Machine Learning Practicals Package (my_ml_package / ml-1)

A comprehensive Python package containing clean implementations and datasets for 9 fundamental Machine Learning practical tasks.

⚡ Quick Start: Download Practical & Dataset to Your Downloads Folder

Once installed via pip, you can extract any practical code and its dataset right into your Downloads folder:

# Download Practical 1 (practical_1.py + salary.csv)
ml-1 download 1

# Download ALL 9 practicals and all CSVs
ml-1 download all

The folder will open in Windows Explorer. You can double-click or open practical_1.py in VS Code / IDLE, inspect the clean code, and run:

python practical_1.py

You can also run directly from Python:

import my_ml_package
my_ml_package.download(1)       # Downloads practical 1 + salary.csv
my_ml_package.download('all')   # Downloads all practicals + CSVs

Tasks Included

1. Simple Linear Regression (practical_1.py)

   • Dataset: salary.csv
   • Features: months -> Target: salary
   • Evaluation: MAE, MSE, RMSE

2. Simple Linear Regression (practical_2.py)

   • Dataset: rent.csv
   • Features: month -> Target: rent
   • Evaluation: MAE, MSE, RMSE

3. Simple Linear Regression (practical_3.py)

   • Dataset: sales.csv
   • Features: fahrenheit -> Target: sales
   • Evaluation: MAE, MSE, RMSE

4. Multiple Linear Regression (practical_4.py)

   • Dataset: house.csv
   • Features: Square footage, bedrooms, bathrooms, etc. -> Target: price
   • Evaluation: MAE, MSE, RMSE

5. Multiple Linear Regression (practical_5.py)

   • Dataset: income.csv
   • Features: age, experience -> Target: income
   • Evaluation: MAE, MSE, RMSE

6. Logistic Regression (practical_6.py)

   • Dataset: Scikit-learn Built-in Digits Dataset
   • Multi-class classification (0-9 digits)
   • Evaluation: Confusion Matrix, Classification Report, 5-Fold Cross Validation

7. Support Vector Machine (SVM) (practical_7.py)

   • Dataset: Scikit-learn Built-in Iris Dataset
   • Linear SVM classification
   • Evaluation: Confusion Matrix, Classification Report, 5-Fold Cross Validation

8. Bagging Ensemble Classifier (practical_8.py)

   • Dataset: Scikit-learn Built-in Wine Dataset
   • Bagging with Decision Trees (50 estimators)
   • Evaluation: Confusion Matrix, Classification Report, 5-Fold Cross Validation

9. Principal Component Analysis (PCA) (practical_9.py)

   • Dataset: Scikit-learn Built-in Wine Dataset
   • 2D dimensionality reduction and visualization with Matplotlib

Installation

From Local Source (Development Mode):

cd my_ml_package
pip install -e .

From PyPI (once published):

pip install <your-chosen-package-name>

How to Run in Terminal

Option 1: Command Line CLI

# Run Practical 1
ml-1 1

# Run all practicals
ml-1 all

# Download Practical 1 into Downloads
ml-1 download 1

Option 2: Python Code Import

from my_ml_package import practical_1, run_practical, run_all

# Run a single practical
result_1 = practical_1.run()

# Run all practicals
run_all()

Packaging & Publishing to PyPI

1. Set Your Unique PyPI Package Name

Open setup.py and set name='your-unique-name' (e.g. ml-practicals-kadam).

2. Build Distribution Files

python -m build

3. Upload to PyPI

twine upload dist/*

Enter __token__ as the username and your PyPI API token as the password.

License

MIT License