Metadata-Version: 2.1
Name: fastemc
Version: 0.0.2
Summary: FastEMC is a method for dimensionality reduction.
Home-page: https://github.com/rowland-208/fastemc
Author: James Rowland
Author-email: rowland.208@gmail.com
License: UNKNOWN
Platform: UNKNOWN
Requires-Python: >=2.7
Description-Content-Type: text/markdown
Requires-Dist: numpy
Requires-Dist: pandas
Requires-Dist: scikit-learn
Requires-Dist: tqdm

# FastEMC
### Fast Exponential Monte Carlo

FastEMC is a modified version of exponential Monte Carlo.
FastEMC takes class features and labels as input,
and returns a list of scores and a list of selected features.
The score is based on logistic regression.
Two logistic regression classifiers are used:
1) a fast classifier with limited training,
2) and a slow classifier with full training.

The fast classifier is used to explore feature space rapidly.
Features are occasionaly compared using the slow classifier.


