Metadata-Version: 2.1
Name: PyIFS
Version: 0.0.2
Summary: A python3 package for infinite feature selection
Home-page: https://https://github.com/InfOmics/PyIFS
Author: nightwnvol
Author-email: notte_94@hotmail.it
License: UNKNOWN
Description: # PyIFS
        A python3 package for infinite feature selection
        
        ### Installation
        ```sh
        $ pip install PyIFS
        ```
        
        ### How to use
        ```python
        import PyIFS
        inf = PyIFS.InfFS()
        [RANKED, WEIGHT] = inf.infFS(x, y, alpha, supervision, verbose)
        ```
        ###### INPUT:
        + `x` is a T by n matrix, where T is the number of samples and n the number of features
        + `y` is a column vector with class labels
        + `alpha` is the mixing parameter
        + `supervision` is a boolean variable (0 = unsupervised version, 1 = supervised version)
        + `verbose` is a boolean variable (0, 1)
        ###### OUTPUT:
        + `RANKED` are indices of columns in `x` ordered by attribute importance
        + `WEIGHT` are attribute weights with large positive weights assigned to important attributes
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=2.7
Description-Content-Type: text/markdown
