From 5b01e8e90ab314448f23ccc6b77f52d2a552a2d8 Mon Sep 17 00:00:00 2001 From: Rasmus Kronberg Date: Thu, 11 Apr 2024 16:16:02 +0300 Subject: [PATCH] clear outputs of cells --- AI4Spec_Tutorial1.ipynb | 1968 +++++++++++++++++---------------------- AI4Spec_Tutorial2.ipynb | 734 +-------------- AI4Spec_Tutorial3.ipynb | 539 +---------- 3 files changed, 902 insertions(+), 2339 deletions(-) diff --git a/AI4Spec_Tutorial1.ipynb b/AI4Spec_Tutorial1.ipynb index b02f827..4745df9 100644 --- a/AI4Spec_Tutorial1.ipynb +++ b/AI4Spec_Tutorial1.ipynb @@ -1,1130 +1,846 @@ { - "cells": [ - { - "cell_type": "markdown", - "source": [ - "# AI4Spec 1: Predicting individual energy levels with kernel methods\n", - "\n", - "In these tutorials exercises, we review different AI approaches to predicting ground or excited state energy levels simply based on the atomic structure of materials. Here we focus on molecules and molecular orbitals, but the sample principles apply to crystal structures and electronic bands.\n", - "\n", - "We start by predicting individual electronic states (Tutorial 1), proceed towards predicting multiple states at once (Tutorial 2) and finish by predicting entire spectral curves (Tutorial 3). The tutorials were prepared by Milica Todorović (University of Turku) and Kunal Ghosh (Aalto University).\n", - "\n", - "\n", - "\n", - "In the exercise below, our AI objective is to train a model to predict a single electronic energy level, HOMO for example. This is a classic example of supervised machine learning regression, where the objective (label) is a single floating-point number. Many AI models can address this task, from decision trees, via kernel-based learning to neural networks. Here, we demonstrate the use of Kernel Ridge Regression, a relatively simple regression approach that has performed well on numerous prediction tasks in physics and chemistry **{Cite Mathias Rupp}**\n", - "\n", - "We use a large dataset of molecular structures and their computed HOMO energies to train the AI. Once the model is trained, it can be used as a tool: one can input a new molecule (previously unseen by the model) and instantly receive a value for its HOMO, within the expected error of the trained model.\n", - "\n", - "\n", - "\n", - "\n", - "\n" - ], - "metadata": { - "id": "Fl2hw46ADkH4" - } - }, - { - "cell_type": "markdown", - "metadata": { - "id": "XegnO6aTwrmX" - }, - "source": [ - "## 1. HOMO energy prediction with kernel ridge regression\n", - "\n", - "\n", - "Here we will machine-learn the relationship between molecular structure (represented by the Coulomb matrix CM) and their HOMO (Highest Occupied Molecular Orbital) energy using KRR.\n", - "\n", - "This tutorial shows step by step how to load the data, visualize them, select the hyperparameters, train the model and validate it. We use the QM7 dataset of 7000 small organic molecules. The HOMO energies of all molecules were pre-computed with first principles quantum mechanical methods (DFT) to obtain the target data that our model can be trained on. Detailed descriptions and results for a similar dataset (QM9) can be found in [A. Stuke, et al. \"Chemical diversity in molecular orbital energy predictions with kernel ridge regression.\" J. Chem. Phys. 150. 204121 (2019)](https://aip.scitation.org/doi/10.1063/1.5086105).\n", - "\n", - "\n", - "## Setup" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "id": "qdphsPPRwwNF" - }, - "outputs": [], - "source": [ - "from sklearn.model_selection import GridSearchCV\n", - "from sklearn.model_selection import cross_validate\n", - "from sklearn.kernel_ridge import KernelRidge\n", - "from sklearn.metrics import r2_score\n", - "\n", - "import numpy as np\n", - "import matplotlib.pyplot as plt\n", - "import pandas as pd\n", - "import seaborn as sns\n", - "import json\n", - "import math, random\n", - "from scipy.sparse import load_npz\n", - "from matplotlib.colors import LinearSegmentedColormap\n", - "import time" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "hi4ISia7wrmc" - }, - "source": [ - "### Load and visualize data\n", - "\n", - "At first, we load the data.\n", - "\n", - "The input data x is an array that contains all 7000 molecules of the QM7 dataset, represented by their Coulomb matrices, which were computed with the [Dscribe](https://www.sciencedirect.com/science/article/pii/S0010465519303042?via%3Dihub) package.\n", - "\n", - "The output data y is a list that contains the corresponding (pre-computed) HOMO energies." - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "id": "jTZ_1hpqLBK5", - "colab": { - "base_uri": "https://localhost:8080/" - }, - "outputId": "a15f3c92-4b6c-453a-e0d6-1a9e91e72112" - }, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "--2023-11-09 13:22:58-- https://github.com/fullmetalfelix/ML-CSC-tutorial/raw/master/data/qm7/cm.npz\n", - "Resolving github.com (github.com)... 140.82.113.3\n", - "Connecting to github.com (github.com)|140.82.113.3|:443... connected.\n", - "HTTP request sent, awaiting response... 302 Found\n", - "Location: https://raw.githubusercontent.com/fullmetalfelix/ML-CSC-tutorial/master/data/qm7/cm.npz [following]\n", - "--2023-11-09 13:22:58-- https://raw.githubusercontent.com/fullmetalfelix/ML-CSC-tutorial/master/data/qm7/cm.npz\n", - "Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.110.133, 185.199.111.133, 185.199.108.133, ...\n", - "Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|185.199.110.133|:443... connected.\n", - "HTTP request sent, awaiting response... 200 OK\n", - "Length: 3638980 (3.5M) [application/octet-stream]\n", - "Saving to: ‘cm.npz’\n", - "\n", - "cm.npz 100%[===================>] 3.47M --.-KB/s in 0.1s \n", - "\n", - "2023-11-09 13:22:58 (33.9 MB/s) - ‘cm.npz’ saved [3638980/3638980]\n", - "\n", - "--2023-11-09 13:22:58-- https://raw.githubusercontent.com/fullmetalfelix/ML-CSC-tutorial/master/data/qm7/HOMO.txt\n", - "Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.111.133, 185.199.108.133, 185.199.110.133, ...\n", - "Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|185.199.111.133|:443... connected.\n", - "HTTP request sent, awaiting response... 200 OK\n", - "Length: 54610 (53K) [text/plain]\n", - "Saving to: ‘HOMO.txt’\n", - "\n", - "HOMO.txt 100%[===================>] 53.33K --.-KB/s in 0.02s \n", - "\n", - "2023-11-09 13:22:58 (3.18 MB/s) - ‘HOMO.txt’ saved [54610/54610]\n", - "\n" - ] - } - ], - "source": [ - "!wget https://github.com/fullmetalfelix/ML-CSC-tutorial/raw/master/data/qm7/cm.npz\n", - "!wget https://raw.githubusercontent.com/fullmetalfelix/ML-CSC-tutorial/master/data/qm7/HOMO.txt" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "id": "6tTcc8Mtwrmd", - "colab": { - "base_uri": "https://localhost:8080/" - }, - "outputId": "baf6dc4d-80fb-4b36-f3ba-026677ad11ee" - }, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "Number of molecules: 6926\n" - ] - } - ], - "source": [ - "x = load_npz(\"cm.npz\").toarray()\n", - "y = np.genfromtxt(\"HOMO.txt\")\n", - "\n", - "print(\"Number of molecules:\", len(y))" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "yWa4pRHxwrmf" - }, - "source": [ - "Print the Coulomb matrix of a random molecule in the dataset." - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "id": "7CovKOElwrmg", - "colab": { - "base_uri": "https://localhost:8080/" - }, - "outputId": "68c822c8-6e05-431d-8223-791fc3851287" - }, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "[36.858 26.966 14.341 11.895 7.709 7.345 5.506 5.493 2.845 2.279\n", - " 1.861 1.677 1.227 1.045 0. 0. 0. 0. 0. 0.\n", - " 0. 0. 0. 26.966 36.858 23.934 17.032 10.47 9.284 2.828\n", - " 2.83 5.483 2.795 2.79 2.176 1.669 1.281 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 14.341 23.934 36.858 28.805\n", - " 14.417 11.301 1.711 2.169 2.714 5.446 5.448 2.834 2.293 1.506\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. 11.895\n", - " 17.032 28.805 53.359 30.553 20.365 1.581 1.825 2.501 3.319 3.39\n", - " 6.889 3.399 2.748 0. 0. 0. 0. 0. 0. 0.\n", - " 0. 0. 7.709 10.47 14.417 30.553 36.858 32.739 1.095 1.175\n", - " 1.761 1.83 2.343 2.928 5.455 3.124 0. 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 7.345 9.284 11.301 20.365 32.739\n", - " 53.359 1.085 1.132 1.606 1.574 1.822 2.628 3.422 6.802 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 5.506 2.828\n", - " 1.711 1.581 1.095 1.085 0.5 0.538 0.407 0.269 0.241 0.227\n", - " 0.176 0.155 0. 0. 0. 0. 0. 0. 0. 0.\n", - " 0. 5.493 2.83 2.169 1.825 1.175 1.132 0.538 0.5 0.324\n", - " 0.412 0.284 0.262 0.187 0.163 0. 0. 0. 0. 0.\n", - " 0. 0. 0. 0. 2.845 5.483 2.714 2.501 1.761 1.606\n", - " 0.407 0.324 0.5 0.322 0.389 0.32 0.286 0.218 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 2.279 2.795 5.446\n", - " 3.319 1.83 1.574 0.269 0.412 0.322 0.5 0.566 0.396 0.291\n", - " 0.217 0. 0. 0. 0. 0. 0. 0. 0. 0.\n", - " 1.861 2.79 5.448 3.39 2.343 1.822 0.241 0.284 0.389 0.566\n", - " 0.5 0.337 0.454 0.229 0. 0. 0. 0. 0. 0.\n", - " 0. 0. 0. 1.677 2.176 2.834 6.889 2.928 2.628 0.227\n", - " 0.262 0.32 0.396 0.337 0.5 0.338 0.418 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 1.227 1.669 2.293 3.399\n", - " 5.455 3.422 0.176 0.187 0.286 0.291 0.454 0.338 0.5 0.343\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. 1.045\n", - " 1.281 1.506 2.748 3.124 6.802 0.155 0.163 0.218 0.217 0.229\n", - " 0.418 0.343 0.5 0. 0. 0. 0. 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. ]\n" - ] - } - ], - "source": [ - "rand_mol = random.randint(0, len(y))\n", - "\n", - "print(x[rand_mol])" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "BKo-SoN2wrmh" - }, - "source": [ - "Visualize the Coulomb matrix of the random molecule." - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "id": "GJu2RtUhwrmh", - "colab": { - "base_uri": "https://localhost:8080/", - "height": 502 - }, - "outputId": "1466b332-185d-4ad7-e2f6-c3696ceed6d5" - }, - "outputs": [ - { - "output_type": "display_data", - "data": { - "text/plain": [ - "
" - ] - }, - "metadata": {} - }, - { - "output_type": "display_data", - "data": { - "text/plain": [ - "
" - ], - "image/png": "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\n" - }, - "metadata": {} - } - ], - "source": [ - "shape = (23, 23)\n", - "mat = x[rand_mol].reshape(shape)\n", - "\n", - "plt.figure()\n", - "plt.figure(figsize = (6,6))\n", - "plt.imshow(mat, origin=\"upper\", cmap='rainbow', vmin=-15, vmax=75, interpolation='nearest')\n", - "plt.colorbar(fraction=0.046, pad=0.04).ax.tick_params(labelsize=20)\n", - "plt.axis('off')\n", - "plt.show()" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "n434DnNSwrmi" - }, - "source": [ - "Note that many of the outputs are zero in the Coulomb matrix. This is because the number of non-zero outputs depends on the size of the molecule, and all smaller molecules contain zero padding.\n", - "\n", - "Visualize the target data by plotting the distribution of HOMO energies in the dataset:" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "id": "YxjygJgJwrmj", - "colab": { - "base_uri": "https://localhost:8080/", - "height": 510 - }, - "outputId": "c0683fc7-7a3d-490a-e012-bc6e7210c3a5" - }, - "outputs": [ - { - "output_type": "display_data", - "data": { - "text/plain": [ - "
" - ], - "image/png": "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\n" - }, - "metadata": {} - }, - { - "output_type": "stream", - "name": "stdout", - "text": [ - "Mean value of HOMO energies in QM7 dataset: -5.66 eV\n" - ] - } - ], - "source": [ - "plt.hist(y, bins=20, density=False, facecolor='blue')\n", - "plt.xlabel(\"Energy [eV]\")\n", - "plt.ylabel(\"Number of molecules\")\n", - "plt.title(\"Distribution of HOMO energies\")\n", - "plt.show()\n", - "\n", - "## mean value of distribution\n", - "print(\"Mean value of HOMO energies in QM7 dataset: %0.2f eV\" %np.mean(y))" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "QpgK9ky-wrmk" - }, - "source": [ - "Before dividing the dataset into training and test set, we shuffle the data. This is because data are often stored in a logical order (e.g., certain types of molecules grouped one after each other). Simply taking the first part for training and the second for testing would not result in a well trained model, since the training set would not represent the test data well (and vice versa)." - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "id": "6luJyqCKwrmk" - }, - "outputs": [], - "source": [ - "## shuffle the data\n", - "\n", - "c = list(zip(x, y))\n", - "random.shuffle(c)\n", - "\n", - "x, y = zip(*c)\n", - "\n", - "x = np.array(x)\n", - "y = np.array(y)" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "XQh-MAv5wrml" - }, - "source": [ - "Now, we divide the data into training and test set." - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "id": "wmnl8ZzAwrmm" - }, - "outputs": [], - "source": [ - "# decide how many samples to take from the database for training and testing\n", - "n_train = 1000\n", - "n_test = 1000\n", - "\n", - "# split data in training and test\n", - "# take first n_train molecules for training\n", - "x_train = x[0:n_train]\n", - "y_train = y[0:n_train]\n", - "\n", - "# take the next n_test data for testing\n", - "x_test = x[n_train:n_train + n_test]\n", - "y_test = y[n_train:n_train + n_test]" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "uEP7iSchwrmm" - }, - "source": [ - "Check that the training data resemble the test data well by plotting the distribution of HOMO energies for both sets. The distributions should be centered around the same mean value and have the same shape." - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "id": "w_H7kOBTwrmn", - "colab": { - "base_uri": "https://localhost:8080/", - "height": 504 - }, - "outputId": "14677f4e-42d1-4de3-8360-dbadedd01a3d" - }, - "outputs": [ - { - "output_type": "display_data", - "data": { - "text/plain": [ - "
