Switch branches/tags
Nothing to show
Clone or download
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.
cwc
datasets
icdm2016
jupyter
utils
.gitignore
README.md
compare_mvn.py
contributors.txt
diary.py
digits_vs_letters.py
results_Ferri2004.py
results_Hempstalk2008.py
results_Krawczyk2015.py
results_Li2014.py
results_Orallo2011.py
results_Tax2008.py
results_Tax2008_multiclass.py
save_hidden_representation.py
summarize_results.sh
test_chain_synthetic.py
test_chars74k.py
test_different_mvns.py
test_generate_rej_given_data.py
test_mnist.py
test_optimality.py
test_real_datasets.py
test_rgrpg_synthetic.py
test_volume_calculation.py

README.md

Background Check

This is a framework to create and evaluate classifier models with confidence levels.

For a better explanation of the method go to the official web-page of the paper.

Supplementary material

The suplementary material can be found in icdm2016.

Dependencies

  • Numpy - NumPy is the fundamental package for scientific computing with Python.

Todos

  • Evaluate classifier with confidence given two thresholds
  • Evaluate classifier with confidence with volume under the Precision Recall Gain and ROC curve
  • Select optimal threshold for given deployment specification

License

MIT