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

brancheneinstufung2.py aktualisiert

Browse Source
This commit is contained in:
Floke
2025-08-28 05:25:45 +00:00
parent 573a5252fa
commit 318cbe5fea
1 changed files with 25 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files

60
brancheneinstufung2.py
View File

@@ -67,15 +67,14 @@ def main():
import argparse import argparse
import time import time
import logging import logging
import os # <<< NEU: für Dateipfad-Prüfung import os
from config import Config from config import Config, log_module_versions, create_log_filename
from helpers import log_module_versions, create_log_filename
from google_sheet_handler import GoogleSheetHandler from google_sheet_handler import GoogleSheetHandler
from wikipedia_scraper import WikipediaScraper from wikipedia_scraper import WikipediaScraper
from data_processor import DataProcessor from data_processor import DataProcessor
from sync_manager import SyncManager # <<< NEU: SyncManager importieren from sync_manager import SyncManager
import helpers import helpers
import google_sheet_handler # Für Version-Logging import google_sheet_handler
# --- Argument Parser --- # --- Argument Parser ---
parser = argparse.ArgumentParser( parser = argparse.ArgumentParser(
@@ -83,7 +82,7 @@ def main():
formatter_class=argparse.RawTextHelpFormatter formatter_class=argparse.RawTextHelpFormatter
) )
mode_categories = { mode_categories = {
"Daten-Synchronisation": ["sync"], # <<< NEU: Eigene Kategorie für den Sync "Daten-Synchronisation": ["sync"],
"Batch-Verarbeitung": ["wiki_verify", "website_scraping", "summarize_website", "branch_eval", "suggest_parents", "fsm_pitch"], "Batch-Verarbeitung": ["wiki_verify", "website_scraping", "summarize_website", "branch_eval", "suggest_parents", "fsm_pitch"],
"Sequentielle Verarbeitung": ["full_run"], "Sequentielle Verarbeitung": ["full_run"],
"Re-Evaluation": ["reeval"], "Re-Evaluation": ["reeval"],
@@ -105,8 +104,6 @@ def main():
parser.add_argument("--steps", type=str, help=f"Schritte für 'reeval'/'full_run' (z.B. 'wiki,chat'). Optionen: {', '.join(valid_steps)}.", default=','.join(valid_steps)) parser.add_argument("--steps", type=str, help=f"Schritte für 'reeval'/'full_run' (z.B. 'wiki,chat'). Optionen: {', '.join(valid_steps)}.", default=','.join(valid_steps))
parser.add_argument("--min_umsatz", type=float, help="Mindestumsatz in MIO € für 'find_wiki_serp'.", default=200.0) parser.add_argument("--min_umsatz", type=float, help="Mindestumsatz in MIO € für 'find_wiki_serp'.", default=200.0)
parser.add_argument("--min_employees", type=int, help="Mindest-MA für 'find_wiki_serp'.", default=500) parser.add_argument("--min_employees", type=int, help="Mindest-MA für 'find_wiki_serp'.", default=500)
# <<< NEU: Argument für den Pfad der Sync-Datei
parser.add_argument("--sync_file", type=str, help="Pfad zur D365 Excel-Exportdatei für den 'sync'-Modus.", default="d365_export.xlsx") parser.add_argument("--sync_file", type=str, help="Pfad zur D365 Excel-Exportdatei für den 'sync'-Modus.", default="d365_export.xlsx")
args = parser.parse_args() args = parser.parse_args()
@@ -142,13 +139,11 @@ def main():
return return
# --- Logging Konfiguration --- # --- Logging Konfiguration ---
# Definiere hier die Logging-Konstanten, falls sie nicht global sind
LOG_LEVEL = logging.DEBUG if Config.DEBUG else logging.INFO LOG_LEVEL = logging.DEBUG if Config.DEBUG else logging.INFO
LOG_FORMAT = '%(asctime)s - %(levelname)-8s - %(name)-25s - %(message)s' LOG_FORMAT = '%(asctime)s - %(levelname)-8s - %(name)-25s - %(message)s'
logging.basicConfig(level=LOG_LEVEL, format=LOG_FORMAT) logging.basicConfig(level=LOG_LEVEL, format=LOG_FORMAT)
logger = logging.getLogger(__name__) logger = logging.getLogger(__name__)
# --- Logdatei-Konfiguration abschließen ---
log_file_path = create_log_filename(selected_mode) log_file_path = create_log_filename(selected_mode)
if log_file_path: if log_file_path:
file_handler = logging.FileHandler(log_file_path, mode='a', encoding='utf-8') file_handler = logging.FileHandler(log_file_path, mode='a', encoding='utf-8')
@@ -163,15 +158,21 @@ def main():
# --- Hauptlogik --- # --- Hauptlogik ---
try: try:
# --- Vorbereitung & Initialisierung ---
Config.load_api_keys() Config.load_api_keys()
sheet_handler = GoogleSheetHandler() sheet_handler = GoogleSheetHandler()
# <<< NEU: Früher Ausstieg für den Sync-Modus, da er keine Scraper/Prozessoren braucht # --- Modus-Dispatching ---
print("DEBUG: Bin direkt vor der 'if selected_mode == sync'-Abfrage.") # <<< HINZUGEFÜGT start_time = time.time()
if selected_mode == "sync": if selected_mode == "sync":
print("DEBUG: Sync-Modus wurde betreten.") # <<< HINZUGEFÜGT # --- SPEZIFISCHE LOGIK FÜR DEN SYNC-MODUS ---
logger.info("Führe Initialisierung für Sync-Modus durch...")
