Morten Hjorth-Jensen
1064 lines
65 KiB
HTML
1064 lines
65 KiB
HTML
|
||
<!DOCTYPE html>
|
||
|
||
<html>
|
||
<head>
|
||
<meta charset="utf-8" />
|
||
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
||
<title>Project 1 on Machine Learning, deadline October 7 (midnight), 2024 — Applied Data Analysis and Machine Learning</title>
|
||
|
||
<link href="_static/css/theme.css" rel="stylesheet">
|
||
<link href="_static/css/index.ff1ffe594081f20da1ef19478df9384b.css" rel="stylesheet">
|
||
|
||
|
||
<link rel="stylesheet"
|
||
href="_static/vendor/fontawesome/5.13.0/css/all.min.css">
|
||
<link rel="preload" as="font" type="font/woff2" crossorigin
|
||
href="_static/vendor/fontawesome/5.13.0/webfonts/fa-solid-900.woff2">
|
||
<link rel="preload" as="font" type="font/woff2" crossorigin
|
||
href="_static/vendor/fontawesome/5.13.0/webfonts/fa-brands-400.woff2">
|
||
|
||
|
||
|
||
|
||
|
||
<link rel="stylesheet" type="text/css" href="_static/pygments.css" />
|
||
<link rel="stylesheet" type="text/css" href="_static/sphinx-book-theme.css?digest=c3fdc42140077d1ad13ad2f1588a4309" />
|
||
<link rel="stylesheet" type="text/css" href="_static/togglebutton.css" />
|
||
<link rel="stylesheet" type="text/css" href="_static/copybutton.css" />
|
||
<link rel="stylesheet" type="text/css" href="_static/mystnb.css" />
|
||
<link rel="stylesheet" type="text/css" href="_static/sphinx-thebe.css" />
|
||
<link rel="stylesheet" type="text/css" href="_static/panels-main.c949a650a448cc0ae9fd3441c0e17fb0.css" />
|
||
<link rel="stylesheet" type="text/css" href="_static/panels-variables.06eb56fa6e07937060861dad626602ad.css" />
|
||
|
||
<link rel="preload" as="script" href="_static/js/index.be7d3bbb2ef33a8344ce.js">
|
||
|
||
<script data-url_root="./" id="documentation_options" src="_static/documentation_options.js"></script>
|
||
<script src="_static/jquery.js"></script>
|
||
<script src="_static/underscore.js"></script>
|
||
<script src="_static/doctools.js"></script>
|
||
<script src="_static/clipboard.min.js"></script>
|
||
<script src="_static/copybutton.js"></script>
|
||
<script>let toggleHintShow = 'Click to show';</script>
|
||
<script>let toggleHintHide = 'Click to hide';</script>
|
||
<script>let toggleOpenOnPrint = 'true';</script>
|
||
<script src="_static/togglebutton.js"></script>
|
||
<script>var togglebuttonSelector = '.toggle, .admonition.dropdown, .tag_hide_input div.cell_input, .tag_hide-input div.cell_input, .tag_hide_output div.cell_output, .tag_hide-output div.cell_output, .tag_hide_cell.cell, .tag_hide-cell.cell';</script>
|
||
<script src="_static/sphinx-book-theme.d59cb220de22ca1c485ebbdc042f0030.js"></script>
|
||
<script>const THEBE_JS_URL = "https://unpkg.com/thebe@0.8.2/lib/index.js"
|
||
const thebe_selector = ".thebe,.cell"
|
||
const thebe_selector_input = "pre"
|
||
const thebe_selector_output = ".output, .cell_output"
|
||
</script>
|
||
<script async="async" src="_static/sphinx-thebe.js"></script>
|
||
<script>window.MathJax = {"options": {"processHtmlClass": "tex2jax_process|mathjax_process|math|output_area"}}</script>
|
||
<script defer="defer" src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js"></script>
|
||
<link rel="index" title="Index" href="genindex.html" />
|
||
<link rel="search" title="Search" href="search.html" />
|
||
<link rel="prev" title="Exercises week 38" href="exercisesweek38.html" />
|
||
<meta name="viewport" content="width=device-width, initial-scale=1" />
|
||
<meta name="docsearch:language" content="None">
|
||
|
||
|
||
<!-- Google Analytics -->
|
||
|
||
</head>
|
||
<body data-spy="scroll" data-target="#bd-toc-nav" data-offset="80">
|
||
|
||
<div class="container-fluid" id="banner"></div>
|
||
|
||
|
||
|
||
<div class="container-xl">
|
||
<div class="row">
|
||
|
||
<div class="col-12 col-md-3 bd-sidebar site-navigation show" id="site-navigation">
|
||
|
||
<div class="navbar-brand-box">
|
||
<a class="navbar-brand text-wrap" href="index.html">
|
||
|
||
<!-- `logo` is deprecated in Sphinx 4.0, so remove this when we stop supporting 3 -->
|
||
|
||
|
||
|
||
<img src="_static/logo.png" class="logo" alt="logo">
|
||
|
||
|
||
<h1 class="site-logo" id="site-title">Applied Data Analysis and Machine Learning</h1>
|
||
|
||
</a>
|
||
</div><form class="bd-search d-flex align-items-center" action="search.html" method="get">
|
||
<i class="icon fas fa-search"></i>
|
||
<input type="search" class="form-control" name="q" id="search-input" placeholder="Search this book..." aria-label="Search this book..." autocomplete="off" >
|
||
</form><nav class="bd-links" id="bd-docs-nav" aria-label="Main">
|
||
<div class="bd-toc-item active">
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1">
|
||
<a class="reference internal" href="intro.html">
|
||
Applied Data Analysis and Machine Learning
|
||
</a>
|
||
</li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading">
|
||
<span class="caption-text">
|
||
About the course
|
||
</span>
|
||
</p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1">
|
||
<a class="reference internal" href="schedule.html">
|
||
Teaching schedule with links to material
|
||
</a>
|
||
</li>
|
||
<li class="toctree-l1">
|
||
<a class="reference internal" href="teachers.html">
|
||
Teachers and Grading
|
||
</a>
|
||
</li>
|
||
<li class="toctree-l1">
|
||
<a class="reference internal" href="textbooks.html">
|
||
Textbooks
|
||
</a>
|
||
</li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading">
|
||
<span class="caption-text">
|
||
Review of Statistics with Resampling Techniques and Linear Algebra
|
||
</span>
|
||
</p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1">
|
||
<a class="reference internal" href="statistics.html">
|
||
1. Elements of Probability Theory and Statistical Data Analysis
|
||
</a>
|
||
</li>
|
||
<li class="toctree-l1">
|
||
<a class="reference internal" href="linalg.html">
|
||
2. Linear Algebra, Handling of Arrays and more Python Features
|
||
</a>
|
||
</li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading">
|
||
<span class="caption-text">
|
||
From Regression to Support Vector Machines
|
||
</span>
|
||
</p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1">
|
||
<a class="reference internal" href="chapter1.html">
|
||
3. Linear Regression
|
||
</a>
|
||
</li>
|
||
<li class="toctree-l1">
|
||
<a class="reference internal" href="chapter2.html">
|
||
4. Ridge and Lasso Regression
|
||
</a>
|
||
</li>
|
||
<li class="toctree-l1">
|
||
<a class="reference internal" href="chapter3.html">
|
||
5. Resampling Methods
|
||
</a>
|
||
</li>
|
||
<li class="toctree-l1">
|
||
<a class="reference internal" href="chapter4.html">
|
||
6. Logistic Regression
|
||
</a>
|
||
</li>
|
||
<li class="toctree-l1">
|
||
<a class="reference internal" href="chapteroptimization.html">
|
||
7. Optimization, the central part of any Machine Learning algortithm
|
||
</a>
|
||
</li>
|
||
<li class="toctree-l1">
|
||
<a class="reference internal" href="chapter5.html">
|
||
8. Support Vector Machines, overarching aims
|
||
</a>
|
||
</li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading">
|
||
<span class="caption-text">
|
||
Decision Trees, Ensemble Methods and Boosting
|
||
</span>
|
||
</p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1">
|
||
<a class="reference internal" href="chapter6.html">
|
||
9. Decision trees, overarching aims
|
||
</a>
|
||
</li>
|
||
<li class="toctree-l1">
|
||
<a class="reference internal" href="chapter7.html">
|
||
10. Ensemble Methods: From a Single Tree to Many Trees and Extreme Boosting, Meet the Jungle of Methods
|
||
</a>
|
||
</li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading">
|
||
<span class="caption-text">
|
||
Dimensionality Reduction
|
||
</span>
|
||
</p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1">
|
||
<a class="reference internal" href="chapter8.html">
|
||
11. Basic ideas of the Principal Component Analysis (PCA)
|
||
</a>
|
||
</li>
|
||
<li class="toctree-l1">
|
||
<a class="reference internal" href="clustering.html">
|
||
12. Clustering and Unsupervised Learning
|
||
</a>
|
||
