Skip to main content

Ruled based feature engineering for regression

Project description

https://travis-ci.org/Ohjeah/symfeat.svg?branch=master https://badge.fury.io/py/symfeat.svg https://zenodo.org/badge/79949716.svg

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

Features

  • Builds a features based on all valid rule specified combinations

  • Discards non-finite transformations

  • Optional: remove equivalent expressions

Installation

pip install symfeat

Usage

import numpy as np
import symfeat as sf

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

x = np.random.normal(size=10).reshape(-1, 1)

sym = sf.SymbolicFeatures(exponents=exponents, operators=operators)
features = sym.fit_transform(x)
names = sym.names

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

symfeat-0.2.0.tar.gz (3.2 kB view hashes)

Uploaded Source

Built Distribution

symfeat-0.2.0-py3-none-any.whl (4.9 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page