Model evealuation (#11)

* Add model selection script and evaluation metrics for phishing detection

* Add modular components for phishing detection model training and evaluation

* Add training script for phishing detection model with extensive hyperparameter search and Hopsworks integration

* Add workflow for training final model with hyperparameter search and Hopsworks integration

* Refactor import statements to use src directory structure for URL scanning and sitemap extraction

* Refactor import statements to align with src directory structure for data preprocessing

* fix to the pipline

.github/workflows/scheduled_data_pipeline.yml

@@ -87,7 +87,7 @@ jobs:
           HOPSWORKS_API_KEY: ${{ secrets.HOPSWORKS_API_KEY }}
           HOPSWORKS_PROJECT_NAME: ${{ secrets.HOPSWORKS_PROJECT_NAME }}
         run: |
-          uv run python src/phising_detection/features/batch_url_scanner.py \
+          uv run python -m src.phising_detection.features.batch_url_scanner \
             --fg1-name phishing_urls \
             --fg1-version 2 \
             --fg2-name legit_urls_before_scan \