文件名称：python-programmers-artificial-intelligence-studies
文件大小：25.69MB
文件格式：PDF
更新时间：2022-04-17 01:45:27
Python 人工智能 AI
The professional programmer’s Deitel guide to Python with introductory artificial intelligence case studies Written for programmers with a background in another high-level language, this book uses hands-on instruction to teach today’s most compelling, leading-edge computing technologies and programming in Python–one of the world’s most popular and fastest-growing languages. Please read the Table of Contents diagram inside the front cover and the Preface for more details. In the context of 500+, real-world examples ranging from individual snippets to 40 large scripts and full implementation case studies, you’ll use the interactive IPython interpreter with code in Jupyter Notebooks to quickly master the latest Python coding idioms. After covering Python Chapters 1—5 and a few key parts of Chapters 6—7, you’ll be able to handle significant portions of the hands-on introductory AI case studies in Chapters 11—16, which are loaded with cool, powerful, contemporary examples. These include natural language processing, data mining Twitter for sentiment analysis, cognitive computing with IBM Watson™, supervised machine learning with classification and regression, unsupervised machine learning with clustering, computer vision through deep learning and convolutional neural networks, deep learning with recurrent neural networks, big data with Hadoop, Spark™ and NoSQL databases, the Internet of Things and more. You’ll also work directly or indirectly with cloud-based services, including Twitter, Google Translate™, IBM Watson, Microsoft Azure, OpenMapQuest, PubNub and more. Features 500+ hands-on, real-world, live-code examples from snippets to case studies IPython + code in Jupyter Notebooks Library-focused: Uses Python Standard Library and data science libraries to accomplish significant tasks with minimal code Rich Python coverage: Control statements, functions, strings, files, JSON serialization, CSV, exceptions Procedural, functional-style and object-oriented programming Collections: Lists, tuples, dictionaries, sets, NumPy arrays, pandas Series & DataFrames Static, dynamic and interactive visualizations Data experiences with real-world datasets and data sources Intro to Data Science sections: AI, basic stats, simulation, animation, random variables, data wrangling, regression AI, big data and cloud data science case studies: NLP, data mining Twitter, IBM Watson™, machine learning, deep learning, computer vision, Hadoop, Spark™, NoSQL, IoT Open-source libraries: NumPy, pandas, Matplotlib, Seaborn, Folium, SciPy, NLTK, TextBlob, spaCy, Textatistic, Tweepy, scikit-learn, Keras and more.