Skip to content
Implementation and evaluation of multidimensional extension for k-means algorithm
Jupyter Notebook Python
Branch: master
Clone or download
Pull request Compare This branch is even with kshatilov:master.
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
eval
stats
README.txt
SubKMeans.py
Utilities.py
main.py
result.png

README.txt

1. Requirements:
   Program was developed and tested under Python 3.6.2 :: Anaconda, Inc.

2. How to execute:
   To run  subKMeans with wine dataset use following command:
        python main.py
   To use subKMeans with arbitrary dataset (as 2D array named X)
   in Python code use (similar to sklearn.kmeans):
        subkmeans = SubKMeans(n_clusters=3).fit(X)
        #clustered labels are accessible through
        subkmeans.labels_

3. The description of each source file:
   Utilities.py
        File containing supplementary function rvs() for generating random orthogonal matrices
   SubKMeans.py
        File containing source code of algorithm. Most functions has short descriptions.
   main.py
        File containing simple examples of dataset reading and clustering.

4. The operating system, where program was tested:
   Windows 10 Home

5. Additionally
   ---
You can’t perform that action at this time.