The PyClustKit Module: All about clustering in a single Python Module!
The pyclustkit module is built on top of various libraries to enable many clustering operations. Currently, the module is built for clustering evaluation and meta-learning.
Table of Contents
Installation Instructions
The pyclustkit is available to download with pypi
pip install pyclustkit
I
Useful Links
Usage Examples
Calculating Internal Cluster Validity Indices (CVI)
PyClustKit comes with an evaluation suite of 46 internal validity indices. Each is implemented on top of numpy and, the module incorporates specific methods for speeding up the execution of multiple CVI by implementing a shared process tracking.
from pyclustkit.eval import CVIToolbox
ct = CVIToolbox(X,y)
ct.calculate_icvi(cvi=["dunn", "silhouette"]) # if no CVI are specified it defaults to 'all'.
print(ct.cvi_results)
Meta Learning
Meta-Feature Extraction
PyClustKit comes with an evaluation suite of 46 internal validity indices. Each is implemented on top of numpy and, the module incorporates specific methods for speeding up the execution of multiple CVI by implementing a shared process tracking.
from pyclustkit.eval import CVIToolbox
ct = CVIToolbox(X,y)
ct.calculate_icvi(cvi=["dunn", "silhouette"]) # if no CVI are specified it defaults to 'all'.
print(ct.cvi_results)
Citing This Work
List of Implemented CVI with citations
Currently the collection consists of the following internal CVIs. R does not do gdi 61,62,63 due to hausdorff:-
ball_hall: G. H. Ball and D. J. Hall. Isodata: A novel method of data analysis and pattern classification. Menlo Park: Stanford Research Institute. (NTIS No. AD 699616),1965.
-
banfeld_raftery: J.D. Banfield and A.E. Raftery. Model-based gaussian and non-gaussian clustering. Biometrics, 49:803–821, 1993.
-
c_index: Hubert, Lawrence & Levin, Joel. (1976). A general statistical framework for assessing categorical clustering in free recall. Psychological Bulletin. 83. 1072-1080. 10.1037/0033-2909.83.6.1072.
-
CDbw : Halkidi, M., & Vazirgiannis, M. (2008). A density-based cluster validity approach using multi-representatives. Pattern Recognit. Lett., 29, 773-786.
-
det_ratio : A. J. Scott and M. J. Symons. Clustering methods based on likelihood ratio criteria. Biometrics, 27:387–397, 1971.
-
Dunn Index : J. Dunn. Well separated clusters and optimal fuzzy partitions. Journal of Cybernetics, 4:95–104, 1974.
-
GDI [11,21,31,41,51,61][12,22,32,42,52,62][13,23,33,43,53,63]: J. C. Bezdek and N. R. Pal. Some new indexes of cluster validity. IEEE Transactions on Systems, Man, and CyberneticsÑPART B: CYBERNETICS, 28, no.3:301–315, 1998.
-
ksq_detw: F. H. B. Marriot. Practical problems in a method of cluster analysis. Biometrics, 27:456–460, 1975.
-
log_det_ratio: Halkidi et al. On clustering validation techniques. J. Intell. Inf. Syst., 2001.
-
log_ss_ratio: J. A. Hartigan. Clustering algorithms. New York: Wiley, 1975.
-
McClain_Rao: J. O. McClain and V. R. Rao. Clustisz: A program to test for the quality of clustering of a set of objects. Journal of Marketing Research, 12:456–460, 1975.
-
trace_w Index
-
Friedman-Rudin 1 Index
-
Friedman-Rudin 2 Index
-
S_dbw: M. Halkidi and M. Vazirgiannis, "Clustering validity assessment: finding the optimal partitioning of a data set," Proceedings 2001 IEEE International Conference on Data Mining.
-
sd_dis Index: Halkidi et al. On clustering validation techniques. J. Intell. Inf. Syst., 2001.
-
sd_scat Index: Halkidi et al. On clustering validation techniques. J. Intell. Inf. Syst., 2001.
-
pbm: Bandyopadhyay S. Pakhira M. K. and Maulik U. Validity index for crisp and fuzzy clusters. Pattern Recognition, 2004.
-
ratkowsky_lance
-
ray_turi: Ray et al. Determination of number of clusters in k-means clustering and application in colour image segmentation. 4th International Conference on Advances in Pattern Recognition and Digital Techniques, 1999.
-
wemmert_gancarski
-
xie_beni: X.L. Xie and G. Beni. A validity measure for fuzzy clustering. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1991.
-
banfeld_raftery
-
trace_wib
-
log_det_ratio
-
point_biserial
-
calinski_harabasz
-
silhouette
-
davies_bouldin
-
scott_symons
1 maintainer
Metadata
1 maintainer
Release files for pyclust-evl 0.1.0
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 | |
|---|---|---|---|---|
| pyclust_evl-0.1.0.tar.gz | 44.7 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| pyclust_evl-0.1.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 99.2 kB
Release files / pyclust_evl-0.1.0.tar.gz
| Download URL | pyclust_evl-0.1.0.tar.gz |
|---|---|
| Size | 44.7 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
678981305d8fdbdae2f4333bdb1a2f263ed239c64c77f68627f8652d6002dde9
|
|
BLAKE2b-256 checksum How to use checksums |
dcd4b0ba4712fc323ee7379648fabee8f6fe62ac4976050cca4c1584dfe5fe4c
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.0.1 CPython/3.12.7
|
Release files / pyclust_evl-0.1.0-py3-none-any.whl
| Download URL | pyclust_evl-0.1.0-py3-none-any.whl |
|---|---|
| Size | 54.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
24433de6f41346fe55b27229c0b83ea7ed678b3f78d30652151ae3c8438a9be4
|
|
BLAKE2b-256 checksum How to use checksums |
b64b539bc1e8206dcb69df9a75e9c81e832a5796b3ca66463b384a882f91dc3b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.0.1 CPython/3.12.7
|
Security for pyclust-evl 0.1.0
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.
