This repository contains the complete code examples, snippets, and datasets from the book "Python for AI and Data Science".
The book is available on Amazon in both Kindle and Paperback formats:
The code is organized by chapter to follow the book's learning path:
- 01-toolkit: Setup and essential tools.
- 02-python-fundamentals: Python core for data science.
- 03-sql: SQL for data analysis using SQLite and BigQuery.
- 04-pandas: Data wrangling and transformation.
- 05-visualization: Professional plotting with Matplotlib and Seaborn.
- 06-ml-principles: Machine learning foundations and preprocessing.
- 07-classification: Churn prediction case study.
- 08-unsupervised-learning: Clustering and PCA.
- 09-neural-networks: Introduction to Deep Learning with Keras.
- 10-computer-vision: CNNs and Image Classification.
- 11-sequential-data: RNNs, LSTMs, and Time Series.
- 12-transformers: Modern NLP and Transformer architectures.
- 13-llm-apps: Building applications with Large Language Models.
- 14-mlops: Machine Learning Operations and MLflow.
- 15-deployment: Building and deploying APIs with FastAPI and Docker.
- 16-monitoring: Testing and monitoring models in production.
- 17-capstone: End-to-end data science project.
-
Clone the repository:
git clone https://github.com/wkambale/python-ds-ai-book.git
-
Datasets: The datasets used in the book are available in the datasets directory.
-
Environments: It is recommended to use a virtual environment for the projects. Specific requirements are often listed within the code comments.
Many of these examples utilize African-centric datasets (e.g., MobiCash transactions, agriculture data, local language tokenization) to provide relevant, real-world context for practitioners on the continent.