1419 lines
48 KiB
HTML
1419 lines
48 KiB
HTML
|
||
<!doctype html>
|
||
<html lang="en" class="no-js">
|
||
<head>
|
||
|
||
<meta charset="utf-8">
|
||
<meta name="viewport" content="width=device-width,initial-scale=1">
|
||
|
||
|
||
|
||
|
||
<link rel="canonical" href="https://www.rapids.science/workflow-examples/analysis/">
|
||
|
||
|
||
|
||
|
||
<link rel="icon" href="../../assets/images/favicon.png">
|
||
<meta name="generator" content="mkdocs-1.1.2, mkdocs-material-7.0.7+insiders-2.4.0">
|
||
|
||
|
||
|
||
<title>Analysis - RAPIDS</title>
|
||
|
||
|
||
|
||
<link rel="stylesheet" href="../../assets/stylesheets/main.ec3b3678.min.css">
|
||
|
||
|
||
<link rel="stylesheet" href="../../assets/stylesheets/palette.de2705de.min.css">
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
|
||
<link rel="stylesheet" href="https://fonts.googleapis.com/css?family=Roboto:300,400,400i,700%7CRoboto+Mono&display=fallback">
|
||
<style>:root{--md-text-font-family:"Roboto";--md-code-font-family:"Roboto Mono"}</style>
|
||
|
||
|
||
|
||
|
||
<link rel="stylesheet" href="../../stylesheets/extra.css">
|
||
|
||
|
||
|
||
|
||
|
||
</head>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<body dir="ltr" data-md-color-scheme="default" data-md-color-primary="blue" data-md-color-accent="blue">
|
||
|
||
|
||
<script>function __prefix(e){return new URL("../..",location).pathname+"."+e}function __get(e,t=localStorage){return JSON.parse(t.getItem(__prefix(e)))}</script>
|
||
|
||
<script>var palette=__get("__palette");if(null!==palette&&"object"==typeof palette.color)for(var key in palette.color)document.body.setAttribute("data-md-color-"+key,palette.color[key])</script>
|
||
|
||
<input class="md-toggle" data-md-toggle="drawer" type="checkbox" id="__drawer" autocomplete="off">
|
||
<input class="md-toggle" data-md-toggle="search" type="checkbox" id="__search" autocomplete="off">
|
||
<label class="md-overlay" for="__drawer"></label>
|
||
<div data-md-component="skip">
|
||
|
||
|
||
<a href="#analysis-workflow-example" class="md-skip">
|
||
Skip to content
|
||
</a>
|
||
|
||
</div>
|
||
<div data-md-component="announce">
|
||
|
||
</div>
|
||
|
||
<div data-md-component="outdated" hidden>
|
||
<aside class="md-banner md-banner--warning">
|
||
|
||
<div class="md-banner__inner md-grid md-typeset">
|
||
|
||
You're not viewing the latest version.
|
||
<a href="https://www.rapids.science/">
|
||
<strong> Click here to go to latest. </strong>
|
||
</a>
|
||
|
||
</div>
|
||
<script>var el=document.querySelector("[data-md-component=outdated]"),outdated=__get("__outdated",sessionStorage);!0===outdated&&el&&(el.hidden=!1)</script>
|
||
|
||
</aside>
|
||
</div>
|
||
|
||
|
||
|
||
|
||
<header class="md-header" data-md-component="header">
|
||
<nav class="md-header__inner md-grid" aria-label="Header">
|
||
<a href="../.." title="RAPIDS" class="md-header__button md-logo" aria-label="RAPIDS" data-md-component="logo">
|
||
|
||
|
||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M19 18.31V20a2 2 0 0 1-2 2H7a2 2 0 0 1-2-2v-3.7c-.46-.18-1.05-.3-2-.3a1 1 0 0 1-1-1 1 1 0 0 1 1-1c.82 0 1.47.08 2 .21V12.3c-.46-.18-1.05-.3-2-.3a1 1 0 0 1-1-1 1 1 0 0 1 1-1c.82 0 1.47.08 2 .21V8.3C4.54 8.12 3.95 8 3 8a1 1 0 0 1-1-1 1 1 0 0 1 1-1c.82 0 1.47.08 2 .21V4a2 2 0 0 1 2-2h10a2 2 0 0 1 2 2v2.16c1.78.31 2.54.97 2.71 1.13.39.39.39 1.03 0 1.42-.39.39-.91.38-1.42 0 0 0-1.04-.71-3.29-.71-1.26 0-2.09.41-3.05.9-1.04.51-2.21 1.1-3.95 1.1-.36 0-.69 0-1-.04V7.95c.3.05.63.05 1 .05 1.26 0 2.09-.41 3.05-.89C14.09 6.59 15.27 6 17 6V4H7v16h10v-2c1.5 0 1.97.29 2 .31M17 10c-1.73 0-2.91.59-3.95 1.11-.96.48-1.79.89-3.05.89-.37 0-.7 0-1-.05v2.01c.31.04.64.04 1 .04 1.74 0 2.91-.59 3.95-1.1.96-.48 1.79-.9 3.05-.9 2.25 0 3.29.71 3.29.71.51.39 1.03.39 1.42 0 .39-.39.39-1.02 0-1.42C21.5 11.08 20.25 10 17 10m0 4c-1.73 0-2.91.59-3.95 1.11-.96.48-1.79.89-3.05.89-.37 0-.7 0-1-.05v2.01c.31.04.64.04 1 .04 1.74 0 2.91-.59 3.95-1.1.96-.48 1.79-.9 3.05-.9 2.25 0 3.29.71 3.29.71.51.39 1.03.39 1.42 0 .39-.39.39-1.02 0-1.42C21.5 15.08 20.25 14 17 14z"/></svg>
|
||
|
||
</a>
|
||
<label class="md-header__button md-icon" for="__drawer">
|
||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M3 6h18v2H3V6m0 5h18v2H3v-2m0 5h18v2H3v-2z"/></svg>
|
||
</label>
|
||
<div class="md-header__title" data-md-component="header-title">
|
||
<div class="md-header__ellipsis">
|
||
<div class="md-header__topic">
|
||
<span class="md-ellipsis">
|
||
RAPIDS
|
||
</span>
|
||
</div>
|
||
<div class="md-header__topic" data-md-component="header-topic">
|
||
<span class="md-ellipsis">
|
||
|
||
Analysis
|
||
|
||
</span>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
|
||
<form class="md-header__option" data-md-component="palette">
