{ "cells": [ { "cell_type": "markdown", "id": "1576f175-58ed-48b5-800b-dac201db55a3", "metadata": {}, "source": [ "# Similarity matrices and clustering" ] }, { "cell_type": "markdown", "id": "8ea0d68d-1f9c-4b0e-8aa3-a5b426205425", "metadata": {}, "source": [ "We can use fingerprints to compute the similarities between all members of a dataset and denote them in a symmetric matrix. This matrix is called similarity matrix. Each row and column of this matrix represents the similarity of a fingerprint to the rest of the dataset. \n", "\n", "To compute similarity matrices, we need fingerprints, which are introduced in the tutorial \"Using material fingerprints\". These fingerprints are used to encode the electronic density-of-states (DOS) of a material as a binary-valued vector. If you didn't do this tutorial yet, you at least have to run the whole notebook in the same folder as this tutorial, in order to create the required data." ] }, { "cell_type": "markdown", "id": "3458478f-24f4-462f-bc7e-61620bdea6c6", "metadata": {}, "source": [ "In this tutorial, we will learn how to:\n", "\n", "