# KORREKTUR: Explizites Laden der Sheet-Daten, da der DataProcessor umgangen wird.
if not sheet_handler.load_data():
logger.critical("Konnte initiale Daten aus dem Google Sheet nicht laden. Sync-Prozess wird abgebrochen.")
return
d365_file_path = args.sync_file d365_file_path = args.sync_file
if not os.path.exists(d365_file_path): if not os.path.exists(d365_file_path):
logger.critical(f"Export-Datei nicht gefunden: {d365_file_path}") logger.critical(f"Export-Datei nicht gefunden: {d365_file_path}")
@@ -180,16 +181,13 @@ def main():
sync_manager = SyncManager(sheet_handler, d365_file_path) sync_manager = SyncManager(sheet_handler, d365_file_path)
sync_manager.run_sync() sync_manager.run_sync()
else: else:
# Bisherige Initialisierung für alle anderen Modi # --- BISHERIGE LOGIK FÜR ALLE ANDEREN MODI ---
wiki_scraper = WikipediaScraper() wiki_scraper = WikipediaScraper()
data_processor = DataProcessor(sheet_handler=sheet_handler, wiki_scraper=wiki_scraper) data_processor = DataProcessor(sheet_handler=sheet_handler, wiki_scraper=wiki_scraper)
# --- Modul-Versionen loggen ---
modules_to_log = { modules_to_log = {
"DataProcessor": data_processor, "DataProcessor": data_processor, "GoogleSheetHandler": google_sheet_handler,
"GoogleSheetHandler": google_sheet_handler, "WikipediaScraper": wikipedia_scraper, "Helpers": helpers
"WikipediaScraper": wikipedia_scraper,
"Helpers": helpers
} }
log_module_versions(modules_to_log) log_module_versions(modules_to_log)
@@ -197,12 +195,10 @@ def main():
logger.critical("Setup des DataProcessors fehlgeschlagen. Das Skript wird beendet.") logger.critical("Setup des DataProcessors fehlgeschlagen. Das Skript wird beendet.")
return return
# --- Modus-Dispatching ---
start_time = time.time()
steps_to_run_set = set(step.strip().lower() for step in args.steps.split(',') if step.strip() in valid_steps) if args.steps else set(valid_steps) steps_to_run_set = set(step.strip().lower() for step in args.steps.split(',') if step.strip() in valid_steps) if args.steps else set(valid_steps)
if selected_mode == "full_run": if selected_mode == "full_run":
# ... (Rest der Logik bleibt unverändert)
start_row = args.start_sheet_row or sheet_handler.get_start_row_index("Timestamp letzte Pruefung") + sheet_handler._header_rows + 1 start_row = args.start_sheet_row or sheet_handler.get_start_row_index("Timestamp letzte Pruefung") + sheet_handler._header_rows + 1
num_to_process = args.limit or (len(sheet_handler.get_all_data_with_headers()) - start_row + 1) num_to_process = args.limit or (len(sheet_handler.get_all_data_with_headers()) - start_row + 1)
data_processor.process_rows_sequentially( data_processor.process_rows_sequentially(
@@ -220,21 +216,15 @@ def main():
process_website_steps='web' in steps_to_run_set, process_website_steps='web' in steps_to_run_set,
process_ml_steps='ml_predict' in steps_to_run_set process_ml_steps='ml_predict' in steps_to_run_set
) )
# ... (alle anderen elif-Blöcke bleiben wie sie sind) ... # ... (usw. für alle anderen Modi)
elif selected_mode == "reclassify_branches": elif selected_mode == "reclassify_branches":
data_processor.reclassify_all_branches( data_processor.reclassify_all_branches(start_sheet_row=args.start_sheet_row, limit=args.limit)
start_sheet_row=args.start_sheet_row,
limit=args.limit
)
elif selected_mode == "alignment": elif selected_mode == "alignment":
alignment_demo(sheet_handler) alignment_demo(sheet_handler)
elif selected_mode == "train_technician_model": elif selected_mode == "train_technician_model":
data_processor.train_technician_model() data_processor.train_technician_model()
elif selected_mode == "predict_technicians": elif selected_mode == "predict_technicians":
data_processor.process_predict_technicians( data_processor.process_predict_technicians(start_sheet_row=args.start_sheet_row, limit=args.limit)
start_sheet_row=args.start_sheet_row,
limit=args.limit
)
elif hasattr(data_processor, f"process_{selected_mode}"): elif hasattr(data_processor, f"process_{selected_mode}"):
method_to_call = getattr(data_processor, f"process_{selected_mode}") method_to_call = getattr(data_processor, f"process_{selected_mode}")
method_args = {} method_args = {}
@@ -250,8 +240,8 @@ def main():
else: else:
logger.error(f"Unbekannter Modus '{selected_mode}' im Dispatcher.") logger.error(f"Unbekannter Modus '{selected_mode}' im Dispatcher.")
duration = time.time() - start_time duration = time.time() - start_time
logger.info(f"Verarbeitung im Modus '{selected_mode}' abgeschlossen. Dauer: {duration:.2f} Sekunden.") logger.info(f"Verarbeitung im Modus '{selected_mode}' abgeschlossen. Dauer: {duration:.2f} Sekunden.")
except (KeyboardInterrupt, EOFError): except (KeyboardInterrupt, EOFError):
logger.warning("Skript durch Benutzer unterbrochen.") logger.warning("Skript durch Benutzer unterbrochen.")