|
||
|
||
|
||
|
||
<input class="md-option" data-md-color-media="" data-md-color-scheme="default" data-md-color-primary="blue" data-md-color-accent="blue" type="radio" name="__palette" id="__palette_1">
|
||
<label class="md-header__button md-icon" title="Switch to light mode" for="__palette_2" hidden>
|
||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M17 7H7a5 5 0 0 0-5 5 5 5 0 0 0 5 5h10a5 5 0 0 0 5-5 5 5 0 0 0-5-5m0 8a3 3 0 0 1-3-3 3 3 0 0 1 3-3 3 3 0 0 1 3 3 3 3 0 0 1-3 3z"/></svg>
|
||
</label>
|
||
|
||
|
||
|
||
<input class="md-option" data-md-color-media="" data-md-color-scheme="slate" data-md-color-primary="blue" data-md-color-accent="blue" type="radio" name="__palette" id="__palette_2">
|
||
<label class="md-header__button md-icon" title="Switch to dark mode" for="__palette_1" hidden>
|
||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M7 10a2 2 0 0 1 2 2 2 2 0 0 1-2 2 2 2 0 0 1-2-2 2 2 0 0 1 2-2m10-3a5 5 0 0 1 5 5 5 5 0 0 1-5 5H7a5 5 0 0 1-5-5 5 5 0 0 1 5-5h10M7 9a3 3 0 0 0-3 3 3 3 0 0 0 3 3h10a3 3 0 0 0 3-3 3 3 0 0 0-3-3H7z"/></svg>
|
||
</label>
|
||
|
||
</form>
|
||
|
||
|
||
|
||
<label class="md-header__button md-icon" for="__search">
|
||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.516 6.516 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5z"/></svg>
|
||
</label>
|
||
|
||
<div class="md-search" data-md-component="search" role="dialog">
|
||
<label class="md-search__overlay" for="__search"></label>
|
||
<div class="md-search__inner" role="search">
|
||
<form class="md-search__form" name="search">
|
||
<input type="text" class="md-search__input" name="query" aria-label="Search" placeholder="Search" autocapitalize="off" autocorrect="off" autocomplete="off" spellcheck="false" data-md-component="search-query" required>
|
||
<label class="md-search__icon md-icon" for="__search">
|
||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.516 6.516 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5z"/></svg>
|
||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M20 11v2H8l5.5 5.5-1.42 1.42L4.16 12l7.92-7.92L13.5 5.5 8 11h12z"/></svg>
|
||
</label>
|
||
<nav class="md-search__options" aria-label="Search">
|
||
|
||
<button type="reset" class="md-search__icon md-icon" aria-label="Clear" tabindex="-1">
|
||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M19 6.41 17.59 5 12 10.59 6.41 5 5 6.41 10.59 12 5 17.59 6.41 19 12 13.41 17.59 19 19 17.59 13.41 12 19 6.41z"/></svg>
|
||
</button>
|
||
</nav>
|
||
|
||
<div class="md-search__suggest" data-md-component="search-suggest"></div>
|
||
|
||
</form>
|
||
<div class="md-search__output">
|
||
<div class="md-search__scrollwrap" data-md-scrollfix>
|
||
<div class="md-search-result" data-md-component="search-result">
|
||
<div class="md-search-result__meta">
|
||
Initializing search
|
||
</div>
|
||
<ol class="md-search-result__list"></ol>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
|
||
|
||
<div class="md-header__source">
|
||
|
||
<a href="https://github.com/carissalow/rapids/" title="Go to repository" class="md-source" data-md-component="source">
|
||
<div class="md-source__icon md-icon">
|
||
|
||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512"><path d="M439.55 236.05 244 40.45a28.87 28.87 0 0 0-40.81 0l-40.66 40.63 51.52 51.52c27.06-9.14 52.68 16.77 43.39 43.68l49.66 49.66c34.23-11.8 61.18 31 35.47 56.69-26.49 26.49-70.21-2.87-56-37.34L240.22 199v121.85c25.3 12.54 22.26 41.85 9.08 55a34.34 34.34 0 0 1-48.55 0c-17.57-17.6-11.07-46.91 11.25-56v-123c-20.8-8.51-24.6-30.74-18.64-45L142.57 101 8.45 235.14a28.86 28.86 0 0 0 0 40.81l195.61 195.6a28.86 28.86 0 0 0 40.8 0l194.69-194.69a28.86 28.86 0 0 0 0-40.81z"/></svg>
|
||
</div>
|
||
<div class="md-source__repository">
|
||
carissalow/rapids
|
||
</div>
|
||
</a>
|
||
</div>
|
||
|
||
</nav>
|
||
|
||
</header>
|
||
|
||
<div class="md-container" data-md-component="container">
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<main class="md-main" data-md-component="main">
|
||
<div class="md-main__inner md-grid">
|
||
|
||
|
||
|
||
<div class="md-sidebar md-sidebar--primary" data-md-component="sidebar" data-md-type="navigation" >
|
||
<div class="md-sidebar__scrollwrap">
|
||
<div class="md-sidebar__inner">
|
||
|
||
|
||
|
||
<nav class="md-nav md-nav--primary" aria-label="Navigation" data-md-level="0">
|
||
<label class="md-nav__title" for="__drawer">
|
||
<a href="../.." title="RAPIDS" class="md-nav__button md-logo" aria-label="RAPIDS" data-md-component="logo">
|
||
|
||
|
