SpatialDataScience/01_Rintro.html at dev · learner-python-R/SpatialDataScience

History

741 lines (661 loc) · 22.9 KB

Raw

100

101

102

103

104

105

106

107

108

109

110

111

112

113

114

115

116

117

118

119

120

121

122

123

124

125

126

127

128

129

130

131

132

133

134

135

136

137

138

139

140

141

142

143

144

145

146

147

148

149

150

151

152

153

154

155

156

157

158

159

160

161

162

163

164

165

166

167

168

169

170

171

172

173

174

175

176

177

178

179

180

181

182

183

184

185

186

187

188

189

190

191

192

193

194

195

196

197

198

199

200

201

202

203

204

205

206

207

208

209

210

211

212

213

214

215

216

217

218

219

220

221

222

223

224

225

226

227

228

229

230

231

232

233

234

235

236

237

238

239

240

241

242

243

244

245

246

247

248

249

250

251

252

253

254

255

256

257

258

259

260

261

262

263

264

265

266

267

268

269

270

271

272

273

274

275

276

277

278

279

280

281

282

283

284

285

286

287

288

289

290

291

292

293

294

295

296

297

298

299

300

301

302

303

304

305

306

307

308

309

310

311

312

313

314

315

316

317

318

319

320

321

322

323

324

325

326

327

328

329

330

331

332

333

334

335

336

337

338

339

340

341

342

343

344

345

346

347

348

349

350

351

352

353

354

355

356

357

358

359

360

361

362

363

364

365

366

367

368

369

370

371

372

373

374

375

376

377

378

379

380

381

382

383

384

385

386

387

388

389

390

391

392

393

394

395

396

397

398

399

400

401

402

403

404

405

406

407

408

409

410

411

412

413

414

415

416

417

418

419

420

421

422

423

424

425

426

427

428

429

430

431

432

433

434

435

436

437

438

439

440

441

442

443

444

445

446

447

448

449

450

451

452

453

454

455

456

457

458

459

460

461

462

463

464

465

466

467

468

469

470

471

472

473

474

475

476

477

478

479

480

481

482

483

484

485

486

487

488

489

490

491

492

493

494

495

496

497

498

499

500

501

502

503

504

505

506

507

508

509

510

511

512

513

514

515

516

517

518

519

520

521

522

523

524

525

526

527

528

529

530

531

532

533

534

535

536

537

538

539

540

541

542

543

544

545

546

547

548

549

550

551

552

553

554

555

556

557

558

559

560

561

562

563

564

565

566

567

568

569

570

571

572

573

574

575

576

577

578

579

580

581

582

583

584

585

586

587

588

589

590

591

592

593

594

595

596

597

598

599

600

601

602

603

604

605

606

607

608

609

610

611

612

613

614

615

616

617

618

619

620

621

622

623

624

625

626

627

628

629

630

631

632

633

634

635

636

637

638

639

640

641

642

643

644

645

646

647

648

649

650

651

652

653

654

655

656

657

658

659

660

661

662

663

664

665

666

667

668

669

670

671

672

673

674

675

676

677

678

679

680

681

682

683

684

685

686

687

688

689

690

691

692

693

694

695

696

697

698

699

700

701

702

703

704

705

706

707

708

709

710

711

712

713

714

715

716

717

718

719

720

721

722

723

724

725

726

727

728

729

730

731

732

733

734

735

736

737

738

739

740

741

<!DOCTYPE html>

<head>

<title>Introduction to R</title>

pre:not([class]) {

background-color: white;

}

</style>

if (window.hljs) {

hljs.configure({languages: []});

hljs.initHighlightingOnLoad();

if (document.readyState && document.readyState === "complete") {

window.setTimeout(function() { hljs.initHighlighting(); }, 0);

}

</script>

h1 {

font-size: 34px;

}

h1.title {

font-size: 38px;

}

h2 {

font-size: 30px;

}

h3 {

font-size: 24px;

}

h4 {

font-size: 18px;

}

h5 {

font-size: 16px;

}

h6 {

font-size: 12px;

}

.table th:not([align]) {

text-align: left;

}

</style>

</head>

<body>

.main-container {

max-width: 940px;

margin-left: auto;

margin-right: auto;

}

code {

color: inherit;

background-color: rgba(0, 0, 0, 0.04);

}

img {

max-width:100%;

height: auto;

}

.tabbed-pane {

padding-top: 12px;

}

.html-widget {

margin-bottom: 20px;

}

button.code-folding-btn:focus {

outline: none;

}

</style>

/* padding for bootstrap navbar */

body {

padding-top: 51px;

padding-bottom: 40px;

