Foundation for Data Science

The teaching will be performed in the form of lectures (one per week), practises (two per week), and independent studies. All the material will be taught in three stages. The first stage explains the motivation and intuition behind a particular notion or method. Then, a more formal explanation is given, supported with proper numeric example and exercises to be conducted during the practise. Finally, directions for studies are provided for those willing to study the subject in depth. The performance of the students will be evaluated on the basis of their progress with respect to the first two stages. The evaluation of the students' knowledge will be evaluated through practical tests conducted during practise and a general written exam at the end of the course. Starting with the general overview of the data science field, we first position the scope of the problems and explain relations to statistics and probability theory, mathematics, and computer science. Then, students are taught to formally state the problem of data science. As the intermediate step we explain the meaning of the main notions inherited from statistics, probability theory, calculus, linear algebra, and computer science. The usual workflow used in data science is then explained in detail and illustrated by the numeric examples. Besides the classical steps such as data preprocessing, feature engineering, model training, and validation, results interpretation using the methods of explainable AI will be considered.

NB! This course will take place in autumn semester 2026/2027 which starts on 31st of August and ends on 24th of January (you can find that information under start date section). TalTech's timetables for autumn semester 2026 will be published at the end of June via tunniplaan.taltech.ee.

After completing this course, the student:

• describes the scope of data science problems and methods;
• defines the notions used in the data science (incl. those inherited from other disciplines);
• uses Jupyter environment to write simple code in Python programming language;
• chooses and uses the packages used in data science, such as NumPy, Pandas, and SK Learn;
• designs and codes (program) the workflow to solve problems of clustering, classification and regression;
• chooses and uses basic visualisation tools.

Final assessment can consist of one test/assignment or several smaller assignments completed during the whole course. After declaring a course the student can re-sit the exam/assessment once. Assessment can be graded or non-graded. For specific information about the assessment process please get in touch with the contact person of this course. For specific information about grade transfer please contact your home university

no prerequisites

• Loengute slaidid, harjutused ja harjutuste lühijuhendid jagatakse Moodle'i keskkonnas.

lectures, exercises