||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M19 18.31V20a2 2 0 0 1-2 2H7a2 2 0 0 1-2-2v-3.7c-.46-.18-1.05-.3-2-.3a1 1 0 0 1-1-1 1 1 0 0 1 1-1c.82 0 1.47.08 2 .21V12.3c-.46-.18-1.05-.3-2-.3a1 1 0 0 1-1-1 1 1 0 0 1 1-1c.82 0 1.47.08 2 .21V8.3C4.54 8.12 3.95 8 3 8a1 1 0 0 1-1-1 1 1 0 0 1 1-1c.82 0 1.47.08 2 .21V4a2 2 0 0 1 2-2h10a2 2 0 0 1 2 2v2.16c1.78.31 2.54.97 2.71 1.13.39.39.39 1.03 0 1.42-.39.39-.91.38-1.42 0 0 0-1.04-.71-3.29-.71-1.26 0-2.09.41-3.05.9-1.04.51-2.21 1.1-3.95 1.1-.36 0-.69 0-1-.04V7.95c.3.05.63.05 1 .05 1.26 0 2.09-.41 3.05-.89C14.09 6.59 15.27 6 17 6V4H7v16h10v-2c1.5 0 1.97.29 2 .31M17 10c-1.73 0-2.91.59-3.95 1.11-.96.48-1.79.89-3.05.89-.37 0-.7 0-1-.05v2.01c.31.04.64.04 1 .04 1.74 0 2.91-.59 3.95-1.1.96-.48 1.79-.9 3.05-.9 2.25 0 3.29.71 3.29.71.51.39 1.03.39 1.42 0 .39-.39.39-1.02 0-1.42C21.5 11.08 20.25 10 17 10m0 4c-1.73 0-2.91.59-3.95 1.11-.96.48-1.79.89-3.05.89-.37 0-.7 0-1-.05v2.01c.31.04.64.04 1 .04 1.74 0 2.91-.59 3.95-1.1.96-.48 1.79-.9 3.05-.9 2.25 0 3.29.71 3.29.71.51.39 1.03.39 1.42 0 .39-.39.39-1.02 0-1.42C21.5 15.08 20.25 14 17 14z"/></svg>
|
||
|
||
</a>
|
||
RAPIDS
|
||
</label>
|
||
|
||
<div class="md-nav__source">
|
||
|
||
<a href="https://github.com/carissalow/rapids/" title="Go to repository" class="md-source" data-md-component="source">
|
||
<div class="md-source__icon md-icon">
|
||
|
||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512"><path d="M439.55 236.05 244 40.45a28.87 28.87 0 0 0-40.81 0l-40.66 40.63 51.52 51.52c27.06-9.14 52.68 16.77 43.39 43.68l49.66 49.66c34.23-11.8 61.18 31 35.47 56.69-26.49 26.49-70.21-2.87-56-37.34L240.22 199v121.85c25.3 12.54 22.26 41.85 9.08 55a34.34 34.34 0 0 1-48.55 0c-17.57-17.6-11.07-46.91 11.25-56v-123c-20.8-8.51-24.6-30.74-18.64-45L142.57 101 8.45 235.14a28.86 28.86 0 0 0 0 40.81l195.61 195.6a28.86 28.86 0 0 0 40.8 0l194.69-194.69a28.86 28.86 0 0 0 0-40.81z"/></svg>
|
||
</div>
|
||
<div class="md-source__repository">
|
||
carissalow/rapids
|
||
</div>
|
||
</a>
|
||
</div>
|
||
|
||
<ul class="md-nav__list" data-md-scrollfix>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../.." class="md-nav__link">
|
||
Home
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
|
||
|
||
|
||
<input class="md-nav__toggle md-toggle" data-md-toggle="__nav_2" type="checkbox" id="__nav_2" >
|
||
|
||
|
||
|
||
|
||
<label class="md-nav__link" for="__nav_2">
|
||
Setup
|
||
<span class="md-nav__icon md-icon"></span>
|
||
</label>
|
||
|
||
<nav class="md-nav" aria-label="Setup" data-md-level="1">
|
||
<label class="md-nav__title" for="__nav_2">
|
||
<span class="md-nav__icon md-icon"></span>
|
||
Setup
|
||
</label>
|
||
<ul class="md-nav__list" data-md-scrollfix>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../file-structure/" class="md-nav__link">
|
||
File Structure
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../setup/installation/" class="md-nav__link">
|
||
Installation
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../setup/configuration/" class="md-nav__link">
|
||
Configuration
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../setup/execution/" class="md-nav__link">
|
||
Execution
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
</ul>
|
||
</nav>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item md-nav__item--active md-nav__item--section md-nav__item--nested">
|
||
|
||
|
||
<input class="md-nav__toggle md-toggle" data-md-toggle="__nav_3" type="checkbox" id="__nav_3" checked>
|
||
|
||
|
||
|
||
|
||
<label class="md-nav__link" for="__nav_3">
|
||
Example Workflows
|
||
<span class="md-nav__icon md-icon"></span>
|
||
</label>
|
||
|
||
<nav class="md-nav" aria-label="Example Workflows" data-md-level="1">
|
||
<label class="md-nav__title" for="__nav_3">
|
||
<span class="md-nav__icon md-icon"></span>
|
||
Example Workflows
|
||
</label>
|
||
<ul class="md-nav__list" data-md-scrollfix>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../minimal/" class="md-nav__link">
|
||
Minimal
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item md-nav__item--active">
|
||
|
||
<input class="md-nav__toggle md-toggle" data-md-toggle="toc" type="checkbox" id="__toc">
|
||
|
||
|
||
|
||
|
||
<label class="md-nav__link md-nav__link--active" for="__toc">
|
||
Analysis
|
||
<span class="md-nav__icon md-icon"></span>
|
||
</label>
|
||
|
||
<a href="./" class="md-nav__link md-nav__link--active">
|
||
Analysis
|
||
</a>
|
||
|
||
|
||
<nav class="md-nav md-nav--secondary" aria-label="Table of contents">
|
||
|
||
|
||
|
||
|
||
|
||
<label class="md-nav__title" for="__toc">
|
||
<span class="md-nav__icon md-icon"></span>
|
||
Table of contents
|
||
</label>
|
||
<ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
|
||
|
||
<li class="md-nav__item">
|
||
<a href="#why-should-i-integrate-my-analysis-in-rapids" class="md-nav__link">
|
||
Why should I integrate my analysis in RAPIDS?