</li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading">
|
||
<span class="caption-text">
|
||
Deep Learning Methods
|
||
</span>
|
||
</p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1">
|
||
<a class="reference internal" href="chapter9.html">
|
||
13. Neural networks
|
||
</a>
|
||
</li>
|
||
<li class="toctree-l1">
|
||
<a class="reference internal" href="chapter10.html">
|
||
14. Building a Feed Forward Neural Network
|
||
</a>
|
||
</li>
|
||
<li class="toctree-l1">
|
||
<a class="reference internal" href="chapter11.html">
|
||
15. Solving Differential Equations with Deep Learning
|
||
</a>
|
||
</li>
|
||
<li class="toctree-l1">
|
||
<a class="reference internal" href="chapter12.html">
|
||
16. Convolutional Neural Networks
|
||
</a>
|
||
</li>
|
||
<li class="toctree-l1">
|
||
<a class="reference internal" href="chapter13.html">
|
||
17. Recurrent neural networks: Overarching view
|
||
</a>
|
||
</li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading">
|
||
<span class="caption-text">
|
||
Weekly material, notes and exercises
|
||
</span>
|
||
</p>
|
||
<ul class="nav bd-sidenav">
|
||
<li class="toctree-l1">
|
||
<a class="reference internal" href="exercisesweek34.html">
|
||
Exercises week 34
|
||
</a>
|
||
</li>
|
||
<li class="toctree-l1">
|
||
<a class="reference internal" href="week34.html">
|
||
Week 34: Introduction to the course, Logistics and Practicalities
|
||
</a>
|
||
</li>
|
||
<li class="toctree-l1">
|
||
<a class="reference internal" href="exercisesweek35.html">
|
||
Exercises week 35
|
||
</a>
|
||
</li>
|
||
<li class="toctree-l1">
|
||
<a class="reference internal" href="week35.html">
|
||
Week 35: From Ordinary Linear Regression to Ridge and Lasso Regression
|
||
</a>
|
||
</li>
|
||
<li class="toctree-l1">
|
||
<a class="reference internal" href="exercisesweek36.html">
|
||
Exercises week 36
|
||
</a>
|
||
</li>
|
||
<li class="toctree-l1">
|
||
<a class="reference internal" href="week36.html">
|
||
Week 36: Linear Regression and Statistical interpretations
|
||
</a>
|
||
</li>
|
||
<li class="toctree-l1">
|
||
<a class="reference internal" href="exercisesweek37.html">
|
||
Exercises week 37
|
||
</a>
|
||
</li>
|
||
<li class="toctree-l1">
|
||
<a class="reference internal" href="week37.html">
|
||
Week 37: Statistical interpretations and Resampling Methods
|
||
</a>
|
||
</li>
|
||
<li class="toctree-l1">
|
||
<a class="reference internal" href="exercisesweek38.html">
|
||
Exercises week 38
|
||
</a>
|
||
</li>
|
||
</ul>
|
||
<p aria-level="2" class="caption" role="heading">
|
||
<span class="caption-text">
|
||
Projects
|
||
</span>
|
||
</p>
|
||
<ul class="current nav bd-sidenav">
|
||
<li class="toctree-l1 current active">
|
||
<a class="current reference internal" href="#">
|
||
Project 1 on Machine Learning, deadline October 7 (midnight), 2024
|
||
</a>
|
||
</li>
|
||
</ul>
|
||
|
||
</div>
|
||
</nav> <!-- To handle the deprecated key -->
|
||
|
||
<div class="navbar_extra_footer">
|
||
Powered by <a href="https://jupyterbook.org">Jupyter Book</a>
|
||
</div>
|
||
|
||
</div>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<main class="col py-md-3 pl-md-4 bd-content overflow-auto" role="main">
|
||
|
||
<div class="topbar container-xl fixed-top">
|
||
<div class="topbar-contents row">
|
||
<div class="col-12 col-md-3 bd-topbar-whitespace site-navigation show"></div>
|
||
<div class="col pl-md-4 topbar-main">
|
||
|
||
<button id="navbar-toggler" class="navbar-toggler ml-0" type="button" data-toggle="collapse"
|
||
data-toggle="tooltip" data-placement="bottom" data-target=".site-navigation" aria-controls="navbar-menu"
|
||
aria-expanded="true" aria-label="Toggle navigation" aria-controls="site-navigation"
|
||
title="Toggle navigation" data-toggle="tooltip" data-placement="left">
|
||
<i class="fas fa-bars"></i>
|
||
<i class="fas fa-arrow-left"></i>
|
||
<i class="fas fa-arrow-up"></i>
|
||
</button>
|
||
|
||
|
||
<div class="dropdown-buttons-trigger">
|
||
<button id="dropdown-buttons-trigger" class="btn btn-secondary topbarbtn" aria-label="Download this page"><i
|
||
class="fas fa-download"></i></button>
|
||
|
||
<div class="dropdown-buttons">
|
||
<!-- ipynb file if we had a myst markdown file -->
|
||
|
||
<!-- Download raw file -->
|
||
<a class="dropdown-buttons" href="_sources/project1.ipynb"><button type="button"
|
||
class="btn btn-secondary topbarbtn" title="Download source file" data-toggle="tooltip"
|
||
data-placement="left">.ipynb</button></a>
|
||
<!-- Download PDF via print -->
|
||
<button type="button" id="download-print" class="btn btn-secondary topbarbtn" title="Print to PDF"
|
||
onclick="printPdf(this)" data-toggle="tooltip" data-placement="left">.pdf</button>
|
||
</div>
|
||
</div>
|
||
|
||
<!-- Source interaction buttons -->
|
||
|
||
<!-- Full screen (wrap in <a> to have style consistency -->
|
||
|
||
<a class="full-screen-button"><button type="button" class="btn btn-secondary topbarbtn" data-toggle="tooltip"
|
||
data-placement="bottom" onclick="toggleFullScreen()" aria-label="Fullscreen mode"
|
||
title="Fullscreen mode"><i
|
||
class="fas fa-expand"></i></button></a>
|
||
|
||
<!-- Launch buttons -->
|
||
|
||
</div>
|
||
|
||
<!-- Table of contents -->
|
||
<div class="d-none d-md-block col-md-2 bd-toc show noprint">
|
||
|
||
<div class="tocsection onthispage pt-5 pb-3">
|
||
<i class="fas fa-list"></i> Contents
|
||
</div>
|
||
<nav id="bd-toc-nav" aria-label="Page">
|
||
<ul class="visible nav section-nav flex-column">
|
||
<li class="toc-h2 nav-item toc-entry">
|
||
<a class="reference internal nav-link" href="#preamble-note-on-writing-reports-using-reference-material-ai-and-other-tools">
|
||
Preamble: Note on writing reports, using reference material, AI and other tools
|
||
</a>
|
||
</li>
|
||
<li class="toc-h2 nav-item toc-entry">
|
||
<a class="reference internal nav-link" href="#regression-analysis-and-resampling-methods">
|
||
Regression analysis and resampling methods
|
||
</a>
|
||
<ul class="nav section-nav flex-column">
|
||
<li class="toc-h3 nav-item toc-entry">
|
||
<a class="reference internal nav-link" href="#description-of-two-dimensional-function">
|
||
Description of two-dimensional function
|
||
</a>
|
||
</li>
|
||
<li class="toc-h3 nav-item toc-entry">
|
||
<a class="reference internal nav-link" href="#part-a-ordinary-least-square-ols-on-the-franke-function">
|
||
Part a) : Ordinary Least Square (OLS) on the Franke function
|
||
</a>
|
||
</li>
|
||
<li class="toc-h3 nav-item toc-entry">
|
||
<a class="reference internal nav-link" href="#part-b-adding-ridge-regression-for-the-franke-function">
|
||
Part b): Adding Ridge regression for the Franke function
|
||
</a>
|
||
</li>
|
||
<li class="toc-h3 nav-item toc-entry">
|
||
<a class="reference internal nav-link" href="#part-c-adding-lasso-for-the-franke-function">
|
||
Part c): Adding Lasso for the Franke function
|
||
</a>
|
||
</li>
|
||
<li class="toc-h3 nav-item toc-entry">
|
||
<a class="reference internal nav-link" href="#part-d-paper-and-pencil-part">
|
||
Part d): Paper and pencil part
|
||
</a>
|
||
</li>
|
||
<li class="toc-h3 nav-item toc-entry">
|
||
<a class="reference internal nav-link" href="#part-e-bias-variance-trade-off-and-resampling-techniques">
|
||
Part e): Bias-variance trade-off and resampling techniques
|
||
</a>
|
||
</li>
|
||
<li class="toc-h3 nav-item toc-entry">
|
||
<a class="reference internal nav-link" href="#part-f-cross-validation-as-resampling-techniques-adding-more-complexity">
|
||
Part f): Cross-validation as resampling techniques, adding more complexity
|
||
</a>
|
||
</li>
|
||
<li class="toc-h3 nav-item toc-entry">
|
||
<a class="reference internal nav-link" href="#part-g-analysis-of-real-data">
|
||
Part g): Analysis of real data
|
||
</a>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
<li class="toc-h2 nav-item toc-entry">
|
||
<a class="reference internal nav-link" href="#background-literature">
|
||
Background literature
|
||
</a>
|
||
</li>
|
||
<li class="toc-h2 nav-item toc-entry">
|
||
<a class="reference internal nav-link" href="#introduction-to-numerical-projects">
