Department of Computer Science and Technology

Course pages 2018–19

Data Science: principles and practice

Practicals

There will be four short practicals. Each practical is worth 5% of the final module mark. These will be `ticked' rather than graded: i.e., for each assignment, 100% of the mark is awarded for satisfactory completion and 0% for inadequate work or failure to submit. This does NOT mean that the answers have to be completely `correct', (there is anyway often genuine disagreement on some aspects of e.g. dataset preprocessing), just that a reasonable and informed attempt has been made.

Students are free to work on these practicals after they have been uploaded to this page after the proceeding lecture but should attend the practical session in order to complete the work and obtain their 'tick'. As a rough guide students should spend no more than 4 hours per practical.

  • Practical 1: Linear Regression (Scikit-Learn) Deadline 11am, 7th November.
  • Practical 2: Linear Classification (Scikit-Learn) Deadline 11am, 12th November.
  • Practical 3: Deep Learning (TensorFlow) Deadline 11am, 19th November.
  • Practical 4: Visualization Deadline 11am, 26th November.

    Further information about the practicals can be found here:

  • https://github.com/marekrei/cl-datasci-pnp
  • https://notebooks.azure.com/marekrei/libraries/cl-datasci-pnp

    Take-home Assessment

    • Final Practical: (max. 24 hours) Available after final lecture 28th November

    There will be an assessed and graded final practical based on the material covered in the lectures and previous practicals. Students will write a practical report that will consist of a description and evaluation of the work done of not more than 2500 words excluding tables, graphs and images. It will contribute 80% of the final mark. The deadline for handing in completed reports to student administration is Friday 30th November 2018, 5pm.