|
||
</a>
|
||
|
||
</li>
|
||
|
||
<li class="md-nav__item">
|
||
<a href="#analysis-workflow-structure" class="md-nav__link">
|
||
Analysis workflow structure
|
||
</a>
|
||
|
||
</li>
|
||
|
||
<li class="md-nav__item">
|
||
<a href="#description-of-the-study-modeled-in-our-analysis-workflow-example" class="md-nav__link">
|
||
Description of the study modeled in our analysis workflow example
|
||
</a>
|
||
|
||
</li>
|
||
|
||
<li class="md-nav__item">
|
||
<a href="#configure-and-run-the-analysis-workflow-example" class="md-nav__link">
|
||
Configure and run the analysis workflow example
|
||
</a>
|
||
|
||
</li>
|
||
|
||
<li class="md-nav__item">
|
||
<a href="#modules-of-our-analysis-workflow-example" class="md-nav__link">
|
||
Modules of our analysis workflow example
|
||
</a>
|
||
|
||
</li>
|
||
|
||
</ul>
|
||
|
||
</nav>
|
||
|
||
</li>
|
||
|
||
|
||
|
||
|
||
</ul>
|
||
</nav>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
|
||
|
||
|
||
<input class="md-nav__toggle md-toggle" data-md-toggle="__nav_4" type="checkbox" id="__nav_4" >
|
||
|
||
|
||
|
||
|
||
<label class="md-nav__link" for="__nav_4">
|
||
Behavioral Features
|
||
<span class="md-nav__icon md-icon"></span>
|
||
</label>
|
||
|
||
<nav class="md-nav" aria-label="Behavioral Features" data-md-level="1">
|
||
<label class="md-nav__title" for="__nav_4">
|
||
<span class="md-nav__icon md-icon"></span>
|
||
Behavioral Features
|
||
</label>
|
||
<ul class="md-nav__list" data-md-scrollfix>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../features/feature-introduction/" class="md-nav__link">
|
||
Introduction
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item md-nav__item--nested">
|
||
|
||
|
||
<input class="md-nav__toggle md-toggle" data-md-toggle="__nav_4_2" type="checkbox" id="__nav_4_2" >
|
||
|
||
|
||
|
||
|
||
<label class="md-nav__link" for="__nav_4_2">
|
||
Phone
|
||
<span class="md-nav__icon md-icon"></span>
|
||
</label>
|
||
|
||
<nav class="md-nav" aria-label="Phone" data-md-level="2">
|
||
<label class="md-nav__title" for="__nav_4_2">
|
||
<span class="md-nav__icon md-icon"></span>
|
||
Phone
|
||
</label>
|
||
<ul class="md-nav__list" data-md-scrollfix>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../features/phone-accelerometer/" class="md-nav__link">
|
||
Phone Accelerometer
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../features/phone-activity-recognition/" class="md-nav__link">
|
||
Phone Activity Recognition
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../features/phone-applications-foreground/" class="md-nav__link">
|
||
Phone Applications Foreground
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../features/phone-battery/" class="md-nav__link">
|
||
Phone Battery
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../features/phone-bluetooth/" class="md-nav__link">
|
||
Phone Bluetooth
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../features/phone-calls/" class="md-nav__link">
|
||
Phone Calls
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../features/phone-conversation/" class="md-nav__link">
|
||
Phone Conversation
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../features/phone-data-yield/" class="md-nav__link">
|
||
Phone Data Yield
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../features/phone-light/" class="md-nav__link">
|
||
Phone Light
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../features/phone-locations/" class="md-nav__link">
|
||
Phone Locations
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../features/phone-messages/" class="md-nav__link">
|
||
Phone Messages
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../features/phone-screen/" class="md-nav__link">
|
||
Phone Screen
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../features/phone-wifi-connected/" class="md-nav__link">
|
||
Phone WiFI Connected
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../features/phone-wifi-visible/" class="md-nav__link">
|
||
Phone WiFI Visible
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
</ul>
|
||
</nav>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item md-nav__item--nested">
|
||
|
||
|
||
<input class="md-nav__toggle md-toggle" data-md-toggle="__nav_4_3" type="checkbox" id="__nav_4_3" >
|
||
|
||
|
||
|
||
|
||
<label class="md-nav__link" for="__nav_4_3">
|
||
Fitbit
|
||
<span class="md-nav__icon md-icon"></span>
|
||
</label>
|
||
|
||
<nav class="md-nav" aria-label="Fitbit" data-md-level="2">
|
||
<label class="md-nav__title" for="__nav_4_3">
|
||
<span class="md-nav__icon md-icon"></span>
|
||
Fitbit
|
||
</label>
|
||
<ul class="md-nav__list" data-md-scrollfix>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../features/fitbit-heartrate-summary/" class="md-nav__link">
|
||
Fitbit Heart Rate Summary
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../features/fitbit-heartrate-intraday/" class="md-nav__link">
|
||
