A python package for LSH-k-Centers algorithm
Project description
Python implementations of the LSH-k-Centers algorithms for clustering categorical data:
Installation:
Using pip:
pip install lshkcenters
Import the packages:
import numpy as np
from LSHkCenters.LSHkCenters import LSHkCenters
Generate a simple categorical dataset:
X = np.array([[0,0,0],[0,1,1],[0,0,0],[1,0,1],[2,2,2],[2,3,2],[2,3,2]])
y = np.array([0,0,0,0,1,1,1])
LSH-k-Centers:
kcens = LSHkCenters(X,y,n_init=5,k=2)
kcens.SetupLSH()
kcens.DoCluster()
Built-in evaluattion metrics:
kcens.CalcScore()
Out come:
Purity: 1.000 NMI: 1.00 ARI: 1.00 Sil: -1.00 Acc: 1.00 Recall: 1.00 Precision: 1.00
Built-in fuzzy evaluattion metrics:
kcens.CalcFuzzyScore()
Out come:
Fuzzy scores PC:1.00 NPC:1.00 FHV↓:0.02 FS↓:-2000.00 XB↓:0.11 BH↓:0.06 BWS:-2000.00 FPC:3.50 SIL_R:0.70 FSIL:0.70 MPO:12.15 NPE:0.01 PE:0.01 PEB:0.01
References:
To be updated
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
lshkcenters-1.0.3.tar.gz
(23.7 kB
view hashes)