Skip to content

Latest commit

 

History

History
49 lines (29 loc) · 2.48 KB

File metadata and controls

49 lines (29 loc) · 2.48 KB

Python Machine Learning - Code Examples

Chapter 11: Working with Unlabeled Data – Clustering Analysis

Chapter Outline

  • Grouping objects by similarity using k-means
    • K-means clustering using scikit-learn
    • A smarter way of placing the initial cluster centroids using k-means++
    • Hard versus soft clustering
    • Using the elbow method to find the optimal number of clusters
    • Quantifying the quality of clustering via silhouette plots
  • Organizing clusters as a hierarchical tree
    • Grouping clusters in bottom-up fashion
    • Performing hierarchical clustering on a distance matrix
    • Attaching dendrograms to a heat map
    • Applying agglomerative clustering via scikit-learn
  • Locating regions of high density via DBSCAN
  • Summary

A note on using the code examples

The recommended way to interact with the code examples in this book is via Jupyter Notebook (the .ipynb files). Using Jupyter Notebook, you will be able to execute the code step by step and have all the resulting outputs (including plots and images) all in one convenient document.

Setting up Jupyter Notebook is really easy: if you are using the Anaconda Python distribution, all you need to install jupyter notebook is to execute the following command in your terminal:

conda install jupyter notebook

Then you can launch jupyter notebook by executing

jupyter notebook

A window will open up in your browser, which you can then use to navigate to the target directory that contains the .ipynb file you wish to open.

More installation and setup instructions can be found in the README.md file of Chapter 1.

(Even if you decide not to install Jupyter Notebook, note that you can also view the notebook files on GitHub by simply clicking on them: ch11.ipynb)

In addition to the code examples, I added a table of contents to each Jupyter notebook as well as section headers that are consistent with the content of the book. Also, I included the original images and figures in hope that these make it easier to navigate and work with the code interactively as you are reading the book.

When I was creating these notebooks, I was hoping to make your reading (and coding) experience as convenient as possible! However, if you don't wish to use Jupyter Notebooks, I also converted these notebooks to regular Python script files (.py files) that can be viewed and edited in any plaintext editor.