Fitbit Heart Rate Intraday
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../features/fitbit-sleep-summary/" class="md-nav__link">
|
||
Fitbit Sleep Summary
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../features/fitbit-steps-summary/" class="md-nav__link">
|
||
Fitbit Steps Summary
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../features/fitbit-steps-intraday/" class="md-nav__link">
|
||
Fitbit Steps Intraday
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
</ul>
|
||
</nav>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../features/add-new-features/" class="md-nav__link">
|
||
Add New Features
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
</ul>
|
||
</nav>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
|
||
|
||
|
||
<input class="md-nav__toggle md-toggle" data-md-toggle="__nav_5" type="checkbox" id="__nav_5" >
|
||
|
||
|
||
|
||
|
||
<label class="md-nav__link" for="__nav_5">
|
||
Visualizations
|
||
<span class="md-nav__icon md-icon"></span>
|
||
</label>
|
||
|
||
<nav class="md-nav" aria-label="Visualizations" data-md-level="1">
|
||
<label class="md-nav__title" for="__nav_5">
|
||
<span class="md-nav__icon md-icon"></span>
|
||
Visualizations
|
||
</label>
|
||
<ul class="md-nav__list" data-md-scrollfix>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../visualizations/data-quality-visualizations/" class="md-nav__link">
|
||
Data Quality
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../visualizations/feature-visualizations/" class="md-nav__link">
|
||
Features
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
</ul>
|
||
</nav>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
|
||
|
||
|
||
<input class="md-nav__toggle md-toggle" data-md-toggle="__nav_6" type="checkbox" id="__nav_6" >
|
||
|
||
|
||
|
||
|
||
<label class="md-nav__link" for="__nav_6">
|
||
Developers
|
||
<span class="md-nav__icon md-icon"></span>
|
||
</label>
|
||
|
||
<nav class="md-nav" aria-label="Developers" data-md-level="1">
|
||
<label class="md-nav__title" for="__nav_6">
|
||
<span class="md-nav__icon md-icon"></span>
|
||
Developers
|
||
</label>
|
||
<ul class="md-nav__list" data-md-scrollfix>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../developers/remote-support/" class="md-nav__link">
|
||
Remote Support
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../developers/virtual-environments/" class="md-nav__link">
|
||
Virtual Environments
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../developers/documentation/" class="md-nav__link">
|
||
Documentation
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../developers/testing/" class="md-nav__link">
|
||
Testing
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../developers/test-cases/" class="md-nav__link">
|
||
Test cases
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
</ul>
|
||
</nav>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
|
||
|
||
|
||
<input class="md-nav__toggle md-toggle" data-md-toggle="__nav_7" type="checkbox" id="__nav_7" >
|
||
|
||
|
||
|
||
|
||
<label class="md-nav__link" for="__nav_7">
|
||
Others
|
||
<span class="md-nav__icon md-icon"></span>
|
||
</label>
|
||
|
||
<nav class="md-nav" aria-label="Others" data-md-level="1">
|
||
<label class="md-nav__title" for="__nav_7">
|
||
<span class="md-nav__icon md-icon"></span>
|
||
Others
|
||
</label>
|
||
<ul class="md-nav__list" data-md-scrollfix>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../migrating-from-old-versions/" class="md-nav__link">
|
||
Migrating from beta
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../code_of_conduct/" class="md-nav__link">
|
||
Code of Conduct
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../faq/" class="md-nav__link">
|
||
FAQ
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../team/" class="md-nav__link">
|
||
Team
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../change-log/" class="md-nav__link">
|
||
Change Log
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<li class="md-nav__item">
|
||
<a href="../../citation/" class="md-nav__link">
|
||
Citation
|
||
</a>
|
||
</li>
|
||
|
||
|
||
|
||
|
||
</ul>
|
||
</nav>
|
||
</li>
|
||
|
||
|
||
|
||
</ul>
|
||
</nav>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
|
||
|
||
|
||
<div class="md-sidebar md-sidebar--secondary" data-md-component="sidebar" data-md-type="toc" >
|
||
<div class="md-sidebar__scrollwrap">
|
||
<div class="md-sidebar__inner">
|
||
|
||
<nav class="md-nav md-nav--secondary" aria-label="Table of contents">
|
||
|
||
|
||
|
||
|
||
|
||
<label class="md-nav__title" for="__toc">
|
||
<span class="md-nav__icon md-icon"></span>
|
||
Table of contents
|
||
</label>
|
||
<ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
|
||
|
||
<li class="md-nav__item">
|
||
<a href="#why-should-i-integrate-my-analysis-in-rapids" class="md-nav__link">
|
||
Why should I integrate my analysis in RAPIDS?
