This repository hosts a series of Jupyter notebooks designed as hands-on laboratory exercises in data mining and data analysis. Each notebook walks through stages such as data exploration, cleaning, feature engineering, modelling, and evaluation.
| Notebook | Focus |
|---|---|
lab1.ipynb |
Linear & Logistic regression from scratch |
lab2.ipynb |
Data preprocessing, cleaning, and visualisation. Trained main ML models for Binary classification: 1) KNN 2) Decision Tree 3) SVM 4) SVM with Gridsearch 5) Random Forest 6) Random Forest with Gridsearch 7) AdaBoost 8) AdaBoost with Gridsearch |
lab3.ipynb |
- Clusterisation: 1) PCA 2) TSNE 3) Clustering applying in images size reducing 4) EM - Word Cloud - Classification: 1) SVM 2) LDA |
lab4.ipynb |
Basic Neural Networks: 1) Fully connected feed-forward network 2) Convolutional neural network 3) Recurrent neural network |
lab5.ipynb |
Deep Generative Models: 1) Sequence generation (seq2seq + ReacherForsing) 2) Image generation |
- Python 3.7+
- Jupyter / JupyterLab
- Common data science libraries:
pandas,numpy,scikit-learn,matplotlib,seaborn, etc.