Scikit-Learn Practice Projects

This repository contains machine learning practice notebooks, datasets, saved models, and a small Flask-based house price prediction project.

Folder Structure

1. Bagging - Bagging classifier examples with the diabetes dataset.
2. Decision Tree - Decision tree examples using salary and Titanic datasets.
3. One Hot Encoding - One-hot encoding and dummy variable examples.
4. Hyperparameter Tuning - Model tuning examples.
5. K-Means Clustering - K-Means clustering examples for income and Iris datasets.
6. K-Fold Cross Validation - K-Fold and cross-validation examples.
7. K-Nearest Neighbor Classification - KNN classification notebook.
8. Linear Regression - Linear regression notebooks, sample CSV files, and saved models.
9. Logistic Regression - Binary and multiclass logistic regression notebooks.
10. Multivariate Regression - Multivariate regression examples.
11. Naive Bayes - Naive Bayes examples for Titanic, wine, and spam classification.
12. Principal Component Analysis - PCA example notebook.
13. Projects - Bangalore house price prediction project with notebook, model, client, and Flask server.
14. Random Forest - Random forest notebook.
15. Regularization - Regularization notebook and housing dataset.
16. Support Vector Machine - SVM notebook.
17. Train And Test Split - Train/test split notebook and data.
18. Miscellaneous Files - Additional compiled class files.

Requirements

The notebooks use common Python data science packages:

• Python
• Jupyter Notebook
• numpy
• pandas
• matplotlib
• scikit-learn
• flask and flask-cors for the house price prediction server

Install the main dependencies with:

pip install numpy pandas matplotlib scikit-learn flask flask-cors notebook

Running Notebooks

Start Jupyter from the repository root:

jupyter notebook

Then open any notebook from the numbered topic folders.

House Price Prediction Project

The project is under 13. Projects.

To run the Flask server:

cd "13. Projects/server"
python server.py

Then open 13. Projects/client/app.html in a browser. The client expects the API at http://127.0.0.1:5000.

Notes

• Folder names have been numbered and capitalized for a cleaner learning sequence.
• Generated Python cache files and Jupyter checkpoint folders are ignored by git.