|
||
</a>
|
||
|
||
</li>
|
||
|
||
<li class="md-nav__item">
|
||
<a href="#analysis-workflow-structure" class="md-nav__link">
|
||
Analysis workflow structure
|
||
</a>
|
||
|
||
</li>
|
||
|
||
<li class="md-nav__item">
|
||
<a href="#description-of-the-study-modeled-in-our-analysis-workflow-example" class="md-nav__link">
|
||
Description of the study modeled in our analysis workflow example
|
||
</a>
|
||
|
||
</li>
|
||
|
||
<li class="md-nav__item">
|
||
<a href="#configure-and-run-the-analysis-workflow-example" class="md-nav__link">
|
||
Configure and run the analysis workflow example
|
||
</a>
|
||
|
||
</li>
|
||
|
||
<li class="md-nav__item">
|
||
<a href="#modules-of-our-analysis-workflow-example" class="md-nav__link">
|
||
Modules of our analysis workflow example
|
||
</a>
|
||
|
||
</li>
|
||
|
||
</ul>
|
||
|
||
</nav>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
|
||
|
||
<div class="md-content" data-md-component="content">
|
||
<article class="md-content__inner md-typeset">
|
||
|
||
|
||
<a href="https://github.com/carissalow/rapids/edit/master/docs/workflow-examples/analysis.md" title="Edit this page" class="md-content__button md-icon">
|
||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M20.71 7.04c.39-.39.39-1.04 0-1.41l-2.34-2.34c-.37-.39-1.02-.39-1.41 0l-1.84 1.83 3.75 3.75M3 17.25V21h3.75L17.81 9.93l-3.75-3.75L3 17.25z"/></svg>
|
||
</a>
|
||
|
||
|
||
<h1 id="analysis-workflow-example">Analysis Workflow Example<a class="headerlink" href="#analysis-workflow-example" title="Permanent link">¶</a></h1>
|
||
<div class="admonition info">
|
||
<p class="admonition-title">TL;DR</p>
|
||
<ul>
|
||
<li>In addition to using RAPIDS to extract behavioral features and create plots, you can structure your data analysis within RAPIDS (i.e. cleaning your features and creating ML/statistical models)</li>
|
||
<li>We include an analysis example in RAPIDS that covers raw data processing, cleaning, feature extraction, machine learning modeling, and evaluation</li>
|
||
<li>Use this example as a guide to structure your own analysis within RAPIDS</li>
|
||
<li>RAPIDS analysis workflows are compatible with your favorite data science tools and libraries</li>
|
||
<li>RAPIDS analysis workflows are reproducible and we encourage you to publish them along with your research papers</li>
|
||
</ul>
|
||
</div>
|
||
<h2 id="why-should-i-integrate-my-analysis-in-rapids">Why should I integrate my analysis in RAPIDS?<a class="headerlink" href="#why-should-i-integrate-my-analysis-in-rapids" title="Permanent link">¶</a></h2>
|
||
<p>Even though the bulk of RAPIDS current functionality is related to the computation of behavioral features, we recommend RAPIDS as a complementary tool to create a mobile data analysis workflow. This is because the cookiecutter data science file organization guidelines, the use of Snakemake, the provided behavioral features, and the reproducible R and Python development environments allow researchers to divide an analysis workflow into small parts that can be audited, shared in an online repository, reproduced in other computers, and understood by other people as they follow a familiar and consistent structure. We believe these advantages outweigh the time needed to learn how to create these workflows in RAPIDS.</p>
|
||
<p>We clarify that to create analysis workflows in RAPIDS, researchers can still use any data manipulation tools, editors, libraries or languages they are already familiar with. RAPIDS is meant to be the final destination of analysis code that was developed in interactive notebooks or stand-alone scripts. For example, a user can compute call and location features using RAPIDS, then, they can use Jupyter notebooks to explore feature cleaning approaches and once the cleaning code is final, it can be moved to RAPIDS as a new step in the pipeline. In turn, the output of this cleaning step can be used to explore machine learning models and once a model is finished, it can also be transferred to RAPIDS as a step of its own. The idea is that when it is time to publish a piece of research, a RAPIDS workflow can be shared in a public repository as is.</p>
|
||
<p>In the following sections we share an example of how we structured an analysis workflow in RAPIDS.</p>
|
||
<h2 id="analysis-workflow-structure">Analysis workflow structure<a class="headerlink" href="#analysis-workflow-structure" title="Permanent link">¶</a></h2>
|
||
<p>To accurately reflect the complexity of a real-world modeling scenario, we decided not to oversimplify this example. Importantly, every step in this example follows a basic structure: an input file and parameters are manipulated by an R or Python script that saves the results to an output file. Input files, parameters, output files and scripts are grouped into Snakemake rules that are described on <code>smk</code> files in the rules folder (we point the reader to the relevant rule(s) of each step). </p>
|
||
<p>Researchers can use these rules and scripts as a guide to create their own as it is expected every modeling project will have different requirements, data and goals but ultimately most follow a similar chainned pattern.</p>
|
||
<div class="admonition hint">
|
||
<p class="admonition-title">Hint</p>
|
||
<p>The example’s config file is <code>example_profile/example_config.yaml</code> and its Snakefile is in <code>example_profile/Snakefile</code>. The config file is already configured to process the sensor data as explained in <a href="#analysis-workflow-modules">Analysis workflow modules</a>.</p>
|
||
</div>
|
||
<h2 id="description-of-the-study-modeled-in-our-analysis-workflow-example">Description of the study modeled in our analysis workflow example<a class="headerlink" href="#description-of-the-study-modeled-in-our-analysis-workflow-example" title="Permanent link">¶</a></h2>
|
||
<p>Our example is based on a hypothetical study that recruited 2 participants that underwent surgery and collected mobile data for at least one week before and one week after the procedure. Participants wore a Fitbit device and installed the AWARE client in their personal Android and iOS smartphones to collect mobile data 24/7. In addition, participants completed daily severity ratings of 12 common symptoms on a scale from 0 to 10 that we summed up into a daily symptom burden score. </p>
|
||
<p>The goal of this workflow is to find out if we can predict the daily symptom burden score of a participant. Thus, we framed this question as a binary classification problem with two classes, high and low symptom burden based on the scores above and below average of each participant. We also want to compare the performance of individual (personalized) models vs a population model. </p>