" - ], - "image/png": "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\n" - }, - "metadata": {} - }, - { - "output_type": "stream", - "name": "stdout", - "text": [ - "Mean value of HOMO energies in training set: -5.66 eV\n", - "Mean value of HOMO energies in test set: -5.66 eV\n" - ] - } - ], - "source": [ - "plt.hist(y_test, bins=20, density=False, alpha=0.5, facecolor='red', label='test set')\n", - "plt.hist(y_train, bins=20, density=False, alpha=0.5, facecolor='gray', label='training set')\n", - "plt.xlabel(\"Energy [eV]\")\n", - "plt.ylabel(\"Number of molecules\")\n", - "plt.legend()\n", - "plt.show()\n", - "\n", - "## mean value of distributions\n", - "print(\"Mean value of HOMO energies in training set: %0.2f eV\" %np.mean(y_train))\n", - "print(\"Mean value of HOMO energies in test set: %0.2f eV\" %np.mean(y_test))" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "0FxS6Kazwrmo" - }, - "source": [ - "### Training\n", - "\n", - "In the training phase we use a kernel function to measure the distance between all pairs of molecules (represented by their Coulomb matrices) in the training set. We here employ one of two kernels, the Gaussian kernel or the Laplacian kernel. Both kernels have two hyperparameters: $\\alpha$ controls the penalty term and $\\gamma$ the kernel width.\n", - "\n", - "To find the optimal hyperparameters, we will do a grid search, i.e. we test the performance of a model trained with values of the hyperparameters that are spaced out on a grid in search space and choose the hyperparameters that yield the best performance.\n", - "\n", - "The model performance is quantified by splitting off part of the training set as validation set. We validate the model by making predictions on this validation set. This check of the model performance can be further refined with cross-validation, where the roles of training and validation sets alternate. The ratio can be varied, for example in 5-fold cross-validation, the training set is split in 5 equal parts. The model is trained on 80% of the data and validated on the other 20%. Then the roles of training and validation set rotate until each part has served as validation set exactly once.\n", - "\n", - "For our implementation, we will use the scikit-learn module.\n", - "\n", - "A more detailed optional explanation, which is not required for the solution of the exercise, can be found in the hidden cell below." - ] - }, - { - "cell_type": "markdown", - "source": [ - "The Gaussian kernel is given by\n", - "\n", - "\\begin{equation}\n", - "k_{Gaussian}(\\boldsymbol{x},\\boldsymbol{x}')=e^{-\\frac{||{\\boldsymbol{x}-\\boldsymbol{x}'}||_2^2}{2\\gamma^2}},\n", - "\\end{equation}\n", - "\n", - "which employs the Euclidean distance as similarity measure. The parameter $\\gamma$ is defined as $\\frac{1}{2\\sigma^2}$, where $\\sigma$ is the standard deviation of the Gaussian kernel (kernel width). The Laplacian kernel is given by\n", - "\n", - "\\begin{equation}\n", - " k_{Laplacian}(\\boldsymbol{x},\\boldsymbol{x}')=e^{-\\frac{||{\\boldsymbol{x}-\\boldsymbol{x}'}||_1}{\\gamma}},\n", - "\\end{equation}\n", - "\n", - "which uses the 1-norm as similarity measure. Here, $\\gamma$ is defined as $\\frac{1}{\\sigma}$, where $\\sigma$ is the kernel width of the Laplacian kernel.\n", - "\n", - "In the KRR training phase with $N$ training molecules, the machine learns the relationship between the molecules (represented by their Coulomb matrix) and their corresponding (pre-computed) HOMO energies. It does so by employing a function $f(\\boldsymbol{x})$ that maps a training molecule $\\boldsymbol{x}$ to its reference HOMO energy:\n", - "\n", - "\\begin{equation}\n", - "f(\\boldsymbol{x}) = \\sum_{i=1}^N \\omega_i k(\\boldsymbol{x}, \\boldsymbol{x}_i) = HOMO^{ref},\n", - "\\end{equation}\n", - "\n", - "For a given training molecule $\\boldsymbol{x}$, the distance to each molecule in the training set is computed by employing the kernel function $k$ (either Gaussian or Laplacian). Each kernel contribution (distance) is then weighted by a regression weight $\\omega_i$. The above function is thus given by the weighted sum of kernel contributions (sum over $N$ training molecules). The purpose of training is to fit the regression weight $\\omega_i$ so that HOMO$_{ref}$ is matched for each training molecule. In practice, the machine solves the minimization problem\n", - "\n", - "\n", - "\\begin{equation}\n", - " \\underset{\\omega}{min} \\sum_{i=1}^N (f(\\boldsymbol{x}_i) - HOMO^{ref}_i)^2 + \\alpha \\boldsymbol{\\omega}^T \\mathbf{K} \\boldsymbol{\\omega}.\n", - "\\end{equation}\n", - "\n", - "for a vector $\\boldsymbol{\\omega} \\in \\mathbb{R}^N = (\\omega_1, \\omega_2, ..., \\omega_N)$ of regression weights. In KRR, the penalty term $ \\alpha \\boldsymbol{\\omega}^T \\mathbf{K} \\boldsymbol{\\omega}$ is added to the minimization problem in order to avoid over- and underfitting. Overfitting occurs when the model learns the training data too well, even the noise and other unimportant details. The model is unable to generalize on unseen data and therefore yields high prediction errors on the test data. Underfitting occurs when the model is too simple and does not learn the training data at all, and therefore is not able to predict test data well either. Both behaviours can be avoided by tuning the parameter $\\alpha \\in \\left[0,1\\right]$ to a reasonable value. This has do be done separately from training. Both the regularization parameter $\\alpha$ and the kernel width $\\gamma$ are so called hyperparameters. Hyperparameters cannot be learned during training and have to be selected beforehand. However, it is not always obvious how to choose these hyperparameters and it often requires intuition or rules of thumb. We here employ a cross-validated grid search in order to find the best values for these two hyperparameters.\n", - "\n", - "In grid search, a part of the training set is split off as validation set. We set up a grid of pre-defined hyperparameter values and train the machine on the remaining training set, for each possible combination of $\\alpha$ and $\\gamma$ values. We validate each possible combination by making predictions on the validation set. The two hyperparameter values that yield the best performance (lowest error) are then selected for the final model to make predictions on the test set.\n", - "\n", - "In cross-validation, the roles of training and validation sets alternate. As described above, a part from the training set is split off as validation set. After training one combination of hyperparameters on the remaining training set and validating on the validation set, the validation set becomes the training set and vice versa, and the model is trained on the new training set and validated on the new validation set for the same combination of hyperparameters. The ratio can be varied, for example in 5-fold cross-validation, the training set is split in 5 equal parts. For each combination of hyperparameters, the model is trained on 80% of the data and validated on the other 20%. Then the roles of training and validation set rotate until each part has served as validation set exactly once. The final validation error for one particular combination of hyperparameters is computed as the mean from all 5 errors on the 5 validation sets. The combination with lowest average error is chosen for the final model.\n", - "\n", - "The cross-validated grid search routine is implemented in scikit-learn." - ], - "metadata": { - "id": "IqRlAI8983CM" - } - }, - { - "cell_type": "markdown", - "source": [ - "### KRR Code" - ], - "metadata": { - "id": "O5e2EytL8aDY" - } - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "id": "hbcOapWDwrmp", - "colab": { - "base_uri": "https://localhost:8080/", - "height": 778 - }, - "outputId": "1d28b29e-0eb8-4473-fa33-4ae2bd9ee3af" - }, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "Fitting 2 folds for each of 9 candidates, totalling 18 fits\n", - "[CV 1/2; 1/9] START alpha=0.0001, gamma=0.0001, kernel=laplacian................\n", - "[CV 1/2; 1/9] END alpha=0.0001, gamma=0.0001, kernel=laplacian;, score=-0.310 total time= 0.3s\n", - "[CV 2/2; 1/9] START alpha=0.0001, gamma=0.0001, kernel=laplacian................\n", - "[CV 2/2; 1/9] END alpha=0.0001, gamma=0.0001, kernel=laplacian;, score=-0.318 total time= 0.3s\n", - "[CV 1/2; 2/9] START alpha=0.0001, gamma=0.001, kernel=laplacian.................\n", - "[CV 1/2; 2/9] END alpha=0.0001, gamma=0.001, kernel=laplacian;, score=-0.313 total time= 0.3s\n", - "[CV 2/2; 2/9] START alpha=0.0001, gamma=0.001, kernel=laplacian.................\n", - "[CV 2/2; 2/9] END alpha=0.0001, gamma=0.001, kernel=laplacian;, score=-0.298 total time= 0.3s\n", - "[CV 1/2; 3/9] START alpha=0.0001, gamma=0.01, kernel=laplacian..................\n", - "[CV 1/2; 3/9] END alpha=0.0001, gamma=0.01, kernel=laplacian;, score=-1.578 total time= 0.3s\n", - "[CV 2/2; 3/9] START alpha=0.0001, gamma=0.01, kernel=laplacian..................\n", - "[CV 2/2; 3/9] END alpha=0.0001, gamma=0.01, kernel=laplacian;, score=-1.649 total time= 0.3s\n", - "[CV 1/2; 4/9] START alpha=0.001, gamma=0.0001, kernel=laplacian.................\n", - "[CV 1/2; 4/9] END alpha=0.001, gamma=0.0001, kernel=laplacian;, score=-0.305 total time= 0.3s\n", - "[CV 2/2; 4/9] START alpha=0.001, gamma=0.0001, kernel=laplacian.................\n", - "[CV 2/2; 4/9] END alpha=0.001, gamma=0.0001, kernel=laplacian;, score=-0.307 total time= 0.3s\n", - "[CV 1/2; 5/9] START alpha=0.001, gamma=0.001, kernel=laplacian..................\n", - "[CV 1/2; 5/9] END alpha=0.001, gamma=0.001, kernel=laplacian;, score=-0.313 total time= 0.4s\n", - "[CV 2/2; 5/9] START alpha=0.001, gamma=0.001, kernel=laplacian..................\n", - "[CV 2/2; 5/9] END alpha=0.001, gamma=0.001, kernel=laplacian;, score=-0.298 total time= 0.5s\n", - "[CV 1/2; 6/9] START alpha=0.001, gamma=0.01, kernel=laplacian...................\n", - "[CV 1/2; 6/9] END alpha=0.001, gamma=0.01, kernel=laplacian;, score=-1.579 total time= 0.5s\n", - "[CV 2/2; 6/9] START alpha=0.001, gamma=0.01, kernel=laplacian...................\n", - "[CV 2/2; 6/9] END alpha=0.001, gamma=0.01, kernel=laplacian;, score=-1.650 total time= 0.5s\n", - "[CV 1/2; 7/9] START alpha=0.01, gamma=0.0001, kernel=laplacian..................\n", - "[CV 1/2; 7/9] END alpha=0.01, gamma=0.0001, kernel=laplacian;, score=-0.301 total time= 0.5s\n", - "[CV 2/2; 7/9] START alpha=0.01, gamma=0.0001, kernel=laplacian..................\n", - "[CV 2/2; 7/9] END alpha=0.01, gamma=0.0001, kernel=laplacian;, score=-0.285 total time= 0.5s\n", - "[CV 1/2; 8/9] START alpha=0.01, gamma=0.001, kernel=laplacian...................\n", - "[CV 1/2; 8/9] END alpha=0.01, gamma=0.001, kernel=laplacian;, score=-0.313 total time= 0.5s\n", - "[CV 2/2; 8/9] START alpha=0.01, gamma=0.001, kernel=laplacian...................\n", - "[CV 2/2; 8/9] END alpha=0.01, gamma=0.001, kernel=laplacian;, score=-0.295 total time= 0.3s\n", - "[CV 1/2; 9/9] START alpha=0.01, gamma=0.01, kernel=laplacian....................\n", - "[CV 1/2; 9/9] END alpha=0.01, gamma=0.01, kernel=laplacian;, score=-1.586 total time= 0.3s\n", - "[CV 2/2; 9/9] START alpha=0.01, gamma=0.01, kernel=laplacian....................\n", - "[CV 2/2; 9/9] END alpha=0.01, gamma=0.01, kernel=laplacian;, score=-1.657 total time= 0.3s\n" - ] - }, - { - "output_type": "execute_result", - "data": { - "text/plain": [ - "GridSearchCV(cv=2, estimator=KernelRidge(),\n", - " param_grid=[{'alpha': array([0.0001, 0.001 , 0.01 ]),\n", - " 'gamma': array([0.0001, 0.001 , 0.01 ]),\n", - " 'kernel': ['laplacian']}],\n", - " scoring='neg_mean_absolute_error', verbose=1000)" - ], - "text/html": [ - "
GridSearchCV(cv=2, estimator=KernelRidge(),\n",
-              "             param_grid=[{'alpha': array([0.0001, 0.001 , 0.01  ]),\n",
-              "                          'gamma': array([0.0001, 0.001 , 0.01  ]),\n",
-              "                          'kernel': ['laplacian']}],\n",
-              "             scoring='neg_mean_absolute_error', verbose=1000)
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
" - ] - }, - "metadata": {}, - "execution_count": 10 - } - ], - "source": [ - "# set up grids for alpha and gamma hyperparameters.\n", - "# first value: lower bound; second value: upper bound;\n", - "# third value: number of points to evaluate (here set to '3' --> '-2', '-1' and '0' are evaluated)\n", - "# --> make sure to change third value as well when changing the bounds!\n", - "alpha = np.logspace(-4, -2, 3)\n", - "gamma = np.logspace(-4, -2, 3)\n", - "\n", - "cv_number = 2 ## choose into how many parts training set is divided for cross-validation\n", - "kernel = 'laplacian' # select kernel function here ('rbf': Gaussian kernel, 'laplacian': Laplacian kernel)\n", - "scoring_function = 'neg_mean_absolute_error' # it is called \"negative\" because scikit-learn interprets\n", - " # highest scoring value as best, but we want small errors\n", - "\n", - "## define settings for grid search routine in scikit-learn with above defined grids as input\n", - "\n", - "grid_search = GridSearchCV(KernelRidge(), #machine learning method (KRR here)\n", - " [{'kernel':[kernel],'alpha': alpha, 'gamma': gamma}],\n", - " cv = cv_number,\n", - " scoring = scoring_function,\n", - " verbose=1000) ## produces detailed output statements of grid search\n", - " # routine so we can see what is computed\n", - "\n", - "# call the fit function in scikit-learn which fits the Coulomb matrices in the training set\n", - "# to their corresponding HOMO energies.\n", - "grid_search.fit(x_train, y_train)" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "mTrweQ1Mwrmr" - }, - "source": [ - "### Grid search results\n", - "\n", - "Print out the average validation errors and corresponding hyperparameter combinations" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "id": "066IjiWawrmr", - "colab": { - "base_uri": "https://localhost:8080/" - }, - "outputId": "de299c89-9c65-437c-c798-72bb63bd89e0" - }, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "0.314 (+/-0.007) for {'alpha': 0.0001, 'gamma': 0.0001, 'kernel': 'laplacian'}\n", - "0.306 (+/-0.015) for {'alpha': 0.0001, 'gamma': 0.001, 'kernel': 'laplacian'}\n", - "1.613 (+/-0.071) for {'alpha': 0.0001, 'gamma': 0.01, 'kernel': 'laplacian'}\n", - "0.306 (+/-0.002) for {'alpha': 0.001, 'gamma': 0.0001, 'kernel': 'laplacian'}\n", - "0.306 (+/-0.015) for {'alpha': 0.001, 'gamma': 0.001, 'kernel': 'laplacian'}\n", - "1.614 (+/-0.071) for {'alpha': 0.001, 'gamma': 0.01, 'kernel': 'laplacian'}\n", - "0.293 (+/-0.016) for {'alpha': 0.01, 'gamma': 0.0001, 'kernel': 'laplacian'}\n", - "0.304 (+/-0.018) for {'alpha': 0.01, 'gamma': 0.001, 'kernel': 'laplacian'}\n", - "1.621 (+/-0.071) for {'alpha': 0.01, 'gamma': 0.01, 'kernel': 'laplacian'}\n" - ] - } - ], - "source": [ - "means = grid_search.cv_results_['mean_test_score']\n", - "stds = grid_search.cv_results_['std_test_score']\n", - "for mean, std, params in zip(-means, stds, grid_search.cv_results_['params']):\n", - " print(\"%0.3f (+/-%0.03f) for %r\" % (mean, std * 2, params))" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "SrfhK2fTwrms" - }, - "source": [ - "Next, we visualize the grid search results by plotting a heatmap." - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "id": "T2swGFTLwrmt", - "colab": { - "base_uri": "https://localhost:8080/", - "height": 488 - }, - "outputId": "e8b282a6-56fb-4a2e-93c0-bacf613f594e" - }, - "outputs": [ - { - "output_type": "display_data", - "data": { - "text/plain": [ - "
" - ], - "image/png": "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\n" - }, - "metadata": {} - }, - { - "output_type": "stream", - "name": "stdout", - "text": [ - "The best combinations of parameters are {'alpha': 0.01, 'gamma': 0.0001, 'kernel': 'laplacian'} with a score of 0.293 eV on the validation set.\n" - ] - } - ], - "source": [ - "results = pd.DataFrame(grid_search.cv_results_)\n", - "#pd.DataFrame(grid_search.cv_results_)\n", - "\n", - "pvt = pd.pivot_table(results, values='mean_test_score',\n", - " index='param_gamma', columns='param_alpha')\n", - "heatmap = sns.heatmap(-pvt, annot=True, cmap='viridis', cbar_kws={'label': \"Mean absolute error [eV]\"})\n", - "figure = heatmap.get_figure()\n", - "plt.show()\n", - "\n", - "\n", - "print(\"The best combinations of parameters are %s with a score of %0.3f eV on the validation set.\"\n", - " % (grid_search.best_params_, -grid_search.best_score_))" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "-tv1CciKwrmu" - }, - "source": [ - "### Testing\n", - "\n", - "With the best combination of hyperparameters, the model is once again trained on the entire training set (this is done automatically in scikit-learn). Then, with the best combination of hyperparameters, predictions are made on the test set to evaluate the final model, which we will use for predictions.\n", - "\n", - "The mean absolute error of the predicted from the reference HOMO energies and $R^2$ score will be our measure for the quality of the fit.\n" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "id": "k8e9G1iNwrmv", - "colab": { - "base_uri": "https://localhost:8080/", - "height": 504 - }, - "outputId": "42be6aaa-f279-436b-97d1-b4a137005585" - }, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "Mean absolute error on test set: 0.255 eV\n" - ] - }, - { - "output_type": "display_data", - "data": { - "text/plain": [ - "
