Floke/Brancheneinstufung2
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

bugfix

Browse Source
This commit is contained in:
Floke
2025-04-18 10:57:37 +00:00
parent f3f55cd2e5
commit 6e7a6bd949
1 changed files with 7 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
brancheneinstufung.py
View File

@@ -36,19 +36,20 @@ from difflib import SequenceMatcher
import unicodedata import unicodedata
import csv import csv
import gender_guesser.detector as gender import gender_guesser.detector as gender
from urllib.parse import urlparse, urlencode # --- HIER unquote hinzufügen ---
from urllib.parse import urlparse, urlencode, unquote
import argparse import argparse
import pandas as pd import pandas as pd
import numpy as np import numpy as np
# --- NEUE IMPORTE für ML ---
from sklearn.model_selection import train_test_split, GridSearchCV from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.impute import SimpleImputer from sklearn.impute import SimpleImputer
from sklearn.tree import DecisionTreeClassifier, export_text from sklearn.tree import DecisionTreeClassifier, export_text
from sklearn.metrics import accuracy_score, classification_report, confusion_matrix from sklearn.metrics import accuracy_score, classification_report, confusion_matrix
import json # Zum Speichern der Muster als JSON (optional) import json
import pickle # Zum Speichern des trainierten Modells und Imputers import pickle
import concurrent.futures # Für parallele Verarbeitung (bereits vorhanden) import concurrent.futures
import threading # Für Semaphore (bereits vorhanden) import threading
import traceback # Importiere traceback für detailliertere Fehlermeldungen
# --- Ende neue Importe --- # --- Ende neue Importe ---
# Optional: tiktoken für Token-Zählung (Modus 8) # Optional: tiktoken für Token-Zählung (Modus 8)