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

train_model.py aktualisiert

Browse Source
This commit is contained in:
Floke
2025-09-24 19:21:45 +00:00
parent 1e996a0023
commit e052933704
1 changed files with 47 additions and 44 deletions
Download Patch File Download Diff File Expand all files Collapse all files

83
train_model.py
View File

@@ -1,3 +1,4 @@
# train_model_v3.0.py (final)
import pandas as pd
import numpy as np
import re
@@ -10,7 +11,7 @@ from thefuzz import fuzz
from collections import Counter
import logging
import sys
import os
from google_sheet_handler import GoogleSheetHandler
from helpers import normalize_company_name
@@ -25,91 +26,93 @@ CRM_PREDICTION_FILE = 'crm_for_prediction.pkl'
BEST_MATCH_COL = 'Best Match Option'
SUGGESTION_COLS = ['V2_Match_Suggestion', 'V3_Match_Suggestion', 'V4_Match_Suggestion']
STOP_TOKENS_BASE = {
'gmbh','mbh','ag','kg','ug','ohg','se','co','kgaa','inc','llc','ltd','sarl', 'b.v', 'bv',
'holding','gruppe','group','international','solutions','solution','service','services',
}
CITY_TOKENS = set()
# ... (Alle Hilfsfunktionen bleiben identisch zu Version 2.4/2.5) ...
def _tokenize(s: str):
if not s: return []
return re.split(r"[^a-z0-9äöüß]+", str(s).lower())
def clean_name_for_scoring(norm_name: str):
STOP_TOKENS_BASE = {'gmbh','mbh','ag','kg','ug','ohg','se','co','kgaa','inc','llc','ltd','sarl', 'b.v', 'bv','holding','gruppe','group','international','solutions','solution','service','services'}
CITY_TOKENS = set()
if not norm_name: return "", set()
tokens = [t for t in _tokenize(norm_name) if len(t) >= 3]
stop_union = STOP_TOKENS_BASE | CITY_TOKENS
final_tokens = [t for t in tokens if t not in stop_union]
return " ".join(final_tokens), set(final_tokens)
def choose_rarest_token(norm_name: str, term_weights: dict):
_, toks = clean_name_for_scoring(norm_name)
if not toks: return None
return max(toks, key=lambda t: term_weights.get(t, 0))
def create_features(mrec: dict, crec: dict, term_weights: dict):
features = {}
n1_raw = mrec.get('normalized_CRM Name', '')
n2_raw = crec.get('normalized_name', '')
clean1, toks1 = clean_name_for_scoring(n1_raw)
clean2, toks2 = clean_name_for_scoring(n2_raw)
features['fuzz_ratio'] = fuzz.ratio(n1_raw, n2_raw)
features['fuzz_partial_ratio'] = fuzz.partial_ratio(n1_raw, n2_raw)
features['fuzz_token_set_ratio'] = fuzz.token_set_ratio(clean1, clean2)
features['fuzz_token_sort_ratio'] = fuzz.token_sort_ratio(clean1, clean2)
domain1_raw = str(mrec.get('CRM Website', '')).lower()
domain2_raw = str(crec.get('CRM Website', '')).lower()
domain1 = domain1_raw.replace('www.', '').split('/')[0].strip()
domain2 = domain2_raw.replace('www.', '').split('/')[0].strip()
features['domain_match'] = 1 if domain1 and domain1 == domain2 else 0
features['city_match'] = 1 if mrec.get('CRM Ort') and crec.get('CRM Ort') and mrec['CRM Ort'] == crec['CRM Ort'] else 0
features['country_match'] = 1 if mrec.get('CRM Land') and crec.get('CRM Land') and mrec['CRM Land'] == crec['CRM Land'] else 0
features['country_mismatch'] = 1 if (mrec.get('CRM Land') and crec.get('CRM Land') and mrec['CRM Land'] != crec['CRM Land']) else 0
overlapping_tokens = toks1 & toks2
rarest_token_mrec = choose_rarest_token(n1_raw, term_weights)
features['rarest_token_overlap'] = 1 if rarest_token_mrec and rarest_token_mrec in toks2 else 0
features['weighted_token_score'] = sum(term_weights.get(t, 0) for t in overlapping_tokens)