|
||
<p>In total, our example workflow has nine steps that are in charge of sensor data preprocessing, feature extraction, feature cleaning, machine learning model training and model evaluation (see figure below). We ship this workflow with RAPIDS and share a database with <a href="https://osf.io/skqfv/files/">test data</a> in an Open Science Framework repository. </p>
|
||
<figure>
|
||
<img src="../../img/analysis_workflow.png" max-width="100%" />
|
||
<figcaption>Modules of RAPIDS example workflow, from raw data to model evaluation</figcaption>
|
||
</figure>
|
||
|
||
<h2 id="configure-and-run-the-analysis-workflow-example">Configure and run the analysis workflow example<a class="headerlink" href="#configure-and-run-the-analysis-workflow-example" title="Permanent link">¶</a></h2>
|
||
<ol>
|
||
<li><a href="../../setup/installation">Install</a> RAPIDS</li>
|
||
<li>Configure the <a href="../../setup/configuration/#database-credentials">user credentials</a> of a local or remote MySQL server with writing permissions in your <code>.env</code> file. The example config file is at <code>example_profile/example_config.yaml</code>.</li>
|
||
<li>Unzip the <a href="https://osf.io/skqfv/files/">test database</a> to <code>data/external/rapids_example.sql</code> and run:
|
||
<div class="highlight"><pre><span></span><code>./rapids -j1 restore_sql_file --profile example_profile
|
||
</code></pre></div></li>
|
||
<li>Create the participant files for this example by running:
|
||
<div class="highlight"><pre><span></span><code>./rapids -j1 create_example_participant_files
|
||
</code></pre></div></li>
|
||
<li>Run the example pipeline with:
|
||
<div class="highlight"><pre><span></span><code>./rapids -j1 --profile example_profile
|
||
</code></pre></div></li>
|
||
</ol>
|
||
<h2 id="modules-of-our-analysis-workflow-example">Modules of our analysis workflow example<a class="headerlink" href="#modules-of-our-analysis-workflow-example" title="Permanent link">¶</a></h2>
|
||
<details class="info"><summary>1. Feature extraction</summary><p>We extract daily behavioral features for data yield, received and sent messages, missed, incoming and outgoing calls, resample fused location data using Doryab provider, activity recognition, battery, Bluetooth, screen, light, applications foreground, conversations, Wi-Fi connected, Wi-Fi visible, Fitbit heart rate summary and intraday data, Fitbit sleep summary data, and Fitbit step summary and intraday data without excluding sleep periods with an active bout threshold of 10 steps. In total, we obtained 237 daily sensor features over 12 days per participant. </p>
|
||
</details>
|
||
<details class="info"><summary>2. Extract demographic data.</summary><p>It is common to have demographic data in addition to mobile and target (ground truth) data. In this example we include participants’ age, gender and the number of days they spent in hospital after their surgery as features in our model. We extract these three columns from the participant_info table of our test database . As these three features remain the same within participants, they are used only on the population model. Refer to the <code>demographic_features</code> rule in <code>rules/models.smk</code>.</p>
|
||
</details>
|
||
<details class="info"><summary>3. Create target labels.</summary><p>The two classes for our machine learning binary classification problem are high and low symptom burden. Target values are already stored in the <code>participant_target</code> table of our test database and transferred to a CSV file. A new rule/script can be created if further manipulation is necessary. Refer to the <code>parse_targets</code> rule in <code>rules/models.smk</code>.</p>
|
||
</details>
|
||
<details class="info"><summary>4. Feature merging.</summary><p>These daily features are stored on a CSV file per sensor, a CSV file per participant, and a CSV file including all features from all participants (in every case each column represents a feature and each row represents a day). Refer to the <code>merge_sensor_features_for_individual_participants</code> and <code>merge_features_for_population_model</code> rules in <code>rules/features.smk</code>.</p>
|
||
</details>
|
||
<details class="info"><summary>5. Data visualization.</summary><p>At this point the user can use the five plots RAPIDS provides (or implement new ones) to explore and understand the quality of the raw data and extracted features and decide what sensors, days, or participants to include and exclude. Refer to <code>rules/reports.smk</code> to find the rules that generate these plots.</p>
|
||
</details>
|
||
<details class="info"><summary>6. Feature cleaning.</summary><p>In this stage we perform four steps to clean our sensor feature file. First, we discard days with a data yield hour ratio less than or equal to 0.75, i.e. we include days with at least 18 hours of data. Second, we drop columns (features) with more than 30% of missing rows. Third, we drop columns with zero variance. Fourth, we drop rows (days) with more than 30% of missing columns (features). In this cleaning stage several parameters are created and exposed in <code>example_profile/example_config.yaml</code>. </p>
|
||
<p>After this step, we kept 162 features over 11 days for the individual model of p01, 107 features over 12 days for the individual model of p02 and 101 features over 20 days for the population model. Note that the difference in the number of features between p01 and p02 is mostly due to iOS restrictions that stops researchers from collecting the same number of sensors than in Android phones. </p>
|
||
<p>Feature cleaning for the individual models is done in the <code>clean_sensor_features_for_individual_participants</code> rule and for the population model in the <code>clean_sensor_features_for_all_participants</code> rule in <code>rules/models.smk</code>.</p>
|
||
</details>
|
||
<details class="info"><summary>7. Merge features and targets.</summary><p>In this step we merge the cleaned features and target labels for our individual models in the <code>merge_features_and_targets_for_individual_model</code> rule in <code>rules/models.smk</code>. Additionally, we merge the cleaned features, target labels, and demographic features of our two participants for the population model in the <code>merge_features_and_targets_for_population_model</code> rule in <code>rules/models.smk</code>. These two merged files are the input for our individual and population models. </p>
|
||
</details>
|
||