" - ], - "image/png": "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\n" - }, - "metadata": {} - }, - { - "output_type": "stream", - "name": "stdout", - "text": [ - "R^2 score on test set: 0.607\n" - ] - } - ], - "source": [ - "# predicted HOMO energies for all test molecules\n", - "\n", - "y_pred = grid_search.predict(x_test) # scikit-learn automatically takes the best combination\n", - " # of hyperparameters from grid search\n", - "\n", - "print(\"Mean absolute error on test set: %0.3f eV\" %(np.abs(y_pred-y_test)).mean())\n", - "\n", - "# do the regression plot\n", - "plt.plot(y_test, y_pred, 'o')\n", - "plt.plot([np.min(y_test),np.max(y_test)], [np.min(y_test),np.max(y_test)], '-')\n", - "plt.xlabel('reference HOMO energy [eV]')\n", - "plt.ylabel('predicted HOMO energy [eV]')\n", - "plt.show()\n", - "print(\"R^2 score on test set: %.3f\" % r2_score(y_test, y_pred))" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "pYf2oHVbwrmw" - }, - "source": [ - "The $R^2$ score indicates how close the predicted energies in the test set are to the reference energies. The closer the points in the above figure are located to the diagonal, the better the predictions. Points on the diagonal (\"predicted energy\"=\"reference energy\") correspond to $R^2=1$. Therefore, $R^2$ values close to 1 indicate good model performance." - ] - }, - { - "cell_type": "markdown", - "metadata": { - "collapsed": true, - "id": "zcdZdkThwrmw" - }, - "source": [ - "###**Exercises**\n", - "\n", - "#### a. Grid search\n", - "\n", - "Increase the number and range of grid points used for grid search. Which combination of $\\alpha$ and $\\gamma$ works best? How does the computational time increase? Choose a reasonable number of grid points that don't take too long to evaluate." - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "id": "mqN4J1xVwrmx" - }, - "outputs": [], - "source": [ - "#Choose alpha and gamma on a finer logarithmically spaced grid. The other parameters can be chosen as above.\n", - "alpha = None\n", - "gamma = None\n", - "cv_number=None\n", - "kernel = None\n", - "scoring_function = None\n", - "\n", - "\n", - "grid_search = GridSearchCV(KernelRidge(), #machine learning method (KRR here)\n", - " [{'kernel':[kernel],'alpha': alpha, 'gamma': gamma}],\n", - " cv = cv_number,\n", - " scoring = scoring_function,\n", - " verbose=1000) ## produces detailed output statements of grid search routine\n", - "\n", - "grid_search.fit(x_train, y_train)\n", - "\n", - "results = pd.DataFrame(grid_search.cv_results_)\n", - "\n", - "pvt = pd.pivot_table(results, values='mean_test_score',\n", - " index='param_gamma', columns='param_alpha')\n", - "heatmap = sns.heatmap(-pvt, annot=True, cmap='viridis', cbar_kws={'label': \"Mean absolute error [eV]\"})\n", - "figure = heatmap.get_figure()\n", - "plt.show()\n", - "\n", - "print(\"The best combinations of parameters are %s with a score of %0.3f eV on the validation set.\"\n", - " % (grid_search.best_params_, -grid_search.best_score_))\n", - "\n", - "y_pred = grid_search.predict(x_test) # scikit-learn automatically takes the best combination of hyperparameters from grid search\n", - "\n", - "print(\"Mean absolute error on test set: %0.3f eV\" %(np.abs(y_pred-y_test)).mean())\n", - "\n", - "plt.plot(y_test, y_pred, 'o')\n", - "plt.plot([np.min(y_test),np.max(y_test)], [np.min(y_test),np.max(y_test)], '-')\n", - "plt.xlabel('reference HOMO energy [eV]')\n", - "plt.ylabel('predicted HOMO energy [eV]')\n", - "plt.show()\n", - "print(\"R^2 score on test set: %.3f\" % r2_score(y_test, y_pred))" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "Gsy36Rzowrmy" - }, - "source": [ - "#### b. Kernel function\n", - "\n", - "Use the Gaussian kernel instead of the Laplacian kernel. Which kernel leads to better model performance?" - ] - }, - { - "cell_type": "code", - "source": [ - "#Repeat the above calculation with the Gaussian kernel. The Gaussian kernel is identified with the string 'rbf'.\n", - "alpha = None\n", - "gamma = None\n", - "cv_number=None\n", - "kernel = None\n", - "scoring_function = None\n", - "\n", - "grid_search = GridSearchCV(KernelRidge(), #machine learning method (KRR here)\n", - " [{'kernel':[kernel],'alpha': alpha, 'gamma': gamma}],\n", - " cv = cv_number,\n", - " scoring = scoring_function,\n", - " verbose=1000) ## produces detailed output statements of grid search routine\n", - "\n", - "grid_search.fit(x_train, y_train)\n", - "\n", - "results = pd.DataFrame(grid_search.cv_results_)\n", - "\n", - "pvt = pd.pivot_table(results, values='mean_test_score',\n", - " index='param_gamma', columns='param_alpha')\n", - "heatmap = sns.heatmap(-pvt, annot=True, cmap='viridis', cbar_kws={'label': \"Mean absolute error [eV]\"})\n", - "figure = heatmap.get_figure()\n", - "plt.show()\n", - "\n", - "print(\"The best combinations of parameters are %s with a score of %0.3f eV on the validation set.\"\n", - " % (grid_search.best_params_, -grid_search.best_score_))\n", - "\n", - "y_pred = grid_search.predict(x_test) # scikit-learn automatically takes the best combination of hyperparameters from grid search\n", - "\n", - "print(\"Mean absolute error on test set: %0.3f eV\" %(np.abs(y_pred-y_test)).mean())\n", - "\n", - "plt.plot(y_test, y_pred, 'o')\n", - "plt.plot([np.min(y_test),np.max(y_test)], [np.min(y_test),np.max(y_test)], '-')\n", - "plt.xlabel('reference HOMO energy [eV]')\n", - "plt.ylabel('predicted HOMO energy [eV]')\n", - "plt.show()\n", - "print(\"R^2 score on test set: %.3f\" % r2_score(y_test, y_pred))" - ], - "metadata": { - "id": "srWUmjKapUMD" - }, - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "5yJUdzhewrmx" - }, - "source": [ - "#### c. Cross-validation\n", - "\n", - "For this exercise, choose the kernel that performed better in the previous exercise. Increase the number of folds used for cross-validation. Does the quality of the model increase? Take note as well of the increasing computational time and choose a number of folds that does not require too much computational time." - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "id": "Jqy3rfT9wrmy" - }, - "outputs": [], - "source": [ - "#Repeat the above calculation with a higher number of cross-validation folds. Use the kernel that showed better performance.\n", - "alpha = None\n", - "gamma = None\n", - "cv_number=None\n", - "kernel = None\n", - "scoring_function = None\n", - "\n", - "grid_search = GridSearchCV(KernelRidge(), #machine learning method (KRR here)\n", - " [{'kernel':[kernel],'alpha': alpha, 'gamma': gamma}],\n", - " cv = cv_number,\n", - " scoring = scoring_function,\n", - " verbose=1000) ## produces detailed output statements of grid search routine\n", - "\n", - "grid_search.fit(x_train, y_train)\n", - "\n", - "results = pd.DataFrame(grid_search.cv_results_)\n", - "#pd.DataFrame(grid_search.cv_results_)\n", - "\n", - "pvt = pd.pivot_table(results, values='mean_test_score',\n", - " index='param_gamma', columns='param_alpha')\n", - "heatmap = sns.heatmap(-pvt, annot=True, cmap='viridis', cbar_kws={'label': \"Mean absolute error [eV]\"})\n", - "figure = heatmap.get_figure()\n", - "plt.show()\n", - "\n", - "print(\"The best combinations of parameters are %s with a score of %0.3f eV on the validation set.\"\n", - " % (grid_search.best_params_, -grid_search.best_score_))\n", - "\n", - "y_pred = grid_search.predict(x_test) # scikit-learn automatically takes the best combination of hyperparameters from grid search\n", - "\n", - "print(\"Mean absolute error on test set: %0.3f eV\" %(np.abs(y_pred-y_test)).mean())\n", - "\n", - "plt.plot(y_test, y_pred, 'o')\n", - "plt.plot([np.min(y_test),np.max(y_test)], [np.min(y_test),np.max(y_test)], '-')\n", - "plt.xlabel('reference HOMO energy [eV]')\n", - "plt.ylabel('predicted HOMO energy [eV]')\n", - "plt.show()\n", - "print(\"R^2 score on test set: %.3f\" % r2_score(y_test, y_pred))" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "jjoUSLWuwrmz" - }, - "source": [ - "#### d. Training set size\n", - "\n", - "Increase the size of the training set and plot the mean absolute error and $R^2$ score and training time on the test set as a function of the training set size (e.g. use 1000, 2000, 3000 etc. as training set size). For the MAE and $R^2$ values use a logarithmic time axis. Compare with the previous exercises.\n", - "\n", - "The optimal hyperparameter values for $\\alpha$ and $\\gamma$ can change throughout varying training set sizes. Therefore, when increasing the training set size, it is recommended to perform a cross-validated grid search for each training set size. For the sake of this exercise, we will limit ourselves to taking the optimal hyperparameters from the previous exercise as an approximation and not perform a grid search. Furthermore, we will not cross-validate our model in this exercise in the interest of time." - ] - }, - { - "cell_type": "code", - "source": [ - "#We keep the size of the test set constant in this exercise\n", - "n_test = 1000\n", - "\n", - "#We want to iterate over different training set sizes n_train.\n", - "#Prepare an iterator with reasonable choices of n_train.\n", - "n_train_iterator=range(None,None,None)\n", - "\n", - "#These lists we want to fill during the iteration with the mean absolute error,\n", - "#R^2 score and elapsed training time.\n", - "mae_list=[]\n", - "r2_list=[]\n", - "time_list=[]\n", - "\n", - "#In alpha and gamma, we want to save the best choice of parameters from\n", - "#the previous exercise. Compare with the exercise above, if you are unsure\n", - "#how to access them from grid_search.\n", - "alpha=None\n", - "gamma=None\n", - "\n", - "#Use the kernel that has shown better performance.\n", - "kernel=None\n", - "\n", - "for n_train in n_train_iterator:\n", - " x_train = x[0:n_train]\n", - " y_train = y[0:n_train]\n", - "\n", - " x_test = x[n_train:n_train + n_test]\n", - " y_test = y[n_train:n_train + n_test]\n", - "\n", - " #Here we save the starting time of the kernel ridge training.\n", - " start = time.time()\n", - "\n", - " #In the following we will perform the kernel ridge training without\n", - " #cross-validation. For this we use the Object KernelRidge, which\n", - " #has previously been used as the estimator in the cross-validation.\n", - " #We need to set alpha, gamma and the kernel. For documentation, see:\n", - " #https://scikit-learn.org/stable/modules/generated/sklearn.kernel_ridge.KernelRidge.html\n", - " kernel_ridge=None\n", - "\n", - " #After settung up the kernel_ridge object, we need to train with our\n", - " #training data using the method fit and make predictions on the test set\n", - " #using the method predict in analogy to the cross-validation example.\n", - "\n", - " #Fill in your answer here!\n", - "\n", - " #Here we save the ending time of the kernel ridge training.\n", - " end = time.time()\n", - "\n", - " #Compute from the starting and ending time, the elapsed training time and\n", - " #append it to the list\n", - " time_list.append(None)\n", - " #Append the mean absolute error to the following list. Confer with the\n", - " #previous exercise, if you are unsure how to compute it.\n", - " mae_list.append(None)\n", - " r2_list.append(r2_score(y_test, y_pred))\n", - "\n", - "#In the following plot the size of the training set versus the elapsed time,\n", - "#mean absolute error and R^2 score in three separate plots.\n", - "\n", - "#Fill in your answer here!\n", - "\n", - "#Here we plot the exact vs. the predicted HOMO energies for our largest training\n", - "#set size. Can you see the reduced error from this plot in comparison with\n", - "#the previous exercises?\n", - "plt.plot(y_test, y_pred, 'o')\n", - "plt.plot([np.min(y_test),np.max(y_test)], [np.min(y_test),np.max(y_test)], '-')\n", - "plt.xlabel('reference HOMO energy [eV]')\n", - "plt.ylabel('predicted HOMO energy [eV]')\n", - "plt.show()" - ], - "metadata": { - "id": "0o6HAqu4bYPb" - }, - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "markdown", - "source": [ - "#####If you did everything correctly, the plots should look something like the following. Note that because of the random data shuffling in the beginning, they will not look exactly the same.\n", - "\n", - "![image.png](data:image/png;base64,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)\n", - "\n", - "![image.png](data:image/png;base64,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)\n", - "\n", - "![image.png](data:image/png;base64,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)\n", - "\n", - "![image.png](data:image/png;base64,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)" - ], - "metadata": { - "id": "HNAUxo7IYwkX" - } - } - ], - "metadata": { - "anaconda-cloud": {}, + "cells": [ + { + "cell_type": "markdown", + "metadata": { + "id": "Fl2hw46ADkH4" + }, + "source": [ + "# AI4Spec 1: Predicting individual energy levels with kernel methods\n", + "\n", + "In these tutorials exercises, we review different AI approaches to predicting ground or excited state energy levels simply based on the atomic structure of materials. Here we focus on molecules and molecular orbitals, but the sample principles apply to crystal structures and electronic bands.\n", + "\n", + "We start by predicting individual electronic states (Tutorial 1), proceed towards predicting multiple states at once (Tutorial 2) and finish by predicting entire spectral curves (Tutorial 3). The tutorials were prepared by Milica Todorović (University of Turku) and Kunal Ghosh (Aalto University).\n", + "\n", + "\n", + "\n", + "In the exercise below, our AI objective is to train a model to predict a single electronic energy level, HOMO for example. This is a classic example of supervised machine learning regression, where the objective (label) is a single floating-point number. Many AI models can address this task, from decision trees, via kernel-based learning to neural networks. Here, we demonstrate the use of Kernel Ridge Regression, a relatively simple regression approach that has performed well on numerous prediction tasks in physics and chemistry **{Cite Mathias Rupp}**\n", + "\n", + "We use a large dataset of molecular structures and their computed HOMO energies to train the AI. Once the model is trained, it can be used as a tool: one can input a new molecule (previously unseen by the model) and instantly receive a value for its HOMO, within the expected error of the trained model.\n", + "\n", + "\n", + "\n", + "\n", + "\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "XegnO6aTwrmX" + }, + "source": [ + "## 1. HOMO energy prediction with kernel ridge regression\n", + "\n", + "\n", + "Here we will machine-learn the relationship between molecular structure (represented by the Coulomb matrix CM) and their HOMO (Highest Occupied Molecular Orbital) energy using KRR.\n", + "\n", + "This tutorial shows step by step how to load the data, visualize them, select the hyperparameters, train the model and validate it. We use the QM7 dataset of 7000 small organic molecules. The HOMO energies of all molecules were pre-computed with first principles quantum mechanical methods (DFT) to obtain the target data that our model can be trained on. Detailed descriptions and results for a similar dataset (QM9) can be found in [A. Stuke, et al. \"Chemical diversity in molecular orbital energy predictions with kernel ridge regression.\" J. Chem. Phys. 150. 204121 (2019)](https://aip.scitation.org/doi/10.1063/1.5086105).\n", + "\n", + "\n", + "## Setup" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "qdphsPPRwwNF" + }, + "outputs": [], + "source": [ + "from sklearn.model_selection import GridSearchCV\n", + "from sklearn.model_selection import cross_validate\n", + "from sklearn.kernel_ridge import KernelRidge\n", + "from sklearn.metrics import r2_score\n", + "\n", + "import numpy as np\n", + "import matplotlib.pyplot as plt\n", + "import pandas as pd\n", + "import seaborn as sns\n", + "import json\n", + "import math, random\n", + "from scipy.sparse import load_npz\n", + "from matplotlib.colors import LinearSegmentedColormap\n", + "import time" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "hi4ISia7wrmc" + }, + "source": [ + "### Load and visualize data\n", + "\n", + "At first, we load the data.\n", + "\n", + "The input data x is an array that contains all 7000 molecules of the QM7 dataset, represented by their Coulomb matrices, which were computed with the [Dscribe](https://www.sciencedirect.com/science/article/pii/S0010465519303042?via%3Dihub) package.\n", + "\n", + "The output data y is a list that contains the corresponding (pre-computed) HOMO energies." