This project offers a great initiation into Machine Learning Operations. It's a comprehensive end-to-end machine learning project, providing an immersive experience through a full project cycle. Hosted on an AWS server, this application is an ideal learning platform for enthusiasts keen on SQL, cloud services, machine learning, MLOps (Machine Learning Operations), CI/CD (Continuous Integration and Continuous Deployment), among other areas.
Deep Learning Model: Developed a transformer-based deep learning model using PyTorch for weather forecasting, focusing on time-series analysis. This model accurately predicts temperatures by analyzing humidity and other relevant features.
SQL Database Management: Acquired extensive expertise in SQL database management. Responsibilities included designing, querying, and manipulating multiple datasets, with a focus on historical weather data.
Cloud Integration (AWS): Demonstrated proficiency in deploying applications and managing databases on Amazon Web Services (AWS). Gained experience in various AWS services like AWS RDS, AWS S3, and AWS EC2.
MLOps Application: Seamlessly integrated MLflow for deploying, monitoring, and maintaining machine learning models, ensuring their robustness and reliability in real-world applications.
CI/CD Expertise: Implemented and managed a Continuous Integration and Continuous Deployment (CI/CD) pipeline using GitHub Actions. This automated deployment processes and maintained application functionality.
Docker and AWS Deployment: Showcased skills in Docker containerization and efficient application management. Proficiently used AWS for scalable cloud deployment.
Automated Data Processing: Implemented automated data processing and scheduling using Cron Jobs. Utilized Python scripts for data ingestion, model predictions, and monitoring on an AWS EC2 instance, enhancing operational efficiency.