Review of the week

This week you have learned the basics of data science work. We took a simple data set from the Tate Modern composed of information about paintings, and demonstrated the process of cleaning, transforming and filtering the data to obtain a subset of the data that we can use to explore our research question.

You also learned the process of building, and exploring an initial model based on computing simple ratios for classifying landscapes and portraits. You then saw how to use other aspects of the data in order to build a competing model.

Finally, you learned about vectors and metrics and saw how these concepts allowed us to transform our data in a way that encompassed both of the simple models and allowed us to user an unsupervised learning algorithm called k-means.

Your task

• Did you find this type of work interesting? Can you imagine working as data scientist?
• What other ideas would you like to try on the Tate dataset?

Please share your responses with your fellow learners in the comments.