Self Organising Map (SOM) for clustering of atomistic samples through unsupervised learning.

Overview

Self Organising Map for Clustering of Atomistic Samples - V2

Description

Self Organising Map (also known as Kohonen Network) implemented in Python for clustering of atomistic samples through unsupervised learning. The program allows the user to select wich per-atom quantities to use for training and application of the network, this quantities must be specified in the LAMMPS input file that is being analysed. The algorithm also requires the user to introduce some of the networks parameters:

  • f: Fraction of the input data to be used when training the network, must be between 0 and 1.
  • SIGMA: Maximum value of the sigma function, present in the neighbourhood function.
  • ETA: Maximum value of the eta funtion, which acts as the learning rate of the network.
  • N: Number of output neurons of the SOM, this is the number of groups the algorithm will use when classifying the atoms in the sample.
  • Whether to use batched or serial learning for the training process.
  • B: Batch size, in case the training is performed with batched learning.

The input file must be inside the same folder as the main.py file. Furthermore, the input file passed to the algorithm must have the LAMMPS dump format, or at least have a line with the following format:

ITEM: ATOMS id x y z feature_1 feature_2 ...

To run the software, simply execute the following command in a terminal (from the folder that contains the files and with a python environment activated):

python3 main.py

Check the software report in the general repository for more information: https://github.com/rambo1309/SOM_for_Atomistic_Samples_GeneralRepo

Dependencies:

This software is written in Python 3.8.8 and uses the following external libraries:

  • NumPy 1.20.1
  • Pandas 1.2.4

(Both packages come with the basic installation of Anaconda)

What's new in V2:

Its important to clarify that V2 of the software isn't designed to replace V1, but to be used when multiple files need to be analysed sequentially with a network that has been trained using a specific training file. It is recommended for the user to first use V1 to explore the results given by different parameters and features of the sample, and then to use V2 to get consistent results for a series of samples. Another reason why V1 will be continually updated is its command-line interactive interface, which allows the users to implement the algorithm without ever having to open and edit a python file.

The most fundamental change with respect to V.1 is the way of communicating with the program. While V.1 uses an interactive command-line interface, V.2 requests an input_params.py file that contains a dictionary specifying the parameters and sample files for the algorithm.

Check the report file in the repository for a complete description of the changes made in the software.

Updates:

Currently working on giving the user the option to change the learning rate funtion, eta, with a few alternatives such as a power-law and an exponential decrease. Another important issue still to be addressed is the training time of the SOM.

Owner
Franco Aquistapace
Undergraduate Physics student at FCEN, UNCuyo
Franco Aquistapace
A Python implementation of GRAIL, a generic framework to learn compact time series representations.

GRAIL A Python implementation of GRAIL, a generic framework to learn compact time series representations. Requirements Python 3.6+ numpy scipy tslearn

3 Nov 24, 2021
Random Forest Classification for Neural Subtypes

Random Forest classifier for neural subtypes extracted from extracellular recordings from human brain organoids.

Michael Zabolocki 1 Jan 31, 2022
A GitHub action that suggests type annotations for Python using machine learning.

Typilus: Suggest Python Type Annotations A GitHub action that suggests type annotations for Python using machine learning. This action makes suggestio

40 Sep 18, 2022
Automated Machine Learning with scikit-learn

auto-sklearn auto-sklearn is an automated machine learning toolkit and a drop-in replacement for a scikit-learn estimator. Find the documentation here

AutoML-Freiburg-Hannover 6.7k Jan 07, 2023
Short PhD seminar on Machine Learning Security (Adversarial Machine Learning)

Short PhD seminar on Machine Learning Security (Adversarial Machine Learning)

141 Dec 27, 2022
Built on python (Mathematical straight fit line coordinates error predictor machine learning foundational model)

Sum-Square_Error-Business-Analytical-Tool- Built on python (Mathematical straight fit line coordinates error predictor machine learning foundational m

om Podey 1 Dec 03, 2021
Machine Learning Model to predict the payment date of an invoice when it gets created in the system.

Payment-Date-Prediction Machine Learning Model to predict the payment date of an invoice when it gets created in the system.

15 Sep 09, 2022
Library of Stan Models for Survival Analysis

survivalstan: Survival Models in Stan author: Jacki Novik Overview Library of Stan Models for Survival Analysis Features: Variety of standard survival

Hammer Lab 122 Jan 06, 2023
Python Automated Machine Learning library for tabular data.

Simple but powerful Automated Machine Learning library for tabular data. It uses efficient in-memory SAP HANA algorithms to automate routine Data Scie

Daniel Khromov 47 Dec 17, 2022
Compare MLOps Platforms. Breakdowns of SageMaker, VertexAI, AzureML, Dataiku, Databricks, h2o, kubeflow, mlflow...

Compare MLOps Platforms. Breakdowns of SageMaker, VertexAI, AzureML, Dataiku, Databricks, h2o, kubeflow, mlflow...

Thoughtworks 318 Jan 02, 2023
MegFlow - Efficient ML solutions for long-tailed demands.

Efficient ML solutions for long-tailed demands.

旷视天元 MegEngine 371 Dec 21, 2022
Esse é o meu primeiro repo tratando de fim a fim, uma pipeline de dados abertos do governo brasileiro relacionado a compras de contrato e cronogramas anuais com spark, em pyspark e SQL!

Olá! Esse é o meu primeiro repo tratando de fim a fim, uma pipeline de dados abertos do governo brasileiro relacionado a compras de contrato e cronogr

Henrique de Paula 10 Apr 04, 2022
Generate music from midi files using BPE and markov model

Generate music from midi files using BPE and markov model

Aditya Khadilkar 37 Oct 24, 2022
PyPOTS - A Python Toolbox for Data Mining on Partially-Observed Time Series

A python toolbox/library for data mining on partially-observed time series, supporting tasks of forecasting/imputation/classification/clustering on incomplete multivariate time series with missing va

Wenjie Du 179 Dec 31, 2022
Python factor analysis library (PCA, CA, MCA, MFA, FAMD)

Prince is a library for doing factor analysis. This includes a variety of methods including principal component analysis (PCA) and correspondence anal

Max Halford 915 Dec 31, 2022
Simple structured learning framework for python

PyStruct PyStruct aims at being an easy-to-use structured learning and prediction library. Currently it implements only max-margin methods and a perce

pystruct 666 Jan 03, 2023
A collection of neat and practical data science and machine learning projects

Data Science A collection of neat and practical data science and machine learning projects Explore the docs » Report Bug · Request Feature Table of Co

Will Fong 2 Dec 10, 2021
Coursera Machine Learning - Python code

Coursera Machine Learning This repository contains python implementations of certain exercises from the course by Andrew Ng. For a number of assignmen

Jordi Warmenhoven 859 Dec 10, 2022
This is a Machine Learning model which predicts the presence of Diabetes in Patients

Diabetes Disease Prediction This is a machine Learning mode which tries to determine if a person has a diabetes or not. Data The dataset is in comma s

Edem Gold 4 Mar 16, 2022
Customers Segmentation with RFM Scores and K-means

Customer Segmentation with RFM Scores and K-means RFM Segmentation table: K-Means Clustering: Business Problem Rule-based customer segmentation machin

5 Aug 10, 2022