|
||
Introduction to numerical projects
|
||
</a>
|
||
</li>
|
||
<li class="toc-h2 nav-item toc-entry">
|
||
<a class="reference internal nav-link" href="#format-for-electronic-delivery-of-report-and-programs">
|
||
Format for electronic delivery of report and programs
|
||
</a>
|
||
</li>
|
||
<li class="toc-h2 nav-item toc-entry">
|
||
<a class="reference internal nav-link" href="#software-and-needed-installations">
|
||
Software and needed installations
|
||
</a>
|
||
</li>
|
||
</ul>
|
||
|
||
</nav>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
<div id="main-content" class="row">
|
||
<div class="col-12 col-md-9 pl-md-3 pr-md-0">
|
||
<!-- Table of contents that is only displayed when printing the page -->
|
||
<div id="jb-print-docs-body" class="onlyprint">
|
||
<h1>Project 1 on Machine Learning, deadline October 7 (midnight), 2024</h1>
|
||
<!-- Table of contents -->
|
||
<div id="print-main-content">
|
||
<div id="jb-print-toc">
|
||
|
||
<div>
|
||
<h2> Contents </h2>
|
||
</div>
|
||
<nav aria-label="Page">
|
||
<ul class="visible nav section-nav flex-column">
|
||
<li class="toc-h2 nav-item toc-entry">
|
||
<a class="reference internal nav-link" href="#preamble-note-on-writing-reports-using-reference-material-ai-and-other-tools">
|
||
Preamble: Note on writing reports, using reference material, AI and other tools
|
||
</a>
|
||
</li>
|
||
<li class="toc-h2 nav-item toc-entry">
|
||
<a class="reference internal nav-link" href="#regression-analysis-and-resampling-methods">
|
||
Regression analysis and resampling methods
|
||
</a>
|
||
<ul class="nav section-nav flex-column">
|
||
<li class="toc-h3 nav-item toc-entry">
|
||
<a class="reference internal nav-link" href="#description-of-two-dimensional-function">
|
||
Description of two-dimensional function
|
||
</a>
|
||
</li>
|
||
<li class="toc-h3 nav-item toc-entry">
|
||
<a class="reference internal nav-link" href="#part-a-ordinary-least-square-ols-on-the-franke-function">
|
||
Part a) : Ordinary Least Square (OLS) on the Franke function
|
||
</a>
|
||
</li>
|
||
<li class="toc-h3 nav-item toc-entry">
|
||
<a class="reference internal nav-link" href="#part-b-adding-ridge-regression-for-the-franke-function">
|
||
Part b): Adding Ridge regression for the Franke function
|
||
</a>
|
||
</li>
|
||
<li class="toc-h3 nav-item toc-entry">
|
||
<a class="reference internal nav-link" href="#part-c-adding-lasso-for-the-franke-function">
|
||
Part c): Adding Lasso for the Franke function
|
||
</a>
|
||
</li>
|
||
<li class="toc-h3 nav-item toc-entry">
|
||
<a class="reference internal nav-link" href="#part-d-paper-and-pencil-part">
|
||
Part d): Paper and pencil part
|
||
</a>
|
||
</li>
|
||
<li class="toc-h3 nav-item toc-entry">
|
||
<a class="reference internal nav-link" href="#part-e-bias-variance-trade-off-and-resampling-techniques">
|
||
Part e): Bias-variance trade-off and resampling techniques
|
||
</a>
|
||
</li>
|
||
<li class="toc-h3 nav-item toc-entry">
|
||
<a class="reference internal nav-link" href="#part-f-cross-validation-as-resampling-techniques-adding-more-complexity">
|
||
Part f): Cross-validation as resampling techniques, adding more complexity
|
||
</a>
|
||
</li>
|
||
<li class="toc-h3 nav-item toc-entry">
|
||
<a class="reference internal nav-link" href="#part-g-analysis-of-real-data">
|
||
Part g): Analysis of real data
|
||
</a>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
<li class="toc-h2 nav-item toc-entry">
|
||
<a class="reference internal nav-link" href="#background-literature">
|
||
Background literature
|
||
</a>
|
||
</li>
|
||
<li class="toc-h2 nav-item toc-entry">
|
||
<a class="reference internal nav-link" href="#introduction-to-numerical-projects">
|
||
Introduction to numerical projects
|
||
</a>
|
||
</li>
|
||
<li class="toc-h2 nav-item toc-entry">
|
||
<a class="reference internal nav-link" href="#format-for-electronic-delivery-of-report-and-programs">
|
||
Format for electronic delivery of report and programs
|
||
</a>
|
||
</li>
|
||
<li class="toc-h2 nav-item toc-entry">
|
||
<a class="reference internal nav-link" href="#software-and-needed-installations">
|
||
Software and needed installations
|
||
</a>
|
||
</li>
|
||
</ul>
|
||
|
||
</nav>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
|
||
<div>
|
||
|
||
<!-- HTML file automatically generated from DocOnce source (https://github.com/doconce/doconce/)
|
||
doconce format html Project1.do.txt -->
|
||
<!-- dom:TITLE: Project 1 on Machine Learning, deadline October 7 (midnight), 2024 --><div class="tex2jax_ignore mathjax_ignore section" id="project-1-on-machine-learning-deadline-october-7-midnight-2024">
|
||
<h1>Project 1 on Machine Learning, deadline October 7 (midnight), 2024<a class="headerlink" href="#project-1-on-machine-learning-deadline-october-7-midnight-2024" title="Permalink to this headline">¶</a></h1>
|
||
<p><strong><a class="reference external" href="http://www.uio.no/studier/emner/matnat/fys/FYS3155/index-eng.html">Data Analysis and Machine Learning FYS-STK3155/FYS4155</a></strong>, University of Oslo, Norway</p>
|
||
<p>Date: <strong>September 2</strong></p>
|
||
<div class="section" id="preamble-note-on-writing-reports-using-reference-material-ai-and-other-tools">
|
||
<h2>Preamble: Note on writing reports, using reference material, AI and other tools<a class="headerlink" href="#preamble-note-on-writing-reports-using-reference-material-ai-and-other-tools" title="Permalink to this headline">¶</a></h2>
|
||
<p>We want you to answer the three different projects by handing in
|
||
reports written like a standard scientific/technical report. The link
|
||
at
|
||
<a class="reference external" href="https://github.com/CompPhysics/MachineLearning/blob/master/doc/Projects/ProjectWriting/projectwriting.ipynb">https://github.com/CompPhysics/MachineLearning/blob/master/doc/Projects/ProjectWriting/projectwriting.ipynb</a>
|
||
gives some guidance. See also the grading suggestion at
|
||
<a class="reference external" href="https://github.com/CompPhysics/MachineLearning/blob/master/doc/Projects/EvaluationGrading/EvaluationForm.md">https://github.com/CompPhysics/MachineLearning/blob/master/doc/Projects/EvaluationGrading/EvaluationForm.md</a>.</p>
|
||
<p>Furthermore, at
|
||
<a class="reference external" href="https://github.com/CompPhysics/MachineLearning/blob/master/doc/Projects/ReportExample/">https://github.com/CompPhysics/MachineLearning/blob/master/doc/Projects/ReportExample/</a>
|
||
you can find examples of previous reports. How to write reports will
|
||
also be discussed during the various lab sessions. Please do ask us if you are in doubt.</p>
|
||
<p>When using codes and material from other sources, you should refer to these in the bibliography of your report, indicating wherefrom you for example
|
||
got the code, whether this is from the lecture notes, softwares like
|
||
Scikit-Learn, TensorFlow, PyTorch or other sources. These should
|
||
always be cited correctly. How to cite some of the libraries is often
|
||
indicated from their corresponding GitHub sites or websites, see for example how to cite Scikit-Learn at <a class="reference external" href="https://scikit-learn.org/dev/about.html">https://scikit-learn.org/dev/about.html</a>.</p>
|
||
<p>We enocurage you to use tools like
|
||
<a class="reference external" href="https://openai.com/chatgpt/">ChatGPT</a> or similar in writing the report. If you use for example ChatGPT,
|
||
please do cite it properly and include (if possible) your questions and answers as an addition to the report. This can
|
||
be uploaded to for example your website, GitHub/GitLab or similar as supplemental material.</p>
|
||
</div>
|
||
<div class="section" id="regression-analysis-and-resampling-methods">
|
||
<h2>Regression analysis and resampling methods<a class="headerlink" href="#regression-analysis-and-resampling-methods" title="Permalink to this headline">¶</a></h2>
|
||
<p>The main aim of this project is to study in more detail various
|
||
regression methods, including the Ordinary Least Squares (OLS) method.
