Your data, your insights: creating personal data projects to (re-)own the data you share

Data Scientists are often restricted with working with the specific kind of data their company or projects are focused on. At the same time, we’re all constantly sharing our own personal data with diverse apps that use our information in trade for a service: social networking & messaging apps, fitness tracking, internet searches i.a.. And although this data is often more valuable to us that the one we spend hours dealing with at our jobs and we have the skills to use it, we rarely take the time to work with it.

In this talk, I will show three examples to illustrate how we can apply common data science libraries - pandas, scikit-learn, seaborn ,plolty and streamlit - together with data shared via mobile apps or collected manually to build little personal projects that we can learn something from. The examples will include whatsapp data turned into infographics; family game statistics data tuned into a predictive model deployed as a web app; and manually collected language acquisition data turned into interactive data visualizations.

For Data Scientists working with personal data, not only extends the scope of applications for their skills but also help reconnect data to people beyond commercial tecnological applications. For other python coders, these kind of personal data projects are a great introduction to the tasks of a the Data Scientists. And as we're all collecting and sharing data anyway we might as well make use of it to regain power over it.