I read the book "Theory and Practice by Expert Data Scientists Python Machine Learning Programming" because it was well received. https://www.amazon.co.jp/dp/B01HGIPIAK/ref=dp-kindle-redirect?_encoding=UTF8&btkr=1
At that time, I proceeded with the study while making notes in a notebook file of Jupyter Notebooks so that I could review it later. I would like to share the summary note at that time because it is a big deal. I added points that I thought were particularly important and a little supplement, and wrote it so that it could be used as a memorandum of "How do you write using this method, scikit-learn?" However, there are many parts that are omitted, so I would appreciate it if you could look at the original book and make up for it. I haven't made notes for chapters 1,2,8,9,12,13. (Deep learning has a lot of dedicated books, so it may be better to study there)
Python Machine Learning Programming Summary Notes (Jupyter) https://github.com/lyakaap/notebooks/tree/master/MachineLearning
If you look at the Readme, you can see what content is written in which file.
It is a book that you can recommend because you can learn all the important parts of machine learning methods and the explanations are written very carefully. As a prerequisite knowledge, if you have a little knowledge of mathematics and numpy, you can read it relatively smoothly. In particular, I found it very attractive to be able to learn how to handle libraries required for machine learning such as pandas and matplotlib, as well as scikit-learn, through the source code.