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { "colab": { - "provenance": [], - "collapsed_sections": [ - "0FxS6Kazwrmo" - ], - "toc_visible": true - }, - "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": "3.6.3" + "base_uri": "https://localhost:8080/" + }, + "id": "jTZ_1hpqLBK5", + "outputId": "a15f3c92-4b6c-453a-e0d6-1a9e91e72112" + }, + "outputs": [], + "source": [ + "!wget https://github.com/fullmetalfelix/ML-CSC-tutorial/raw/master/data/qm7/cm.npz\n", + "!wget https://raw.githubusercontent.com/fullmetalfelix/ML-CSC-tutorial/master/data/qm7/HOMO.txt" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "6tTcc8Mtwrmd", + "outputId": "baf6dc4d-80fb-4b36-f3ba-026677ad11ee" + }, + "outputs": [], + "source": [ + "x = load_npz(\"cm.npz\").toarray()\n", + "y = np.genfromtxt(\"HOMO.txt\")\n", + "\n", + "print(\"Number of molecules:\", len(y))" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "yWa4pRHxwrmf" + }, + "source": [ + "Print the Coulomb matrix of a random molecule in the dataset." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "7CovKOElwrmg", + "outputId": "68c822c8-6e05-431d-8223-791fc3851287" + }, + "outputs": [], + "source": [ + "rand_mol = random.randint(0, len(y))\n", + "\n", + "print(x[rand_mol])" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "BKo-SoN2wrmh" + }, + "source": [ + "Visualize the Coulomb matrix of the random molecule." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 502 + }, + "id": "GJu2RtUhwrmh", + "outputId": "1466b332-185d-4ad7-e2f6-c3696ceed6d5" + }, + "outputs": [], + "source": [ + "shape = (23, 23)\n", + "mat = x[rand_mol].reshape(shape)\n", + "\n", + "plt.figure()\n", + "plt.figure(figsize = (6,6))\n", + "plt.imshow(mat, origin=\"upper\", cmap='rainbow', vmin=-15, vmax=75, interpolation='nearest')\n", + "plt.colorbar(fraction=0.046, pad=0.04).ax.tick_params(labelsize=20)\n", + "plt.axis('off')\n", + "plt.show()" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "n434DnNSwrmi" + }, + "source": [ + "Note that many of the outputs are zero in the Coulomb matrix. This is because the number of non-zero outputs depends on the size of the molecule, and all smaller molecules contain zero padding.\n", + "\n", + "Visualize the target data by plotting the distribution of HOMO energies in the dataset:" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 510 + }, + "id": "YxjygJgJwrmj", + "outputId": "c0683fc7-7a3d-490a-e012-bc6e7210c3a5" + }, + "outputs": [], + "source": [ + "plt.hist(y, bins=20, density=False, facecolor='blue')\n", + "plt.xlabel(\"Energy [eV]\")\n", + "plt.ylabel(\"Number of molecules\")\n", + "plt.title(\"Distribution of HOMO energies\")\n", + "plt.show()\n", + "\n", + "## mean value of distribution\n", + "print(\"Mean value of HOMO energies in QM7 dataset: %0.2f eV\" %np.mean(y))" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "QpgK9ky-wrmk" + }, + "source": [ + "Before dividing the dataset into training and test set, we shuffle the data. This is because data are often stored in a logical order (e.g., certain types of molecules grouped one after each other). Simply taking the first part for training and the second for testing would not result in a well trained model, since the training set would not represent the test data well (and vice versa)." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "6luJyqCKwrmk" + }, + "outputs": [], + "source": [ + "## shuffle the data\n", + "\n", + "c = list(zip(x, y))\n", + "random.shuffle(c)\n", + "\n", + "x, y = zip(*c)\n", + "\n", + "x = np.array(x)\n", + "y = np.array(y)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "XQh-MAv5wrml" + }, + "source": [ + "Now, we divide the data into training and test set." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "wmnl8ZzAwrmm" + }, + "outputs": [], + "source": [ + "# decide how many samples to take from the database for training and testing\n", + "n_train = 1000\n", + "n_test = 1000\n", + "\n", + "# split data in training and test\n", + "# take first n_train molecules for training\n", + "x_train = x[0:n_train]\n", + "y_train = y[0:n_train]\n", + "\n", + "# take the next n_test data for testing\n", + "x_test = x[n_train:n_train + n_test]\n", + "y_test = y[n_train:n_train + n_test]" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "uEP7iSchwrmm" + }, + "source": [ + "Check that the training data resemble the test data well by plotting the distribution of HOMO energies for both sets. The distributions should be centered around the same mean value and have the same shape." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 504 + }, + "id": "w_H7kOBTwrmn", + "outputId": "14677f4e-42d1-4de3-8360-dbadedd01a3d" + }, + "outputs": [], + "source": [ + "plt.hist(y_test, bins=20, density=False, alpha=0.5, facecolor='red', label='test set')\n", + "plt.hist(y_train, bins=20, density=False, alpha=0.5, facecolor='gray', label='training set')\n", + "plt.xlabel(\"Energy [eV]\")\n", + "plt.ylabel(\"Number of molecules\")\n", + "plt.legend()\n", + "plt.show()\n", + "\n", + "## mean value of distributions\n", + "print(\"Mean value of HOMO energies in training set: %0.2f eV\" %np.mean(y_train))\n", + "print(\"Mean value of HOMO energies in test set: %0.2f eV\" %np.mean(y_test))" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "0FxS6Kazwrmo" + }, + "source": [ + "### Training\n", + "\n", + "In the training phase we use a kernel function to measure the distance between all pairs of molecules (represented by their Coulomb matrices) in the training set. We here employ one of two kernels, the Gaussian kernel or the Laplacian kernel. Both kernels have two hyperparameters: $\\alpha$ controls the penalty term and $\\gamma$ the kernel width.\n", + "\n", + "To find the optimal hyperparameters, we will do a grid search, i.e. we test the performance of a model trained with values of the hyperparameters that are spaced out on a grid in search space and choose the hyperparameters that yield the best performance.\n", + "\n", + "The model performance is quantified by splitting off part of the training set as validation set. We validate the model by making predictions on this validation set. This check of the model performance can be further refined with cross-validation, where the roles of training and validation sets alternate. The ratio can be varied, for example in 5-fold cross-validation, the training set is split in 5 equal parts. The model is trained on 80% of the data and validated on the other 20%. Then the roles of training and validation set rotate until each part has served as validation set exactly once.\n", + "\n", + "For our implementation, we will use the scikit-learn module.\n", + "\n", + "A more detailed optional explanation, which is not required for the solution of the exercise, can be found in the hidden cell below." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "IqRlAI8983CM" + }, + "source": [ + "The Gaussian kernel is given by\n", + "\n", + "\\begin{equation}\n", + "k_{Gaussian}(\\boldsymbol{x},\\boldsymbol{x}')=e^{-\\frac{||{\\boldsymbol{x}-\\boldsymbol{x}'}||_2^2}{2\\gamma^2}},\n", + "\\end{equation}\n", + "\n", + "which employs the Euclidean distance as similarity measure. The parameter $\\gamma$ is defined as $\\frac{1}{2\\sigma^2}$, where $\\sigma$ is the standard deviation of the Gaussian kernel (kernel width). The Laplacian kernel is given by\n", + "\n", + "\\begin{equation}\n", + " k_{Laplacian}(\\boldsymbol{x},\\boldsymbol{x}')=e^{-\\frac{||{\\boldsymbol{x}-\\boldsymbol{x}'}||_1}{\\gamma}},\n", + "\\end{equation}\n", + "\n", + "which uses the 1-norm as similarity measure. Here, $\\gamma$ is defined as $\\frac{1}{\\sigma}$, where $\\sigma$ is the kernel width of the Laplacian kernel.\n", + "\n", + "In the KRR training phase with $N$ training molecules, the machine learns the relationship between the molecules (represented by their Coulomb matrix) and their corresponding (pre-computed) HOMO energies. It does so by employing a function $f(\\boldsymbol{x})$ that maps a training molecule $\\boldsymbol{x}$ to its reference HOMO energy:\n", + "\n", + "\\begin{equation}\n", + "f(\\boldsymbol{x}) = \\sum_{i=1}^N \\omega_i k(\\boldsymbol{x}, \\boldsymbol{x}_i) = HOMO^{ref},\n", + "\\end{equation}\n", + "\n", + "For a given training molecule $\\boldsymbol{x}$, the distance to each molecule in the training set is computed by employing the kernel function $k$ (either Gaussian or Laplacian). Each kernel contribution (distance) is then weighted by a regression weight $\\omega_i$. The above function is thus given by the weighted sum of kernel contributions (sum over $N$ training molecules). The purpose of training is to fit the regression weight $\\omega_i$ so that HOMO$_{ref}$ is matched for each training molecule. In practice, the machine solves the minimization problem\n", + "\n", + "\n", + "\\begin{equation}\n", + " \\underset{\\omega}{min} \\sum_{i=1}^N (f(\\boldsymbol{x}_i) - HOMO^{ref}_i)^2 + \\alpha \\boldsymbol{\\omega}^T \\mathbf{K} \\boldsymbol{\\omega}.\n", + "\\end{equation}\n", + "\n", + "for a vector $\\boldsymbol{\\omega} \\in \\mathbb{R}^N = (\\omega_1, \\omega_2, ..., \\omega_N)$ of regression weights. In KRR, the penalty term $ \\alpha \\boldsymbol{\\omega}^T \\mathbf{K} \\boldsymbol{\\omega}$ is added to the minimization problem in order to avoid over- and underfitting. Overfitting occurs when the model learns the training data too well, even the noise and other unimportant details. The model is unable to generalize on unseen data and therefore yields high prediction errors on the test data. Underfitting occurs when the model is too simple and does not learn the training data at all, and therefore is not able to predict test data well either. Both behaviours can be avoided by tuning the parameter $\\alpha \\in \\left[0,1\\right]$ to a reasonable value. This has do be done separately from training. Both the regularization parameter $\\alpha$ and the kernel width $\\gamma$ are so called hyperparameters. Hyperparameters cannot be learned during training and have to be selected beforehand. However, it is not always obvious how to choose these hyperparameters and it often requires intuition or rules of thumb. We here employ a cross-validated grid search in order to find the best values for these two hyperparameters.\n", + "\n", + "In grid search, a part of the training set is split off as validation set. We set up a grid of pre-defined hyperparameter values and train the machine on the remaining training set, for each possible combination of $\\alpha$ and $\\gamma$ values. We validate each possible combination by making predictions on the validation set. The two hyperparameter values that yield the best performance (lowest error) are then selected for the final model to make predictions on the test set.\n", + "\n", + "In cross-validation, the roles of training and validation sets alternate. As described above, a part from the training set is split off as validation set. After training one combination of hyperparameters on the remaining training set and validating on the validation set, the validation set becomes the training set and vice versa, and the model is trained on the new training set and validated on the new validation set for the same combination of hyperparameters. The ratio can be varied, for example in 5-fold cross-validation, the training set is split in 5 equal parts. For each combination of hyperparameters, the model is trained on 80% of the data and validated on the other 20%. Then the roles of training and validation set rotate until each part has served as validation set exactly once. The final validation error for one particular combination of hyperparameters is computed as the mean from all 5 errors on the 5 validation sets. The combination with lowest average error is chosen for the final model.\n", + "\n", + "The cross-validated grid search routine is implemented in scikit-learn." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "O5e2EytL8aDY" + }, + "source": [ + "### KRR Code" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 778 + }, + "id": "hbcOapWDwrmp", + "outputId": "1d28b29e-0eb8-4473-fa33-4ae2bd9ee3af" + }, + "outputs": [], + "source": [ + "# set up grids for alpha and gamma hyperparameters.\n", + "# first value: lower bound; second value: upper bound;\n", + "# third value: number of points to evaluate (here set to '3' --> '-2', '-1' and '0' are evaluated)\n", + "# --> make sure to change third value as well when changing the bounds!\n", + "alpha = np.logspace(-4, -2, 3)\n", + "gamma = np.logspace(-4, -2, 3)\n", + "\n", + "cv_number = 2 ## choose into how many parts training set is divided for cross-validation\n", + "kernel = 'laplacian' # select kernel function here ('rbf': Gaussian kernel, 'laplacian': Laplacian kernel)\n", + "scoring_function = 'neg_mean_absolute_error' # it is called \"negative\" because scikit-learn interprets\n", + " # highest scoring value as best, but we want small errors\n", + "\n", + "## define settings for grid search routine in scikit-learn with above defined grids as input\n", + "\n", + "grid_search = GridSearchCV(KernelRidge(), #machine learning method (KRR here)\n", + " [{'kernel':[kernel],'alpha': alpha, 'gamma': gamma}],\n", + " cv = cv_number,\n", + " scoring = scoring_function,\n", + " verbose=1000) ## produces detailed output statements of grid search\n", + " # routine so we can see what is computed\n", + "\n", + "# call the fit function in scikit-learn which fits the Coulomb matrices in the training set\n", + "# to their corresponding HOMO energies.\n", + "grid_search.fit(x_train, y_train)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "mTrweQ1Mwrmr" + }, + "source": [ + "### Grid search results\n", + "\n", + "Print out the average validation errors and corresponding hyperparameter combinations" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "066IjiWawrmr", + "outputId": "de299c89-9c65-437c-c798-72bb63bd89e0" + }, + "outputs": [], + "source": [ + "means = grid_search.cv_results_['mean_test_score']\n", + "stds = grid_search.cv_results_['std_test_score']\n", + "for mean, std, params in zip(-means, stds, grid_search.cv_results_['params']):\n", + " print(\"%0.3f (+/-%0.03f) for %r\" % (mean, std * 2, params))" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "SrfhK2fTwrms" + }, + "source": [ + "Next, we visualize the grid search results by plotting a heatmap." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 488 + }, + "id": "T2swGFTLwrmt", + "outputId": "e8b282a6-56fb-4a2e-93c0-bacf613f594e" + }, + "outputs": [], + "source": [ + "results = pd.DataFrame(grid_search.cv_results_)\n", + "#pd.DataFrame(grid_search.cv_results_)\n", + "\n", + "pvt = pd.pivot_table(results, values='mean_test_score',\n", + " index='param_gamma', columns='param_alpha')\n", + "heatmap = sns.heatmap(-pvt, annot=True, cmap='viridis', cbar_kws={'label': \"Mean absolute error [eV]\"})\n", + "figure = heatmap.get_figure()\n", + "plt.show()\n", + "\n", + "\n", + "print(\"The best combinations of parameters are %s with a score of %0.3f eV on the validation set.\"\n", + " % (grid_search.best_params_, -grid_search.best_score_))" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "-tv1CciKwrmu" + }, + "source": [ + "### Testing\n", + "\n", + "With the best combination of hyperparameters, the model is once again trained on the entire training set (this is done automatically in scikit-learn). Then, with the best combination of hyperparameters, predictions are made on the test set to evaluate the final model, which we will use for predictions.\n", + "\n", + "The mean absolute error of the predicted from the reference HOMO energies and $R^2$ score will be our measure for the quality of the fit.\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 504 + }, + "id": "k8e9G1iNwrmv", + "outputId": "42be6aaa-f279-436b-97d1-b4a137005585" + }, + "outputs": [], + "source": [ + "# predicted HOMO energies for all test molecules\n", + "\n", + "y_pred = grid_search.predict(x_test) # scikit-learn automatically takes the best combination\n", + " # of hyperparameters from grid search\n", + "\n", + "print(\"Mean absolute error on test set: %0.3f eV\" %(np.abs(y_pred-y_test)).mean())\n", + "\n", + "# do the regression plot\n", + "plt.plot(y_test, y_pred, 'o')\n", + "plt.plot([np.min(y_test),np.max(y_test)], [np.min(y_test),np.max(y_test)], '-')\n", + "plt.xlabel('reference HOMO energy [eV]')\n", + "plt.ylabel('predicted HOMO energy [eV]')\n", + "plt.show()\n", + "print(\"R^2 score on test set: %.3f\" % r2_score(y_test, y_pred))" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "pYf2oHVbwrmw" + }, + "source": [ + "The $R^2$ score indicates how close the predicted energies in the test set are to the reference energies. The closer the points in the above figure are located to the diagonal, the better the predictions. Points on the diagonal (\"predicted energy\"=\"reference energy\") correspond to $R^2=1$. Therefore, $R^2$ values close to 1 indicate good model performance." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "collapsed": true, + "id": "zcdZdkThwrmw", + "jupyter": { + "outputs_hidden": true } + }, + "source": [ + "###**Exercises**\n", + "\n", + "#### a. Grid search\n", + "\n", + "Increase the number and range of grid points used for grid search. Which combination of $\\alpha$ and $\\gamma$ works best? How does the computational time increase? Choose a reasonable number of grid points that don't take too long to evaluate." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "mqN4J1xVwrmx" + }, + "outputs": [], + "source": [ + "#Choose alpha and gamma on a finer logarithmically spaced grid. The other parameters can be chosen as above.\n", + "alpha = None\n", + "gamma = None\n", + "cv_number=None\n", + "kernel = None\n", + "scoring_function = None\n", + "\n", + "\n", + "grid_search = GridSearchCV(KernelRidge(), #machine learning method (KRR here)\n", + " [{'kernel':[kernel],'alpha': alpha, 'gamma': gamma}],\n", + " cv = cv_number,\n", + " scoring = scoring_function,\n", + " verbose=1000) ## produces detailed output statements of grid search routine\n", + "\n", + "grid_search.fit(x_train, y_train)\n", + "\n", + "results = pd.DataFrame(grid_search.cv_results_)\n", + "\n", + "pvt = pd.pivot_table(results, values='mean_test_score',\n", + " index='param_gamma', columns='param_alpha')\n", + "heatmap = sns.heatmap(-pvt, annot=True, cmap='viridis', cbar_kws={'label': \"Mean absolute error [eV]\"})\n", + "figure = heatmap.get_figure()\n", + "plt.show()\n", + "\n", + "print(\"The best combinations of parameters are %s with a score of %0.3f eV on the validation set.\"\n", + " % (grid_search.best_params_, -grid_search.best_score_))\n", + "\n", + "y_pred = grid_search.predict(x_test) # scikit-learn automatically takes the best combination of hyperparameters from grid search\n", + "\n", + "print(\"Mean absolute error on test set: %0.3f eV\" %(np.abs(y_pred-y_test)).mean())\n", + "\n", + "plt.plot(y_test, y_pred, 'o')\n", + "plt.plot([np.min(y_test),np.max(y_test)], [np.min(y_test),np.max(y_test)], '-')\n", + "plt.xlabel('reference HOMO energy [eV]')\n", + "plt.ylabel('predicted HOMO energy [eV]')\n", + "plt.show()\n", + "print(\"R^2 score on test set: %.3f\" % r2_score(y_test, y_pred))" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "Gsy36Rzowrmy" + }, + "source": [ + "#### b. Kernel function\n", + "\n", + "Use the Gaussian kernel instead of the Laplacian kernel. Which kernel leads to better model performance?" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "srWUmjKapUMD" + }, + "outputs": [], + "source": [ + "#Repeat the above calculation with the Gaussian kernel. The Gaussian kernel is identified with the string 'rbf'.\n", + "alpha = None\n", + "gamma = None\n", + "cv_number=None\n", + "kernel = None\n", + "scoring_function = None\n", + "\n", + "grid_search = GridSearchCV(KernelRidge(), #machine learning method (KRR here)\n", + " [{'kernel':[kernel],'alpha': alpha, 'gamma': gamma}],\n", + " cv = cv_number,\n", + " scoring = scoring_function,\n", + " verbose=1000) ## produces detailed output statements of grid search routine\n", + "\n", + "grid_search.fit(x_train, y_train)\n", + "\n", + "results = pd.DataFrame(grid_search.cv_results_)\n", + "\n", + "pvt = pd.pivot_table(results, values='mean_test_score',\n", + " index='param_gamma', columns='param_alpha')\n", + "heatmap = sns.heatmap(-pvt, annot=True, cmap='viridis', cbar_kws={'label': \"Mean absolute error [eV]\"})\n", + "figure = heatmap.get_figure()\n", + "plt.show()\n", + "\n", + "print(\"The best combinations of parameters are %s with a score of %0.3f eV on the validation set.\"\n", + " % (grid_search.best_params_, -grid_search.best_score_))\n", + "\n", + "y_pred = grid_search.predict(x_test) # scikit-learn automatically takes the best combination of hyperparameters from grid search\n", + "\n", + "print(\"Mean absolute error on test set: %0.3f eV\" %(np.abs(y_pred-y_test)).mean())\n", + "\n", + "plt.plot(y_test, y_pred, 'o')\n", + "plt.plot([np.min(y_test),np.max(y_test)], [np.min(y_test),np.max(y_test)], '-')\n", + "plt.xlabel('reference HOMO energy [eV]')\n", + "plt.ylabel('predicted HOMO energy [eV]')\n", + "plt.show()\n", + "print(\"R^2 score on test set: %.3f\" % r2_score(y_test, y_pred))" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "5yJUdzhewrmx" + }, + "source": [ + "#### c. Cross-validation\n", + "\n", + "For this exercise, choose the kernel that performed better in the previous exercise. Increase the number of folds used for cross-validation. Does the quality of the model increase? Take note as well of the increasing computational time and choose a number of folds that does not require too much computational time." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "Jqy3rfT9wrmy" + }, + "outputs": [], + "source": [ + "#Repeat the above calculation with a higher number of cross-validation folds. Use the kernel that showed better performance.\n", + "alpha = None\n", + "gamma = None\n", + "cv_number=None\n", + "kernel = None\n", + "scoring_function = None\n", + "\n", + "grid_search = GridSearchCV(KernelRidge(), #machine learning method (KRR here)\n", + " [{'kernel':[kernel],'alpha': alpha, 'gamma': gamma}],\n", + " cv = cv_number,\n", + " scoring = scoring_function,\n", + " verbose=1000) ## produces detailed output statements of grid search routine\n", + "\n", + "grid_search.fit(x_train, y_train)\n", + "\n", + "results = pd.DataFrame(grid_search.cv_results_)\n", + "#pd.DataFrame(grid_search.cv_results_)\n", + "\n", + "pvt = pd.pivot_table(results, values='mean_test_score',\n", + " index='param_gamma', columns='param_alpha')\n", + "heatmap = sns.heatmap(-pvt, annot=True, cmap='viridis', cbar_kws={'label': \"Mean absolute error [eV]\"})\n", + "figure = heatmap.get_figure()\n", + "plt.show()\n", + "\n", + "print(\"The best combinations of parameters are %s with a score of %0.3f eV on the validation set.\"\n", + " % (grid_search.best_params_, -grid_search.best_score_))\n", + "\n", + "y_pred = grid_search.predict(x_test) # scikit-learn automatically takes the best combination of hyperparameters from grid search\n", + "\n", + "print(\"Mean absolute error on test set: %0.3f eV\" %(np.abs(y_pred-y_test)).mean())\n", + "\n", + "plt.plot(y_test, y_pred, 'o')\n", + "plt.plot([np.min(y_test),np.max(y_test)], [np.min(y_test),np.max(y_test)], '-')\n", + "plt.xlabel('reference HOMO energy [eV]')\n", + "plt.ylabel('predicted HOMO energy [eV]')\n", + "plt.show()\n", + "print(\"R^2 score on test set: %.3f\" % r2_score(y_test, y_pred))" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "jjoUSLWuwrmz" + }, + "source": [ + "#### d. Training set size\n", + "\n", + "Increase the size of the training set and plot the mean absolute error and $R^2$ score and training time on the test set as a function of the training set size (e.g. use 1000, 2000, 3000 etc. as training set size). For the MAE and $R^2$ values use a logarithmic time axis. Compare with the previous exercises.\n", + "\n", + "The optimal hyperparameter values for $\\alpha$ and $\\gamma$ can change throughout varying training set sizes. Therefore, when increasing the training set size, it is recommended to perform a cross-validated grid search for each training set size. For the sake of this exercise, we will limit ourselves to taking the optimal hyperparameters from the previous exercise as an approximation and not perform a grid search. Furthermore, we will not cross-validate our model in this exercise in the interest of time." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "0o6HAqu4bYPb" + }, + "outputs": [], + "source": [ + "#We keep the size of the test set constant in this exercise\n", + "n_test = 1000\n", + "\n", + "#We want to iterate over different training set sizes n_train.\n", + "#Prepare an iterator with reasonable choices of n_train.\n", + "n_train_iterator=range(None,None,None)\n", + "\n", + "#These lists we want to fill during the iteration with the mean absolute error,\n", + "#R^2 score and elapsed training time.\n", + "mae_list=[]\n", + "r2_list=[]\n", + "time_list=[]\n", + "\n", + "#In alpha and gamma, we want to save the best choice of parameters from\n", + "#the previous exercise. Compare with the exercise above, if you are unsure\n", + "#how to access them from grid_search.\n", + "alpha=None\n", + "gamma=None\n", + "\n", + "#Use the kernel that has shown better performance.\n", + "kernel=None\n", + "\n", + "for n_train in n_train_iterator:\n", + " x_train = x[0:n_train]\n", + " y_train = y[0:n_train]\n", + "\n", + " x_test = x[n_train:n_train + n_test]\n", + " y_test = y[n_train:n_train + n_test]\n", + "\n", + " #Here we save the starting time of the kernel ridge training.\n", + " start = time.time()\n", + "\n", + " #In the following we will perform the kernel ridge training without\n", + " #cross-validation. For this we use the Object KernelRidge, which\n", + " #has previously been used as the estimator in the cross-validation.\n", + " #We need to set alpha, gamma and the kernel. For documentation, see:\n", + " #https://scikit-learn.org/stable/modules/generated/sklearn.kernel_ridge.KernelRidge.html\n", + " kernel_ridge=None\n", + "\n", + " #After settung up the kernel_ridge object, we need to train with our\n", + " #training data using the method fit and make predictions on the test set\n", + " #using the method predict in analogy to the cross-validation example.\n", + "\n", + " #Fill in your answer here!\n", + "\n", + " #Here we save the ending time of the kernel ridge training.\n", + " end = time.time()\n", + "\n", + " #Compute from the starting and ending time, the elapsed training time and\n", + " #append it to the list\n", + " time_list.append(None)\n", + " #Append the mean absolute error to the following list. Confer with the\n", + " #previous exercise, if you are unsure how to compute it.\n", + " mae_list.append(None)\n", + " r2_list.append(r2_score(y_test, y_pred))\n", + "\n", + "#In the following plot the size of the training set versus the elapsed time,\n", + "#mean absolute error and R^2 score in three separate plots.\n", + "\n", + "#Fill in your answer here!\n", + "\n", + "#Here we plot the exact vs. the predicted HOMO energies for our largest training\n", + "#set size. Can you see the reduced error from this plot in comparison with\n", + "#the previous exercises?\n", + "plt.plot(y_test, y_pred, 'o')\n", + "plt.plot([np.min(y_test),np.max(y_test)], [np.min(y_test),np.max(y_test)], '-')\n", + "plt.xlabel('reference HOMO energy [eV]')\n", + "plt.ylabel('predicted HOMO energy [eV]')\n", + "plt.show()" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "HNAUxo7IYwkX" + }, + "source": [ + "#####If you did everything correctly, the plots should look something like the following. Note that because of the random data shuffling in the beginning, they will not look exactly the same.\n", + "\n", + "![image.png](data:image/png;base64,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)\n", + "\n", + "![image.png](data:image/png;base64,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)\n", + "\n", + "![image.png](data:image/png;base64,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)\n", + "\n", + "![image.png](data:image/png;base64,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)" + ] + } + ], + "metadata": { + "anaconda-cloud": {}, + "colab": { + "collapsed_sections": [ + "0FxS6Kazwrmo" + ], + "provenance": [], + "toc_visible": true + }, + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "language": "python", + "name": "python3" }, - "nbformat": 4, - "nbformat_minor": 0 -} \ No newline at end of file + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.9.18" + } + }, + "nbformat": 4, + "nbformat_minor": 4 +} diff --git a/AI4Spec_Tutorial2.ipynb b/AI4Spec_Tutorial2.ipynb index ad52a2b..1450ba5 100644 --- a/AI4Spec_Tutorial2.ipynb +++ b/AI4Spec_Tutorial2.ipynb @@ -36,7 +36,7 @@ }, { "cell_type": "code", - "execution_count": 1, + "execution_count": null, "metadata": { "id": "qdphsPPRwwNF" }, @@ -66,7 +66,7 @@ }, { "cell_type": "code", - "execution_count": 2, + "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" @@ -74,36 +74,7 @@ "id": "jTZ_1hpqLBK5", "outputId": "efa921b4-fb04-4fe9-dc78-8e039f748f37" }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "--2024-03-04 21:34:38-- https://zenodo.org/records/10069732/files/coulomb_7000.npz\n", - "Resolving zenodo.org (zenodo.org)... 188.184.103.159, 188.184.98.238, 188.185.79.172, ...\n", - "Connecting to zenodo.org (zenodo.org)|188.184.103.159|:443... connected.\n", - "HTTP request sent, awaiting response... 200 OK\n", - "Length: 47096264 (45M) [application/octet-stream]\n", - "Saving to: ‘coulomb_7000.npz.1’\n", - "\n", - "coulomb_7000.npz.1 100%[===================>] 44.91M 46.3MB/s in 1.0s \n", - "\n", - "2024-03-04 21:34:39 (46.3 MB/s) - ‘coulomb_7000.npz.1’ saved [47096264/47096264]\n", - "\n", - "--2024-03-04 21:34:40-- https://zenodo.org/records/10069732/files/energies_7000.npz\n", - "Resolving zenodo.org (zenodo.org)... 188.184.98.238, 188.185.79.172, 188.184.103.159, ...\n", - "Connecting to zenodo.org (zenodo.org)|188.184.98.238|:443... connected.\n", - "HTTP request sent, awaiting response... 