Metadata-Version: 2.0
Name: symfeat
Version: 0.1.1
Summary: Ruled based feature engineering for regression
Home-page: https://github.com/ohjeah/symfeat
Author: Markus Quade
Author-email: info@markusqua.de
License: MIT
Platform: UNKNOWN
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 3.5
Classifier: Programming Language :: Python :: 3.6
Requires-Dist: numpy
Requires-Dist: scikit-learn


symfeat
=======

.. image:: https://travis-ci.org/Ohjeah/symfeat.svg?branch=master
    :target: https://travis-ci.org/Ohjeah/symfeat

**symfeat** is a rule based feature engineering library to be used as a
preprocessor for regression tasks.

It is based on:

    Mcconaghy, T. (2011). FFX: Fast, Scalable, Deterministic Symbolic Regression Technology. Genetic Programming Theory and Practice IX, 235-260. `DOI: 10.1007/978-1-4614-1770-5\_13 <http://dx.doi.org/10.1007/978-1-4614-1770-5_13http://dx.doi.org/10.1007/978-1-4614-1770-5_13>`_


Features
--------


Installation
------------

``pip install symfeat``


Usage
-----

.. code-block:: python

    import numpy as np
    import symfeat as sf

    operators = {"sin": np.sin}
    exponents = [1, 2, -1, -2]

    x = np.random.normal(size=10)

    features = sf.SymbolicFeatures(exponents=exponents, operators=operators).transform(x)


