[PYTHON] [Summary of books and online courses used for programming and data science learning]

Books

** Deep Learning G Test Official Text, Shinichi Asakawa, Arisa Ema, Ikuko Kudo, Yusuke Negago, Keisuke Seya, Takayuki Matsui, Yutaka Matsuo, 2018, JDLA ** https://www.amazon.co.jp/深層学習教科書-ディープラーニング-G検定(ジェネラリスト)-公式テキスト-浅川-ebook/dp/B07H2ZR6M2/ It covers a wide range of content from the basics of deep learning to the handling of big data. Beginners.

** Deep Learning from scratch-Theory and implementation of deep learning learned with Python, Yasuki Saito, 2016, O'Reilly Japan ** https://www.amazon.co.jp/ゼロから作るDeep-Learning-―Pythonで学ぶディープラーニングの理論と実装-斎藤-康毅/dp/4873117585 Basic content. Beginners.

** Data analysis technology that wins at Kaggle, Daisuke Kadowaki, Takashi Sakata, Keisuke Hosaka, Yuji Hiramatsu, 2019, Gijutsu-Hyoronsha ** https://www.amazon.co.jp/Kaggleで勝つデータ分析の技術-門脇-大輔/dp/4297108437/ A wide range of practical techniques are introduced. Recommended.

Fluent Python, Clear, Concise, and Effective Programming, Luciano Ramalho, 2015, O'Reil https://www.amazon.com/Fluent-Python-Concise-Effective-Programming/dp/1491946008/ The latter half is difficult to understand at once, but it is a book for those who are familiar with Python to learn more Pythonic writing.

Deep Learning with Python, François Chollet, 2017, Manning https://www.amazon.com/Deep-Learning-Python-Francois-Chollet/dp/1617294438/ A popular book written by the developers of Keras. For beginners to intermediates who can do Python to some extent and have basic knowledge of DL / ML. Recommended.

Hands-On Machine Learning with Scikit-Learn, Keras & TensorFlow, 2nd Edition, Updated for TensorFlow 2, Concepts, Tools, and Techniques to Build Intelligent Systems, Aurélien Géron, 2019, O'Reilly https://www.amazon.com/Hands-Machine-Learning-Scikit-Learn-TensorFlow/dp/1492032646/ This is also a classic. Contents that cover the whole of machine learning and deep learning. The 2nd Edition is color printed, so it's easy to see.

Geoprocessing with Python, Chris Garrard, 2016, Manning https://www.amazon.com/Geoprocessing-Python-Chris-Garrard/dp/1617292141/ Little is mentioned about ArcGIS, the book of people who handle GIS data in Python. An open library is used in the book.

Natural Language Processing IN ACTION, Understanding analyzing, and generating text with Python, Hobson Lane, Cole Howard, Hannes Max Hapke, 2019, Manning https://www.amazon.com/Natural-Language-Processing-Action-Understanding/dp/1617294632/ If you want to learn natural language, this is the first book.

Keras Reinforcement Learning Projects, Giuseppe Ciaburro, 2018, Packt https://www.amazon.com/Keras-Reinforcement-Learning-Projects-reinforcement-dp-1789342090/dp/1789342090/ I don't recommend this very much.

Hands-on GPU Programming with Python and CUDA, Dr, Brian Tuomanen, 2018, Packt https://www.amazon.com/Hands-Programming-Python-CUDA-high-performance-ebook/dp/B07FSKH35Q/ A book for learning parallel computing programming of GPU with Python. Some knowledge of C ++ is also required.

Online course

Python Bootcamp: Go from zero to hero in Python online course (13 hours), Jose Portilla, Udemy https://www.udemy.com/course/complete-python-bootcamp/ Take 3 to look back on the basics of Python. Take 1.5 to 2 times faster for review.

Python for Data Science and Machine Learning Bootcamp online course (21.5 hours), Jose Portilla, Udemy https://www.udemy.com/course/python-for-data-science-and-machine-learning-bootcamp/ I forgot the content, but I think it was good.

Python for Financial Analysis and Algorithmic Trading online course (17 hours), Jose Portilla, Udemy https://www.udemy.com/course/python-for-finance-and-trading-algorithms/ Studying finance data. Analysis of conventional finance data, not content like stock forecasting by AI.

Beginning C++ Programming - From Beginner to Beyond online course (39.5 hours), Frank J. Mitropoulos, Udemy https://www.udemy.com/course/beginning-c-plus-plus-programming/ I was interested in GPU programming, so I learned the basics in this course. C ++ itself is difficult in the first place, so you need to study it carefully.

Microsoft Power BI - A Complete Introduction (10.5 hours), Maximilian Schwarzmüller, Maximilian Schwarzmüller, Udemy https://www.udemy.com/course/powerbi-complete-introduction/ English with a German accent, but the content is easy to understand. This alone makes me feel like I've almost mastered Power BI.

CUDA programming Masterclas (11 hours), Kasun Liyanage, Udemy https://www.udemy.com/course/cuda-programming-masterclass/learn/lecture/11833442/ Frustrated by the content and the difficulty of Indian English ...

Recommended Posts

[Summary of books and online courses used for programming and data science learning]
Summary of mathematical scope and learning resources required for machine learning and data science
[For beginners of artificial intelligence] Machine learning / Deep Learning Programming Learning path and reference books
Recommended books and sources of data analysis programming (Python or R)
Summary of recommended APIs for artificial intelligence, machine learning, and AI
Quickly build a python environment for deep learning and data science (Windows)
Summary of evaluation functions used in machine learning
Overview and useful features of scikit-learn that can also be used for deep learning
List of Python libraries for data scientists and data engineers
Summary of Pandas methods used when extracting data [Python]
Private memos used for list operations and competitive programming
Summary of sites where you can learn programming online
Numerical summary of data
Summary for learning RAPIDS
Performance verification of data preprocessing for machine learning (numerical data) (Part 2)
Summary of Hash (Dictionary) operation support for Ruby and Python
[For beginners] A word summary of popular programming languages (2018 version)
Performance verification of data preprocessing for machine learning (numerical data) (Part 1)
Data set for machine learning
1st month of programming learning
Install Networkx in Python 3.7 environment for use in malware data science books
Summary of pages useful for studying the deep learning framework Chainer
[For beginners] Summary of suffering from kaggle's EDA and its struggle
Feature engineering for machine learning starting with the 1st Google Colaboratory --Binarization and discretization of count data