https://github.com/adamvvu/tsfracdiff

Efficient and easy to use fractional differentiation transformations for stationarizing time series data in Python.
https://github.com/adamvvu/tsfracdiff

data-science machine-learning python quantitative-finance

Last synced: 4 days ago
JSON representation

Efficient and easy to use fractional differentiation transformations for stationarizing time series data in Python.

• Host: GitHub
• URL: https://github.com/adamvvu/tsfracdiff
• Owner: adamvvu
• License: mit
• Created: 2022-05-06T00:03:21.000Z (over 2 years ago)
• Default Branch: master
• Last Pushed: 2023-02-10T12:23:00.000Z (almost 2 years ago)
• Last Synced: 2024-10-21T10:52:24.506Z (26 days ago)
• Topics: data-science, machine-learning, python, quantitative-finance
• Language: Python
• Homepage:
• Size: 479 KB
• Stars: 18
• Watchers: 3
• Forks: 4
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
[![Build](https://img.shields.io/github/actions/workflow/status/adamvvu/tsfracdiff/tsfracdiff_tests.yml?style=for-the-badge)](https://github.com/adamvvu/tsfracdiff/actions/workflows/tsfracdiff_tests.yml)

[![PyPi](https://img.shields.io/pypi/v/tsfracdiff?style=for-the-badge)](https://pypi.org/project/tsfracdiff/)

[![Downloads](https://img.shields.io/pypi/dm/tsfracdiff?style=for-the-badge)](https://pypi.org/project/tsfracdiff/)

[![License](https://img.shields.io/badge/license-MIT-green?style=for-the-badge)](https://github.com/adamvvu/tsfracdiff/blob/master/LICENSE)

Efficient and easy to use fractional differentiation transformations for

stationarizing time series data in Python.

------------------------------------------------------------------------

## **tsfracdiff**

Data with high persistence, serial correlation, and non-stationarity

pose significant challenges when used directly as predictive signals in

many machine learning and statistical models. A common approach is to

take the first difference as a stationarity transformation, but this

wipes out much of the information available in the data. For datasets

where there is a low signal-to-noise ratio such as financial market

data, this effect can be particularly severe. Hosking (1981) introduces

fractional (non-integer) differentiation for its flexibility in modeling

short-term and long-term time series dynamics, and López de Prado (2018)

proposes the use of fractional differentiation as a feature

transformation for financial machine learning applications. This library

is an extension of their ideas, with some modifications for efficiency

and robustness.

[Documentation](https://adamvvu.github.io/tsfracdiff/docs/)

## Getting Started

### Installation

`pip install tsfracdiff`

#### Dependencies:

    # Required

    python3 # Python 3.7+

    numpy

    pandas

    arch

    # Suggested

    joblib

### Usage

``` python

# A pandas.DataFrame/np.array with potentially non-stationary time series

df 

# Automatic stationary transformation with minimal information loss

from tsfracdiff import FractionalDifferentiator

fracDiff = FractionalDifferentiator()

df = fracDiff.FitTransform(df)

```

For a more in-depth example, see this

[notebook](https://adamvvu.github.io/tsfracdiff/examples/Example.html).

## References

Hosking, J. R. M. (1981). Fractional Differencing. Biometrika, 68(1),

165--176. 

López de Prado, Marcos (2018). Advances in Financial Machine Learning.

John Wiley & Sons, Inc.