Overall about the course¶
This course will teach you how to think about data and analyze it in order to perform a professional exploratory data analysis (EDA) report.
It will include data analytics problems such as:
How is the dataset formatted and is it the right format for what I want to do?
Is this dataset representative or does it reflect an objective sample?
What technical issues should be considered when organizing and cleaning the data?
What method of data visualization and analysis should be used for a given measurement scale of the selected variable?
How to make a statistical description of the data?
How to select the method of inference from the sample for the given research problem?
These topics will be discussed in the context of a series of short practical exercises with real data sets in the Python development environment. We will be using Visual Studio Code, Jupyter Notebook format, possibly a Markdown (MD) file permanently linked to your repository on GitHub thanks to the GitLens plugin.
Key Learning Outcomes¶
This course is designed to provide the student(s) with a range of conceptual and technical tools. My goal is that by the end of the course you will be able to:
Diagnose and fix technical data problems ranging from data gaps, outlier observations, dirty data (non-constant).
Design and implement clear, concise and accurate cross-sectional data visualizations.
Course logistics¶
Teaching team¶
Karol Flisikowski: University Professor in the Department of Statistics and Econometrics PG.
Consultations¶
| Who | When | Where? |
|---|---|---|
| Karol Flisikowski | Wednesdays 12-13 | Online |
Final evaluation¶
Final project¶
Your final grade is based on all activitites & gradebook on Enauczanie (Moodle platform).
Grading scale¶
If you are taking the course for a grade, your grade will be determined according to the following scale.
Note that the number on the right side of the range is not included in the given range: that is, “4.5” ranges from 84% all the way up to 90.99%, but does not include 91% (91% is 5.0).
| Percentage | Rating |
|---|---|
| > 94% | 5.0 |
| 86-94% | 4.5 |
| 79-86% | 4.0 |
| 70-79% | 3.5 |
| 60-70% | 3.0 |
| < 60% | no credit |
About rounding up¶
Please note that my policy is not to round grades up for two reasons:
if rounding is applied selectively (i.e., only to listeners who request it), it is unfair to others.
if rounding is applied universally, it simply redefines the boundary between two letter grades (e.g., making 87% the cutoff point for 4.5).
Late submission of a projects etc.¶
Students may submit late assignments up to 48 hours after the submission deadline, earning 75% of the points they would have received (i.e., if they scored 90%, they will receive 67.5% with a late penalty).
Otherwise - in accordance with the regulations of the postgraduate program and the contract, you are entitled to corrective credit in the next edition of the 2026 study.
Questions, feedback and communication¶
Instructors can be contacted as follows:
Office hours.
Public question on the Discord channel of the DS 2026 course.
Private message via Discord.
E-mail.
Join the DS 2026 course Teams channel here: DS 2026 Teams channel
Please note that we generally prefer to communicate via Discord rather than email.
Academic integrity¶
We ask you to turn in your own work. Although we encourage you to work together on some assignments, you should still understand the submitted code.
Task sets and the final project should be done independently.
Cheating and plagiarizing are unfair to others and ultimately to you. Instead, if you have difficulties with something - ask for help!