Let me introduce myself!
My full name is Tiago Patricio Santos and I'm a highly skilled and experienced software engineer with a strong foundation in computer engineering and deep learning. I hold Data Scientist Professional and Data Analyst Associate certifications from DataCamp, as well as a Deep Learning Specialization from DeepLearning.AI.
My main skills include troubleshooting, problem resolution, a positive and friendly attitude, and a strong work ethic. I am proficient in programming languages such as C#, SQL, and Python. In my previous experience, I have successfully worked as a team leader, project manager, and software developer, with experience in the oil and gas industry and implementing ERP solutions.
Problem statement: "My friend is in the job market. However, they keep wasting time applying for fraudulent job postings. They have asked me to use my data skills to filter out fake postings and save them effort. They have mentioned that job postings are abundant, so they would prefer my solution to risk filtering out real posts if it decreases the number of fraudulent posts they apply to."
Part 1 - is all about getting to know the Dataset using Exploratory analysis, cleaning data, choosing the metrics, and doing the first model prediction experiments.
In this part of the project, the setup of DagsHub, DVC, and MLFlow was demonstrated to create a version-controlled data science project, as well as tracking experiment parameters and metrics and comparing experiments. The steps for creating a virtual Python environment, installing requirements, and downloading raw data were also discussed. Finally, the code to load, process, train, and evaluate a classification model was shown, with environment variables stored in the .env file and tracked using MLFlow. This part of the project demonstrates the importance of using tools like DagsHub, DVC, and MLFlow to simplify data science workflows and ensure reproducibility.
Part 3 focuses on the deployment, where MLFlow and FastAPI are used to deploy the model into a WebAPI and serve it with Mogenius, a Virtual DevOps platform. The three parts of the project work together to provide a comprehensive overview of end-to-end ML development, from data exploration to deployment.
I developed a tool called Jupyter2Hashnode that simplifies the process of converting Jupyter Notebooks into Hashnode stories. I discovered Hashnode, a platform specifically designed for developers and the tech industry that offers a powerful editor that supports markdown text and provides an Amazon AWS S3 bucket for uploading images. Jupyter2Hashnode compresses images, uploads them to the Hashnode server, updates image URLs in the markdown file, and publishes the story article with just a single command. This tool is designed to help data scientists share their work with a larger audience and overcome limitations when it comes to data representation on other platforms like Medium.