|
||
In addition to the scientific part, in this course we want also to
|
||
give you an experience in writing scientific reports.</p>
|
||
<p><strong>A small recommendation when developing the codes here</strong>. Instead of
|
||
jumping on to the two-dimensional function described below, we
|
||
recommend to do the code development and testing with a simpler
|
||
one-dimensional function, similar to those discussed in the exercises
|
||
of weeks 35 and 36. A simple test, as discussed during the lectures the first
|
||
three weeks is to set the design matrix equal to the identity
|
||
matrix. Then your model should give a mean square error which is exactly equal to zero.
|
||
When you are sure that your codes function well, you can then replace
|
||
the one-dimensional test function with the two-dimensional <strong>Franke</strong> function
|
||
discussed here.</p>
|
||
<p>The Franke function serves as a stepping stone towards the analysis of
|
||
real topographic data. The latter is the last part of this project.</p>
|
||
<div class="section" id="description-of-two-dimensional-function">
|
||
<h3>Description of two-dimensional function<a class="headerlink" href="#description-of-two-dimensional-function" title="Permalink to this headline">¶</a></h3>
|
||
<p>We will first study how to fit polynomials to a specific
|
||
two-dimensional function called <a class="reference external" href="http://www.dtic.mil/dtic/tr/fulltext/u2/a081688.pdf">Franke’s
|
||
function</a>. This
|
||
is a function which has been widely used when testing various
|
||
interpolation and fitting algorithms. Furthermore, after having
|
||
established the model and the method, we will employ resamling
|
||
techniques such as cross-validation and/or bootstrap in order to perform a
|
||
proper assessment of our models. We will also study in detail the
|
||
so-called Bias-Variance trade off.</p>
|
||
<p>The Franke function, which is a weighted sum of four exponentials reads as follows</p>
|
||
<div class="math notranslate nohighlight">
|
||
\[\begin{split}
|
||
\begin{align*}
|
||
f(x,y) &= \frac{3}{4}\exp{\left(-\frac{(9x-2)^2}{4} - \frac{(9y-2)^2}{4}\right)}+\frac{3}{4}\exp{\left(-\frac{(9x+1)^2}{49}- \frac{(9y+1)}{10}\right)} \\
|
||
&+\frac{1}{2}\exp{\left(-\frac{(9x-7)^2}{4} - \frac{(9y-3)^2}{4}\right)} -\frac{1}{5}\exp{\left(-(9x-4)^2 - (9y-7)^2\right) }.
|
||
\end{align*}
|
||
\end{split}\]</div>
|
||
<p>The function will be defined for <span class="math notranslate nohighlight">\(x,y\in [0,1]\)</span>. In a sense, our data are thus scaled to a particular domain for the input values.</p>
|
||
<p>Our first step will
|
||
be to perform an OLS regression analysis of this function, trying out
|
||
a polynomial fit with an <span class="math notranslate nohighlight">\(x\)</span> and a <span class="math notranslate nohighlight">\(y\)</span> dependence of the form <span class="math notranslate nohighlight">\([x, y,
|
||
x^2, y^2, xy, \dots]\)</span>. We will also include bootstrap first as a
|
||
resampling technique. After that we will include the cross-validation
|
||
technique.</p>
|
||
<p>We can
|
||
use a uniform distribution to set up the arrays of values for <span class="math notranslate nohighlight">\(x\)</span> and
|
||
<span class="math notranslate nohighlight">\(y\)</span>, or as in the example below just a set of fixed values for <span class="math notranslate nohighlight">\(x\)</span> and
|
||
<span class="math notranslate nohighlight">\(y\)</span> with a given step size. We will fit a function (for example a
|
||
polynomial) of <span class="math notranslate nohighlight">\(x\)</span> and <span class="math notranslate nohighlight">\(y\)</span>. Thereafter we will repeat much of the
|
||
same procedure using the Ridge and Lasso regression methods,
|
||
introducing thus a dependence on the bias (penalty) <span class="math notranslate nohighlight">\(\lambda\)</span>.</p>
|
||
<p>Finally we are going to use (real) digital terrain data and try to
|
||
reproduce these data using the same methods. We will also try to go
|
||
beyond the second-order polynomials metioned above and explore
|
||
which polynomial fits the data best.</p>
|
||
<p>The Python code for the Franke function is included here (it performs also a three-dimensional plot of it)</p>
|
||
<div class="cell docutils container">
|
||
<div class="cell_input docutils container">
|
||
<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="o">%</span><span class="k">matplotlib</span> inline
|
||
|
||
<span class="kn">from</span> <span class="nn">mpl_toolkits.mplot3d</span> <span class="kn">import</span> <span class="n">Axes3D</span>
|
||
<span class="kn">import</span> <span class="nn">matplotlib.pyplot</span> <span class="k">as</span> <span class="nn">plt</span>
|
||
<span class="kn">from</span> <span class="nn">matplotlib</span> <span class="kn">import</span> <span class="n">cm</span>
|
||
<span class="kn">from</span> <span class="nn">matplotlib.ticker</span> <span class="kn">import</span> <span class="n">LinearLocator</span><span class="p">,</span> <span class="n">FormatStrFormatter</span>
|
||
<span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
|
||
<span class="kn">from</span> <span class="nn">random</span> <span class="kn">import</span> <span class="n">random</span><span class="p">,</span> <span class="n">seed</span>
|
||
|
||
<span class="n">fig</span> <span class="o">=</span> <span class="n">plt</span><span class="o">.</span><span class="n">figure</span><span class="p">()</span>
|
||
<span class="n">ax</span> <span class="o">=</span> <span class="n">fig</span><span class="o">.</span><span class="n">add_subplot</span><span class="p">(</span><span class="n">projection</span> <span class="o">=</span> <span class="s1">'3d'</span><span class="p">)</span>
|
||
<span class="c1"># Make data.</span>
|
||
<span class="n">x</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">arange</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mf">0.05</span><span class="p">)</span>
|
||
<span class="n">y</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">arange</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mf">0.05</span><span class="p">)</span>
|
||
<span class="n">x</span><span class="p">,</span> <span class="n">y</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">meshgrid</span><span class="p">(</span><span class="n">x</span><span class="p">,</span><span class="n">y</span><span class="p">)</span>
|
||
|
||
|
||
<span class="k">def</span> <span class="nf">FrankeFunction</span><span class="p">(</span><span class="n">x</span><span class="p">,</span><span class="n">y</span><span class="p">):</span>
|
||
<span class="n">term1</span> <span class="o">=</span> <span class="mf">0.75</span><span class="o">*</span><span class="n">np</span><span class="o">.</span><span class="n">exp</span><span class="p">(</span><span class="o">-</span><span class="p">(</span><span class="mf">0.25</span><span class="o">*</span><span class="p">(</span><span class="mi">9</span><span class="o">*</span><span class="n">x</span><span class="o">-</span><span class="mi">2</span><span class="p">)</span><span class="o">**</span><span class="mi">2</span><span class="p">)</span> <span class="o">-</span> <span class="mf">0.25</span><span class="o">*</span><span class="p">((</span><span class="mi">9</span><span class="o">*</span><span class="n">y</span><span class="o">-</span><span class="mi">2</span><span class="p">)</span><span class="o">**</span><span class="mi">2</span><span class="p">))</span>
|
||
<span class="n">term2</span> <span class="o">=</span> <span class="mf">0.75</span><span class="o">*</span><span class="n">np</span><span class="o">.</span><span class="n">exp</span><span class="p">(</span><span class="o">-</span><span class="p">((</span><span class="mi">9</span><span class="o">*</span><span class="n">x</span><span class="o">+</span><span class="mi">1</span><span class="p">)</span><span class="o">**</span><span class="mi">2</span><span class="p">)</span><span class="o">/</span><span class="mf">49.0</span> <span class="o">-</span> <span class="mf">0.1</span><span class="o">*</span><span class="p">(</span><span class="mi">9</span><span class="o">*</span><span class="n">y</span><span class="o">+</span><span class="mi">1</span><span class="p">))</span>
|
||
