Metadata-Version: 2.1
Name: pottscompleteshrinkage
Version: 1.0.11
Summary: Potts Clustering with Complete Shrinkage
Home-page: https://github.com/kgalahassa/pottscompleteshrinkage
Author: Alejandro, Murua and Alahassa, Nonvikan Karl-Augustt
Author-email: alahassa@dms.umontreal.ca
License: GNU General Public License v3.0
Keywords: Potts models,Clustering,Complete Shrinkage
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: GNU Lesser General Public License v3 (LGPLv3)
Classifier: Operating System :: OS Independent
Description-Content-Type: text/markdown
Requires-Dist: numpy (==1.20.2)
Requires-Dist: pandas (==1.2.4)
Requires-Dist: scikit-learn (==0.24.2)

# Potts Complete Shrinkage
Potts Clustering with Complete Shrinkage

## Installation
Install using pip
```pip install pottscompleteshrinkage```

## Requirements
* Python 3.6 or greater
* numpy
* pandas

## Usage
Import the Potts Complete Shrinkage module
```import pottsshrinkage.completeshrinkage as PCS```
Compute Initial Potts Clusters as a first Random Partition (with Potts Model)
```InitialPottsClusters = PCS.InitialPottsConfiguration(Train_PottsData_demo, q, Kernel='Mercel')```
Choose your temperature (T) level
```T = 1000```
Set the bandwidth of the model
```sigma = 1```
Set the Number of Random_Partitions you want to simulate
```Number_of_Random_Partitions = 3```
Set your initial (random) Potts partition as computed above
```Initial_Partition = InitialPottsClusters```
Set the Minimum Size desired for each partition generated
```MinClusterSize = 5```
Run your Potts Complete Shrinkage Model to simulate the Randomly Shrunk Potts Partitions. Partitions_Sets is a dictionary that can be saved with pickle package.
```Partitions_Sets,Spin_Configuration_Sets = PCS.Potts_Random_Partition (Train_PottsData_demo, T, sigma, Number_of_Random_Partitions, MinClusterSize, Initial_Partition,  Kernel='Mercel')```

## Pypi Project Page
 https://pypi.org/project/pottscompleteshrinkage/1.0.0/

