Fix data ingestion path, update README images, and enable reload

Optimize deployment config

feat: Initialize project structure with ML components, utilities, exception handling, and S3 integration.

feat: Implement web application for phishing URL detection with new UI, integrated model training, and prediction endpoints, removing old artifacts.

full CI/CD pipeline with Docker Compose + MongoDB fallback

Changed the port to 8080 and dagshub init enavles uding Variable "ENABLE_DAGSHUB"

Cloud pushed and s3 data storage implemented

Pipeline completed and fastapi created

mlflow and dagshub and you can see the models and compare them side by side and pick the best model according to you , I am using test_f1 as decision metric

mlflow implemented in model_trainer.py

Model Trainer And Evaluation With Hyperparameter Tuning

Data Transformation done

Data Validation done

Data Ingestion done

Exception Handling and logging done

Created file structure