{
  "cells": [
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": false
      },
      "outputs": [],
      "source": [
        "%matplotlib inline"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "\n# Select structures\n\nThis example shows how to select structures from dataset\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": false
      },
      "outputs": [],
      "source": [
        "from pynep.calculate import NEP\nfrom pynep.select import FarthestPointSample\nfrom ase.io import read, write\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom sklearn.decomposition import PCA\n\n\na = read('data.traj', ':')\ncalc = NEP(\"C_2022_NEP3.txt\")\nprint(calc)\ndes = np.array([np.mean(calc.get_property('descriptor', i), axis=0) for i in a])\nsampler = FarthestPointSample(min_distance=0.05)\nselected_i = sampler.select(des, [])\nwrite('selected.traj', [a[i] for  i in selected_i])\n\nreducer = PCA(n_components=2)\nreducer.fit(des)\nproj = reducer.transform(des)\nplt.scatter(proj[:,0], proj[:,1], label='all data')\nselected_proj = reducer.transform(np.array([des[i] for i in selected_i]))\nplt.scatter(selected_proj[:,0], selected_proj[:,1], label='selected data')\nplt.legend()\nplt.axis('off')\nplt.savefig('select.png')"
      ]
    }
  ],
  "metadata": {
    "kernelspec": {
      "display_name": "Python 3",
      "language": "python",
      "name": "python3"
    },
    "language_info": {
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "file_extension": ".py",
      "mimetype": "text/x-python",
      "name": "python",
      "nbconvert_exporter": "python",
      "pygments_lexer": "ipython3",
      "version": "3.7.9"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}