Administrative Information
| Title | Unsupervised Learning |
| Duration | 60 mins |
| Module | A |
| Lesson Type | Practical |
| Focus | Practical - AI Modelling |
| Topic | Data analysis |
Keywords
Clustering, Ethics, Data normalization,
Learning Goals
- learn basics of unsupervised learning
Expected Preparation
Learning Events to be Completed Before
Obligatory for Students
- Python
- pandas
Optional for Students
None.
References and background for students
None.
Recommended for Teachers
None.
Lesson materials
- [ Notebook 1 on clustering]
- [ Notebook 2 on clustering]
Instructions for Teachers
This learning event consist of laboratory tasks that shall be solved by the students with the help of the leading instructor.
You can base this class around the notebooks.
Outline/time schedule
| Duration (min) | Description | Concepts | Activity | Material | |
|---|---|---|---|---|---|
| 5 | Dataset | Tesco loyalty program DB, customers, dates, spend, days of week | Practice | Data: DataSet_Tesco5000_withDaynum.csv | |
| 15 | Clustering in 2D | Observations with raw data, Kmeans with 2, 3, 4 clusters | Notebook, coding | Notebook: 03_Clustering_I | |
| 10 | Clustering in 2D | effect of data normalization (MinMax / StandardScaler), Kmeans with 2, 3, ... 25 clusters | Notebook, coding | Notebook: 03_Clustering_I | |
| 5 | Cluster centers | plot custer centers: raw vs normalized data | Notebook, coding | Notebook: 03_Clustering_I | |
| 5 | Clustering depending on day of week | plot dependence of spending vs day-of-week (Mon, Tue, ...Sun) | Notebook, coding | Notebook: 03_Clustering_I | |
| 10 | Clustering depending on monthly visit | plot which months do the customers prefer. effect of cluster size. observations of extreme customers | Notebook, coding | Notebook: 03_Clustering_I | |
| 10 | Clustering: relate to ethics | relation to ethical datasets | ? | ? |
Acknowledgements
The Human-Centered AI Masters programme was Co-Financed by the Connecting Europe Facility of the European Union Under Grant №CEF-TC-2020-1 Digital Skills 2020-EU-IA-0068.