200 OK\n", - "Length: 896264 (875K) [application/octet-stream]\n", - "Saving to: ‘energies_7000.npz.1’\n", - "\n", - "energies_7000.npz.1 100%[===================>] 875.26K 4.13MB/s in 0.2s \n", - "\n", - "2024-03-04 21:34:40 (4.13 MB/s) - ‘energies_7000.npz.1’ saved [896264/896264]\n", - "\n" - ] - } - ], + "outputs": [], "source": [ "!wget https://zenodo.org/records/10069732/files/coulomb_7000.npz\n", "!wget https://zenodo.org/records/10069732/files/energies_7000.npz" @@ -111,7 +82,7 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" @@ -119,15 +90,7 @@ "id": "6tTcc8Mtwrmd", "outputId": "e96ae7fe-8e7b-49f5-96d8-f54f9980ddb5" }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Number of molecules: 7000\n" - ] - } - ], + "outputs": [], "source": [ "# Here we load all the data\n", "x = np.abs(np.load(\"coulomb_7000.npz\")['arr_0'])\n", @@ -154,7 +117,7 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" @@ -162,102 +125,7 @@ "id": "7CovKOElwrmg", "outputId": "63b5843a-2a4e-4ae5-92d3-69efb8bf4ce9" }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "(29, 29)\n", - "[[36.858 23.545 19.643 14.298 12.615 8.577 10.93 14.165 5.46 5.451\n", - " 5.466 2.245 2.124 2.203 1.135 2.263 2.071 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. ]\n", - " [23.545 36.858 33.353 23.482 19.429 13.106 16.645 23.444 2.74 2.752\n", - " 2.774 3.039 2.741 2.759 1.571 2.759 2.788 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. ]\n", - " [19.643 33.353 73.517 19.681 21.95 15.243 18.479 20.284 2.35 2.933\n", - " 2.975 8.241 2.959 2.359 1.972 2.415 3.243 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. ]\n", - " [14.298 23.482 19.681 36.858 33.39 15.238 15.014 14.537 2.16 2.15\n", - " 1.729 2.339 5.456 5.44 1.819 2.07 1.759 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. ]\n", - " [12.615 19.429 21.95 33.39 73.517 35.114 23.509 16.879 1.95 1.931\n", - " 1.732 2.55 3.934 3.857 3.966 2.322 2.135 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. ]\n", - " [ 8.577 13.106 15.243 15.238 35.114 36.858 33.114 15.338 1.343 1.247\n", - " 1.253 1.617 1.854 2.131 5.488 2.008 1.916 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. ]\n", - " [10.93 16.645 18.479 15.014 23.509 33.114 53.359 28.812 1.713 1.496\n", - " 1.667 1.825 1.835 2.231 3.402 3.348 3.366 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. ]\n", - " [14.165 23.444 20.284 14.537 16.879 15.338 28.812 36.858 2.122 1.714\n", - " 2.161 1.863 1.738 2.159 1.784 5.445 5.453 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. ]\n", - " [ 5.46 2.74 2.35 2.16 1.95 1.343 1.713 2.122 0.5 0.562\n", - " 0.561 0.273 0.313 0.396 0.18 0.4 0.298 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. ]\n", - " [ 5.451 2.752 2.933 2.15 1.931 1.247 1.496 1.714 0.562 0.5\n", - " 0.563 0.392 0.377 0.324 0.171 0.27 0.259 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. ]\n", - " [ 5.466 2.774 2.975 1.729 1.732 1.253 1.667 2.161 0.561 0.563\n", - " 0.5 0.328 0.262 0.268 0.17 0.346 0.369 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. ]\n", - " [ 2.245 3.039 8.241 2.339 2.55 1.617 1.825 1.863 0.273 0.392\n", - " 0.328 0.5 0.415 0.28 0.22 0.245 0.293 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. ]\n", - " [ 2.124 2.741 2.959 5.456 3.934 1.854 1.835 1.738 0.313 0.377\n", - " 0.262 0.415 0.5 0.561 0.247 0.256 0.234 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. ]\n", - " [ 2.203 2.759 2.359 5.44 3.857 2.131 2.231 2.159 0.396 0.324\n", - " 0.268 0.28 0.561 0.5 0.27 0.361 0.262 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. ]\n", - " [ 1.135 1.571 1.972 1.819 3.966 5.488 3.402 1.784 0.18 0.171\n", - " 0.17 0.22 0.247 0.27 0.5 0.253 0.248 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. ]\n", - " [ 2.263 2.759 2.415 2.07 2.322 2.008 3.348 5.445 0.4 0.27\n", - " 0.346 0.245 0.256 0.361 0.253 0.5 0.567 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. ]\n", - " [ 2.071 2.788 3.243 1.759 2.135 1.916 3.366 5.453 0.298 0.259\n", - " 0.369 0.293 0.234 0.262 0.248 0.567 0.5 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. ]\n", - " [ 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. ]\n", - " [ 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. ]\n", - " [ 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. ]\n", - " [ 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. ]\n", - " [ 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. ]\n", - " [ 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. ]\n", - " [ 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. ]\n", - " [ 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. ]\n", - " [ 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. ]\n", - " [ 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. ]\n", - " [ 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. ]\n", - " [ 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.\n", - " 0. 0. 0. 0. 0. 0. 0. 0. 0. ]]\n" - ] - } - ], + "outputs": [], "source": [ "rand_mol = random.randint(0, len(y))\n", "\n", @@ -279,7 +147,7 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/", @@ -288,27 +156,7 @@ "id": "GJu2RtUhwrmh", "outputId": "0d52abe6-0262-4ac4-d53b-4f5e4d71ef3b" }, - "outputs": [ - { - "data": { - "text/plain": [ - "
" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "data": { - "image/png": "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\n", - "text/plain": [ - "
" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], + "outputs": [], "source": [ "shape = (29, 29)\n", "mat = x[rand_mol].reshape(shape)\n", @@ -332,7 +180,7 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" @@ -340,19 +188,7 @@ "id": "u44zKs0_4IJv", "outputId": "603a67c1-86f4-4d47-a578-940126f085f4" }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "[-13.97184 -12.99997 -12.46609 -11.83582 -11.2511 -10.46114 -10.41363\n", - " -10.08263 -9.84337 -9.36033 -8.81967 -8.51355 -8.09764 -6.67936\n", - " -6.13557 -5.84277]\n", - "-5.84277\n", - "[-6.67936 -6.13557 -5.84277]\n" - ] - } - ], + "outputs": [], "source": [ "# Here we review the entire vector of orbital energies\n", "print(energies[rand_mol,:])\n", @@ -375,7 +211,7 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/", @@ -384,26 +220,7 @@ "id": "YxjygJgJwrmj", "outputId": "89f2f6cc-45de-4473-a771-691cfc00f932" }, - "outputs": [ - { - "data": { - "image/png": "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\n", - "text/plain": [ - "
" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Mean value of HOMO energies in QM9 dataset: -5.75 eV\n", - "[-9.42518 -8.12121 -6.48731 ... -5.94942 -5.47667 -5.69919]\n" - ] - } - ], + "outputs": [], "source": [ "plt.hist(y, bins=20, density=False, facecolor='blue')\n", "plt.xlabel(\"Energy [eV]\")\n", @@ -427,7 +244,7 @@ }, { "cell_type": "code", - "execution_count": 8, + "execution_count": null, "metadata": { "id": "6luJyqCKwrmk" }, @@ -455,7 +272,7 @@ }, { "cell_type": "code", - "execution_count": 9, + "execution_count": null, "metadata": { "id": "wmnl8ZzAwrmm" }, @@ -491,7 +308,7 @@ }, { "cell_type": "code", - "execution_count": 10, + "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/", @@ -500,27 +317,7 @@ "id": "w_H7kOBTwrmn", "outputId": "2a4683d7-30dc-4419-cf0a-e064632f88c2" }, - "outputs": [ - { - "data": { - "image/png": "iVBORw0KGgoAAAANSUhEUgAAAj8AAAG2CAYAAACQ++e6AAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAAPYQAAD2EBqD+naQAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDMuMC4zLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvnQurowAAIABJREFUeJzs3XtclGX+//H3gHJQTkICsqKglocEPJvaFqapWG4ediu10jLt4KF0XZXNVKwVtSwz7Wzi7upabZnlFp5RMyRPiJpZmqdWwAxlAteRw/z+8Od8G0FkcIYZnNfz8bgfX+7TdX9m5Lu8u67rvm+D2Ww2CwAAwE14OLsAAACA6kT4AQAAboXwAwAA3ArhBwAAuBXCDwAAcCuEHwAA4FYIPwAAwK0QfgAAgFsh/AAAALdC+AEAAG7FqeEnOTlZHTt2lL+/v0JDQ9W/f38dOnTIsj8vL09jx45V8+bN5evrq0aNGmncuHHKz8+3asdgMJRZVqxYUd0fBwAA1ABODT+bN2/W6NGjtX37dq1bt05FRUXq1auXCgsLJUmnTp3SqVOn9PLLL2v//v1KSUlRamqqRowYUaatJUuWKDs727L079+/uj8OAACoAQyu9GLTn3/+WaGhodq8ebPuuOOOco/56KOP9NBDD6mwsFC1atWSdKnnZ+XKlQQeAABwTbWcXcBvXR7OCg4OrvCYgIAAS/C5bPTo0Xr88cfVpEkTPfnkk3r00UdlMBjKbcNkMslkMlnWS0tLlZeXp5CQkKueAwAAXIvZbNavv/6qiIgIeXjYMJhldhElJSXme+65x9ytW7erHvPzzz+bGzVqZP7rX/9qtX3mzJnmr776yrx7927z7Nmzzd7e3ubXXnvtqu1Mnz7dLImFhYWFhYXlBlhOnjxpU+ZwmWGvp556Sl9++aW++uorNWzYsMx+o9Gou+++W8HBwfrss89Uu3btq7Y1bdo0LVmyRCdPnix3/5U9P/n5+WrUqJFOnjypgICA6/8wAADA4YxGoyIjI3Xu3DkFBgZW+jyXGPYaM2aMVq9erS1btpQbfH799Vf16dNH/v7+WrlyZYXBR5I6d+6sF154QSaTSd7e3mX2e3t7l7s9ICCA8AMAQA1j65QVp97tZTabNWbMGK1cuVIbN25UdHR0mWOMRqN69eolLy8vffbZZ/Lx8blmu5mZmapXr165AQcAALg3p/b8jB49WsuXL9eqVavk7++vnJwcSVJgYKB8fX0twef8+fP65z//KaPRKKPRKEmqX7++PD099fnnnys3N1e33XabfHx8tG7dOs2aNUsTJ0505kcDAAAuyqlzfq7WTbVkyRINHz5caWlp6t69e7nHHD16VFFRUUpNTVViYqIOHz4ss9msZs2a6amnntLIkSMrPfPbaDQqMDDQcicZAABwfVX9++0yE56difADAI5XUlKioqIiZ5eBGqR27dry9PS86v6q/v12iQnPAIAbl9lsVk5Ojs6dO+fsUlADBQUFKTw83K7P4SP8AAAc6nLwCQ0NVZ06dXiYLCrFbDbr/PnzOn36tCSpQYMGdmub8AMAcJiSkhJL8AkJCXF2OahhfH19JUmnT59WaGhohUNgtnDqre4AgBvb5Tk+derUcXIlqKku/+7Yc74Y4QcA4HAMdaGqHPG7Q/gBAABuhfADAADcChOeAQDOMWOGS18vPj5ebdq00fz58+1WwvDhw3Xu3Dl9+umndmvzSseOHVN0dLT27NmjNm3aOOw6NRk9PwAAwK0QfgAAuMLw4cO1efNmvfbaazIYDDIYDDp27Jgkaf/+/UpISJCfn5/CwsL08MMP68yZM5Zz//3vfysmJka+vr4KCQlRz549VVhYqBkzZmjp0qVatWqVpc20tLRyr3+1Ni5777331LJlS/n4+KhFixZ64403LPsuvyS8bdu2MhgMio+Pt/v3U9Mx7AUAwBVee+01ff/992rdurVmzpwp6dILtc+dO6e77rpLjz/+uF599VX973//0+TJk3X//fdr48aNys7O1uDBgzV37lwNGDBAv/76q7Zu3Sqz2ayJEyfq4MGDMhqNWrJkiSQpODi4zLUrakOSli1bpmnTpmnhwoVq27at9uzZo5EjR6pu3boaNmyYvvnmG3Xq1Enr16/XrbfeKi8vr+r74moIwg8A3CCu1otQGfQOWAsMDJSXl5fq1Kmj8PBwy/bLgWPWrFmWbe+//74iIyP1/fffq6CgQMXFxRo4cKAaN24sSYqJibEc6+vrK5PJZNXmlbKzsytsY/r06Zo3b54GDhwo6VJPz7fffqu3335bw4YNU/369SVJISEhFV7HnRF+AACopL1792rTpk3y8/Mrs+/IkSPq1auXevTooZiYGPXu3Vu9evXSH//4R9WrV6/S14iLi7tqG4WFhTpy5IhGjBihkSNHWs4pLi5WYGCgXT6jOyD8AABQSQUFBerXr5/mzJlTZl+DBg3k6empdevW6euvv9batWv1+uuv67nnnlNGRoZlLs61VNTG5acdv/vuu+rcuXOZ81A5THgGAKAcXl5eKikpsdrWrl07HThwQFFRUWrWrJnVUrduXUmXnkjcrVs3JSUlac+ePfLy8tLKlSuv2mZ5rtZGWFiYIiIi9OOPP5a5/uVwdXmOT2Wu467o+QEAoBxRUVHKyMjQsWPH5Ofnp+DgYI0ePVrvvvuuBg8erEmTJik4OFiHDx/WihUr9N5772nnzp3asGGDevXqpdDQUGVkZOjnn39Wy5YtLW2uWbNGhw4dUkhIiAIDA1W7dm2r62ZkZFTYRlJSksaNG6fAwED16dNHJpNJO3fu1NmzZzVhwgSFhobK19dXqampatiwoXx8fBgSuwI9PwAAlGPixIny9PRUq1atVL9+fZ04cUIRERHatm2bSkpK1KtXL8XExOjZZ59VUFCQPDw8FBAQoC1btqhv37665ZZbNHXqVM2bN08JCQmSpJEjR6p58+bq0KGD6tevr23btpW57rXaePzxx/Xee+9pyZIliomJ0Z133qmUlBRLz0+tWrW0YMECvf3224qIiNB9991XfV9aDWEwX753zo0ZjUYFBgYqPz9fAQEBzi4HAKrEFe/2unDhgo4eParo6Gj5+Pg45Bq4sVX0O1TVv9/0/AAAALdC+AEAAG6F8AMAANwK4QcAALgVwg8AAHArhB8AAOBWCD8AAMCtEH4AAIBbIfwAAAC3QvgBAMBBoqKiNH/+fMu6wWDQp59+etXjjx07JoPBoMzMzOu6rr3auVHxYlMAgHNkzaje68VW8/XKkZ2drXr16tm1zeHDh+vcuXNWoSoyMlLZ2dm66aab7HotezMYDFq5cqX69+9frdcl/AAAUE3Cw8Or5Tqenp7Vdq2ayKnDXsnJyerYsaP8/f0VGhqq/v3769ChQ1bHXLhwQaNHj1ZISIj8/Pw0aNAg5ebmWh1z4sQJ3XPPPapTp45CQ0P1l7/8RcXFxdX5UQAAN5B33nlHERERKi0ttdp+33336bHHHpMkHTlyRPfdd5/CwsLk5+enjh07av369RW2e+Ww1zfffKO2bdvKx8dHHTp00J49e6yOLykp0YgRIxQdHS1fX181b95cr732mmX/jBkztHTpUq1atUoGg0EGg0FpaWnlDntt3rxZnTp1kre3txo0aKApU6ZY/a2Mj4/XuHHjNGnSJAUHBys8PFwzZsyo8POkpaWpU6dOqlu3roKCgtStWzcdP37csn/VqlVq166dfHx81KRJEyUlJVmuGRUVJUkaMGCADAaDZb06ODX8bN68WaNHj9b27du1bt06FRUVqVevXiosLLQcM378eH3++ef66KOPtHnzZp06dUoDBw607C8pKdE999yjixcv6uuvv9bSpUuVkpKiadOmOeMjAQBuAH/605/0yy+/aNOmTZZteXl5Sk1N1dChQyVJBQUF6tu3rzZs2KA9e/aoT58+6tevn06cOFGpaxQUFOjee+9Vq1attGvXLs2YMUMTJ060Oqa0tFQNGzbURx99pG+//VbTpk3TX//6V3344YeSpIkTJ+r+++9Xnz59lJ2drezsbHXt2rXMtf773/+qb9++6tixo/bu3as333xTixcv1osvvmh13NKlS1W3bl1lZGRo7ty5mjlzptatW1du/cXFxerfv7/uvPNOZWVlKT09XaNGjZLBYJAkbd26VY888oieeeYZffvtt3r77beVkpKiv/3tb5KkHTt2SJKWLFmi7Oxsy3p1cOqwV2pqqtV6SkqKQkNDtWvXLt1xxx3Kz8/X4sWLtXz5ct11112SLn1JLVu21Pbt23Xbbbdp7dq1+vbbb7V+/XqFhYWpTZs2euGFFzR58mTNmDFDXl5ezvhoAIAarF69ekpISNDy5cvVo0cPSdK///1v3XTTTerevbskKS4uTnFxcZZzXnjhBa1cuVKfffaZxowZc81rLF++XKWlpVq8eLF8fHx066236qefftJTTz1lOaZ27dpKSkqyrEdHRys9PV0ffvih7r//fvn5+cnX11cmk6nCYa433nhDkZGRWrhwoQwGg1q0aKFTp05p8uTJmjZtmjw8LvWFxMbGavr06ZKkm2++WQsXLtSGDRt09913l2nTaDQqPz9f9957r5o2bSpJatmypWV/UlKSpkyZomHDhkmSmjRpohdeeEGTJk3S9OnTVb9+fUlSUFBQtQ/RudTdXvn5+ZKk4OBgSdKuXbtUVFSknj17Wo5p0aKFGjVqpPT0dElSenq6YmJiFBYWZjmmd+/eMhqNOnDgQLnXMZlMMhqNVgsAAL81dOhQffzxxzKZTJKkZcuW6cEHH7QEhYKCAk2cOFEtW7ZUUFCQ/Pz8dPDgwUr3/Bw8eFCxsbHy8fGxbOvSpUuZ4xYtWqT27durfv368vPz0zvvvFPpa/z2Wl26dLH0ykhSt27dVFBQoJ9++smyLTY21uq8Bg0a6PTp0+W2GRwcrOHDh6t3797q16+fXnvtNWVnZ1v27927VzNnzpSfn59lGTlypLKzs3X+/Hmb6rc3lwk/paWlevbZZ9WtWze1bt1akpSTkyMvLy8FBQVZHRsWFqacnBzLMb8NPpf3X95XnuTkZAUGBlqWyMhIe38cAEAN169fP5nNZv3nP//RyZMntXXrVsuQl3RpyGnlypWaNWuWtm7dqszMTMXExOjixYt2q2HFihWaOHGiRowYobVr1yozM1OPPvqoXa/xW7Vr17ZaNxgMZeY9/daSJUuUnp6url276oMPPtAtt9yi7du3S7oUDpOSkpSZmWlZ9u3bpx9++MEq8DmDy9ztNXr0aO3fv19fffWVw6+VmJioCRMmWNaNRiMBCABgxcfHRwMHDtSyZct0+PBhNW/eXO3atbPs37Ztm4YPH64BAwZIuvTH/tixY5Vuv2XLlvrHP/6hCxcuWMLA5eDw22t07dpVTz/9tGXbkSNHrI7x8vJSSUnJNa/18ccfy2w2W3p/tm3bJn9/fzVs2LDSNZenbdu2atu2rRITE9WlSxctX75ct912m9q1a6dDhw6pWbNmVz23du3a16zdEVyi52fMmDFavXq1Nm3aZPWPEB4erosXL+rcuXNWx+fm5lrGB8PDw8vc/XV5/WpjiN7e3goICLBaAAC40tChQ/Wf//xH77//vlWvj3RpTswnn3yizMxM7d27V0OGDKmwl+RKQ4YMkcFg0MiRI/Xtt9/qiy++0Msvv1zmGjt37tSaNWv0/fff6/nnny8zMTgqKkpZWVk6dOiQzpw5o6KiojLXevrpp3Xy5EmNHTtW3333nVatWqXp06drwoQJlmE8Wx09elSJiYlKT0/X8ePHtXbtWv3www+WeT/Tpk3T3//+dyUlJenAgQM6ePCgVqxYoalTp1rVvmHDBuXk5Ojs2bNVqqMqnBp+zGazxowZo5UrV2rjxo2Kjo622t++fXvVrl1bGzZssGw7dOiQTpw4YRkX7dKli/bt22c1Jrlu3ToFBASoVatW1fNBAAA3pLvuukvBwcE6dOiQhgwZYrXvlVdeUb169dS1a1f169dPvXv3tuoZuhY/Pz99/vnn2rdvn9q2bavnnntOc+bMsTrmiSee0MCBA/XAAw+oc+fO+uWXX6x6gSRp5MiRat68uTp06KD69etr27ZtZa71u9/9Tl988YW++eYbxcXF6cknn9SIESOsgoit6tSpo++++06DBg3SLbfcolGjRmn06NF64oknJF2af7t69WqtXbtWHTt21G233aZXX31VjRs3trQxb948rVu3TpGRkWrbtm2Va7GVwWw2m6vtald4+umntXz5cq1atUrNmze3bA8MDJSvr68k6amnntIXX3yhlJQUBQQEaOzYsZKkr7/+WtKlW93btGmjiIgIzZ07Vzk5OXr44Yf1+OOPa9asWZWqw2g0KjAwUPn5+fQCAaix0tLSqnxufHy83er4rQsXLujo0aOKjo52+jwP1EwV/Q5V9e+3U+f8vPnmm5LK/j/dkiVLNHz4cEnSq6++Kg8PDw0aNEgmk0m9e/fWG2+8YTnW09NTq1ev1lNPPaUuXbqobt26GjZsmGbOnFldHwMAANQgTg0/lel08vHx0aJFi7Ro0aKrHtO4cWN98cUX9iwNAADcoFxiwjMAAEB1IfwAAAC3QvgBAABuhfADAADcCuEHAAC4FcIPAABwK4QfAADgVgg/AABUg6ioKM2fP7/Sx6elpclgMJR5vyWun8u81R0A4F6u53UcVWHrKzzi4+PVpk0bmwJLRXbs2KG6detW+viuXbsqOztbgYGBdrm+o9j7e6oOhB8AAKrIbDarpKREtWpd+89p/fr1bWrby8tL4eHhVS0NFWDYCwCAKwwfPlybN2/Wa6+9JoPBIIPBoGPHjlmGor788ku1b99e3t7e+uqrr3TkyBHdd999CgsLk5+fnzp27Kj169dbtXnlsJfBYNB7772nAQMGqE6dOrr55pv12WefWfZfOeyVkpKioKAgrVmzRi1btpSfn5/69Omj7OxsyznFxcUaN26cgoKCFBISosmTJ2vYsGHq37//VT/r8ePH1a9fP9WrV09169bVrbfeavXKqP379yshIUF+fn4KCwvTww8/rDNnzlT4Pbk6wg8AAFd47bXX1KVLF40cOVLZ2dnKzs5WZGSkZf+UKVM0e/ZsHTx4ULGxsSooKFDfvn21YcMG7dmzR3369FG/fv104sSJCq+TlJSk+++/X1lZWerbt6+GDh2qvLy8qx5//vx5vfzyy/rHP/6hLVu26MSJE5o4caJl/5w5c7Rs2TItWbJE27Ztk9Fo1KefflphDaNHj5bJZNKWLVu0b98+zZkzR35+fpKkc+fO6a677lLbtm21c+dOpaamKjc3V/fff3+lvidXxbAXAABXCAwMlJeXl+rUqVPu0NPMmTN19913W9aDg4MVFxdnWX/hhRe0cuVKffbZZxozZsxVrzN8+HANHjxYkjRr1iwtWLBA33zzjfr06VPu8UVFRXrrrbfUtGlTSdKYMWM0c+ZMy/7XX39diYmJGjBggCRp4cKF13zx94kTJzRo0CDFxMRIkpo0aWLZt3DhQrVt21azZs2ybHv//fcVGRmp77//XrfcckuF35OroucHAAAbdejQwWq9oKBAEydOVMuWLRUUFCQ/Pz8dPHjwmj0/sbGxlp/r1q2rgIAAnT59+qrH16lTxxJ8JKlBgwaW4/Pz85Wbm6tOnTpZ9nt6eqp9+/YV1jBu3Di9+OKL6tatm6ZPn66srCzLvr1792rTpk3y8/OzLC1atJAkHTlypMJ2XRnhBwAAG11519bEiRO1cuVKzZo1S1u3blVmZqZiYmJ08eLFCtupXbu21brBYFBpaalNx5vNZhurt/b444/rxx9/1MMPP6x9+/apQ4cOev311yVdCnX9+vVTZmam1fLDDz/ojjvuuK7rOhPhBwCAcnh5eamkpKRSx27btk3Dhw/XgAEDFBMTo/Dw8Gqf+BsYGKiwsDDt2LHDsq2kpES7d+++5rmRkZF68skn9cknn+jPf/6z3n33XUlSu3btdODAAUVFRalZs2ZWy+UAaMv35CoIPwAAlCMqKkoZGRk6duyYzpw5U2GPzM0336xPPvlEmZmZ2rt3r4YMGVLh8Y4yduxYJScna9WqVTp06JCeeeYZnT17VgaD4arnPPvss1qzZo2OHj2q3bt3a9OmTWrZsqWkS5Oh8/LyNHjwYO3YsUNHjhzRmjVr9Oijj1oCjy3fk6sg/AAAUI6JEyfK09NTrVq1Uv369Sucv/PKK6+oXr166tq1q/r166fevXurXbt21VjtJZMnT9bgwYP1yCOPqEuXLvLz81Pv3r3l4+Nz1XNKSko0evRotWzZUn369NEtt9yiN954Q5IUERGhbdu2qaSkRL169VJMTIyeffZZBQUFycPjUoSw5XtyFQbz9Q4W3gCMRqMCAwOVn5+vgIAAZ5cDAFVyPU9MtvXpx5V14cIFHT16VNHR0RX+AYZjlJaWqmXLlrr//vv1wgsvOLucKqnod6iqf7+51R0AgBvE8ePHtXbtWt15550ymUxauHChjh49qiFDhji7NJfCsBcAADcIDw8PpaSkqGPHjurWrZv27dun9evXW+bw4BJ6fgAAuEFERkZq27Ztzi7D5dHzAwAA3ArhBwDgcNxbg6pyxO8O4QcA4DCXn0h8/vx5J1eCmury786VT7e+Hsz5AQA4jKenp4KCgizvn6pTp06FD9wDLjObzTp//rxOnz6toKAgeXp62q1twg8AwKEuv+27ohd2AlcTFBRk9zfGE34AAA5lMBjUoEEDhYaGqqioyNnloAapXbu2XXt8LiP8AACqhaenp0P+kAG2YsIzAABwK04NP1u2bFG/fv0UEREhg8GgTz/91Gq/wWAod3nppZcsx0RFRZXZP3v27Or+KAAAoIZw6rBXYWGh4uLi9Nhjj2ngwIFl9mdnZ1utf/nllxoxYoQGDRpktX3mzJkaOXKkZd3f398xBQOAA13Pi0kBVJ5Tw09CQoISEhKuuv/K2d2rVq1S9+7d1aRJE6vt/v7+dp8JDgAAbkw1Zs5Pbm6u/vOf/2jEiBFl9s2ePVshISFq27atXnrpJRUXF1fYlslkktFotFoAAIB7qDF3ey1dulT+/v5lhsfGjRundu3aKTg4WF9//bUSExOVnZ2tV1555aptJScnKykpydElAwAAF1Rjws/777+voUOHysfHx2r7hAkTLD/HxsbKy8tLTzzxhJKTk+Xt7V1uW4mJiVbnGY1GRUZGOqZwAADgUmpE+Nm6dasOHTqkDz744JrHdu7cWcXFxTp27JiaN29e7jHe3t5XDUYAAODGViPm/CxevFjt27dXXFzcNY/NzMyUh4eHQkNDq6EyAABQ0zi156egoECHDx+2rB89elSZmZkKDg5Wo0aNJF0akvroo480b968Muenp6crIyND3bt3l7+/v9LT0zV+/Hg99NBDqlevXrV9DgAAUHM4Nfzs3LlT3bt3t6xfnoczbNgwpaSkSJJWrFghs9mswYMHlznf29tbK1as0IwZM2QymRQdHa3x48dbzecBAAD4LYPZbDY7uwhnMxqNCgwMVH5+vgICApxdDgA35cyHHMbHxzvt2kBVVfXvd42Y8wMAAGAvhB8AAOBWCD8AAMCtEH4AAIBbIfwAAAC3QvgBAABuhfADAADcCuEHAAC4FcIPAABwK4QfAADgVgg/AADArRB+AACAWyH8AAAAt0L4AQAAboXwAwAA3ArhBwAAuBXCDwAAcCuEHwAA4FYIPwAAwK0QfgAAgFsh/AAAALdC+AEAAG6F8AMAANwK4QcAALgVm8PPyZMn9dNPP1nWv/nmGz377LN655137FoYAACAI9gcfoYMGaJNmzZJknJycnT33Xfrm2++0XPPPaeZM2favUAAAAB7sjn87N+/X506dZIkffjhh2rdurW+/vprLVu2TCkpKfauDwAAwK5sDj9FRUXy9vaWJK1fv15/+MMfJEktWrRQdna2fasDAACwM5vDz6233qq33npLW7du1bp169SnTx9J0qlTpxQSEmL3AgEAAOzJ5vAzZ84cvf3224qPj9fgwYMVFxcnSfrss88sw2EAAACuyubwEx8frzNnzujMmTN6//33LdtHjRqlt956y6a2tmzZon79+ikiIkIGg0Gffvqp1f7hw4fLYDBYLZd7mi7Ly8vT0KFDFRAQoKCgII0YMUIFBQW2fiwAAOAmqvScH7PZrF27duntt9/Wr7/+Kkny8vJSnTp1bGqnsLBQcXFxWrRo0VWP6dOnj7Kzsy3Lv/71L6v9Q4cO1YEDB7Ru3TqtXr1aW7Zs0ahRo2z/UAAAwC3UsvWE48ePq0+fPjpx4oRMJpPuvvtu+fv7a86cOTKZTDb1/iQkJCghIaHCY7y9vRUeHl7uvoMHDyo1NVU7duxQhw4dJEmvv/66+vbtq5dfflkRERGV/2AAAMAt2Nzz88wzz6hDhw46e/asfH19LdsHDBigDRs22LU4SUpLS1NoaKiaN2+up556Sr/88otlX3p6uoKCgizBR5J69uwpDw8PZWRkXLVNk8kko9FotQAAAPdgc8/P1q1b9fXXX8vLy8tqe1RUlP773//arTDp0pDXwIEDFR0drSNHjuivf/2rEhISlJ6eLk9PT+Xk5Cg0NNTqnFq1aik4OFg5OTlXbTc5OVlJSUl2rRUAANQMNoef0tJSlZSUlNn+008/yd/f3y5FXfbggw9afo6JiVFsbKyaNm2qtLQ09ejRo8rtJiYmasKECZZ1o9GoyMjI66oVAADUDDYPe/Xq1Uvz58+3rBsMBhUUFGj69Onq27evXYu7UpMmTXTTTTfp8OHDkqTw8HCdPn3a6pji4mLl5eVddZ6QdGkeUUBAgNUCAADcg83hZ968edq2bZtatWqlCxcuaMiQIZYhrzlz5jiiRouffvpJv/zyixo0aCBJ6tKli86dO6ddu3ZZjtm4caNKS0vVuXNnh9YCAABqJpuHvRo2bKi9e/dqxYoVysrKUkFBgUaMGKGhQ4daTYCujIKCAksvjiQdPXpUmZmZCg4OVnBwsJKSkjRo0CCFh4fryJEjmjRpkpo1a6bevXtLklq2bKk+ffpo5MiReuutt1RUVKQxY8bowQcf5E4vAABQLpuTD+lXAAAgAElEQVTDj3RpUvFDDz103RffuXOnunfvblm/PA9n2LBhevPNN5WVlaWlS5fq3LlzioiIUK9evfTCCy9Y3i0mScuWLdOYMWPUo0cPeXh4aNCgQVqwYMF11wYAAG5MlQo/n332WaUbvPyi08qIj4+X2Wy+6v41a9Zcs43g4GAtX7680tcEAADurVLhp3///pVqzGAwlHsnGAAAgKuoVPgpLS11dB0AAADVokrv9gIAAKipbJ7wPHPmzAr3T5s2rcrFAAAAOJrN4WflypVW60VFRTp69Khq1aqlpk2bEn4AAIBLszn87Nmzp8w2o9Go4cOHa8CAAXYpCgAAwFHsMucnICBASUlJev755+3RHAAAgMPYbcJzfn6+8vPz7dUcAACAQ9g87HXl05PNZrOys7P1j3/8QwkJCXYrDAAAwBFsDj+vvvqq1bqHh4fq16+vYcOGKTEx0W6FAQAAOILN4efo0aOOqAMAAKBa2DznJz8/X3l5eWW25+XlyWg02qUoAAAAR7E5/Dz44INasWJFme0ffvihHnzwQbsUBQAA4Cg2h5+MjAx17969zPb4+HhlZGTYpSgAAABHsTn8mEwmFRcXl9leVFSk//3vf3YpCgAAwFFsDj+dOnXSO++8U2b7W2+9pfbt29ulKAAAAEex+W6vF198UT179tTevXvVo0cPSdKGDRu0Y8cOrV271u4FAgAA2JPNPT/dunVTenq6GjZsqA8//FCff/65mjVrpqysLP3+9793RI0AAAB2Y3PPjyS1adNGy5cvt3ctAAAADleld3sdOXJEU6dO1ZAhQ3T69GlJ0pdffqkDBw7YtTgAAAB7szn8bN68WTExMcrIyNDHH3+sgoICSdLevXs1ffp0uxcIAABgTzaHnylTpujFF1/UunXr5OXlZdl+1113afv27XYtDgAAwN5sDj/79u3TgAEDymwPDQ3VmTNn7FIUAACAo9gcfoKCgpSdnV1m+549e/S73/3OLkUBAAA4SpXe7TV58mTl5OTIYDCotLRU27Zt08SJE/XII484okYAAAC7sTn8zJo1Sy1atFBkZKQKCgrUqlUr3XHHHerataumTp3qiBoBAADsxubn/Hh5eendd9/V888/r/3796ugoEBt27bVzTff7Ij6AAAA7KpKDzmUpEaNGqlRo0b2rAUAAMDhKhV+JkyYUOkGX3nllSoXAwAA4GiVCj979uypVGMGg+G6igEAAHC0SoWfTZs2OeTiW7Zs0UsvvaRdu3YpOztbK1euVP/+/SVJRUVFmjp1qr744gv9+OOPCgwMVM+ePTV79mxFRERY2oiKitLx48et2k1OTtaUKVMcUjMAAKjZqvRur8t++ukn/fTTT1U+v7CwUHFxcVq0aFGZfefPn9fu3bv1/PPPa/fu3frkk0906NAh/eEPfyhz7MyZM5WdnW1Zxo4dW+WaAADAjc3mCc+lpaV68cUXNW/ePMt7vfz9/fXnP/9Zzz33nDw8Kp+nEhISlJCQUO6+wMBArVu3zmrbwoUL1alTJ504ccJqsrW/v7/Cw8Nt/SgAAMAN2dzz89xzz2nhwoWaPXu29uzZoz179mjWrFl6/fXX9fzzzzuiRov8/HwZDAYFBQVZbZ89e7ZCQkLUtm1bvfTSSyouLq6wHZPJJKPRaLUAAAD3YHPPz9KlS/Xee+9ZDT/Fxsbqd7/7nZ5++mn97W9/s2uBl124cEGTJ0/W4MGDFRAQYNk+btw4tWvXTsHBwfr666+VmJio7OzsCu86S05OVlJSkkPqBAAArs3m8JOXl6cWLVqU2d6iRQvl5eXZpagrFRUV6f7775fZbNabb75pte+3t+HHxsbKy8tLTzzxhJKTk+Xt7V1ue4mJiVbnGY1GRUZGOqR2AADgWmwOP3FxcVq4cKEWLFhgtX3hwoWKi4uzW2GXXQ4+x48f18aNG616fcrTuXNnFRcX69ixY2revHm5x3h7e181GAGAS8hNc0y7YfGOaReoQWwOP3PnztU999yj9evXq0uXLpKk9PR0nTx5Ul988YVdi7scfH744Qdt2rRJISEh1zwnMzNTHh4eCg0NtWstAADgxmBz+Lnzzjv1/fffa9GiRfruu+8kSQMHDtTTTz9t9fydyigoKNDhw4ct60ePHlVmZqaCg4PVoEED/fGPf9Tu3bu1evVqlZSUKCcnR5IUHBwsLy8vpaenKyMjQ927d5e/v7/S09M1fvx4PfTQQ6pXr56tHw0AALgBg9lsNjvr4mlpaerevXuZ7cOGDdOMGTMUHR1d7nmbNm1SfHy8du/eraefflrfffedTCaToqOj9fDDD2vChAk2DWsZjUYFBgYqPz//msNqAOAoaWlp/7dSzcNe8fHlbwdcWVX/flfpxaYXLlxQVlaWTp8+rdLSUqt95T2E8Gri4+NVUfa6Vi5r166dtm/fXunrAQAA2Bx+UlNT9cgjj+jMmTNl9hkMBpWUlNilMAAAAEew+SGHY8eO1Z/+9CdlZ2ertLTUaiH4AAAAV2dz+MnNzdWECRMUFhbmiHoAAAAcyubw88c//tF6Uh4AAEANYvOcn4ULF+pPf/qTtm7dqpiYGNWuXdtq/7hx4+xWHAAAgL3ZHH7+9a9/ae3atfLx8VFaWpoMBoNln8FgIPwAcGv0jAOuz+bw89xzzykpKUlTpkyRh4fNo2YAAABOZXN6uXjxoh544AGCDwAAqJFsTjDDhg3TBx984IhaAAAAHM7mYa+SkhLNnTtXa9asUWxsbJkJz6+88ordigMAALA3m8PPvn371LZtW0nS/v37rfb9dvIzAACAK7I5/GzatMkRdQAAAFQLZi0DAAC3QvgBAABuhfADAADcCuEHAAC4lUqFn3bt2uns2bOSpJkzZ+r8+fMOLQoAAMBRKhV+Dh48qMLCQklSUlKSCgoKHFoUAACAo1TqVvc2bdro0Ucf1e233y6z2ayXX35Zfn5+5R47bdo0uxYIAABgT5UKPykpKZo+fbpWr14tg8GgL7/8UrVqlT3VYDAQfgAAgEurVPhp3ry5VqxYIUny8PDQhg0bFBoa6tDCAAAAHMHmJzyXlpY6og4AAIBqYXP4kaQjR45o/vz5OnjwoCSpVatWeuaZZ9S0aVO7FgcAAGBvNj/nZ82aNWrVqpW++eYbxcbGKjY2VhkZGbr11lu1bt06R9QIAABgNzb3/EyZMkXjx4/X7Nmzy2yfPHmy7r77brsVBwBu79gx+7QTFWWfdoAbgM09PwcPHtSIESPKbH/sscf07bff2qUoAAAAR7G556d+/frKzMzUzTffbLU9MzOTO8AAoIZKS0ur8rnx8fF2qwOoDjaHn5EjR2rUqFH68ccf1bVrV0nStm3bNGfOHE2YMMHuBQIAANiTzeHn+eefl7+/v+bNm6fExERJUkREhGbMmKFx48bZvUAAAAB7sjn8GAwGjR8/XuPHj9evv/4qSfL397d7YQAAAI5Qpef8XEboAQAANY3Nd3vZ05YtW9SvXz9FRETIYDDo008/tdpvNps1bdo0NWjQQL6+vurZs6d++OEHq2Py8vI0dOhQBQQEKCgoSCNGjOCt8wAA4KqcGn4KCwsVFxenRYsWlbt/7ty5WrBggd566y1lZGSobt266t27ty5cuGA5ZujQoTpw4IDWrVun1atXa8uWLRo1alR1fQQAAFDDXNew1/VKSEhQQkJCufvMZrPmz5+vqVOn6r777pMk/f3vf1dYWJg+/fRTPfjggzp48KBSU1O1Y8cOdejQQZL0+uuvq2/fvnr55ZcVERFRbtsmk0kmk8mybjQa7fzJAACAq7Kp56eoqEg9evQoM/TkCEePHlVOTo569uxp2RYYGKjOnTsrPT1dkpSenq6goCBL8JGknj17ysPDQxkZGVdtOzk5WYGBgZYlMjLScR8EAAC4FJvCT+3atZWVleWoWqzk5ORIksLCwqy2h4WFWfbl5OSUebBirVq1FBwcbDmmPImJicrPz7csJ0+etHP1AADAVdk85+ehhx7S4sWLHVFLtfH29lZAQIDVAgAA3IPNc36Ki4v1/vvva/369Wrfvr3q1q1rtf+VV16xS2Hh4eGSpNzcXDVo0MCyPTc3V23atLEcc/r06TL15eXlWc4HAAD4LZvDz/79+9WuXTtJ0vfff2+1z2Aw2KcqSdHR0QoPD9eGDRssYcdoNCojI0NPPfWUJKlLly46d+6cdu3apfbt20uSNm7cqNLSUnXu3NlutQBAubJmlN2WW+1VVM7lt8MfS6l6G1d7M3xW2qX/Gzuj6m0D1cjm8LNp0ya7XbygoECHDx+2rB89elSZmZkKDg5Wo0aN9Oyzz+rFF1/UzTffrOjoaD3//POKiIhQ//79JUktW7ZUnz59NHLkSL311lsqKirSmDFj9OCDD171Ti8AAODeqnyr++HDh3XkyBHdcccd8vX1ldlstrnnZ+fOnerevbtl/fKLUYcNG6aUlBRNmjRJhYWFGjVqlM6dO6fbb79dqamp8vHxsZyzbNkyjRkzRj169JCHh4cGDRqkBQsWVPVjAQCAG5zBbDabbTnhl19+0f33369NmzbJYDDohx9+UJMmTfTYY4+pXr16mjdvnqNqdRij0ajAwEDl5+cz+RlA5ZUz7JV20M7XuDxc5QquMuwV3/L//8CwF6pZVf9+23y31/jx41W7dm2dOHFCderUsWx/4IEHlJqaamtzAAAA1crmYa+1a9dqzZo1atiwodX2m2++WcePH7dbYQAAAI5gc89PYWGhVY/PZXl5efL29rZLUQAAAI5ic/j5/e9/r7///e+WdYPBoNLSUs2dO9dq8jIAAIArsnnYa+7cuerRo4d27typixcvatKkSTpw4IDy8vK0bds2R9QIAABgNzb3/LRu3Vrff/+9br/9dt13330qLCzUwIEDtWfPHjVt2tQRNQIAANhNlZ7zExgYqOeee87etQAAADhclcLP2bNntXjxYh08eOmBFq1atdKjjz6q4OBguxYHAABgbzYPe23ZskVRUVFasGCBzp49q7Nnz2rBggWKjo7Wli1bHFEjAACA3djc8zN69Gg98MADevPNN+Xp6SlJKikp0dNPP63Ro0dr3759di8SAADAXmzu+Tl8+LD+/Oc/W4KPJHl6emrChAlWLykFAABwRTaHn3bt2lnm+vzWwYMHFRcXZ5eiAAAAHKVSw15ZWVmWn8eNG6dnnnlGhw8f1m233SZJ2r59uxYtWqTZs2c7pkoAAAA7qVT4adOmjQwGg377AvhJkyaVOW7IkCF64IEH7FcdAACAnVUq/Bw9etTRdQAAAFSLSoWfxo0bO7oOAACAalGlhxyeOnVKX331lU6fPq3S0lKrfePGjbNLYQAAAI5gc/hJSUnRE088IS8vL4WEhMhgMFj2GQwGwg8AAHBpNoef559/XtOmTVNiYqI8PGy+Ux4AAMCpbE4v58+f14MPPkjwAQAANZLNCWbEiBH66KOPHFELAACAw9k87JWcnKx7771XqampiomJUe3ata32v/LKK3YrDgAAwN6qFH7WrFmj5s2bS1KZCc8AAACuzObwM2/ePL3//vsaPny4A8oBAABwLJvn/Hh7e6tbt26OqAUAAMDhbA4/zzzzjF5//XVH1AIAAOBwNg97ffPNN9q4caNWr16tW2+9tcyE508++cRuxQEAANibzeEnKChIAwcOdEQtAAAADmdz+FmyZIkj6gAAAKgWPKYZAAC4FZt7fqKjoyt8ns+PP/54XQVdKSoqSsePHy+z/emnn9aiRYsUHx+vzZs3W+174okn9NZbb9m1DgCwybFjzq4AwFXYHH6effZZq/WioiLt2bNHqamp+stf/mK3wi7bsWOHSkpKLOv79+/X3XffrT/96U+WbSNHjtTMmTMt63Xq1LF7HQAA4MZgc/h55plnyt2+aNEi7dy587oLulL9+vWt1mfPnq2mTZvqzjvvtGyrU6eOwsPDK92myWSSyWSyrBuNxusvFAAA1Ah2m/OTkJCgjz/+2F7NlevixYv65z//qccee8xq6G3ZsmW66aab1Lp1ayUmJur8+fMVtpOcnKzAwEDLEhkZ6dC6AQCA67C55+dq/v3vfys4ONhezZXr008/1blz56xerTFkyBA1btxYERERysrK0uTJk3Xo0KEKnzeUmJioCRMmWNaNRiMBCAAAN2Fz+Gnbtq1Vr4vZbFZOTo5+/vlnvfHGG3Yt7kqLFy9WQkKCIiIiLNtGjRpl+TkmJkYNGjRQjx49dOTIETVt2rTcdry9veXt7e3QWgEAgGuyOfz079/fat3Dw0P169dXfHy8WrRoYbfCrnT8+HGtX7/+mk+Q7ty5syTp8OHDVw0/AADAfdkcfqZPn+6IOq5pyZIlCg0N1T333FPhcZmZmZKkBg0aVEdZAACghrHbnB9HKi0t1ZIlSzRs2DDVqvV/JR85ckTLly9X3759FRISoqysLI0fP1533HGHYmNjnVgxALiPtIP//4e8tCqdHx8fb69SgEqpdPjx8PCo8OGGkmQwGFRcXHzdRV1p/fr1OnHihB577DGr7V5eXlq/fr3mz5+vwsJCRUZGatCgQZo6dardawAAADeGSoeflStXXnVfenq6FixYoNLSUrsUdaVevXrJbDaX2R4ZGVnm6c4AcL3S0tIqd2CuQ8sA4CCVDj/33XdfmW2HDh3SlClT9Pnnn2vo0KFWT1kGAABwRVV6yOGpU6c0cuRIxcTEqLi4WJmZmVq6dKkaN25s7/oAAADsyqbwk5+fr8mTJ6tZs2Y6cOCANmzYoM8//1ytW7d2VH0AAAB2Velhr7lz52rOnDkKDw/Xv/71r3KHwQAAAFxdpcPPlClT5Ovrq2bNmmnp0qVaunRpucdd6yGEAAAAzlTp8PPII49c81Z3AAAAV1fp8JOSkuLAMgAAAKpHle72AgAAqKkIPwAAwK0QfgAAgFsh/AAAALdC+AEAAG6F8AMAANwK4QcAALgVwg8AAHArhB8AAOBWCD8AAMCtEH4AAIBbIfwAAAC3QvgBAABuhfADAADcCuEHAAC4FcIPAABwK4QfAADgVgg/AADArRB+AACAWyH8AAAAt0L4AQAAboXwAwAA3ArhBwAAuBWXDj8zZsyQwWCwWlq0aGHZf+HCBY0ePVohISHy8/PToEGDlJub68SKAQCAq3Pp8CNJt956q7Kzsy3LV199Zdk3fvx4ff755/roo4+0efNmnTp1SgMHDnRitQAAwNXVcnYB11KrVi2Fh4eX2Z6fn6/Fixdr+fLluuuuuyRJS5YsUcuWLbV9+3bddtttV23TZDLJZDJZ1o1Go/0LBwAALsnle35++OEHRUREqEmTJho6dKhOnDghSdq1a5eKiorUs2dPy7EtWrRQo0aNlJ6eXmGbycnJCgwMtCyRkZEO/QwAAMB1uHT46dy5s1JSUpSamqo333xTR48e1e9//3v9+uuvysnJkZeXl4KCgqzOCQsLU05OToXtJiYmKj8/37KcPHnSkR8DAAC4EJce9kpISLD8HBsbq86dO6tx48b68MMP5evrW+V2vb295e3tbY8SAQBADePSPT9XCgoK0i233KLDhw8rPDxcFy9e1Llz56yOyc3NLXeOEAAAgFTDwk9BQYGOHDmiBg0aqH379qpdu7Y2bNhg2X/o0CGdOHFCXbp0cWKVAADAlbn0sNfEiRPVr18/NW7cWKdOndL06dPl6empwYMHKzAwUCNGjNCECRMUHBysgIAAjR07Vl26dKnwTi8AAODeXDr8/PTTTxo8eLB++eUX1a9fX7fffru2b9+u+vXrS5JeffVVeXh4aNCgQTKZTOrdu7feeOMNJ1cNAABcmUuHnxUrVlS438fHR4sWLdKiRYuqqSIAAFDT1ag5PwAAANeL8AMAANyKSw97AUC1mzGj8sf6HnNUFQAciJ4fAADgVgg/AADArRB+AACAW2HODwDAqdLS0qp8bnx8vN3qgPug5wcAALgVwg8AAHArhB8AAOBWCD8AAMCtEH4AAIBb4W4vAEDlHDtW8f6DaZVrhzu04GT0/AAAALdC+AEAAG6F8AMAANwKc34A3PiyZlT+2JA06XyUgwq5wVX2Lfe5aba1GxZvYyFAxej5AQAAboXwAwAA3ArhBwAAuBXCDwAAcCuEHwAA4FYIPwAAwK0QfgAAgFsh/AAAALdC+AEAAG6F8AMAANwKr7cAcENKS0v7v5VcG07k1RY1itW/s43i4+PtVgdqFnp+AACAW6HnBwDglq6n10ii56gmc+men+TkZHXs2FH+/v4KDQ1V//79dejQIatj4uPjZTAYrJYnn3zSSRUDAABX59LhZ/PmzRo9erS2b9+udevWqaioSL169VJhYaHVcSNHjlR2drZlmTt3rpMqBgAArs6lh71SU1Ot1lNSUhQaGqpdu3bpjjvusGyvU6eOwsPDq7s8AK5kxoyr7/M9Vl1VwBFy0xzXdli849qGy3Lpnp8r5efnS5KCg4Otti9btkw33XSTWrdurcTERJ0/f77Cdkwmk4xGo9UCAADcg0v3/PxWaWmpnn32WXXr1k2tW7e2bB8yZIgaN26siIgIZWVlafLkyTp06JA++eSTq7aVnJyspKSk6igbAAC4GIPZbDY7u4jKeOqpp/Tll1/qq6++UsOGDa963MaNG9WjRw8dPnxYTZs2LfcYk8kkk8lkWTcajYqMjFR+fr4CAgLsXjuAanDFsFfab1cY9nItUVHOrsAu4ltWsDN2RnWV4daMRqMCAwNt/vtdI3p+xowZo9WrV2vLli0VBh9J6ty5syRVGH68vb3l7e1t9zoBAIDrc+nwYzabNXbsWK1cuVJpaWmKjo6+5jmZmZmSpAYNGji6PAAOdL3PYIELO3bMPu3U4B4knkztXC4dfkaPHq3ly5dr1apV8vf3V05OjiQpMDBQvr6+OnLkiJYvX66+ffsqJCREWVlZGj9+vO644w7FxsY6uXoAAOCKXDr8vPnmm5LKptwlS5Zo+PDh8vLy0vr16zV//nwVFhYqMjJSgwYN0tSpU51QLQAAqAlcOvxcay52ZGSkNm/eXE3VAABQSVkzKt5vy8t2y4i/npOhGvacHwAAgOtF+AEAAG6F8AMAANwK4QcAALgVwg8AAHArhB8AAOBWXPpWdwA1W6WfYsvTnAFUI8IPAABVkHbQ2RWgqhj2AgAAboWeHwCAe+NFq26Hnh8AAOBW6PkBANRM9uqxsRd71EPvUbUg/ABwDb7HnF0BADfBsBcAAHArhB8AAOBWCD8AAMCtMOcHAABXUZlJ0zNm2OcYN0b4AQCgBkmr1EFXPyo+Pt4+hdRgDHsBAAC3Qs8PgApV+uWkAFBD0PMDAADcCj0/AGyTm2b/NnnAIYBqRPgBAKAmqcx/LFTwHylpH1x9n8LiK2z2RpkszbAXAABwK/T8AKg6V3uxJABUAuEHAIAbTVX/w+RgmvX6DTLMdSWGvQAAgFuh5weoAWx+1s5vJjvGt7zOi+de5/kA4GLo+QEAAG6Fnh+gmjjrSclpB51yWQBwWTdM+Fm0aJFeeukl5eTkKC4uTq+//ro6derk7LKAS8p7w7IzH+wXFeW8awOAk90Qw14ffPCBJkyYoOnTp2v37t2Ki4tT7969dfr0aWeXBgAAXIzBbDabnV3E9ercubM6duyohQsXSpJKS0sVGRmpsWPHasqUKdc832g0KjAwUPn5+QoICLBvcVkz7Nveb8U6sG1nKq+XxJnt2OPfcHOa0s5HXX87AFCdruglrvINFA76e1XVv981ftjr4sWL2rVrlxITEy3bPDw81LNnT6Wnp5d7jslkkslksqzn5+dLuvQl2l2B6drHVJUj6nUFJjt9Z/b6fuzxb/i/YhVeuHj97QBAdTpv/b9/xoIqtuOgv1eX/27b2o9T48PPmTNnVFJSorCwMKvtYWFh+u6778o9Jzk5WUlJSWW2R0ZGOqRGx5nt7AJc22xX+362ObsAAHASx/7v8a+//qrAwMBKH1/jw09VJCYmasKECZb10tJS5eXlKSQkRAaDwYmVOYbRaFRkZKROnjxp/2G9GxjfW9Xx3VUd313V8d1VTU3+3sxms3799VdFRETYdF6NDz833XSTPD09lZtr/SS23NxchYeHl3uOt7e3vL29rbYFBQU5rEZXERAQUON+sV0B31vV8d1VHd9d1fHdVU1N/d5s6fG5rMbf7eXl5aX27dtrw4YNlm2lpaXasGGDunTp4sTKAACAK6rxPT+SNGHCBA0bNkwdOnRQp06dNH/+fBUWFurRRx91dmkAAMDFeM6YYa/7gZ2ndevWCgoK0t/+9je9/PLLkqRly5apefPmTq7MdXh6eio+Pl61at0Qebfa8L1VHd9d1fHdVR3fXdW42/d2QzznBwAAoLJq/JwfAAAAWxB+AACAWyH8AAAAt0L4AQAAboXw42Z2796tu+++W0FBQQoJCdGoUaNUUFDVl7W4l++//1733XefbrrpJgUEBOj222/Xpk2bnF2WS0tLS5PBYCh32bFjh7PLqxH+85//qHPnzvL19VW9evXUv39/Z5dUI0RFRZX5nZvtcq+8cW0mk0lt2rSRwWBQZmams8uxK8KPGzl16pR69uypZs2aKSMjQ6mpqTpw4ICGDx/u7NJqhHvvvVfFxcXauHGjdu3apbi4ON17773Kyclxdmkuq2vXrsrOzrZaHn/8cUVHR6tDhw7OLs/lffzxx3r44Yf16KOPau/evdq2bZuGDBni7LJqjJkzZ1r97o0dO9bZJdUokyZNsvm1ETWGGW7j7bffNoeGhppLSkos27KyssySzD/88IMTK3N9P//8s1mSecuWLZZtRqPRLMm8bt06J1ZWs1y8eNFcv35988yZM51dissrKioy/+53vzO/9957zi6lRmrcuLH51VdfdXYZNdYXX3xhbtGihfnAgQNmSeY9e/Y4uyS7oufHjZhMJnl5ecnD4//+2X19fSVJX331lbPKqhFCQnJbojUAAAseSURBVELUvHlz/f3vf1dhYaGKi4v19ttvKzQ0VO3bt3d2eTXGZ599pl9++YWnr1fC7t279d///lceHh5q27atGjRooISEBO3fv9/ZpdUYs2fPVkhIiNq2bauXXnpJxcXFzi6pRsjNzdXIkSP1j3/8Q3Xq1HF2OQ5B+HEjd911l3JycvTSSy/p4sWLOnv2rKZMmSJJys7OdnJ1rs1gMGj9+vXas2eP/P395ePjo1deeUWpqamqV6+es8urMRYvXqzevXurYcOGzi7F5f3444+SpBkzZmjq1KlavXq16tWrp/j4eOXl5Tm5Otc3btw4rVixQps2bdITTzyhWbNmadKkSc4uy+WZzWYNHz5cTz755A09NE34uQFMmTLlqpNKLy/fffedbr31Vi1dulTz5s1TnTp1FP7/2rv3kKjSNw7g39FJTadJy2tRWpMWmVba5tbKlpPZDWEikqRmXZshooIu0B+h27hU1G4IkcF22R0zogtdtIK0m0UyRVlLtgUJWZqV2UWDnc3Mxvf3R3TorL9qbGeaqfP9wAHPezvPeRlmnnnnHE9kJAYNGoSIiAjZapCSODt3QggsXrwY4eHhqKqqwuXLl2EwGJCZmanIxNHZeXvX/fv3ceLECZhMJg9F7R2cnbvOzk4AQF5eHmbNmoXk5GQUFxdDpVLhwIEDHj4Lz+jO627FihWYOHEiEhMTsXDhQhQWFqKoqAjt7e0ePgvPcHbuioqK8Pfff2PVqlWeDtmt+HiLr8CTJ0/w7NmzD7YZPHgw/Pz8pP3m5mYEBQVBpVJBq9Vi3759mD17trtD9TrOzl1VVRUyMjLQ2toKrVYr1cXGxsJkMkkraErxKa+5NWvWoKioCA8ePECPHj3cHaLXcnbubDYb9Ho9qqqqkJqaKtWlpKQgPT0d69atc3eoXudTXndv3bx5EyNGjMCtW7cU+dxHZ+cuKysLx44dg0qlksodDgd8fX0xd+5clJSUuDvUz0IZTzD7yoWFhSEsLKxbfSIiIgAAVqsVAQEBmDx5sjtC83rOzt2LFy8AoMsKmY+Pj/QNXUm6+5oTQqC4uBg//PCDohMfwPm5S05Ohr+/P2pra6Xkp6OjA/X19YiOjnZ3mF7pU97r3rp27Rp8fHwQHh7u4qi+DM7O3ebNm7F27Vpp/+HDh5gyZQr279+PlJQUd4b4WTH5UZgtW7Zg/Pjx0Gg0OHXqFFauXIkNGzYgODjY06F5tXHjxiEkJAQ5OTlYvXo1evbsiR07duDu3buYMWOGp8PzepWVlbh79y7MZrOnQ/liaLVaLFy4EBaLBQMGDEB0dDQ2btwIAIpcpe2Oixcv4tKlS0hLS0OvXr1w8eJFLF++HPPmzeM1eh8xcOBA2b5GowEA6HS6r+paPSY/CnP58mVYLBbY7XYMGzYM27Ztg9Fo9HRYXi80NBQVFRXIy8uDXq9HR0cH4uPjceTIEYwcOdLT4Xm9P/74A+PHj8ewYcM8HcoXZePGjVCr1TAajWhra0NKSgoqKyv5Af4R/v7+2LdvHwoKCtDe3o5BgwZh+fLlWLFihadDIy/Ba36IiIhIUZR5iw8REREpFpMfIiIiUhQmP0RERKQoTH6IiIhIUZj8EBERkaIw+SEiIiJFYfJDREREisLkh4iIiBSFyQ8R0f9RUFAgPe1606ZNLh8/JiZGGv/58+cuH5+I3o/JDxH9Zz/++KP0Qf7uNnXqVE+H9p/Ex8ejqakJCxYscKp9YWEhQkJC8PLlyy51L168gFarxebNmwEA1dXVOHTokEvjJSLnMPkhIpeYOnUqmpqaZNvevXvdesxXr165dXy1Wo3IyEgEBgY61d5oNOKff/7B4cOHu9QdPHgQr169wrx58wC8ecp2nz59XBovETmHyQ8RuYS/vz8iIyNl27sP4FSpVPj9998xc+ZMBAYGIjY2FkePHpWNcePGDUybNg0ajQYREREwGo14+vSpVD9x4kQsWbIEy5YtQ2hoKKZMmQIAuHXrFlJTUxEQEIDhw4fj9OnTUKlUKCsrAwDo9XosWbJEdqwnT57Az88PZ86c6dZ5Pn/+HGazGWFhYdBqtdDr9aipqQEAhIeHIzMzE1artUs/q9UKg8HAhIfICzD5IaLP5ueff0ZWVhauX7+O6dOnY+7cuWhpaQHwJqnQ6/UYPXo0rly5goqKCjQ3NyMrK0s2RklJCfz8/GCz2bB161Y4HA4YDAYEBgbi0qVL2L59O/Ly8mR9zGYz9uzZg/b2dqls9+7d6N+/P/R6fbfOYfbs2Xj8+DHKy8tx9epVJCUlYdKkSdJ5mEwmVFZWoqGhQepz584dnD9/HiaTqVvHIiI3EURE/1FOTo7w9fUVQUFBsm3dunVSGwAiPz9f2rfb7QKAKC8vF0IIsWbNGpGRkSEbt7GxUQAQtbW1QgghJkyYIEaPHi1rU15eLtRqtWhqapLKTp06JQCI0tJSIYQQbW1tIiQkROzfv19qk5iYKAoKCt57ThaLRYwcOVJWVlVVJbRarXj58qWsXKfTiW3btgkhhHj9+rXo37+/sFgsUv1PP/0kBg4cKBwOh6zf2bNnBQDR2tr63jiIyPXUHs28iOirkZaWht9++01W9u+feBITE6W/g4KCoNVq8fjxYwBATU0Nzp49C41G02Xsuro6xMXFAQCSk5NldbW1tRgwYAAiIyOlsrFjx8raBAQEwGg0wmq1IisrC3/++Sdu3LjR5We3j6mpqYHdbkffvn1l5W1tbairqwMA+Pr6IicnBzt37oTFYoEQAiUlJcjNzYWPDxfbibwBkx8icomgoCAMGTLkg2169Ogh21epVOjs7AQA2O12ZGZm4pdffunSLyoqSnacT2E2mzFq1Cjcv38fxcXF0Ov1iI6O7tYYdrsdUVFROHfuXJe64OBg6e/58+dj/fr1qKysRGdnJxobG5Gbm/tJcROR6zH5ISKvkJSUhEOHDiEmJgZqtfNvTUOHDkVjYyOam5sREREB4M1t5P+WkJCAMWPGYMeOHdizZw+2bNnySTE+evQIarUaMTEx722n0+kwYcIEWK1WCCGQnp7e7USLiNyHa7BE5BLt7e149OiRbHv3Tq2PWbx4MVpaWpCdnY3q6mrU1dXhxIkTyM3NhcPheG+/yZMnQ6fTIScnB9evX4fNZkN+fj6ANytL7zKbzdiwYQOEEJg5c2a3zzE9PR3jxo2DwWDAyZMnUV9fjwsXLiAvLw9XrlyRtTWZTDh8+DBKS0t5oTORl2HyQ0QuUVFRgaioKNmWmprqdP9+/frBZrPB4XAgIyMDCQkJWLZsGYKDgz94rYyvry/Kyspgt9vxzTffwGw2S3d7BQQEyNpmZ2dDrVYjOzu7S50zVCoVjh8/ju+//x65ubmIi4vDnDlz0NDQIK06vTVr1iz4+/sjMDAQBoOh28ciIvdRCSGEp4MgInIlm82G1NRU3L59GzqdTiqvr6+HTqdDdXU1kpKSPjhGQUEBysrKcO3aNbfFee7cOaSlpaG1tVV2zRARuRev+SGiL15paSk0Gg1iY2Nx+/ZtLF26FN99952U+HR0dODZs2fIz8/Ht99++9HE562//voLGo0Gv/76KxYtWuTSmOPj43Hnzh2XjklEzuHKDxF98Xbt2oW1a9fi3r17CA0NRXp6OgoLC6Vb0t+usMTFxeHgwYNISEj46JgtLS3SPy4MCwtD7969XRpzQ0MDOjo6AACDBw/mbfBEnxGTHyIiIlIUftUgIiIiRWHyQ0RERIrC5IeIiIgUhckPERERKQqTHyIiIlIUJj9ERESkKEx+iIiISFGY/BAREZGi/A+cwmA9GFG9awAAAABJRU5ErkJggg==\n", - "text/plain": [ - "
" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Mean value of HOMO energies in training set: -5.74 eV\n", - "Mean value of HOMO energies in validation set: -5.72 eV\n", - "Mean value of HOMO energies in test set: -5.77 eV\n" - ] - } - ], + "outputs": [], "source": [ "plt.hist(Y_test, bins=20, density=False, alpha=0.5, facecolor='red', label='test set')\n", "plt.hist(Y_val, bins=20, density=False, alpha=0.5, facecolor='orange', label='validation set')\n", @@ -562,7 +359,7 @@ }, { "cell_type": "code", - "execution_count": 12, + "execution_count": null, "metadata": { "id": "mFuHLTSsXc_X" }, @@ -614,7 +411,7 @@ }, { "cell_type": "code", - "execution_count": 14, + "execution_count": null, "metadata": { "id": "-Hg5y-eaoWuw" }, @@ -751,7 +548,7 @@ }, { "cell_type": "code", - "execution_count": 17, + "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/", @@ -806,78 +603,7 @@ "id": "rQNzguz0oFUM", "outputId": "9f10889f-3123-4c4d-f9d6-9ec5c19c18c0" }, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "GPU available: False, used: False\n", - "TPU available: False, using: 0 TPU cores\n", - "IPU available: False, using: 0 IPUs\n", - "HPU available: False, using: 0 HPUs\n", - "\n", - " | Name | Type | Params\n", - "--------------------------------------\n", - "0 | conv1_1 | Conv2d | 200 \n", - "1 | conv1_2 | Conv2d | 3.6 K \n", - "2 | conv1_3 | Conv2d | 724 \n", - "3 | pool | MaxPool2d | 0 \n", - "4 | fc1 | Linear | 197 \n", - "--------------------------------------\n", - "4.7 K Trainable params\n", - "0 Non-trainable params\n", - "4.7 K Total params\n", - "0.019 Total estimated model params size (MB)\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Sanity Checking: 0it [00:00, ?it/s]torch.Size([500, 1, 29, 29])\n", - "torch.Size([1000, 1, 29, 29]) \n", - "Epoch 0: 67%|██████▋ | 16/24 [00:00<00:00, 31.42it/s, loss=9.1, v_num=2] \n", - "Validation: 0it [00:00, ?it/s]\u001b[A\n", - "Validation: 0%| | 0/8 [00:00" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], + "outputs": [], "source": [ "import matplotlib.pyplot as plt\n", "%matplotlib inline\n", @@ -1212,356 +911,7 @@ "id": "m7AEMR2M_cMi", "outputId": "2b4a0512-ede6-42c3-9a79-ad89aa673483" }, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "INFO: GPU available: False, used: False\n", - "INFO:lightning.pytorch.utilities.rank_zero:GPU available: False, used: False\n", - "INFO: TPU available: False, using: 0 TPU cores\n", - "INFO:lightning.pytorch.utilities.rank_zero:TPU available: False, using: 0 TPU cores\n", - "INFO: IPU available: False, using: 0 IPUs\n", - "INFO:lightning.pytorch.utilities.rank_zero:IPU available: False, using: 0 IPUs\n", - "INFO: HPU available: False, using: 0 HPUs\n", - "INFO:lightning.pytorch.utilities.rank_zero:HPU available: False, using: 0 HPUs\n", - "INFO: \n", - " | Name | Type | Params\n", - "--------------------------------------\n", - "0 | conv1_1 | Conv2d | 200 \n", - "1 | conv1_2 | Conv2d | 3.6 K \n", - "2 | conv1_3 | Conv2d | 724 \n", - "3 | pool | MaxPool2d | 0 \n", - "4 | fc1 | Linear | 591 \n", - "--------------------------------------\n", - "5.1 K Trainable params\n", - "0 Non-trainable params\n", - "5.1 K Total params\n", - "0.021 Total estimated model params size (MB)\n", - "INFO:lightning.pytorch.callbacks.model_summary:\n", - " | Name | Type | Params\n", - "--------------------------------------\n", - "0 | conv1_1 | Conv2d | 200 \n", - "1 | conv1_2 | Conv2d | 3.6 K \n", - "2 | conv1_3 | Conv2d | 724 \n", - "3 | pool | MaxPool2d | 0 \n", - "4 | fc1 | Linear | 591 \n", - "--------------------------------------\n", - "5.1 K Trainable params\n", - "0 Non-trainable params\n", - "5.1 K Total params\n", - "0.021 Total estimated model params size (MB)\n" - ] - }, - { - "data": { - "application/vnd.jupyter.widget-view+json": { - "model_id": "da19202d546040338698cd8021ad3d20", - "version_major": 2, - "version_minor": 0 - }, - "text/plain": [ - "Sanity Checking: | | 0/? [00:00" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], + "outputs": [], "source": [ "import matplotlib.pyplot as plt\n", "%matplotlib inline\n", @@ -1702,7 +1032,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.7.12" + "version": "3.9.18" }, "widgets": { "application/vnd.jupyter.widget-state+json": { @@ -5814,5 +5144,5 @@ } }, "nbformat": 4, - "nbformat_minor": 1 + "nbformat_minor": 4 } diff --git a/AI4Spec_Tutorial3.ipynb b/AI4Spec_Tutorial3.ipynb index 01fe11e..eccb327 100644 --- a/AI4Spec_Tutorial3.ipynb +++ b/AI4Spec_Tutorial3.ipynb @@ -36,7 +36,7 @@ }, { "cell_type": "code", - "execution_count": 1, + "execution_count": null, "metadata": { "id": "qdphsPPRwwNF" }, @@ -66,7 +66,7 @@ }, { "cell_type": "code", - "execution_count": 2, + "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" @@ -74,36 +74,7 @@ "id": "jTZ_1hpqLBK5", "outputId": "86bd19b3-a735-4334-cbd0-e5416e7bc1db" }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "--2024-03-04 21:47:36-- https://zenodo.org/records/10069732/files/coulomb_7000.npz\n", - "Resolving zenodo.org (zenodo.org)... 188.184.103.159, 188.184.98.238, 188.185.79.172, ...\n", - "Connecting to zenodo.org (zenodo.org)|188.184.103.159|:443... connected.\n", - "HTTP request sent, awaiting response... 200 OK\n", - "Length: 47096264 (45M) [application/octet-stream]\n", - "Saving to: ‘coulomb_7000.npz.3’\n", - "\n", - "coulomb_7000.npz.3 100%[===================>] 44.91M 43.4MB/s in 1.0s \n", - "\n", - "2024-03-04 21:47:38 (43.4 MB/s) - ‘coulomb_7000.npz.3’ saved [47096264/47096264]\n", - "\n", - "--2024-03-04 21:47:38-- https://zenodo.org/records/10069732/files/spectra_7000.npz\n", - "Resolving zenodo.org (zenodo.org)... 188.184.98.238, 188.185.79.172, 188.184.103.159, ...\n", - "Connecting to zenodo.org (zenodo.org)|188.184.98.238|:443... connected.\n", - "HTTP request sent, awaiting response... 200 OK\n", - "Length: 16800264 (16M) [application/octet-stream]\n", - "Saving to: ‘spectra_7000.npz.1’\n", - "\n", - "spectra_7000.npz.1 100%[===================>] 16.02M 27.7MB/s in 0.6s \n", - "\n", - "2024-03-04 21:47:39 (27.7 MB/s) - ‘spectra_7000.npz.1’ saved [16800264/16800264]\n", - "\n" - ] - } - ], + "outputs": [], "source": [ "!wget https://zenodo.org/records/10069732/files/coulomb_7000.npz\n", "!wget https://zenodo.org/records/10069732/files/spectra_7000.npz" @@ -111,7 +82,7 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": null, "metadata": { "id": "6tTcc8Mtwrmd" }, @@ -140,7 +111,7 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" @@ -148,17 +119,7 @@ "id": "aHF8AUmF54MI", "outputId": "3517a7da-9b21-4070-e13f-8d9f99cc19e3" }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Number of molecules: 7000\n", - "(7000, 29, 29)\n", - "(7000, 300)\n" - ] - } - ], + "outputs": [], "source": [ "print(\"Number of molecules:\", len(y))\n", "print(x.shape)\n", @@ -176,7 +137,7 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" @@ -184,89 +145,7 @@ "id": "pst07BLjt3WC", "outputId": "1d32167a-bb45-4a69-e39a-fcdf89b886e4" }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "[3.04832655e-50 3.06806541e-49 3.01570308e-48 2.89489880e-47\n", - " 2.71393245e-46 2.48476615e-45 2.22173804e-44 1.94008617e-43\n", - " 1.65451241e-42 1.37797038e-41 1.12080633e-40 8.90311753e-40\n", - " 6.90676183e-39 5.23272240e-38 3.87170047e-37 2.79767105e-36\n", - " 1.97429655e-35 1.36065796e-34 9.15812126e-34 6.01983591e-33\n", - " 3.86441500e-32 2.42272269e-31 1.48335295e-30 8.86964285e-30\n", - " 5.17950923e-29 2.95387378e-28 1.64519016e-27 8.94872406e-27\n", - " 4.75364755e-26 2.46611708e-25 1.24945682e-24 6.18229421e-24\n", - " 2.98743827e-23 1.40983754e-22 6.49770612e-22 2.92463671e-21\n", - " 1.28559645e-20 5.51897315e-20 2.31383714e-19 9.47388692e-19\n", - " 3.78830135e-18 1.47938690e-17 5.64208946e-17 2.10145037e-16\n", - " 7.64397590e-16 2.71544189e-15 9.42069175e-15 3.19187739e-14\n", - " 1.05616263e-13 3.41300286e-13 1.07711944e-12 3.31980474e-12\n", - " 9.99269925e-12 2.93747957e-11 8.43313118e-11 2.36442237e-10\n", - " 6.47416495e-10 1.73127204e-09 4.52137115e-09 1.15318456e-08\n", - " 2.87244641e-08 6.98763623e-08 1.66010220e-07 3.85182633e-07\n", - " 8.72825255e-07 1.93160511e-06 4.17485972e-06 8.81252655e-06\n", - " 1.81675787e-05 3.65793027e-05 7.19316555e-05 1.38151756e-04\n", - " 2.59149940e-04 4.74801636e-04 8.49668367e-04 1.48516488e-03\n", - " 2.53572527e-03 4.22911400e-03 6.89028598e-03 1.09670833e-02\n", - " 1.70546068e-02 2.59134880e-02 3.84758353e-02 5.58317942e-02\n", - " 7.91899922e-02 1.09807092e-01 1.48885504e-01 1.97443802e-01\n", - " 2.56170828e-01 3.25280562e-01 4.04388994e-01 4.92434925e-01\n", - " 5.87662791e-01 6.87677324e-01 7.89568351e-01 8.90091688e-01\n", - " 9.85881892e-01 1.07366742e+00 1.15046005e+00 1.21369831e+00\n", - " 1.26133673e+00 1.29188598e+00 1.30441906e+00 1.29856294e+00\n", - " 1.27449226e+00 1.23293286e+00 1.17517169e+00 1.10305917e+00\n", - " 1.01898532e+00 9.25812377e-01 8.26755415e-01 7.25214793e-01\n", - " 6.24577682e-01 5.28015551e-01 4.38308338e-01 3.57722671e-01\n", - " 2.87962132e-01 2.30194342e-01 1.85145792e-01 1.53243404e-01\n", - " 1.34773990e-01 1.30029832e-01 1.39410665e-01 1.63458596e-01\n", - " 2.02812115e-01 2.58077177e-01 3.29626272e-01 4.17349180e-01\n", - " 5.20390261e-01 6.36914793e-01 7.63949362e-01 8.97337122e-01\n", - " 1.03183720e+00 1.16137946e+00 1.27946313e+00 1.37966429e+00\n", - " 1.45619670e+00 1.50445740e+00 1.52148592e+00 1.50627521e+00\n", - " 1.45989189e+00 1.38539118e+00 1.28754114e+00 1.17239846e+00\n", - " 1.04679665e+00 9.17816086e-01 7.92301269e-01 6.76476230e-01\n", - " 5.75687297e-01 4.94278128e-01 4.35579837e-01 4.01982955e-01\n", - " 3.95050348e-01 4.15631312e-01 4.63945630e-01 5.39619629e-01\n", - " 6.41671100e-01 7.68453295e-01 9.17577916e-01 1.08584207e+00\n", - " 1.26918468e+00 1.46269456e+00 1.66068688e+00 1.85685766e+00\n", - " 2.04451835e+00 2.21690461e+00 2.36754512e+00 2.49066792e+00\n", - " 2.58161409e+00 2.63722198e+00 2.65614236e+00 2.63904499e+00\n", - " 2.58868297e+00 2.50979162e+00 2.40881264e+00 2.29345224e+00\n", - " 2.17209955e+00 2.05314985e+00 1.94429207e+00 1.85183097e+00\n", - " 1.78011868e+00 1.73116656e+00 1.70449494e+00 1.69725495e+00\n", - " 1.70462551e+00 1.72045175e+00 1.73805563e+00 1.75111926e+00\n", - " 1.75452489e+00 1.74503446e+00 1.72170946e+00 1.68600602e+00\n", - " 1.64152600e+00 1.59345511e+00 1.54776583e+00 1.51029852e+00\n", - " 1.48585265e+00 1.47741924e+00 1.48566489e+00 1.50874117e+00\n", - " 1.54244571e+00 1.58071046e+00 1.61634601e+00 1.64193563e+00\n", - " 1.65075386e+00 1.63758480e+00 1.59933509e+00 1.53537073e+00\n", - " 1.44755098e+00 1.33997717e+00 1.21851288e+00 1.09015746e+00\n", - " 9.62364843e-01 8.42392979e-01 7.36750948e-01 6.50784387e-01\n", - " 5.88413430e-01 5.52015072e-01 5.42427659e-01 5.59049749e-01\n", - " 6.00007200e-01 6.62367853e-01 7.42389080e-01 8.35786963e-01\n", - " 9.38015891e-01 1.04454457e+00 1.15111073e+00 1.25393486e+00\n", - " 1.34987480e+00 1.43650903e+00 1.51214600e+00 1.57576779e+00\n", - " 1.62692648e+00 1.66561768e+00 1.69215693e+00 1.70708023e+00\n", - " 1.71108118e+00 1.70498582e+00 1.68975514e+00 1.66649687e+00\n", - " 1.63646428e+00 1.60102216e+00 1.56156833e+00 1.51941175e+00\n", - " 1.47562245e+00 1.43088142e+00 1.38536501e+00 1.33869787e+00\n", - " 1.28999757e+00 1.23801709e+00 1.18136972e+00 1.11880143e+00\n", - " 1.04946289e+00 9.73130335e-01 8.90333266e-01 8.02364765e-01\n", - " 7.11173257e-01 6.19156982e-01 5.28899436e-01 4.42891995e-01\n", - " 3.63287987e-01 2.91722086e-01 2.29213393e-01 1.76153932e-01\n", - " 1.32370091e-01 9.72352617e-02 6.98083893e-02 4.89748052e-02\n", - " 3.35710311e-02 2.24822835e-02 1.47084137e-02 9.39969931e-03\n", - " 5.86764000e-03 3.57764687e-03 2.13060362e-03 1.23927728e-03\n", - " 7.04022632e-04 3.90616401e-04 2.11667822e-04 1.12020009e-04\n", - " 5.78987926e-05 2.92263096e-05 1.44081090e-05 6.93692371e-06\n", - " 3.26176376e-06 1.49783072e-06 6.71733203e-07 2.94207757e-07\n", - " 1.25844473e-07 5.25698216e-08 2.14467199e-08 8.54490087e-09\n", - " 3.32487066e-09 1.26346701e-09 4.68893659e-10 1.69944071e-10\n", - " 6.01532096e-11 2.07937425e-11 7.01984527e-12 2.31442654e-12]\n" - ] - } - ], + "outputs": [], "source": [ "print(y[500,:])" ] @@ -282,7 +161,7 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/", @@ -291,18 +170,7 @@ "id": "NIM-5LzW5IoS", "outputId": "6e5bdeb5-76a0-4bc9-f587-6cb0c717edb5" }, - "outputs": [ - { - "data": { - "image/png": "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\n", - "text/plain": [ - "
" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], + "outputs": [], "source": [ "# first we generate the energy x-axis in the range [-30, 0]eV\n", "x_ticks = np.linspace(0,-30, 300)\n", @@ -329,7 +197,7 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": null, "metadata": { "id": "wmnl8ZzAwrmm" }, @@ -365,7 +233,7 @@ }, { "cell_type": "code", - "execution_count": 8, + "execution_count": null, "metadata": { "id": "8cXiavHCuDVM" }, @@ -392,7 +260,7 @@ }, { "cell_type": "code", - "execution_count": 9, + "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/", @@ -401,18 +269,7 @@ "id": "t-NggJYtXGGs", "outputId": "301254b3-550f-4247-9194-961cbe50087f" }, - "outputs": [ - { - "data": { - "image/png": "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\n", - "text/plain": [ - "
" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], + "outputs": [], "source": [ "plot = plt.figure(1)\n", "plot_mean_and_1std(plot, Y_train, color=\"green\", label=\"train\")\n", @@ -443,20 +300,11 @@ }, { "cell_type": "code", - "execution_count": 10, + "execution_count": null, "metadata": { "id": "7GUgjaEUzqkx" }, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "/PUHTI_TYKKY_VU7CbXh/miniconda/envs/env1/lib/python3.7/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n", - " from .autonotebook import tqdm as notebook_tqdm\n" - ] - } - ], + "outputs": [], "source": [ "from torch import nn\n", "from torch.optim import Adam\n", @@ -500,7 +348,7 @@ }, { "cell_type": "code", - "execution_count": 11, + "execution_count": null, "metadata": { "id": "mFuHLTSsXc_X" }, @@ -598,7 +446,7 @@ }, { "cell_type": "code", - "execution_count": 13, + "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/", @@ -852,289 +700,6 @@ "outputId": "dc4c5416-36da-4c1d-db18-8bdea7326864" }, "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "GPU available: True (cuda), used: False\n", - "TPU available: False, using: 0 TPU cores\n", - "IPU available: False, using: 0 IPUs\n", - "HPU available: False, using: 0 HPUs\n", - "\n", - " | Name | Type | Params\n", - "--------------------------------------\n", - "0 | conv1_1 | Conv2d | 200 \n", - "1 | conv1_2 | Conv2d | 3.6 K \n", - "2 | conv1_3 | Conv2d | 724 \n", - "3 | pool | MaxPool2d | 0 \n", - "4 | fc1 | Linear | 59.1 K\n", - "--------------------------------------\n", - "63.6 K Trainable params\n", - "0 Non-trainable params\n", - "63.6 K Total params\n", - "0.255 Total estimated model params size (MB)\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 0: 80%|████████ | 32/40 [00:01<00:00, 30.22it/s, loss=0.275, v_num=6]\n", - "Validation: 0it [00:00, ?it/s]\u001b[A\n", - "Validation: 0%| | 0/8 [00:00)\n" - ] - } - ], + "outputs": [], "source": [ "X_test = torch.Tensor(X_test).reshape(-1, 29, 29).unsqueeze(1).float()\n", "Y_test = torch.Tensor(Y_test).float()\n", @@ -1200,7 +757,7 @@ }, { "cell_type": "code", - "execution_count": 15, + "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" @@ -1208,15 +765,7 @@ "id": "q76RVoRjtNnc", "outputId": "3f8051f5-4526-40bb-fceb-a8858a47ff24" }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "tensor(0.1033, grad_fn=)\n" - ] - } - ], + "outputs": [], "source": [ "X_train_subset = torch.Tensor(X_train)[[500,1500],:].reshape(-1, 29, 29).unsqueeze(1).float()\n", "Y_train_subset = torch.Tensor(Y_train)[[500,1500],:].float()\n", @@ -1237,7 +786,7 @@ }, { "cell_type": "code", - "execution_count": 16, + "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/", @@ -1246,18 +795,7 @@ "id": "DrTsiyuDBjap", "outputId": "fa29da0b-28f4-4453-e5ac-3f7e86b6181b" }, - "outputs": [ - { - "data": { - "image/png": "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\n", - "text/plain": [ - "
" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], + "outputs": [], "source": [ "x_ticks = np.linspace(0,-30, 300)\n", "\n", @@ -1287,7 +825,7 @@ }, { "cell_type": "code", - "execution_count": 17, + "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/", @@ -1296,28 +834,7 @@ "id": "IZMqh36xGEmF", "outputId": "7a969154-e43e-455d-e68a-e105323b3497" }, - "outputs": [ - { - "data": { - "text/plain": [ - "" - ] - }, - "execution_count": 17, - "metadata": {}, - "output_type": "execute_result" - }, - { - "data": { - "image/png": "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\n", - "text/plain": [ - "
" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], + "outputs": [], "source": [ "plt.plot(x_ticks, Y_test[50,:], color=\"black\", label=\"Reference\")\n", "plt.plot(x_ticks, Y_pred_test[50,:].detach().numpy(), color=\"red\", label=\"Prediction\")\n", @@ -1356,7 +873,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.7.12" + "version": "3.9.18" }, "widgets": { "application/vnd.jupyter.widget-state+json": { @@ -8888,5 +8405,5 @@ } }, "nbformat": 4, - "nbformat_minor": 1 + "nbformat_minor": 4 }