Summary and Schedule

In this section we will focus on setting up the computer for the Lesssons on Unsupervised Machine Learning.

	Setup Instructions	Download files required for the lesson
Duration: 00h 00m	1. Clustering Introduction	How to search for multiple distributions in a dataset? How to use Scikit-learn to perform clustering? How is data labelled in unsupervised learning? How can we score clustering predictions?
Duration: 00h 12m	2. Clustering Images	What makes image data unique for machine learning? How can MR images be clustered and segmented? How can segmentation be improved? How do we visualise clustered image data?
Duration: 00h 24m	3. Dimensionality Reduction	Why is it important to perform dimensionality reduction? How is dimensionality reduction performed? How PCA is used to determine variance? When does PCA fail?
Duration: 00h 36m	Finish

The actual schedule may vary slightly depending on the topics and exercises chosen by the instructor.

Setting up virtual environment

---

In Python, the use of virtual environments allows you to avoid installing Python packages globally which could break system tools or other projects. Each virtual environment has its own Python binary (which matches the version of the binary that was used to create this environment) and can have its own independent set of installed Python packages in its site directories.

A virtual environment can be created by executing the command venv in your Terminal (Mac OS and Unix) or at the command line prompt (Windows):

python3 -m venv pyML

By running this command, a new environment will be installed in your home directory.

The environment can be activated as:

source pyML/bin/activate 

Now the packages required for a specific purpose can be installed. E.g. for the Clustering lessons we need Pandas, Scikit-learn, Matplotlib, and a package called “Nibabel”:

pip3 install pandas scikit-learn matplotlib nibabel

This environment kernel needs to be added to your Jupyter notebook. This can be done as:

conda install -c anaconda ipykernel
python -m ipykernel install --user --name=firstEnv

After running these 2 commands, you will be able to select your virtual environment from the Kernel tab of your Jupyter notebook. More information can be accessed at this link.

Dataset

---

Dataset for this lesson includes:

• patients_data.csv
• heightweight.csv
• Archive.zip
• Images.zip