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
Databricks Certified Associate Spark Developer preparation toolkit to setup single node Standalone Spark Cluster along with material in the form of Jupyter Notebooks.

Databricks Certification Spark Databricks Certified Associate Spark Developer preparation toolkit to setup single node Standalone Spark Cluster along

19 Dec 13, 2022
QML: A Python Toolkit for Quantum Machine Learning

QML is a Python2/3-compatible toolkit for representation learning of properties of molecules and solids.

176 Dec 09, 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 3.6+ toolbox for submitting jobs to Slurm

Submit it! What is submitit? Submitit is a lightweight tool for submitting Python functions for computation within a Slurm cluster. It basically wraps

Facebook Incubator 768 Jan 03, 2023
Neural Machine Translation (NMT) tutorial with OpenNMT-py

Neural Machine Translation (NMT) tutorial with OpenNMT-py. Data preprocessing, model training, evaluation, and deployment.

Yasmin Moslem 29 Jan 09, 2023
Python package for concise, transparent, and accurate predictive modeling

Python package for concise, transparent, and accurate predictive modeling. All sklearn-compatible and easy to use. 📚 docs • 📖 demo notebooks Modern

Chandan Singh 983 Jan 01, 2023
A Collection of Conference & School Notes in Machine Learning 🦄📝🎉

Machine Learning Conference & Summer School Notes. 🦄📝🎉

558 Dec 28, 2022
Evidently helps analyze machine learning models during validation or production monitoring

Evidently helps analyze machine learning models during validation or production monitoring. The tool generates interactive visual reports and JSON profiles from pandas DataFrame or csv files. Current

Evidently AI 3.1k Jan 07, 2023
A modular active learning framework for Python

Modular Active Learning framework for Python3 Page contents Introduction Active learning from bird's-eye view modAL in action From zero to one in a fe

modAL 1.9k Dec 31, 2022
This machine learning model was developed for House Prices

This machine learning model was developed for House Prices - Advanced Regression Techniques competition in Kaggle by using several machine learning models such as Random Forest, XGBoost and LightGBM.

serhat_derya 1 Mar 02, 2022
SynapseML - an open source library to simplify the creation of scalable machine learning pipelines

Synapse Machine Learning SynapseML (previously MMLSpark) is an open source library to simplify the creation of scalable machine learning pipelines. Sy

Microsoft 3.9k Dec 30, 2022
Combines Bayesian analyses from many datasets.

PosteriorStacker Combines Bayesian analyses from many datasets. Introduction Method Tutorial Output plot and files Introduction Fitting a model to a d

Johannes Buchner 19 Feb 13, 2022
fastFM: A Library for Factorization Machines

Citing fastFM The library fastFM is an academic project. The time and resources spent developing fastFM are therefore justified by the number of citat

1k Dec 24, 2022
Can a machine learning project be implemented to estimate the salaries of baseball players whose salary information and career statistics for 1986 are shared?

END TO END MACHINE LEARNING PROJECT ON HITTERS DATASET Can a machine learning project be implemented to estimate the salaries of baseball players whos

Pinar Oner 7 Dec 18, 2021
inding a method to objectively quantify skill versus chance in games, using reinforcement learning

Skill-vs-chance-games-analysis - Finding a method to objectively quantify skill versus chance in games, using reinforcement learning

Marcus Chiam 4 Nov 19, 2022
Summer: compartmental disease modelling in Python

Summer: compartmental disease modelling in Python Summer is a Python-based framework for the creation and execution of compartmental (or "state-based"

6 May 13, 2022
CyLP is a Python interface to COIN-OR’s Linear and mixed-integer program solvers (CLP, CBC, and CGL)

CyLP CyLP is a Python interface to COIN-OR’s Linear and mixed-integer program solvers (CLP, CBC, and CGL). CyLP’s unique feature is that you can use i

COIN-OR Foundation 161 Dec 14, 2022
A chain of stores, 10 different stores and 50 different requests a 3-month demand forecast for its product.

Demand-Forecasting Business Problem A chain of stores, 10 different stores and 50 different requests a 3-month demand forecast for its product.

Ayşe Nur Türkaslan 3 Mar 06, 2022
A linear equation solver using gaussian elimination. Implemented for fun and learning/teaching.

A linear equation solver using gaussian elimination. Implemented for fun and learning/teaching. The solver will solve equations of the type: A can be

Sanjeet N. Dasharath 3 Feb 15, 2022
cuML - RAPIDS Machine Learning Library

cuML - GPU Machine Learning Algorithms cuML is a suite of libraries that implement machine learning algorithms and mathematical primitives functions t

RAPIDS 3.1k Dec 28, 2022