<span class="n">term3</span> <span class="o">=</span> <span class="mf">0.5</span><span class="o">*</span><span class="n">np</span><span class="o">.</span><span class="n">exp</span><span class="p">(</span><span class="o">-</span><span class="p">(</span><span class="mi">9</span><span class="o">*</span><span class="n">x</span><span class="o">-</span><span class="mi">7</span><span class="p">)</span><span class="o">**</span><span class="mi">2</span><span class="o">/</span><span class="mf">4.0</span> <span class="o">-</span> <span class="mf">0.25</span><span class="o">*</span><span class="p">((</span><span class="mi">9</span><span class="o">*</span><span class="n">y</span><span class="o">-</span><span class="mi">3</span><span class="p">)</span><span class="o">**</span><span class="mi">2</span><span class="p">))</span>
|
||
<span class="n">term4</span> <span class="o">=</span> <span class="o">-</span><span class="mf">0.2</span><span class="o">*</span><span class="n">np</span><span class="o">.</span><span class="n">exp</span><span class="p">(</span><span class="o">-</span><span class="p">(</span><span class="mi">9</span><span class="o">*</span><span class="n">x</span><span class="o">-</span><span class="mi">4</span><span class="p">)</span><span class="o">**</span><span class="mi">2</span> <span class="o">-</span> <span class="p">(</span><span class="mi">9</span><span class="o">*</span><span class="n">y</span><span class="o">-</span><span class="mi">7</span><span class="p">)</span><span class="o">**</span><span class="mi">2</span><span class="p">)</span>
|
||
<span class="k">return</span> <span class="n">term1</span> <span class="o">+</span> <span class="n">term2</span> <span class="o">+</span> <span class="n">term3</span> <span class="o">+</span> <span class="n">term4</span>
|
||
|
||
|
||
<span class="n">z</span> <span class="o">=</span> <span class="n">FrankeFunction</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">y</span><span class="p">)</span>
|
||
|
||
<span class="c1"># Plot the surface.</span>
|
||
<span class="n">surf</span> <span class="o">=</span> <span class="n">ax</span><span class="o">.</span><span class="n">plot_surface</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">y</span><span class="p">,</span> <span class="n">z</span><span class="p">,</span> <span class="n">cmap</span><span class="o">=</span><span class="n">cm</span><span class="o">.</span><span class="n">coolwarm</span><span class="p">,</span>
|
||
<span class="n">linewidth</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">antialiased</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
|
||
|
||
<span class="c1"># Customize the z axis.</span>
|
||
<span class="n">ax</span><span class="o">.</span><span class="n">set_zlim</span><span class="p">(</span><span class="o">-</span><span class="mf">0.10</span><span class="p">,</span> <span class="mf">1.40</span><span class="p">)</span>
|
||
<span class="n">ax</span><span class="o">.</span><span class="n">zaxis</span><span class="o">.</span><span class="n">set_major_locator</span><span class="p">(</span><span class="n">LinearLocator</span><span class="p">(</span><span class="mi">10</span><span class="p">))</span>
|
||
<span class="n">ax</span><span class="o">.</span><span class="n">zaxis</span><span class="o">.</span><span class="n">set_major_formatter</span><span class="p">(</span><span class="n">FormatStrFormatter</span><span class="p">(</span><span class="s1">'</span><span class="si">%.02f</span><span class="s1">'</span><span class="p">))</span>
|
||
|
||
<span class="c1"># Add a color bar which maps values to colors.</span>
|
||
<span class="n">fig</span><span class="o">.</span><span class="n">colorbar</span><span class="p">(</span><span class="n">surf</span><span class="p">,</span> <span class="n">shrink</span><span class="o">=</span><span class="mf">0.5</span><span class="p">,</span> <span class="n">aspect</span><span class="o">=</span><span class="mi">5</span><span class="p">)</span>
|
||
|
||
<span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
|
||
</pre></div>
|
||
</div>
|
||
</div>
|
||
<div class="cell_output docutils container">
|
||
<img alt="_images/project1_7_0.png" src="_images/project1_7_0.png" />
|
||
</div>
|
||
</div>
|
||
<p>If you wish to compare your results with other on the Franke function or other popular functions tested with linear regression, see the list in Figure 1 of the article by Cook et al at <a class="reference external" href="https://arxiv.org/abs/2401.11694">https://arxiv.org/abs/2401.11694</a>.</p>
|
||
</div>
|
||
<div class="section" id="part-a-ordinary-least-square-ols-on-the-franke-function">
|
||
<h3>Part a) : Ordinary Least Square (OLS) on the Franke function<a class="headerlink" href="#part-a-ordinary-least-square-ols-on-the-franke-function" title="Permalink to this headline">¶</a></h3>
|
||
<p>We will generate our own dataset for a function
|
||
<span class="math notranslate nohighlight">\(\mathrm{FrankeFunction}(x,y)\)</span> with <span class="math notranslate nohighlight">\(x,y \in [0,1]\)</span>. The function
|
||
<span class="math notranslate nohighlight">\(f(x,y)\)</span> is the Franke function. You should explore also the addition
|
||
of an added stochastic noise to this function using the normal
|
||
distribution <span class="math notranslate nohighlight">\(N(0,1)\)</span>.</p>
|
||
<p><em>Write your own code</em> (using either a matrix inversion or a singular
|
||
value decomposition from e.g., <strong>numpy</strong> ) and perform a standard <strong>ordinary least square regression</strong>
|
||
analysis using polynomials in <span class="math notranslate nohighlight">\(x\)</span> and <span class="math notranslate nohighlight">\(y\)</span> up to fifth order.</p>
|
||
<p>Evaluate the mean Squared error (MSE)</p>
|
||
<div class="math notranslate nohighlight">
|
||
\[
|
||
MSE(\boldsymbol{y},\tilde{\boldsymbol{y}}) = \frac{1}{n}
|
||
\sum_{i=0}^{n-1}(y_i-\tilde{y}_i)^2,
|
||
\]</div>
|
||
<p>and the <span class="math notranslate nohighlight">\(R^2\)</span> score function. If <span class="math notranslate nohighlight">\(\tilde{\boldsymbol{y}}_i\)</span> is the predicted
|
||
value of the <span class="math notranslate nohighlight">\(i-th\)</span> sample and <span class="math notranslate nohighlight">\(y_i\)</span> is the corresponding true value,
|
||
then the score <span class="math notranslate nohighlight">\(R^2\)</span> is defined as</p>
|
||
<div class="math notranslate nohighlight">
|
||
\[
|
||
R^2(\boldsymbol{y}, \tilde{\boldsymbol{y}}) = 1 - \frac{\sum_{i=0}^{n - 1} (y_i - \tilde{y}_i)^2}{\sum_{i=0}^{n - 1} (y_i - \bar{y})^2},
|
||
\]</div>
|
||
<p>where we have defined the mean value of <span class="math notranslate nohighlight">\(\boldsymbol{y}\)</span> as</p>
|
||
<div class="math notranslate nohighlight">
|
||
\[
|
||
\bar{y} = \frac{1}{n} \sum_{i=0}^{n - 1} y_i.
|
||
\]</div>
|
||
<p>Plot the resulting scores (MSE and R<span class="math notranslate nohighlight">\(^2\)</span>) as functions of the polynomial degree (here up to polymial degree five).
|
||
Plot also the parameters <span class="math notranslate nohighlight">\(\beta\)</span> as you increase the order of the polynomial. Comment your results.</p>
|
||
<p>Your code has to include a scaling/centering of the data (for example by
|
||
subtracting the mean value), and
|
||
a split of the data in training and test data. For this exercise you can
|
||
either write your own code or use for example the function for
|
||
splitting training data provided by the library <strong>Scikit-Learn</strong> (make
|
||
sure you have installed it). This function is called
|
||
<span class="math notranslate nohighlight">\(train\_test\_split\)</span>. <strong>You should present a critical discussion of why and how you have scaled or not scaled the data</strong>.</p>
|
||
<p>It is normal in essentially all Machine Learning studies to split the
|
||
data in a training set and a test set (eventually also an additional
|
||
validation set). There
|
||
is no explicit recipe for how much data should be included as training
|
||
data and say test data. An accepted rule of thumb is to use
|
||
approximately <span class="math notranslate nohighlight">\(2/3\)</span> to <span class="math notranslate nohighlight">\(4/5\)</span> of the data as training data.</p>
|
||
<p>You can easily reuse the solutions to your exercises from week 35 and week 36.
