This book introduces pattern mining by presenting various pattern mining techniques and giving hands-on experience with each technique. Pattern mining is a popular data mining technique with many real-world applications, and involves discovering all user interest-based patterns that may exist in a database. Several models and numerous algorithms were described in the literature to find these patterns in binary databases, quantitative databases, uncertain databases, and streams. Since the lack of a Python toolkit containing these algorithms has limited the wide adaptability of pattern-mining techniques, the author developed Pattern Mining (PAMI) Python library, which currently contains 80+ algorithms to discover useful patterns in transactional databases, temporal databases, quantitative databases, and graphs.

The book consists of three main parts:

·Introduction: The first chapter introduces big data, types of learning techniques, and the importance of pattern mining. The second chapter introduces the PAMI library, its organizational structure, installation, and usage.

·Pattern mining algorithms and examples: The following chapters present the state-of-the-art techniques for discovering user interest-based patterns in (1) transactional databases, (2) temporal databases, (3) quantitative databases, (4) uncertain databases, (5) sequential databases, and (6) graphs.

·Applications: The book concludes with several applications, where the predicted knowledge using TensorFlow and PyTorch was transformed into a database to discover future trends or patterns.