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 05:59:05 +00:00
parent 223f719e38
commit 9789b38836
1 changed files with 38 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files

63
duplicate_checker.py
View File

@@ -10,13 +10,15 @@ from google_sheet_handler import GoogleSheetHandler
# --- Konfiguration --- # --- Konfiguration ---
CRM_SHEET_NAME = "CRM_Accounts" CRM_SHEET_NAME = "CRM_Accounts"
MATCHING_SHEET_NAME = "Matching_Accounts" MATCHING_SHEET_NAME = "Matching_Accounts"
SCORE_THRESHOLD = 0.8 # Threshold gesenkt und konfigurierbar im Code
SCORE_THRESHOLD = 0.75
WEIGHTS = { WEIGHTS = {
'domain': 0.5, 'domain': 0.5,
'name': 0.4, 'name': 0.4,
'city': 0.1, 'city': 0.1,
} }
LOG_DIR = '/log' # Relativer Log-Ordner
LOG_DIR = 'log'
LOG_FILENAME = 'duplicate_check.log' LOG_FILENAME = 'duplicate_check.log'
# --- Logging Setup --- # --- Logging Setup ---
@@ -30,11 +32,13 @@ log_path = os.path.join(LOG_DIR, LOG_FILENAME)
logger = logging.getLogger(__name__) logger = logging.getLogger(__name__)
logger.setLevel(logging.DEBUG) logger.setLevel(logging.DEBUG)
formatter = logging.Formatter('%(asctime)s - %(levelname)-8s - %(name)s - %(message)s') formatter = logging.Formatter('%(asctime)s - %(levelname)-8s - %(name)s - %(message)s')
# Console handler # Console handler
console_handler = logging.StreamHandler() console_handler = logging.StreamHandler()
console_handler.setLevel(logging.INFO) console_handler.setLevel(logging.INFO)
console_handler.setFormatter(formatter) console_handler.setFormatter(formatter)
logger.addHandler(console_handler) logger.addHandler(console_handler)
# File handler # File handler
try: try:
file_handler = logging.FileHandler(log_path, mode='a', encoding='utf-8') file_handler = logging.FileHandler(log_path, mode='a', encoding='utf-8')
@@ -55,6 +59,7 @@ def normalize_company_name(name: str) -> str:
tokens = [t for t in s.split() if t and t not in stops] tokens = [t for t in s.split() if t and t not in stops]
return ' '.join(tokens) return ' '.join(tokens)
def normalize_domain(url: str) -> str: def normalize_domain(url: str) -> str:
s = str(url).casefold().strip() s = str(url).casefold().strip()
s = re.sub(r'^https?://', '', s) s = re.sub(r'^https?://', '', s)
@@ -65,8 +70,8 @@ def normalize_domain(url: str) -> str:
def main(): def main():
logger.info("Starte den Duplikats-Check (v2.0 mit korrekten Missing-Werten)...") logger.info("Starte den Duplikats-Check mit Fallback-Blocking...")
# Initialize GoogleSheetHandler # GoogleSheetHandler initialisieren
try: try:
sheet_handler = GoogleSheetHandler() sheet_handler = GoogleSheetHandler()
logger.info("GoogleSheetHandler initialisiert") logger.info("GoogleSheetHandler initialisiert")
@@ -74,7 +79,7 @@ def main():
logger.critical(f"FEHLER bei Initialisierung des GoogleSheetHandler: {e}") logger.critical(f"FEHLER bei Initialisierung des GoogleSheetHandler: {e}")
return return
# Load data # Daten laden
crm_df = sheet_handler.get_sheet_as_dataframe(CRM_SHEET_NAME) crm_df = sheet_handler.get_sheet_as_dataframe(CRM_SHEET_NAME)
match_df = sheet_handler.get_sheet_as_dataframe(MATCHING_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: if crm_df is None or crm_df.empty or match_df is None or match_df.empty:
@@ -82,21 +87,27 @@ def main():
return return
logger.info(f"{len(crm_df)} CRM-Zeilen, {len(match_df)} Matching-Zeilen geladen") logger.info(f"{len(crm_df)} CRM-Zeilen, {len(match_df)} Matching-Zeilen geladen")
# Normalize fields # Normalisierung
for df, label 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())
# Replace empty strings with NaN so they aren't considered matches df['name_token'] = df['norm_name'].apply(lambda x: x.split()[0] if x else np.nan)
# Leere Werte als NaN markieren
df['norm_domain'].replace('', np.nan, inplace=True) df['norm_domain'].replace('', np.nan, inplace=True)
df['city'].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']}}") logger.debug(f"{label}-Normalisierung: norm_domain={df.iloc[0]['norm_domain']}, name_token={df.iloc[0]['name_token']}")
# Blocking per Domain # Blocking: Domain und Name-Token
indexer = recordlinkage.Index() index_dom = recordlinkage.Index()
indexer.block('norm_domain') index_dom.block('norm_domain')
candidate_pairs = indexer.index(crm_df, match_df) pairs_dom = index_dom.index(crm_df, match_df)
logger.info(f"Blocking abgeschlossen: {len(candidate_pairs)} Kandidatenpaare") index_name = recordlinkage.Index()
index_name.block('name_token')
pairs_name = index_name.index(crm_df, match_df)
# Union der Kandidatenpaare
candidate_pairs = pairs_dom.append(pairs_name).drop_duplicates()
logger.info(f"Blocking abgeschlossen: Dom-Paare={len(pairs_dom)}, Name-Paare={len(pairs_name)}, Gesamt={len(candidate_pairs)}")
# Vergleichsregeln definieren # Vergleichsregeln definieren
compare = recordlinkage.Compare() compare = recordlinkage.Compare()
@@ -104,7 +115,7 @@ def main():
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', missing_value=0) compare.exact('city', 'city', label='city', missing_value=0)
features = compare.compute(candidate_pairs, crm_df, match_df) features = compare.compute(candidate_pairs, crm_df, match_df)
logger.debug(f"Features berechnet: {features.head()}\n...") logger.debug(f"Features berechnet: {features.head()}...")
