scikit-learn Tutorials

[agitter]

scikit-learn has many tutorials. Are there any ideas there we should adopt or extend?

[agitter]

• https://github.com/jakevdp/sklearn_tutorial
• https://github.com/jakevdp/PythonDataScienceHandbook
• http://scikit-learn.org/stable/tutorial/index.html

[agitter]

Sebastian will be join the stats faculty here and has some relevant repositories:

• https://github.com/rasbt/python-machine-learning-book-2nd-edition
• https://github.com/rasbt/msu-datascience-ml-tutorial-2018
• https://github.com/rasbt/data-science-tutorial
• https://github.com/rasbt/pydata-chicago2016-ml-tutorial

[agitter]

Sebastian's textbook figures have been excellent for our guides. I'll contact him to discuss what we are working on.

[agitter]

A group in Radiology on campus recently presented a workshop on ML for medical imaging. We can follow their efforts and see if we have common goals. Their workshop is based on Jupyter notebooks, but they said not all the participants had programming experience.

Their materials are here: https://github.com/kmjohnson3/ML4MI_BootCamp

[agitter]

DataCamp has a guide on preprocessing for machine learning. However, it is a paid course: https://www.datacamp.com/courses/preprocessing-for-machine-learning-in-python

[agitter]

This machine learning tutorial for biologists focuses mostly on unsupervised learning for single-cell RNA-seq. It is presented as a Jupyter notebook with some accompanying slides: https://github.com/scottgigante/machine-learning-tutorial