Software developers interested to get started with data science are often overwhelmed by the amount of choices: what language to use, which libraries, where to find suitable data?
Also, many tutorials focus on a single technology making it difficult to understand the whole scope of a data science project. We have created an open-source example application that is optimized to serve as a playground for learning and experimentation. Nevertheless, it works on a realistic dataset, addresses a typical machine learning task one may encounter on the job (demand forecasting), and applies an industry-standard toolset (Python3, Pandas, Jupyter Notebook, AWS).
In this session we'll run you through the entire workflow of a machine learning application and introduce you to the different phases of a data science project: data exploration, prototyping, validation, and productization. From there on we will guide you to work hands-on on improving prediction accuracy or other features of the application.
Target Audience: Software developers who want to learn data science practices
Prerequisites: Bring a computer, ideally have anaconda or a similar python distribution installed