features['jaccard_similarity'] = len(overlapping_tokens) / len(toks1 | toks2) if len(toks1 | toks2) > 0 else 0
features['name_len_diff'] = abs(len(n1_raw) - len(n2_raw))
features['candidate_is_shorter'] = 1 if len(n2_raw) < len(n1_raw) else 0
return features
if __name__ == "__main__":
# ... (der gesamte Trainingsprozess bis zum Speichern) ...
log.info("Starte Trainingsprozess (v3.0 final)")
try:
gold_df = pd.read_csv(GOLD_STANDARD_FILE, sep=';', encoding='utf-8')
sheet_handler = GoogleSheetHandler()
crm_df = sheet_handler.get_sheet_as_dataframe(CRM_SHEET_NAME)
except Exception as e:
log.critical(f"Fehler beim Laden der Daten: {e}")
sys.exit(1)
crm_df.drop_duplicates(subset=['CRM Name'], keep='first', inplace=True)
crm_df['normalized_name'] = crm_df['CRM Name'].astype(str).apply(normalize_company_name)
gold_df['normalized_CRM Name'] = gold_df['CRM Name'].astype(str).apply(normalize_company_name)
term_weights = {token: math.log(len(crm_df) / (count + 1)) for token, count in Counter(t for n in crm_df['normalized_name'] for t in set(clean_name_for_scoring(n)[1])).items()}
features_list, labels = [], []
crm_lookup = crm_df.set_index('CRM Name').to_dict('index')
suggestion_cols_found = [col for col in gold_df.columns if col in SUGGESTION_COLS]
for _, row in gold_df.iterrows():
mrec = row.to_dict()
best_match_name = row.get(BEST_MATCH_COL)
if pd.notna(best_match_name) and str(best_match_name).strip() != '' and best_match_name in crm_lookup:
features_list.append(create_features(mrec, crm_lookup[best_match_name], term_weights))
labels.append(1)
for col_name in suggestion_cols_found:
suggestion_name = row.get(col_name)
if pd.notna(suggestion_name) and suggestion_name != best_match_name and suggestion_name in crm_lookup:
features_list.append(create_features(mrec, crm_lookup[suggestion_name], term_weights))
labels.append(0)
X, y = pd.DataFrame(features_list), np.array(labels)
log.info(f"Trainingsdatensatz erstellt mit {X.shape[0]} Beispielen. Klassenverteilung: {Counter(y)}")
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42, stratify=y)
scale_pos_weight = sum(y_train == 0) / sum(y_train) if sum(y_train) > 0 else 1
model = xgb.XGBClassifier(use_label_encoder=False, eval_metric='logloss', scale_pos_weight=scale_pos_weight)
model.fit(X_train, y_train)
log.info("Modell erfolgreich trainiert.")
y_pred = model.predict(X_test)
log.info(f"\n--- Validierungsergebnis ---\nGenauigkeit: {accuracy_score(y_test, y_pred):.2%}\n" + classification_report(y_test, y_pred, zero_division=0))
try:
model.save_model(MODEL_OUTPUT_FILE)
log.info(f"Modell in '{MODEL_OUTPUT_FILE}' gespeichert.")
# <<< KORREKTUR: Wir exportieren jetzt in das korrekte Format (.so für Linux) >>>
TREELITE_MODEL_SO_FILE = 'xgb_model.so'
treelite_model = treelite.Model.from_xgboost(model.get_booster())
# Dieser Befehl kompiliert das Modell in eine native Bibliothek
treelite_model.export_lib(
toolchain='gcc',
libpath=TREELITE_MODEL_SO_FILE,
params={'parallel_comp': 4}, # Anzahl der CPU-Kerne nutzen
verbose=True
)
log.info(f"Kompiliertes Modell in '{TREELITE_MODEL_SO_FILE}' gespeichert.")
joblib.dump(term_weights, TERM_WEIGHTS_OUTPUT_FILE)
log.info(f"Wortgewichte in '{TERM_WEIGHTS_OUTPUT_FILE}' gespeichert.")
crm_df.to_pickle(CRM_PREDICTION_FILE)
log.info(f"CRM-Daten in '{CRM_PREDICTION_FILE}' gespeichert.")
log.info("Alle Dateien wurden erfolgreich erstellt.")
except Exception as e:
log.critical(f"FEHLER BEIM SPEICHERN DER DATEIEN: {e}")
log.info("Alle 3 Modelldateien erfolgreich erstellt.")