|
||
See also the lecture slides from week 35 and week 36.</p>
|
||
<p>On scaling, we recommend reading the following section from the scikit-learn software description, see <a class="reference external" href="https://scikit-learn.org/stable/auto_examples/preprocessing/plot_all_scaling.html#plot-all-scaling-standard-scaler-section">https://scikit-learn.org/stable/auto_examples/preprocessing/plot_all_scaling.html#plot-all-scaling-standard-scaler-section</a>.</p>
|
||
</div>
|
||
<div class="section" id="part-b-adding-ridge-regression-for-the-franke-function">
|
||
<h3>Part b): Adding Ridge regression for the Franke function<a class="headerlink" href="#part-b-adding-ridge-regression-for-the-franke-function" title="Permalink to this headline">¶</a></h3>
|
||
<p>Write your own code for the Ridge method, either using matrix
|
||
inversion or the singular value decomposition as done in the previous
|
||
exercise. The lecture notes from week 35 and 36 contain more information. Furthermore, the numerical exercise from week 36 is something you can reuse here.</p>
|
||
<p>Perform the same analysis as you did in the previous exercise but now for different values of <span class="math notranslate nohighlight">\(\lambda\)</span>. Compare and
|
||
analyze your results with those obtained in part a) with the ordinary least squares method. Study the
|
||
dependence on <span class="math notranslate nohighlight">\(\lambda\)</span>.</p>
|
||
</div>
|
||
<div class="section" id="part-c-adding-lasso-for-the-franke-function">
|
||
<h3>Part c): Adding Lasso for the Franke function<a class="headerlink" href="#part-c-adding-lasso-for-the-franke-function" title="Permalink to this headline">¶</a></h3>
|
||
<p>This exercise is essentially a repeat of the previous two ones, but now
|
||
with Lasso regression. Write either your own code (difficult and optional) or, in this case,
|
||
you can also use the functionalities of <strong>Scikit-Learn</strong> (recommended). Keep in mind that the library <strong>Scikit-Learn</strong> excludes the intercept by default.
|
||
Give a
|
||
critical discussion of the three methods and a judgement of which
|
||
model fits the data best.</p>
|
||
</div>
|
||
<div class="section" id="part-d-paper-and-pencil-part">
|
||
<h3>Part d): Paper and pencil part<a class="headerlink" href="#part-d-paper-and-pencil-part" title="Permalink to this headline">¶</a></h3>
|
||
<p>This exercise deals with various mean values and variances in linear regression method (here it may be useful to look up chapter 3, equation (3.8) of <a class="reference external" href="https://www.springer.com/gp/book/9780387848570">Trevor Hastie, Robert Tibshirani, Jerome H. Friedman, The Elements of Statistical Learning, Springer</a>). The exercise is also part of the weekly exercises for week 37.</p>
|
||
<p>The assumption we have made is
|
||
that there exists a continuous function <span class="math notranslate nohighlight">\(f(\boldsymbol{x})\)</span> and a normal distributed error <span class="math notranslate nohighlight">\(\boldsymbol{\varepsilon}\sim N(0, \sigma^2)\)</span>
|
||
which describes our data</p>
|
||
<div class="math notranslate nohighlight">
|
||
\[
|
||
\boldsymbol{y} = f(\boldsymbol{x})+\boldsymbol{\varepsilon}
|
||
\]</div>
|
||
<p>We then approximate this function <span class="math notranslate nohighlight">\(f(\boldsymbol{x})\)</span> with our model <span class="math notranslate nohighlight">\(\boldsymbol{\tilde{y}}\)</span> from the solution of the linear regression equations (ordinary least squares OLS), that is our
|
||
function <span class="math notranslate nohighlight">\(f\)</span> is approximated by <span class="math notranslate nohighlight">\(\boldsymbol{\tilde{y}}\)</span> where we minimized <span class="math notranslate nohighlight">\((\boldsymbol{y}-\boldsymbol{\tilde{y}})^2\)</span>, with</p>
|
||
<div class="math notranslate nohighlight">
|
||
\[
|
||
\boldsymbol{\tilde{y}} = \boldsymbol{X}\boldsymbol{\beta}.
|
||
\]</div>
|
||
<p>The matrix <span class="math notranslate nohighlight">\(\boldsymbol{X}\)</span> is the so-called design or feature matrix.</p>
|
||
<p>Show that the expectation value of <span class="math notranslate nohighlight">\(\boldsymbol{y}\)</span> for a given element <span class="math notranslate nohighlight">\(i\)</span></p>
|
||
<div class="math notranslate nohighlight">
|
||
\[
|
||
\mathbb{E}(y_i) =\sum_{j}x_{ij} \beta_j=\mathbf{X}_{i, \ast} \, \boldsymbol{\beta},
|
||
\]</div>
|
||
<p>and that
|
||
its variance is</p>
|
||
<div class="math notranslate nohighlight">
|
||
\[
|
||
\mbox{Var}(y_i) = \sigma^2.
|
||
\]</div>
|
||
<p>Hence, <span class="math notranslate nohighlight">\(y_i \sim N( \mathbf{X}_{i, \ast} \, \boldsymbol{\beta}, \sigma^2)\)</span>, that is <span class="math notranslate nohighlight">\(\boldsymbol{y}\)</span> follows a normal distribution with
|
||
mean value <span class="math notranslate nohighlight">\(\boldsymbol{X}\boldsymbol{\beta}\)</span> and variance <span class="math notranslate nohighlight">\(\sigma^2\)</span>.</p>
|
||
<p>With the OLS expressions for the optimal parameters <span class="math notranslate nohighlight">\(\boldsymbol{\hat{\beta}}\)</span> show that</p>
|
||
<div class="math notranslate nohighlight">
|
||
\[
|
||
\mathbb{E}(\boldsymbol{\hat{\beta}}) = \boldsymbol{\beta}.
|
||
\]</div>
|
||
<p>Show finally that the variance of <span class="math notranslate nohighlight">\(\boldsymbol{\beta}\)</span> is</p>
|
||
<div class="math notranslate nohighlight">
|
||
\[
|
||
\mbox{Var}(\boldsymbol{\hat{\beta}}) = \sigma^2 \, (\mathbf{X}^{T} \mathbf{X})^{-1}.
|
||
\]</div>
|
||
<p>We can use the last expression when we define a so-called confidence interval for the parameters <span class="math notranslate nohighlight">\(\beta\)</span>.
|
||
A given parameter <span class="math notranslate nohighlight">\(\beta_j\)</span> is given by the diagonal matrix element of the above matrix.</p>
|
||
</div>
|
||
<div class="section" id="part-e-bias-variance-trade-off-and-resampling-techniques">
|
||
<h3>Part e): Bias-variance trade-off and resampling techniques<a class="headerlink" href="#part-e-bias-variance-trade-off-and-resampling-techniques" title="Permalink to this headline">¶</a></h3>
|
||
<p>Our aim here is to study the bias-variance trade-off by implementing the <strong>bootstrap</strong> resampling technique.
|
||
<strong>We will only use the simpler ordinary least squares here</strong>.</p>
|
||
<p>With a code which does OLS and includes resampling techniques,
|
||
we will now discuss the bias-variance trade-off in the context of
|
||
continuous predictions such as regression. However, many of the
|
||
intuitions and ideas discussed here also carry over to classification
|
||
tasks and basically all Machine Learning algorithms.</p>
|
||
<p>Before you perform an analysis of the bias-variance trade-off on your test data, make
|
||
first a figure similar to Fig. 2.11 of Hastie, Tibshirani, and
|
||
Friedman. Figure 2.11 of this reference displays only the test and training MSEs. The test MSE can be used to
|
||
indicate possible regions of low/high bias and variance. You will most likely not get an
|
||
equally smooth curve!</p>
|
||
<p>With this result we move on to the bias-variance trade-off analysis.</p>
|
||
<p>Consider a
|
||
dataset <span class="math notranslate nohighlight">\(\mathcal{L}\)</span> consisting of the data
|
||
<span class="math notranslate nohighlight">\(\mathbf{X}_\mathcal{L}=\{(y_j, \boldsymbol{x}_j), j=0\ldots n-1\}\)</span>.</p>
|
||
<p>As in part d), we assume that the true data is generated from a noisy model</p>
|
||
<div class="math notranslate nohighlight">
|
||
\[
|
||
\boldsymbol{y}=f(\boldsymbol{x}) + \boldsymbol{\epsilon}.
|
||
\]</div>
|
||
<p>Here <span class="math notranslate nohighlight">\(\epsilon\)</span> is normally distributed with mean zero and standard
|
||
deviation <span class="math notranslate nohighlight">\(\sigma^2\)</span>.</p>
|
||
<p>In our derivation of the ordinary least squares method we defined then
|
||
an approximation to the function <span class="math notranslate nohighlight">\(f\)</span> in terms of the parameters
|
||
<span class="math notranslate nohighlight">\(\boldsymbol{\beta}\)</span> and the design matrix <span class="math notranslate nohighlight">\(\boldsymbol{X}\)</span> which embody our model,
|
||
that is <span class="math notranslate nohighlight">\(\boldsymbol{\tilde{y}}=\boldsymbol{X}\boldsymbol{\beta}\)</span>.</p>
|
||
<p>The parameters <span class="math notranslate nohighlight">\(\boldsymbol{\beta}\)</span> are in turn found by optimizing the mean
|
||
squared error via the so-called cost function</p>
|
||
<div class="math notranslate nohighlight">
|
||
\[
|
||
C(\boldsymbol{X},\boldsymbol{\beta}) =\frac{1}{n}\sum_{i=0}^{n-1}(y_i-\tilde{y}_i)^2=\mathbb{E}\left[(\boldsymbol{y}-\boldsymbol{\tilde{y}})^2\right].
