Skip to main content

A tool for genetic programming based cross-factor analysis

Project description

gplearn_cross_factor

Welcome to the gplearn_cross_factor project! The primary objective of this project is to enhance the existing gplearn package and enable three-dimensional structured dimension genetic programming (GP) specifically for cross-sectional factor investigation.

Project Overview

In the initial version, the gplearn package only supported rankIC as the fitness metric. However, with this update, we have introduced significant improvements to extend its functionality and empower factor analysis. The key enhancements in this version include:

Expanded Fitness Metrics

We have incorporated a range of additional fitness metrics to complement rankIC. These new metrics include irir, quantile returns and monotonicity. By incorporating these metrics, you can conduct a more comprehensive evaluation of factors, leading to improved GP performance.

Enhanced Base Operators

The modified package now offers an expanded set of base operators, including both time series and cross-sectional capabilities. This enhancement provides increased flexibility, empowering researchers and practitioners to conduct more effective cross-sectional factor analysis. More operators (ts_residual, ts_cov, normalization, standardization, etc.) are coming.

Getting Started

To get started with gplearn_cross_factor, follow these steps:

  1. Download the gp_cross_factor package (pip install gp_cross_factor).
  2. Specify your desired fitness metrics, including rankIC, quantile returns, monotonicity, and correlation within factors.
  3. Define and prepare your data inputs for analysis.
  4. Run the genetic programming algorithm using the provided functions and operators.
  5. Evaluate and interpret the results to gain insights into your cross-sectional factors.

For more detailed instructions and examples, please refer to the documentation provided in the repository.

Contributing

We welcome contributions from the community to further enhance and expand the functionalities of gplearn for cross-sectional factor analysis. If you have any ideas, bug reports, or feature requests, feel free to open an issue or submit a pull request.

Stay Updated

Stay tuned for future releases as I continue to improve and enrich gplearn_cross_factor. Don't miss out on the latest updates and enhancements by watching this repository.

Happy factor analysis with gplearn_cross_factor!

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

gp_cross_factor-1.0.2.tar.gz (26.2 kB view details)

Uploaded Source

Built Distribution

gp_cross_factor-1.0.2-py3-none-any.whl (27.3 kB view details)

Uploaded Python 3

File details

Details for the file gp_cross_factor-1.0.2.tar.gz.

File metadata

  • Download URL: gp_cross_factor-1.0.2.tar.gz
  • Upload date:
  • Size: 26.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.12.4

File hashes

Hashes for gp_cross_factor-1.0.2.tar.gz
Algorithm Hash digest
SHA256 b57b1b94ce052e19565f85c4006284fa70275d930fcd48fd6498fb7285ad8639
MD5 7fbacb02691eb79c7299f8e5a97dec50
BLAKE2b-256 c6b22c905187bcd74a367a7ded8125c0fb70360a49dbeb5d725bcac511733155

See more details on using hashes here.

File details

Details for the file gp_cross_factor-1.0.2-py3-none-any.whl.

File metadata

File hashes

Hashes for gp_cross_factor-1.0.2-py3-none-any.whl
Algorithm Hash digest
SHA256 b01ea057ef756e8a352852f8cd8ecaa1404702579b724bd9c2123b4ec10ed3f4
MD5 a83dea15f29769601025545321d2a14f
BLAKE2b-256 d9e4b57cfe94adc697aad706b635a7fea15d6e485a5890fbcbc0f33f6f799de7

See more details on using hashes here.

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