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
2025-08-04 05:44:23 +00:00
parent 5bc57fab86
commit cb76d4592a
1 changed files with 54 additions and 64 deletions
Download Patch File Download Diff File Expand all files Collapse all files

118
duplicate_checker.py
View File

@@ -1,4 +1,4 @@
# duplicate_checker.py (v2.0 - Maximum Logging)
# duplicate_checker.py (v1.1 - Lauf 1 Logik + Match-Grund)
import logging
import pandas as pd
@@ -11,7 +11,7 @@ import time
# --- Konfiguration ---
CRM_SHEET_NAME = "CRM_Accounts"
MATCHING_SHEET_NAME = "Matching_Accounts"
SCORE_THRESHOLD = 80
SCORE_THRESHOLD = 80 # Treffer unter diesem Wert werden nicht als "potenzieller Treffer" angezeigt
# --- VOLLSTÄNDIGES LOGGING SETUP ---
LOG_LEVEL = logging.DEBUG if Config.DEBUG else logging.INFO
@@ -20,38 +20,54 @@ LOG_FORMAT = '%(asctime)s - %(levelname)-8s - %(name)s - %(message)s'
root_logger = logging.getLogger()
root_logger.setLevel(LOG_LEVEL)
for handler in root_logger.handlers[:]:
root_logger.removeHandler(handler)
# Handler nur hinzufügen, wenn noch keine konfiguriert sind
if not root_logger.handlers:
stream_handler = logging.StreamHandler()
stream_handler.setFormatter(logging.Formatter(LOG_FORMAT))
root_logger.addHandler(stream_handler)
stream_handler = logging.StreamHandler()
stream_handler.setFormatter(logging.Formatter(LOG_FORMAT))
root_logger.addHandler(stream_handler)
log_file_path = create_log_filename("duplicate_check_v2_0")
if log_file_path:
file_handler = logging.FileHandler(log_file_path, mode='a', encoding='utf-8')
file_handler.setFormatter(logging.Formatter(LOG_FORMAT))
root_logger.addHandler(file_handler)
log_file_path = create_log_filename("duplicate_check_final")
if log_file_path:
file_handler = logging.FileHandler(log_file_path, mode='a', encoding='utf-8')
file_handler.setFormatter(logging.Formatter(LOG_FORMAT))
root_logger.addHandler(file_handler)
else:
# Finde den Dateipfad aus dem bereits konfigurierten Handler
log_file_path = None
for handler in root_logger.handlers:
if isinstance(handler, logging.FileHandler):
log_file_path = handler.baseFilename
break
logger = logging.getLogger(__name__)
def calculate_similarity_with_details(record1, record2):
"""
Berechnet einen gewichteten Ähnlichkeits-Score zwischen zwei Datensätzen
und gibt die Details für die Begründung zurück.
Berechnet einen gewichteten Ähnlichkeits-Score und gibt den Score und den Grund zurück.
Dies ist die originale Scoring-Logik von Lauf 1.
"""
scores = {'name': 0, 'location': 0, 'domain': 0}
if record1['normalized_domain'] and record1['normalized_domain'] != 'k.a.' and record1['normalized_domain'] == record2['normalized_domain']:
# Domain-Match (100 Punkte)
domain1 = record1.get('normalized_domain')
domain2 = record2.get('normalized_domain')
if domain1 and domain1 != 'k.a.' and domain1 == domain2:
scores['domain'] = 100
if record1['normalized_name'] and record2['normalized_name']:
name_similarity = fuzz.token_set_ratio(record1['normalized_name'], record2['normalized_name'])
# Namensähnlichkeit (70% Gewichtung)
name1 = record1.get('normalized_name')
name2 = record2.get('normalized_name')
if name1 and name2:
name_similarity = fuzz.token_set_ratio(name1, name2)
scores['name'] = round(name_similarity * 0.7)
if record1['CRM Ort'] and record1['CRM Ort'] == record2['CRM Ort']:
if record1['CRM Land'] and record1['CRM Land'] == record2['CRM Land']:
scores['location'] = 20
# Standort-Bonus (20 Punkte)
ort1 = record1.get('CRM Ort')
ort2 = record2.get('CRM Ort')
land1 = record1.get('CRM Land')
land2 = record2.get('CRM Land')
if ort1 and ort1 == ort2 and land1 and land1 == land2:
scores['location'] = 20
total_score = sum(scores.values())
@@ -64,26 +80,23 @@ def calculate_similarity_with_details(record1, record2):
return round(total_score), reason_text
def main():
"""Hauptfunktion zum Laden, Vergleichen und Schreiben der Daten."""