|
||
\]</div>
|
||
<p>Here the expected value <span class="math notranslate nohighlight">\(\mathbb{E}\)</span> is the sample value.</p>
|
||
<p>Show that you can rewrite this in terms of a term which contains the variance of the model itself (the so-called variance term), a
|
||
term which measures the deviation from the true data and the mean value of the model (the bias term) and finally the variance of the noise.
|
||
That is, show that</p>
|
||
<div class="math notranslate nohighlight">
|
||
\[
|
||
\mathbb{E}\left[(\boldsymbol{y}-\boldsymbol{\tilde{y}})^2\right]=\mathrm{Bias}[\tilde{y}]+\mathrm{var}[\tilde{y}]+\sigma^2,
|
||
\]</div>
|
||
<p>with</p>
|
||
<div class="math notranslate nohighlight">
|
||
\[
|
||
\mathrm{Bias}[\tilde{y}]=\mathbb{E}\left[\left(\boldsymbol{y}-\mathbb{E}\left[\boldsymbol{\tilde{y}}\right]\right)^2\right],
|
||
\]</div>
|
||
<p>and</p>
|
||
<div class="math notranslate nohighlight">
|
||
\[
|
||
\mathrm{var}[\tilde{y}]=\mathbb{E}\left[\left(\tilde{\boldsymbol{y}}-\mathbb{E}\left[\boldsymbol{\tilde{y}}\right]\right)^2\right]=\frac{1}{n}\sum_i(\tilde{y}_i-\mathbb{E}\left[\boldsymbol{\tilde{y}}\right])^2.
|
||
\]</div>
|
||
<p>The answer to this exercise should be included in the theory part of the report. This exercise is also part of the weekly exercises of week 38.
|
||
Explain what the terms mean and discuss their interpretations.</p>
|
||
<p>Perform then a bias-variance analysis of the Franke function by
|
||
studying the MSE value as function of the complexity of your model.</p>
|
||
<p>Discuss the bias and variance trade-off as function
|
||
of your model complexity (the degree of the polynomial) and the number
|
||
of data points, and possibly also your training and test data using the <strong>bootstrap</strong> resampling method.
|
||
You can follow the code example in the jupyter-book at <a class="reference external" href="https://compphysics.github.io/MachineLearning/doc/LectureNotes/_build/html/chapter3.html#the-bias-variance-tradeoff">https://compphysics.github.io/MachineLearning/doc/LectureNotes/_build/html/chapter3.html#the-bias-variance-tradeoff</a>.</p>
|
||
</div>
|
||
<div class="section" id="part-f-cross-validation-as-resampling-techniques-adding-more-complexity">
|
||
<h3>Part f): Cross-validation as resampling techniques, adding more complexity<a class="headerlink" href="#part-f-cross-validation-as-resampling-techniques-adding-more-complexity" title="Permalink to this headline">¶</a></h3>
|
||
<p>The aim here is to implement another widely popular
|
||
resampling technique, the so-called cross-validation method.</p>
|
||
<p>Implement the <span class="math notranslate nohighlight">\(k\)</span>-fold cross-validation algorithm (write your own
|
||
code or use the functionality of <strong>Scikit-Learn</strong>) and evaluate again the MSE function resulting
|
||
from the test folds.</p>
|
||
<p>Compare the MSE you get from your cross-validation code with the one
|
||
you got from your <strong>bootstrap</strong> code. Comment your results. Try <span class="math notranslate nohighlight">\(5-10\)</span>
|
||
folds.</p>
|
||
<p>In addition to using the ordinary least squares method, you should include both Ridge and Lasso regression.</p>
|
||
</div>
|
||
<div class="section" id="part-g-analysis-of-real-data">
|
||
<h3>Part g): Analysis of real data<a class="headerlink" href="#part-g-analysis-of-real-data" title="Permalink to this headline">¶</a></h3>
|
||
<p>With our codes functioning and having been tested properly on a
|
||
simpler function we are now ready to look at real data. We will
|
||
essentially repeat in this exercise what was done in exercises a-f. However, we
|
||
need first to download the data and prepare properly the inputs to our
|
||
codes. We are going to download digital terrain data from the website
|
||
<a class="reference external" href="https://earthexplorer.usgs.gov/">https://earthexplorer.usgs.gov/</a>,</p>
|
||
<p>Or, if you prefer, we have placed selected datafiles at <a class="reference external" href="https://github.com/CompPhysics/MachineLearning/tree/master/doc/Projects/2023/Project1/DataFiles">https://github.com/CompPhysics/MachineLearning/tree/master/doc/Projects/2023/Project1/DataFiles</a></p>
|
||
<p>In order to obtain data for a specific region, you need to register as
|
||
a user (free) at this website and then decide upon which area you want
|
||
to fetch the digital terrain data from. In order to be able to read
|
||
the data properly, you need to specify that the format should be <strong>SRTM
|
||
Arc-Second Global</strong> and download the data as a <strong>GeoTIF</strong> file. The
|
||
files are then stored in <em>tif</em> format which can be imported into a
|
||
Python program using</p>
|
||
<div class="cell docutils container">
|
||
<div class="cell_input docutils container">
|
||
<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="n">scipy</span><span class="o">.</span><span class="n">misc</span><span class="o">.</span><span class="n">imread</span>
|
||
</pre></div>
|
||
</div>
|
||
</div>
|
||
<div class="cell_output docutils container">
|
||
<div class="output traceback highlight-ipythontb notranslate"><div class="highlight"><pre><span></span><span class="gt">---------------------------------------------------------------------------</span>
|
||
<span class="ne">NameError</span><span class="g g-Whitespace"> </span>Traceback (most recent call last)
|
||
<span class="n">Cell</span> <span class="n">In</span><span class="p">[</span><span class="mi">2</span><span class="p">],</span> <span class="n">line</span> <span class="mi">1</span>
|
||
<span class="ne">----> </span><span class="mi">1</span> <span class="n">scipy</span><span class="o">.</span><span class="n">misc</span><span class="o">.</span><span class="n">imread</span>
|
||
|
||
<span class="ne">NameError</span>: name 'scipy' is not defined
|
||
</pre></div>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
<p>Here is a simple part of a Python code which reads and plots the data
|
||
from such files</p>
|
||
<div class="cell docutils container">
|
||
<div class="cell_input docutils container">
|
||
<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
|
||
<span class="kn">from</span> <span class="nn">imageio</span> <span class="kn">import</span> <span class="n">imread</span>
|
||
<span class="kn">import</span> <span class="nn">matplotlib.pyplot</span> <span class="k">as</span> <span class="nn">plt</span>
|
||
<span class="kn">from</span> <span class="nn">mpl_toolkits.mplot3d</span> <span class="kn">import</span> <span class="n">Axes3D</span>
|
||
<span class="kn">from</span> <span class="nn">matplotlib</span> <span class="kn">import</span> <span class="n">cm</span>
|
||
|
||
<span class="c1"># Load the terrain</span>
|
||
<span class="n">terrain1</span> <span class="o">=</span> <span class="n">imread</span><span class="p">(</span><span class="s1">'SRTM_data_Norway_1.tif'</span><span class="p">)</span>
|
||
<span class="c1"># Show the terrain</span>
|
||
<span class="n">plt</span><span class="o">.</span><span class="n">figure</span><span class="p">()</span>
|
||
<span class="n">plt</span><span class="o">.</span><span class="n">title</span><span class="p">(</span><span class="s1">'Terrain over Norway 1'</span><span class="p">)</span>
|
||
<span class="n">plt</span><span class="o">.</span><span class="n">imshow</span><span class="p">(</span><span class="n">terrain1</span><span class="p">,</span> <span class="n">cmap</span><span class="o">=</span><span class="s1">'gray'</span><span class="p">)</span>
|
||
<span class="n">plt</span><span class="o">.</span><span class="n">xlabel</span><span class="p">(</span><span class="s1">'X'</span><span class="p">)</span>
|
||
<span class="n">plt</span><span class="o">.</span><span class="n">ylabel</span><span class="p">(</span><span class="s1">'Y'</span><span class="p">)</span>
|
||
<span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
|
||
</pre></div>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
<p>If you should have problems in downloading the digital terrain data,
|
||
we provide two examples under the data folder of project 1. One is
|
||
from a region close to Stavanger in Norway and the other Møsvatn
|
||
Austfjell, again in Norway.
