Skip to content
master
Switch branches/tags
Code

Latest commit

 

Git stats

Files

Permalink
Failed to load latest commit information.
Type
Name
Latest commit message
Commit time
 
 
 
 
 
 
 
 
 
 
 
 
 
 

An enchiridion for topological data analysis

Following the tradition of providing an enchiridion to master unknown subjects, this repository contains an introduction into the dark art, viz. topological data analysis.

Here are the slides that were shown on the Basel Postdoc Retreat 2018.

To reproduce the results, please use the script svm.py. This requires a working installation of numpy and scikit-learn. To run the script for a given data set (see the Data folder for selected data sets that are shipped with this repository), please run the following:

$ ./Scripts/svm.py /Results/MUTAG

This should result in the following output:

INFO:root:Processing Results/MUTAG...
INFO:root:Setting parameters for data set MUTAG to {'C': 1000.0}
---
MUTAG
---
Accuracy             : 0.95
Classification report:
             precision    recall  f1-score   support

          0       0.86      1.00      0.92         6
          1       1.00      0.92      0.96        13

avg / total       0.95      0.95      0.95        19

The script can also run the analysis for multiple directories.

Methods

There are several repositories available for topological data analysis:

For graph kernels, a general class of methods for analysing graphs with various properties, I recommend the graphkernels package, which offers high-quality and thoroughly-tested implementations of numerous graph kernels. The package has bindings for C, Python, and R. For more information, please read the accompanying paper.

Disclaimer

No manifolds were harmed in the creation of this repository.

About

An enchiridion for instructing mortals in the hidden arts of topological data analysis

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published