As a data scientist, I always felt a missing link between my developed models and putting them in the production process.
Yes, I can create a pipeline, write a model, get results, and interpret the results, but if I cannot scale it, these all will sit on my Jupiter notebooks. This thought led me to my data engineering adventure. I am confident that learning data engineering will make me a better data scientist.
Where did I start?
I joined Andreas's coaching sessions, and I am a member of his sessions from the November 2020 cohort. Our cohort just finished the first week, and the most important lesson I have learned so far is how to think about a given problem in a structured way.
During our first week, Andreas helped us navigate the industry that interests each of us, and this is how we picked a dataset to work on for the next following weeks. I ended up picking yelp dataset, which aligns with my interests in analyzing user behaviors. Like any other problem, we also came up with business objectives and formulated the problem according to the direction.
What will I do next?
Since the available tools are pretty diverse, the next step is to break down the project into smaller pieces, i.e., connect, buffer, processing, storage, visualization, and focus on specific tools for each of these pieces.
I look forward to sharing more details of my yelp project and showcasing what I would learn from my data in my next blogs.
Say hello on LinkedIn: https://www.linkedin.com/in/liuna-issagholian/