|
||
Feel free to produce your own terrain data.</p>
|
||
<p>Alternatively, if you would like to use another data set, feel free to do so. This could be data close to your reseach area or simply a data set you found interesting. See for example <a class="reference external" href="https://www.kaggle.com/datasets">kaggle.com</a> for examples.</p>
|
||
<p>Our final part deals with the parameterization of your digital terrain
|
||
data (or your own data). We will apply all three methods for linear regression, the same type (or higher order) of polynomial
|
||
approximation and cross-validation as resampling technique to evaluate which
|
||
model fits the data best.</p>
|
||
<p>At the end, you should present a critical evaluation of your results
|
||
and discuss the applicability of these regression methods to the type
|
||
of data presented here (either the terrain data we propose or other data sets).</p>
|
||
</div>
|
||
</div>
|
||
<div class="section" id="background-literature">
|
||
<h2>Background literature<a class="headerlink" href="#background-literature" title="Permalink to this headline">¶</a></h2>
|
||
<ol class="simple">
|
||
<li><p>For a discussion and derivation of the variances and mean squared errors using linear regression, see the <a class="reference external" href="https://arxiv.org/abs/1509.09169">Lecture notes on ridge regression by Wessel N. van Wieringen</a></p></li>
|
||
<li><p>The textbook of <a class="reference external" href="https://www.springer.com/gp/book/9780387848570">Trevor Hastie, Robert Tibshirani, Jerome H. Friedman, The Elements of Statistical Learning, Springer</a>, chapters 3 and 7 are the most relevant ones for the analysis here.</p></li>
|
||
</ol>
|
||
</div>
|
||
<div class="section" id="introduction-to-numerical-projects">
|
||
<h2>Introduction to numerical projects<a class="headerlink" href="#introduction-to-numerical-projects" title="Permalink to this headline">¶</a></h2>
|
||
<p>Here follows a brief recipe and recommendation on how to answer the various questions when preparing your answers.</p>
|
||
<ul class="simple">
|
||
<li><p>Give a short description of the nature of the problem and the eventual numerical methods you have used.</p></li>
|
||
<li><p>Describe the algorithm you have used and/or developed. Here you may find it convenient to use pseudocoding. In many cases you can describe the algorithm in the program itself.</p></li>
|
||
<li><p>Include the source code of your program. Comment your program properly. You should have the code at your GitHub/GitLab link. You can also place the code in an appendix of your report.</p></li>
|
||
<li><p>If possible, try to find analytic solutions, or known limits in order to test your program when developing the code.</p></li>
|
||
<li><p>Include your results either in figure form or in a table. Remember to label your results. All tables and figures should have relevant captions and labels on the axes.</p></li>
|
||
<li><p>Try to evaluate the reliabilty and numerical stability/precision of your results. If possible, include a qualitative and/or quantitative discussion of the numerical stability, eventual loss of precision etc.</p></li>
|
||
<li><p>Try to give an interpretation of you results in your answers to the problems.</p></li>
|
||
<li><p>Critique: if possible include your comments and reflections about the exercise, whether you felt you learnt something, ideas for improvements and other thoughts you’ve made when solving the exercise. We wish to keep this course at the interactive level and your comments can help us improve it.</p></li>
|
||
<li><p>Try to establish a practice where you log your work at the computerlab. You may find such a logbook very handy at later stages in your work, especially when you don’t properly remember what a previous test version of your program did. Here you could also record the time spent on solving the exercise, various algorithms you may have tested or other topics which you feel worthy of mentioning.</p></li>
|
||
</ul>
|
||
</div>
|
||
<div class="section" id="format-for-electronic-delivery-of-report-and-programs">
|
||
<h2>Format for electronic delivery of report and programs<a class="headerlink" href="#format-for-electronic-delivery-of-report-and-programs" title="Permalink to this headline">¶</a></h2>
|
||
<p>The preferred format for the report is a PDF file. You can also use DOC or postscript formats or as an ipython notebook file. As programming language we prefer that you choose between C/C++, Fortran2008, Julia or Python. The following prescription should be followed when preparing the report:</p>
|
||
<ul class="simple">
|
||
<li><p>Use Canvas to hand in your projects, log in at <a class="reference external" href="https://www.uio.no/english/services/it/education/canvas/">https://www.uio.no/english/services/it/education/canvas/</a> with your normal UiO username and password.</p></li>
|
||
<li><p>Upload <strong>only</strong> the report file or the link to your GitHub/GitLab or similar typo of repos! For the source code file(s) you have developed please provide us with your link to your GitHub/GitLab or similar domain. The report file should include all of your discussions and a list of the codes you have developed. Do not include library files which are available at the course homepage, unless you have made specific changes to them.</p></li>
|
||
<li><p>In your GitHub/GitLab or similar repository, please include a folder which contains selected results. These can be in the form of output from your code for a selected set of runs and input parameters.</p></li>
|
||
</ul>
|
||
<p>Finally,
|
||
we encourage you to collaborate. Optimal working groups consist of
|
||
2-3 students. You can then hand in a common report.</p>
|
||
</div>
|
||
<div class="section" id="software-and-needed-installations">
|
||
<h2>Software and needed installations<a class="headerlink" href="#software-and-needed-installations" title="Permalink to this headline">¶</a></h2>
|
||
<p>If you have Python installed (we recommend Python3) and you feel pretty familiar with installing different packages,
|
||
we recommend that you install the following Python packages via <strong>pip</strong> as</p>
|
||
<ol class="simple">
|
||
<li><p>pip install numpy scipy matplotlib ipython scikit-learn tensorflow sympy pandas pillow</p></li>
|
||
</ol>
|
||
<p>For Python3, replace <strong>pip</strong> with <strong>pip3</strong>.</p>
|
||
<p>See below for a discussion of <strong>tensorflow</strong> and <strong>scikit-learn</strong>.</p>
|
||
<p>For OSX users we recommend also, after having installed Xcode, to install <strong>brew</strong>. Brew allows
|
||
for a seamless installation of additional software via for example</p>
|
||
<ol class="simple">
|
||
<li><p>brew install python3</p></li>
|
||
</ol>
|
||
<p>For Linux users, with its variety of distributions like for example the widely popular Ubuntu distribution
|
||
you can use <strong>pip</strong> as well and simply install Python as</p>
|
||
<ol class="simple">
|
||
<li><p>sudo apt-get install python3 (or python for python2.7)</p></li>
|
||
</ol>
|
||
<p>etc etc.</p>
|
||
<p>If you don’t want to install various Python packages with their dependencies separately, we recommend two widely used distrubutions which set up all relevant dependencies for Python, namely</p>
|
||
<ol class="simple">
|
||
<li><p><a class="reference external" href="https://docs.anaconda.com/">Anaconda</a> Anaconda is an open source distribution of the Python and R programming languages for large-scale data processing, predictive analytics, and scientific computing, that aims to simplify package management and deployment. Package versions are managed by the package management system <strong>conda</strong></p></li>
|
||
<li><p><a class="reference external" href="https://www.enthought.com/product/canopy/">Enthought canopy</a> is a Python distribution for scientific and analytic computing distribution and analysis environment, available for free and under a commercial license.</p></li>
|
||
</ol>
|
||
<p>Popular software packages written in Python for ML are</p>
|
||
<ul class="simple">
|
||
<li><p><a class="reference external" href="http://scikit-learn.org/stable/">Scikit-learn</a>,</p></li>
|
||
<li><p><a class="reference external" href="https://www.tensorflow.org/">Tensorflow</a>,</p></li>
|
||
<li><p><a class="reference external" href="http://pytorch.org/">PyTorch</a> and</p></li>
|
||
<li><p><a class="reference external" href="https://keras.io/">Keras</a>.</p></li>
|
||
</ul>
|
||
<p>These are all freely available at their respective GitHub sites. They
|
||
encompass communities of developers in the thousands or more. And the number
|
||
of code developers and contributors keeps increasing.</p>
|
||
</div>
|
||
</div>
|
||
|
||
<script type="text/x-thebe-config">
|
||
{
|
||
requestKernel: true,
|
||
binderOptions: {
|
||
repo: "binder-examples/jupyter-stacks-datascience",
|
||
ref: "master",
|
||
},
|
||
codeMirrorConfig: {
|
||
theme: "abcdef",
|
||
mode: "python"
|
||
},
|
||
kernelOptions: {
|
||
kernelName: "python3",
|
||
path: "./."
|
||
},
|
||
predefinedOutput: true
|
||
}
|
||
</script>
|
||
<script>kernelName = 'python3'</script>
|
||
|
||
</div>
|
||
|
||
|
||
<!-- Previous / next buttons -->
|
||
<div class='prev-next-area'>
|
||
<a class='left-prev' id="prev-link" href="exercisesweek38.html" title="previous page">
|
||
<i class="fas fa-angle-left"></i>
|
||
<div class="prev-next-info">
|
||
<p class="prev-next-subtitle">previous</p>
|
||
<p class="prev-next-title">Exercises week 38</p>
|
||
</div>
|
||
</a>
|
||
</div>
|
||
|
||
</div>
|
||
</div>
|
||
<footer class="footer">
|
||
<p>
|
||
|
||
By Morten Hjorth-Jensen<br/>
|
||
|
||
© Copyright 2021.<br/>
|
||
</p>
|
||
</footer>
|
||
</main>
|
||
|
||
|
||
</div>
|
||
</div>
|
||
|
||
<script src="_static/js/index.be7d3bbb2ef33a8344ce.js"></script>
|
||
|
||
</body>
|
||
</html> |