start_time = time.time()
logger.info("Starte den Duplikats-Check (v2.0 mit Blocking und Maximum Logging)...")
logger.info("Starte den Duplikats-Check (v1.1 - Brute-Force mit Match-Grund)...")
logger.info(f"Logdatei: {log_file_path}")
try:
sheet_handler = GoogleSheetHandler()
except Exception as e:
logger.critical(f"FEHLER bei Initialisierung des GoogleSheetHandler: {e}")
logger.critical(f"FEHLER bei Initialisierung: {e}")
return
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:
return
if crm_df is None or crm_df.empty: return
logger.info(f"Lade zu prüfende Daten aus '{MATCHING_SHEET_NAME}'...")
matching_df = sheet_handler.get_sheet_as_dataframe(MATCHING_SHEET_NAME)
if matching_df is None or matching_df.empty:
return
if matching_df is None or matching_df.empty: return
original_matching_df = matching_df.copy()
logger.info("Normalisiere Daten für den Vergleich...")
@@ -92,52 +105,29 @@ def main():
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 Land'] = df['CRM Land'].astype(str).str.lower().str.strip()
df['block_key'] = df['normalized_name'].apply(lambda x: x.split()[0] if x and x.split() else None)
logger.info("Erstelle Index für CRM-Daten zur Beschleunigung...")
crm_index = {}
crm_records = crm_df.to_dict('records')
for record in crm_records:
key = record['block_key']
if key:
if key not in crm_index:
crm_index[key] = []
crm_index[key].append(record)
logger.info("Starte Matching-Prozess...")
matching_records = matching_df.to_dict('records')
logger.info(f"Starte Matching-Prozess: {len(matching_records)} Einträge werden mit {len(crm_records)} CRM-Einträgen verglichen...")
results = []
for match_record in matching_df.to_dict('records'):
for i, match_record in enumerate(matching_records):
best_score = -1
best_match_name = ""
best_reason = ""
logger.info(f"--- Prüfe: '{match_record.get('CRM Name', 'N/A')}' ---")
logger.debug(f" [Normalisiert: '{match_record.get('normalized_name')}', Domain: '{match_record.get('normalized_domain')}', Key: '{match_record.get('block_key')}']")
block_key = match_record.get('block_key')
candidates = crm_index.get(block_key, [])
logger.info(f"--- Prüfe {i + 1}/{len(matching_records)}: '{match_record.get('CRM Name', 'N/A')}' ---")
if not candidates:
logger.debug(" -> Keine Kandidaten im Index gefunden. Überspringe Vergleich.")
results.append({
'Potenzieller Treffer im CRM': "", 'Ähnlichkeits-Score': 0, 'Matching-Grund': "Keine Kandidaten"
})
continue
logger.debug(f" -> Vergleiche mit {len(candidates)} Kandidaten aus Block '{block_key}'.")
for crm_row in candidates:
score, reason = calculate_similarity_with_details(match_record, crm_row)
if score > 0: # Logge jeden Vergleich, der einen Score > 0 hat
logger.debug(f" - Kandidat: '{crm_row.get('CRM Name', 'N/A')}' -> Score: {score} (Grund: {reason})")
# Brute-Force-Vergleich: Jede Zeile wird mit jeder CRM-Zeile verglichen
for crm_record in crm_records:
score, reason = calculate_similarity_with_details(match_record, crm_record)
if score > best_score:
best_score = score
best_match_name = crm_row.get('CRM Name', 'N/A')
best_match_name = crm_record.get('CRM Name', 'N/A')
best_reason = reason
logger.info(f" --> Neuer bester Treffer: '{best_match_name}' mit Score {best_score}")
logger.info(f" --> Bester Treffer: '{best_match_name}' mit Score {best_score} (Grund: {best_reason})")
results.append({
'Potenzieller Treffer im CRM': best_match_name if best_score >= SCORE_THRESHOLD else "",
@@ -154,9 +144,9 @@ def main():
success = sheet_handler.clear_and_write_data(MATCHING_SHEET_NAME, data_to_write)
if success:
logging.info(f"Ergebnisse erfolgreich in '{MATCHING_SHEET_NAME}' geschrieben.")
logger.info(f"Ergebnisse erfolgreich in '{MATCHING_SHEET_NAME}' geschrieben.")
else:
logging.error("FEHLER beim Schreiben der Ergebnisse ins Google Sheet.")
logger.error("FEHLER beim Schreiben der Ergebnisse ins Google Sheet.")
end_time = time.time()
logger.info(f"Gesamtdauer des Duplikats-Checks: {end_time - start_time:.2f} Sekunden.")