This is another End-to-End Data Science project that I implemented during my DS course on Udemy

The project studies the rate of phishing on the network and evaluate its dependency on certain variables to ensure more proper Network Security condition

The Project is fully and comprehensively structured with Exception handling, Logging, Creating pipelines for:

• Ingesting Data from csv-uploaded MongoDB database
• Transforming Data using sklearn transformation pipeline
• Data Validation
• Model Training

The project is also packed with data_training pipeline, including all steps above. Besides, all steps will produce they own tracked logs and output artifact, consisting of output file and pickled applications

Github action is also added with the workflow .yml file to auto deploy the result on AWS and Docker

However, due to my unfamiliarity with the workflow there are still un-solved errors and deployment hardship