# Score berechnen # Score berechnen
features['score'] = ( features['score'] = (
@@ -114,19 +125,17 @@ def main():
) )
logger.info("Scores berechnet") logger.info("Scores berechnet")
# Detailed per-match logging # Per-Match Logging und Auswahl
results = [] results = []
crm_idx_map = crm_df.reset_index() crm_map = crm_df.reset_index()
for match_idx, group in features.reset_index().groupby('level_1'): for match_idx, group in features.reset_index().groupby('level_1'):
logger.info(f"--- Prüfe Matching-Zeile {match_idx} ---") logger.info(f"--- Prüfe Matching-Zeile {match_idx} ---")
df_block = group.sort_values('score', ascending=False).copy() df_block = group.sort_values('score', ascending=False).copy()
# Enrich with CRM info # CRM-Daten für Log
df_block['CRM Name'] = df_block['level_0'].map(crm_idx_map.set_index('index')['CRM Name']) df_block['CRM Name'] = df_block['level_0'].map(crm_map.set_index('index')['CRM Name'])
df_block['CRM Website'] = df_block['level_0'].map(crm_idx_map.set_index('index')['CRM Website']) # Log der Top-Kandidaten
df_block['CRM Ort'] = df_block['level_0'].map(crm_idx_map.set_index('index')['CRM Ort']) for _, row in df_block.head(5).iterrows():
logger.debug("Kandidaten (Index, Score, Domain, Name_sim, City, CRM Name):") logger.debug(f"Candidate [{int(row['level_0'])}]: score={row['score']:.3f}, name_sim={row['name_sim']:.3f}, dom={row['domain']}, city={row['city']} => {row['CRM Name']}")
for _, row in df_block.iterrows():
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] top = df_block.iloc[0]
crm_idx = top['level_0'] if top['score'] >= SCORE_THRESHOLD else None crm_idx = top['level_0'] if top['score'] >= SCORE_THRESHOLD else None
if crm_idx is not None: if crm_idx is not None:
@@ -135,13 +144,13 @@ def main():
logger.info(f" --> Kein Match (höchster Score {top['score']:.2f})") logger.info(f" --> Kein Match (höchster Score {top['score']:.2f})")
results.append((crm_idx, match_idx, top['score'])) results.append((crm_idx, match_idx, top['score']))
# Prepare output # Ausgabe zusammenstellen
match_idx_map = match_df.reset_index() match_map = match_df.reset_index()
output = match_idx_map[['CRM Name','CRM Website','CRM Ort','CRM Land']].copy() output = match_map[['CRM Name','CRM Website','CRM Ort','CRM Land']].copy()
output[['Matched CRM Name','Matched CRM Website','Matched CRM Ort','Matched CRM Land','Score']] = '' output[['Matched CRM Name','Matched CRM Website','Matched CRM Ort','Matched CRM Land','Score']] = ''
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:
crm_row = crm_idx_map[crm_idx_map['index']==crm_idx].iloc[0] crm_row = crm_map[crm_map['index']==crm_idx].iloc[0]
output.at[match_idx, 'Matched CRM Name'] = crm_row['CRM Name'] 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 Website'] = crm_row['CRM Website']
output.at[match_idx, 'Matched CRM Ort'] = crm_row['CRM Ort'] output.at[match_idx, 'Matched CRM Ort'] = crm_row['CRM Ort']