<details class="info"><summary>8. Modelling.</summary><p>This stage has three phases: model building, training and evaluation. </p>
|
||
<p>In the building phase we impute, normalize and oversample our dataset. Missing numeric values in each column are imputed with their mean and we impute missing categorical values with their mode. We normalize each numeric column with one of three strategies (min-max, z-score, and scikit-learn package’s robust scaler) and we one-hot encode each categorial feature as a numerical array. We oversample our imbalanced dataset using SMOTE (Synthetic Minority Over-sampling Technique) or a Random Over sampler from scikit-learn. All these parameters are exposed in <code>example_profile/example_config.yaml</code>.</p>
|
||
<p>In the training phase, we create eight models: logistic regression, k-nearest neighbors, support vector machine, decision tree, random forest, gradient boosting classifier, extreme gradient boosting classifier and a light gradient boosting machine. We cross-validate each model with an inner cycle to tune hyper-parameters based on the Macro F1 score and an outer cycle to predict the test set on a model with the best hyper-parameters. Both cross-validation cycles use a leave-one-out strategy. Parameters for each model like weights and learning rates are exposed in <code>example_profile/example_config.yaml</code>.</p>
|
||
<p>Finally, in the evaluation phase we compute the accuracy, Macro F1, kappa, area under the curve and per class precision, recall and F1 score of all folds of the outer cross-validation cycle.</p>
|
||
<p>Refer to the <code>modelling_for_individual_participants</code> rule for the individual modeling and to the <code>modelling_for_all_participants</code> rule for the population modeling, both in <code>rules/models.smk</code>.</p>
|
||
</details>
|
||
<details class="info"><summary>9. Compute model baselines.</summary><p>We create three baselines to evaluate our classification models.</p>
|
||
<p>First, a majority classifier that labels each test sample with the majority class of our training data. Second, a random weighted classifier that predicts each test observation sampling at random from a binomial distribution based on the ratio of our target labels. Third, a decision tree classifier based solely on the demographic features of each participant. As we do not have demographic features for individual model, this baseline is only available for population model. </p>
|
||
<p>Our baseline metrics (e.g. accuracy, precision, etc.) are saved into a CSV file, ready to be compared to our modeling results. Refer to the <code>baselines_for_individual_model</code> rule for the individual model baselines and to the <code>baselines_for_population_model</code> rule for population model baselines, both in <code>rules/models.smk</code>.</p>
|
||
</details>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
</article>
|
||
</div>
|
||
</div>
|
||
|
||
</main>
|
||
|
||
|
||
<footer class="md-footer">
|
||
|
||
<nav class="md-footer__inner md-grid" aria-label="Footer">
|
||
|
||
<a href="../minimal/" class="md-footer__link md-footer__link--prev" rel="prev">
|
||
<div class="md-footer__button md-icon">
|
||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M20 11v2H8l5.5 5.5-1.42 1.42L4.16 12l7.92-7.92L13.5 5.5 8 11h12z"/></svg>
|
||
</div>
|
||
<div class="md-footer__title">
|
||
<div class="md-ellipsis">
|
||
<span class="md-footer__direction">
|
||
Previous
|
||
</span>
|
||
Minimal
|
||
</div>
|
||
</div>
|
||
</a>
|
||
|
||
|
||
<a href="../../features/feature-introduction/" class="md-footer__link md-footer__link--next" rel="next">
|
||
<div class="md-footer__title">
|
||
<div class="md-ellipsis">
|
||
<span class="md-footer__direction">
|
||
Next
|
||
</span>
|
||
Introduction
|
||
</div>
|
||
</div>
|
||
<div class="md-footer__button md-icon">
|
||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M4 11v2h12l-5.5 5.5 1.42 1.42L19.84 12l-7.92-7.92L10.5 5.5 16 11H4z"/></svg>
|
||
</div>
|
||
</a>
|
||
|
||
</nav>
|
||
|
||
<div class="md-footer-meta md-typeset">
|
||
<div class="md-footer-meta__inner md-grid">
|
||
<div class="md-footer-copyright">
|
||
|
||
<div class="md-footer-copyright__highlight">
|
||
Released under AGPL
|
||
</div>
|
||
|
||
|
||
Made with
|
||
<a href="https://squidfunk.github.io/mkdocs-material/" target="_blank" rel="noopener">
|
||
Material for MkDocs Insiders
|
||
</a>
|
||
|
||
|
||
</div>
|
||
|
||
<div class="md-footer-social">
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<a href="https://twitter.com/julio_ui" target="_blank" rel="noopener" title="twitter.com" class="md-footer-social__link">
|
||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512"><path d="M459.37 151.716c.325 4.548.325 9.097.325 13.645 0 138.72-105.583 298.558-298.558 298.558-59.452 0-114.68-17.219-161.137-47.106 8.447.974 16.568 1.299 25.34 1.299 49.055 0 94.213-16.568 130.274-44.832-46.132-.975-84.792-31.188-98.112-72.772 6.498.974 12.995 1.624 19.818 1.624 9.421 0 18.843-1.3 27.614-3.573-48.081-9.747-84.143-51.98-84.143-102.985v-1.299c13.969 7.797 30.214 12.67 47.431 13.319-28.264-18.843-46.781-51.005-46.781-87.391 0-19.492 5.197-37.36 14.294-52.954 51.655 63.675 129.3 105.258 216.365 109.807-1.624-7.797-2.599-15.918-2.599-24.04 0-57.828 46.782-104.934 104.934-104.934 30.213 0 57.502 12.67 76.67 33.137 23.715-4.548 46.456-13.32 66.599-25.34-7.798 24.366-24.366 44.833-46.132 57.827 21.117-2.273 41.584-8.122 60.426-16.243-14.292 20.791-32.161 39.308-52.628 54.253z"/></svg>
|
||
</a>
|
||
|
||
</div>
|
||
|
||
</div>
|
||
</div>
|
||
</footer>
|
||
|
||
</div>
|
||
<div class="md-dialog" data-md-component="dialog">
|
||
<div class="md-dialog__inner md-typeset"></div>
|
||
</div>
|
||
<script id="__config" type="application/json">{"base": "../..", "features": ["navigation.sections", "search.suggest", "search.highlight"], "translations": {"clipboard.copy": "Copy to clipboard", "clipboard.copied": "Copied to clipboard", "search.config.lang": "en", "search.config.pipeline": "trimmer, stopWordFilter", "search.config.separator": "[\\s\\-]+", "search.placeholder": "Search", "search.result.placeholder": "Type to start searching", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.term.missing": "Missing"}, "search": "../../assets/javascripts/workers/search.d10a1f1d.min.js", "version": {"provider": "mike"}}</script>
|
||
|
||
|
||
<script src="../../assets/javascripts/bundle.9aafa2c6.min.js"></script>
|
||
|
||
<script src="https://polyfill.io/v3/polyfill.min.js?features=es6"></script>
|
||
|
||
<script src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js"></script>
|
||
|
||
|
||
</body>
|
||
</html> |