Machine Learning and Transportation

1. Computer and Internet: Bring your computer to class and make sure the internet is available.
2. Python Anaconda Setup:
   Go to https://www.anaconda.com/products/individual/. Click "Download" and it jumps to "Anaconda Installers". Choose the operating system in your computer Windows, macOS, or Linux. Select Python 3.8 version, 64-Bit Graphical Installer. Download Anaconda installation application. After download, double click to install Anaconda in your computer. Review: Top 20 Python libraries for data science in 2018: https://activewizards.com/blog/top-20-python-libraries-for-data-science-in-2018/ or Top 20 Python libraries for data science in 2018 _ ActiveWizards_ data science and engineering lab.pdf under this repository.
3. Git Setup: Install Git from https://git-scm.com/downloads
4. Set up a Github Account: Go to www.github.com to set up your account if you don’t have a Github account yet. We will use Github to download popular machine learning study materials and projects, as well as turn in your projects in Github.
5. Install Sublime Text: We will learn how to edit Markdown document in Sublime Text for your project writeup.
6. Books and Materials:
   1. We will use “Python Machine Learning Machine Learning and Deep Learning with Python, scikit-learn, and TensorFlow 2, 3rd Edition” by Sebastian Raschka & Vahid Mirjalili in our class. The python codes in this book will be used in class. The code can be downloaded from https://github.com/rasbt/python-machine-learning-book-3rd-edition. Try to use Git to download it instead of downloading directly from Github website. Under Git and the directory you want the downloaded folder to be located at, type “git clone https://github.com/rasbt/python-machine-learning-book-3rd-edition". You can buy this book from website if necessary.
   2. The second book we will use is “Python机器学习及实践：从零开始通往Kaggle竞赛之路” by 范淼 & 李超. The python codes in this book will be used in class. The code can be downloaded from https://github.com/godfanmiao/DIY_ML_Systems_with_Python_1st_Edition. Try to use Git to download it instead of downloading directly from Github website. You can buy this book from website if necessary. The authors have a second edition python code at https://github.com/godfanmiao/DIY_ML_Systems_with_Python_2nd_Edition but I don't see the second edition book yet.
   3. If we have the additional time to learn more machine learning and deep learning applications, then we will learn several machine learning applications under "OpenVINO", developed by Intel. The reference book is "深度学习图像识别技术：基于TensorFlow和OpenVINO工具" by 庄建, 张晶, and 许钰雯. The code downloaded direction can be found at https://github.com/dlod-openvino/book.
   4. There is another reference book, "Hands-On Machine Learning with Scikit-Learn and TensorFlow - Concepts, Tools, and Techniques to Build Intelligent Systems" by Aurélien Géron. This book is very polular for learning "machine learning". I did not find an official github repository provided by the author for this book; however, there are many repositories prepared by many readers. I list two repositores for your reference, https://github.com/DeqianBai/Hands-on-Machine-Learning and https://github.com/Akramz/Hands-on-Machine-Learning-with-Scikit-Learn-Keras-and-TensorFlow.
   5. We will use parts of the books listed above but will not follow their structures in class. However, you will find many useful information from these textbooks/reference books.

See You All in Class!

PC

---

10/21/2020

Project1 Options: https://github.com/udacity/machine-learning/tree/master/projects

---