(venv) PS D:\Zidan\1. Machine Learning\sum_liputan6> python train_evaluate.py --model textrank --train_limit 5000
=== Training TEXTRANK Model ===
Loading training data...
Training data: 5000 articles
Training completed in 0.00 seconds

Evaluating on dev set...

=== Evaluating on DEV set ===
Evaluating on 100 articles...
Extractive Performance:
  accuracy: 0.7547
  precision: 0.2800
  recall: 0.2617
  f1: 0.2705
ROUGE Scores:
  rouge-1: 0.2813
  rouge-2: 0.1247
  rouge-l: 0.2265

Model saved to saved_models/textrank_model.pkl