pyHomogeneity
What is the Homogeneity Test ?
The homogeneity test is a statistical test method, that checks if two (or more) datasets come from the same distribution or not. In a time series, the homogeneity test is applied to detect one (or more) change/breakpoint in the series. This breakpoint occurs where the data set changes its distribution. Lots of statistical analyses require a homogenous dataset. That's why it is an important test in statistical analysis.
pyHomogeneity is a pure Python implementation for the homogeneity test. There are several tests available to check the homogeneity of a time series. pyHomogeneity package can perform six commonly used Homogeneity test listed below:
-
Pettitt test (pettitt_test)
-
Standard Normal Homogeinity Test (SNHT) Test (snht_test)
-
Buishand Q Test (buishand_q_test)
-
Buishand's Range Test (buishand_range_test):
-
Buishand's Likelihood Ration Test (buishand_likelihood_ratio_test)
-
Buishand U Test (buishand_u_test)
Function details:
All Homogeneity test functions have almost similar input parameters. These are:
- x: a vector (list, numpy array or pandas series) data
- alpha: significance level (0.05 default)
- sim: No. of monte carlo simulation for p-value calculation.
And all Homogeneity tests return a named tuple which contained:
- h: True (if data is nonhomogeneous) or False (if data is homogeneous)
- cp: probable change point location
- p: p value of the significance test
- U/T/Q/R/V: test statistics which depends on the test method
- avg: mean values at before and after the change point
Dependencies
For the installation of pyHomogeneity, the following packages are required:
Installation
You can install pyHomogeneity using pip. For Linux users
sudo pip install pyhomogeneity
or, for Windows user
pip install pyhomogeneity
Or you can clone the repo and install it:
git clone https://github.com/mmhs013/pyhomogeneity
cd pyhomogeneity
python setup.py install
Tests
pyHomogeneity is automatically tested using pytest package on each commit here, but the tests can be manually run:
pytest -v
Usage
A quick example of pyHomogeneity usage is given below. Several more examples are provided here.
import numpy as np
import pyhomogeneity as hg
# Data generation for analysis
data = np.random.rand(360,1)
result = hg.pettitt_test(data)
print(result)
Output are like this:
Pettitt_Test(h=False, cp=89, p=0.1428, U=3811.0, avg=mean(mu1=0.5487521427805625, mu2=0.46884198890609463))
Whereas, the output is a named tuple, so user can call by name for specific result:
print(result.cp)
print(result.avg.mu1)
or, user can directly unpack results like this:
h, cp, p, U, mu = hg.pettitt_test(x, 0.05)
Contributions
pyHomogeneity is a community project and welcomes contributions. Additional information can be found in the contribution guidelines
Code of Conduct
pyHomogeneity wishes to maintain a positive community. Additional details can be found in the Code of Conduct
References
-
Alexandersson, H., 1986. A homogeneity test applied to precipitation data. Journal of climatology, 6(6), pp.661-675. doi:10.1002/joc.3370060607
-
Buishand, T.A., 1982. Some methods for testing the homogeneity of rainfall records. Journal of hydrology, 58(1-2), pp.11-27. doi:10.1016/0022-1694(82)90066-X
-
Pettitt, A.N., 1979. A non-parametric approach to the change-point problem. Journal of the Royal Statistical Society: Series C (Applied Statistics), 28(2), pp.126-135. doi:10.2307/2346729
-
Pohlert, T., 2016. Package 'trend'. Title Non-Parametric Trend Tests and Change-Point Detection.
-
Verstraeten, G., Poesen, J., Demaree, G. and Salles, C., 2006. Long-term (105 years) variability in rain erosivity as derived from 10-min rainfall depth data for Ukkel (Brussels, Belgium): Implications for assessing soil erosion rates. Journal of Geophysical Research: Atmospheres, 111(D22). doi:10.1029/2006JD007169
Metadata
Release files for pyhomogeneity 1.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| pyhomogeneity-1.1.tar.gz | 29.0 kB | Without provenance | Details for pyhomogeneity-1.1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| pyhomogeneity-1.1-py3-none-any.whl | Python 3 | none | any | Details for pyhomogeneity-1.1-py3-none-any.whl |
Total release size: 41.4 kB
Release files / pyhomogeneity-1.1.tar.gz
| Download URL | pyhomogeneity-1.1.tar.gz |
|---|---|
| Size | 29.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
55bc59bcc591e7dd9fa04d081c8cd50be74106f349378d7bc97c2ebfd5fb65a1
|
|
BLAKE2b-256 checksum How to use checksums |
7df55e16ae2b77a76733747bad0e7eef611d1556169ebdf301d9134e897d3540
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/1.13.0 pkginfo/1.5.0.1 requests/2.22.0 setuptools/41.0.1 requests-toolbelt/0.9.1 tqdm/4.32.2 CPython/3.7.4
|
Release files / pyhomogeneity-1.1-py3-none-any.whl
| Download URL | pyhomogeneity-1.1-py3-none-any.whl |
|---|---|
| Size | 12.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
837ebcae1f08f7094567265f9b14b27bda2c0857ffb5a65a0a3a2ee701856da2
|
|
BLAKE2b-256 checksum How to use checksums |
e28aa1ffa82674cc748bdf8d46c3d1f681651679038f1cbd9bb0fae7b649d457
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/1.13.0 pkginfo/1.5.0.1 requests/2.22.0 setuptools/41.0.1 requests-toolbelt/0.9.1 tqdm/4.32.2 CPython/3.7.4
|
Security for pyhomogeneity 1.1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.