Skip to main content

Deterministic feature engineering for options chain data

Project description

Options Chain Features (OCF)

Options Chain Features (OCF) is a modular, research-grade Python library for building model-ready features from options chain data.

OCF provides a deterministic, schema-driven pipeline that converts raw vendor data (e.g. Bloomberg-style extracts) into structured, machine-learning-friendly feature tables without imposing trading logic, forecasting assumptions, or model constraints.


Installation

Install via pip:

pip install options-chain-features

What OCF Provides

At a high level, the library includes:

  • Canonical schemas for underlying data and option chains
  • Normalization layers for vendor-style raw inputs
  • Deterministic feature blocks operating on aligned daily data
  • Implied volatility surface & term-structure features
  • Liquidity and positioning features
  • Option-level Greeks and aggregate exposure representations
  • End-to-end pipelines with strict validation and explicit configuration

All components are usable independently or as part of a full pipeline.


Design Principles

OCF is built around a few core principles:

  • No hidden state - All transformations are explicit and deterministic.

  • No implicit joins or IO - File handling is separated from computation.

  • Schema-first design - Every stage operates on clearly defined canonical tables.

  • Feature isolation - Each feature block can be tested, enabled, or disabled independently.

  • Research-friendly - Outputs are flat, numeric, and directly consumable by ML models.


Documentation

Detailed documentation is available here, including data schemas, feature definitions, pipeline architecture, Greeks and exposure construction, and configuration options.


Release Status

Current release: v1.0.0

This project follows Semantic Versioning (MAJOR.MINOR.PATCH).


License

This project is released under the MIT License. See LICENSE for details.


Citation

If you use OCF in research or production systems, attribution is appreciated.

@software{setpalocf2026,
  author = {Vansh Ashok Setpal},
  title  = {Options Chain Features (OCF)},
  year   = {2026},
  url    = {https://github.com/vansh0016/options-chain-features}
}

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

options_chain_features-1.0.0.tar.gz (35.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

options_chain_features-1.0.0-py3-none-any.whl (41.3 kB view details)

Uploaded Python 3

File details

Details for the file options_chain_features-1.0.0.tar.gz.

File metadata

  • Download URL: options_chain_features-1.0.0.tar.gz
  • Upload date:
  • Size: 35.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.11

File hashes

Hashes for options_chain_features-1.0.0.tar.gz
Algorithm Hash digest
SHA256 dd12a75557bad1ca3177cef0e15b5301ddda51a5f318bfecfbd3f82e87dacb28
MD5 a513f3042b7a1b59d9d58beae97c69fc
BLAKE2b-256 858b47b149e307b2618c475baa1a46b88cf55a731619f528fd639af517a84641

See more details on using hashes here.

File details

Details for the file options_chain_features-1.0.0-py3-none-any.whl.

File metadata

File hashes

Hashes for options_chain_features-1.0.0-py3-none-any.whl
Algorithm Hash digest
SHA256 06b90781cd487b33a4181b884f1f13d5bdc71cf8c2dbd159a11910aab9491234
MD5 dd481bb24b9627d9918544e21fea31ed
BLAKE2b-256 cd4211082d66aa0fc3f1a6168232196f1e9e4d54f16cac9b84d5965a55271577

See more details on using hashes here.

Supported by

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