Machine Learning Learning Repository

This repository is a beginner-friendly path for learning machine learning with Python. It is organized like a clean tutorial repo: each numbered folder teaches one topic with a self-contained Jupyter notebook, small datasets where useful, and practice exercises.

Learning Path

Start from Python basics, move into the data stack, then learn supervised learning, unsupervised learning, model evaluation, tuning, saving models, and complete projects.

Folder List

1. 01. Python For ML
2. 02. NumPy
3. 03. Pandas
4. 04. Matplotlib And Seaborn
5. 05. Data Cleaning
6. 06. Exploratory Data Analysis
7. 07. Feature Engineering
8. 08. Train Test Split
9. 09. Linear Regression
10. 10. Multiple Linear Regression
11. 11. Polynomial Regression
12. 12. Logistic Regression
13. 13. Decision Tree
14. 14. Random Forest
15. 15. Support Vector Machine
16. 16. K-Nearest Neighbors
17. 17. Naive Bayes
18. 18. K-Means Clustering
19. 19. Hierarchical Clustering
20. 20. Principal Component Analysis
21. 21. Regularization
22. 22. Cross Validation
23. 23. Hyperparameter Tuning
24. 24. Model Evaluation Metrics
25. 25. Imbalanced Data Handling
26. 26. Ensemble Learning
27. 27. Bagging And Boosting
28. 28. Gradient Boosting
29. 29. XGBoost
30. 30. Model Saving And Loading
31. 31. End-To-End ML Projects

How to Run the Notebooks

1. Create and activate a virtual environment.
2. Install the requirements:

pip install -r requirements.txt

3. Start Jupyter:

jupyter notebook

4. Open the folders in order and run each notebook from top to bottom.

Recommended Study Order

Follow the numbered folders from 01. Python For ML through 31. End-To-End ML Projects. The order is intentional:

• 01 to 08: Python, data handling, visualization, preprocessing, and splitting data.
• 09 to 17: core supervised learning algorithms.
• 18 to 20: unsupervised learning and dimensionality reduction.
• 21 to 24: regularization, validation, tuning, and metrics.
• 25 to 29: imbalanced data and ensemble methods.
• 30 to 31: saving models and building complete ML workflows.

Notebook Pattern

Most notebooks follow this flow:

• Title and objective
• Concept explanation
• Imports
• Dataset loading
• Exploration
• Cleaning or preprocessing
• Modeling when relevant
• Evaluation
• Visualization where useful
• Try This Yourself practice section

Notes for Beginners

• Run cells in order.
• Read the markdown before changing code.
• Keep random_state = 42 while learning so your results are reproducible.
• If a notebook has a datasets folder, the data for that topic is already included locally.