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 14:34:08 +00:00
parent 270a5fc0e2
commit 9685bc5a2d
1 changed files with 52 additions and 42 deletions
Download Patch File Download Diff File Expand all files Collapse all files

94
duplicate_checker.py
View File

@@ -1,4 +1,5 @@
import re
import logging
import pandas as pd
import recordlinkage
from rapidfuzz import fuzz
@@ -14,14 +15,15 @@ WEIGHTS = {
'city': 0.1,
}
# --- Logging Setup ---
logging.basicConfig(
level=logging.DEBUG,
format='%(asctime)s - %(levelname)-8s - %(message)s'
)
logger = logging.getLogger(__name__)
# --- Hilfsfunktionen ---
def normalize_company_name(name: str) -> str:
"""
Vereinfacht Firmennamen:
- Unicode-safe Kleinschreibung
- Umlaute in ae/oe/ue, ß in ss
- Entfernen von Rechtsformen/Stop-Wörtern
"""
s = str(name).casefold()
for src, dst in [('ä','ae'), ('ö','oe'), ('ü','ue'), ('ß','ss')]:
s = s.replace(src, dst)
@@ -32,7 +34,6 @@ def normalize_company_name(name: str) -> str:
def normalize_domain(url: str) -> str:
"""Extrahiere Root-Domain, entferne Protokoll und www-Präfix"""
s = str(url).casefold().strip()
s = re.sub(r'^https?://', '', s)
s = s.split('/')[0]
@@ -42,77 +43,86 @@ def normalize_domain(url: str) -> str:
def main():
# Google Sheets laden
logger.info("Starte Duplikat-Check mit ausführlichem Logging...")
sheet_handler = GoogleSheetHandler()
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)
if crm_df is None or crm_df.empty or match_df is None or match_df.empty:
print("Fehler: Leere Daten in einem der Tabs. Abbruch.")
logger.error("Leere Daten in CRM oder Matching Tab. Abbruch.")
return
# Normalisierung
for df in (crm_df, match_df):
df['norm_name'] = df['CRM Name'].fillna('').apply(normalize_company_name)
for df, name in [(crm_df, 'CRM'), (match_df, 'Matching')]:
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())
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()}")
# 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 gefunden")
# Vergleichsregeln definieren
# Vergleichsregeln
compare = recordlinkage.Compare()
compare.exact('norm_domain', 'norm_domain', label='domain')
compare.string('norm_name', 'norm_name', method='jarowinkler', label='name_sim')
compare.exact('city', 'city', label='city')
features = compare.compute(candidate_pairs, crm_df, match_df)
logger.debug(f"Feature-DataFrame Vorschau:\n{features.head()}" )
# Gewichte und Score
# Score berechnen
features['score'] = (
WEIGHTS['domain'] * features['domain'] +
WEIGHTS['name'] * features['name_sim'] +
WEIGHTS['city'] * features['city']
)
logger.info("Scores berechnet")
# Bestes Match pro neuer Zeile
matches = features.reset_index()
best = matches.sort_values(['level_1','score'], ascending=[True, False]) \
.drop_duplicates('level_1')
best = best[best['score'] >= SCORE_THRESHOLD] \
.rename(columns={'level_0':'crm_idx','level_1':'match_idx'})
# Best Match pro neuer Zeile mit Logging der Kandidaten
results = []
crm_idx_col = []
match_idx_col = []
for match_idx, group in features.reset_index().groupby('level_1'):
crm_idx_col.append(match_idx)
# sortiere Kandidaten nach Score
sorted_group = group.sort_values('score', ascending=False)
logger.debug(f"Matching-Index {match_idx}: untersuchte Kandidaten:\n{sorted_group[['level_0','score','domain','name_sim','city']]}" )
top = sorted_group.iloc[0]
if top['score'] >= SCORE_THRESHOLD:
results.append((top['level_0'], match_idx, top['score']))
logger.info(f"Zeile {match_idx}: Match mit CRM-Index {top['level_0']} Score {top['score']:.2f}")
else:
results.append((None, match_idx, top['score']))
logger.info(f"Zeile {match_idx}: Kein ausreichender Score (top {top['score']:.2f})")
# Merges
crm_df = crm_df.reset_index()
# Ausgabe DataFrame
crm_df = crm_df.reset_index()
match_df = match_df.reset_index()
merged = (best
.merge(crm_df, left_on='crm_idx', right_on='index')
.merge(match_df, left_on='match_idx', right_on='index', suffixes=('_CRM','_NEW'))
)
# Ausgabe aufbauen
output = match_df[['CRM Name','CRM Website','CRM Ort','CRM Land']].copy()
output['Matched CRM Name'] = ''
output['Matched CRM Name'] = ''
output['Matched CRM Website'] = ''
output['Matched CRM Ort'] = ''
output['Matched CRM Land'] = ''
output['Score'] = 0.0
output['Matched CRM Ort'] = ''
output['Matched CRM Land'] = ''
output['Score'] = 0.0
for _, row in merged.iterrows():
i = int(row['match_idx'])
output.at[i, 'Matched CRM Name'] = row['CRM Name_CRM']
output.at[i, 'Matched CRM Website'] = row['CRM Website_CRM']
output.at[i, 'Matched CRM Ort'] = row['CRM Ort_CRM']
output.at[i, 'Matched CRM Land'] = row['CRM Land_CRM']
output.at[i, 'Score'] = row['score']
for crm_idx, match_idx, score in results:
if crm_idx is not None:
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 Website'] = row_crm['CRM Website']
output.at[match_idx, 'Matched CRM Ort'] = row_crm['CRM Ort']
output.at[match_idx, 'Matched CRM Land'] = row_crm['CRM Land']
output.at[match_idx, 'Score'] = round(score, 3)
# Zurückschreiben ins Google Sheet
data = [output.columns.tolist()] + output.values.tolist()
success = sheet_handler.clear_and_write_data(MATCHING_SHEET_NAME, data)
if success:
print(f"Erfolgreich: {len(best)} Matches mit Score ≥ {SCORE_THRESHOLD}")
logger.info("Erfolgreich geschrieben ins Google Sheet")
else:
print("Fehler beim Schreiben ins Google Sheet.")
logger.error("Fehler beim Schreiben ins Google Sheet.")
if __name__ == '__main__':
main()