.exact('norm_domain', 'norm_domain', label='domain', missing_value=0) compare.string('norm_name', 'norm_name', method='jarowinkler', label='name_sim') - compare.exact('city', 'city', label='city') + compare.exact('city', 'city', label='city', missing_value=0) features = compare.compute(candidate_pairs, crm_df, match_df) logger.debug(f"Features berechnet: {features.head()}\n...") - # Score - features['score'] = (WEIGHTS['domain']*features['domain'] + - WEIGHTS['name']*features['name_sim'] + - WEIGHTS['city']*features['city']) + # Score berechnen + features['score'] = ( + WEIGHTS['domain'] * features['domain'] + + WEIGHTS['name'] * features['name_sim'] + + WEIGHTS['city'] * features['city'] + ) logger.info("Scores berechnet") - # Per Match Logging + # Detailed per-match logging results = [] - crm_df_idx = crm_df.reset_index() + crm_idx_map = crm_df.reset_index() for match_idx, group in features.reset_index().groupby('level_1'): logger.info(f"--- Prüfe Matching-Zeile {match_idx} ---") df_block = group.sort_values('score', ascending=False).copy() - # Enrich with CRM fields - df_block['CRM Name'] = df_block['level_0'].map(crm_df_idx.set_index('index')['CRM Name']) - df_block['CRM Website'] = df_block['level_0'].map(crm_df_idx.set_index('index')['CRM Website']) - df_block['CRM Ort'] = df_block['level_0'].map(crm_df_idx.set_index('index')['CRM Ort']) - # Log top candidates - logger.debug("Kandidaten (CRM_Index, Score, Domain, Name_sim, City, CRM Name):") + # Enrich with CRM info + df_block['CRM Name'] = df_block['level_0'].map(crm_idx_map.set_index('index')['CRM Name']) + df_block['CRM Website'] = df_block['level_0'].map(crm_idx_map.set_index('index')['CRM Website']) + df_block['CRM Ort'] = df_block['level_0'].map(crm_idx_map.set_index('index')['CRM Ort']) + logger.debug("Kandidaten (Index, Score, Domain, Name_sim, City, CRM Name):") for _, row in df_block.iterrows(): - logger.debug(f" [{int(row['level_0'])}] score={row['score']:.3f} dom={row['domain']} name_sim={row['name_sim']:.3f} city={row['city']} => {row['CRM Name']}") + logger.debug(f" [{int(row['level_0'])}] score={row['score']:.3f} dom={row['domain']} name={row['name_sim']:.3f} city={row['city']} => {row['CRM Name']}") top = df_block.iloc[0] crm_idx = top['level_0'] if top['score'] >= SCORE_THRESHOLD else None if crm_idx is not None: - logger.info(f" --> Match: CRM-Index {int(crm_idx)} ({top['CRM Name']}) mit Score {top['score']:.2f}") + logger.info(f" --> Match: {int(crm_idx)} ({top['CRM Name']}) mit Score {top['score']:.2f}") else: logger.info(f" --> Kein Match (höchster Score {top['score']:.2f})") results.append((crm_idx, match_idx, top['score'])) # Prepare output - match_df_idx = match_df.reset_index() - output = match_df_idx[['CRM Name','CRM Website','CRM Ort','CRM Land']].copy() - output['Matched CRM Name'] = '' - output['Matched CRM Website'] = '' - output['Matched CRM Ort'] = '' - output['Matched CRM Land'] = '' - output['Score'] = 0.0 + match_idx_map = match_df.reset_index() + output = match_idx_map[['CRM Name','CRM Website','CRM Ort','CRM Land']].copy() + output[['Matched CRM Name','Matched CRM Website','Matched CRM Ort','Matched CRM Land','Score']] = '' for crm_idx, match_idx, score in results: if crm_idx is not None: - crm_row = crm_df_idx[crm_df_idx['index']==crm_idx].iloc[0] - output.at[match_idx, 'Matched CRM Name'] = crm_row['CRM Name'] + crm_row = crm_idx_map[crm_idx_map['index']==crm_idx].iloc[0] + output.at[match_idx, 'Matched CRM Name'] = crm_row['CRM Name'] output.at[match_idx, 'Matched CRM Website'] = crm_row['CRM Website'] - output.at[match_idx, 'Matched CRM Ort'] = crm_row['CRM Ort'] - output.at[match_idx, 'Matched CRM Land'] = crm_row['CRM Land'] + output.at[match_idx, 'Matched CRM Ort'] = crm_row['CRM Ort'] + output.at[match_idx, 'Matched CRM Land'] = crm_row['CRM Land'] output.at[match_idx, 'Score'] = round(score,3) - # Write back + # Zurückschreiben ins Google Sheet data = [output.columns.tolist()] + output.values.tolist() success = sheet_handler.clear_and_write_data(MATCHING_SHEET_NAME, data) if success: