A hands-on Heroku walkthrough: create a conda virtual environment on macOS, install Django and gunicorn, and push a brand-new Django app live step by step.

The last step in the ML workflow is model inference: deploying a trained model and running predictions. See how it differs from training, plus Pruning and Quantization.

Once training is done, how do you know a model is any good? A look at model evaluation, what overfitting is, and the metrics used for classification and regression tasks.

Third in our beginner's ML series: what training a model really means, how parameters and the loss function relate, plus hyperparameters, libraries, and model types.

Data preparation eats up roughly 80% of a machine learning project's time. Learn its four stages: collection, inspection, summary statistics, visualization.

Part 1 of a 5-step ML workflow: how to define a problem clearly, and tell supervised learning (regression, classification) apart from unsupervised clustering.

Learn the key difference between a Python Module and a Package. This beginner-friendly guide explains how to use packages and the __init__.py file to organize your code effectively, with a simple, step-by-step example.