}

/* offset scroll position for anchor links (for fixed navbar) */

.section h1 {

padding-top: 56px;

margin-top: -56px;

}

.section h2 {

padding-top: 56px;

margin-top: -56px;

}

.section h3 {

padding-top: 56px;

margin-top: -56px;

}

.section h4 {

padding-top: 56px;

margin-top: -56px;

}

.section h5 {

padding-top: 56px;

margin-top: -56px;

}

.section h6 {

padding-top: 56px;

margin-top: -56px;

}

</style>

// manage active state of menu based on current page

$(document).ready(function () {

// active menu anchor

href = window.location.pathname

href = href.substr(href.lastIndexOf('/') + 1)

if (href === "")

href = "index.html";

var menuAnchor = $('a[href="' + href + '"]');

// mark it active

menuAnchor.parent().addClass('active');

// if it's got a parent navbar menu mark it active as well

menuAnchor.closest('li.dropdown').addClass('active');

});

</script>

$(document).ready(function () {

window.buildTabsets("TOC");

});

</script>

$(document).ready(function () {

// move toc-ignore selectors from section div to header

$('div.section.toc-ignore')

.removeClass('toc-ignore')

.children('h1,h2,h3,h4,h5').addClass('toc-ignore');

// establish options

var options = {

selectors: "h1,h2",

theme: "bootstrap3",

context: '.toc-content',

hashGenerator: function (text) {

return text.replace(/[.\\/?&!#<>]/g, '').replace(/\s/g, '_').toLowerCase();

ignoreSelector: ".toc-ignore",

scrollTo: 0

};

options.showAndHide = true;

options.smoothScroll = true;

// tocify

var toc = $("#TOC").tocify(options).data("toc-tocify");

});

</script>

#TOC {

margin: 25px 0px 20px 0px;

}

@media (max-width: 768px) {

#TOC {

position: relative;

width: 100%;

}

.toc-content {

padding-left: 30px;

padding-right: 40px;

}

div.main-container {

max-width: 1200px;

}

div.tocify {

width: 20%;

max-width: 260px;

max-height: 85%;

}

@media (min-width: 768px) and (max-width: 991px) {

div.tocify {

width: 25%;

}

@media (max-width: 767px) {

div.tocify {

width: 100%;

max-width: none;

}

.tocify ul, .tocify li {

line-height: 20px;

}

.tocify-subheader .tocify-item {

font-size: 0.90em;

padding-left: 25px;

text-indent: 0;

}

.tocify .list-group-item {

border-radius: 0px;

}

</style>

</div>

</button>

<a class="navbar-brand" href="index.html">GEO 503: Spatial Data Science</a>

</div>

<li>

</li>

<li>

<a href="Syllabus.html">Syllabus</a>

</li>

<li>

<a href="Schedule.html">Schedule</a>

</li>

Content

</a>

<li>

<a href="CourseContent.html">About Course Content</a>

</li>

<li class="dropdown-header">Module 1: Introduction to R</li>

<li>

<a href="00_CourseIntroductionFrame.html">00 Course Introduction</a>

</li>

<li>

<a href="01_Rintro.html">01 First Steps</a>

</li>

<li>

<a href="02_graphics.html">02 Graphics</a>

</li>

<li>

<a href="03_DataWrangling.html">03 Data Wrangling</a>

</li>

<li>

<a href="03b_DataWrangling.html">03 Data Wrangling 2</a>

</li>

<li class="dropdown-header">Module 2: Spatial Analyses</li>

<li>

<a href="04_Spatial_with_sf.html">04 Spatial Data with sf</a>

</li>

<li>

<a href="05_Raster.html">05 Spatial Raster Data</a>

</li>

<li class="dropdown-header">Module 3: Advanced Programming</li>

<li>

<a href="06_CreatingWorkflows.html">06 Creating Workflows</a>

</li>

<li>

<a href="07_Reproducibile.html">07 Reproducible Research</a>

</li>

<li>

<a href="08_WeatherData.html">08 Weather Data Processing</a>

</li>

<li>

<a href="09_RemoteSensing_appeears.html">09 Satellite Data Processing</a>

</li>

<li>

<a href="11_ParallelProcessing.html">11 Parallel Processing</a>

</li>

<li>

<a href="12_DynamicVisualization.html">12 Dynamic Visualization</a>

</li>

<li>

<a href="13_SDM_Exercise.html">13 Species Distribution Modeling</a>

</li>

</ul>

</li>

Assignments

</a>

<li>

</li>

<li>

<a href="DataCamp.html">DataCamp</a>

</li>

<li>

<a href="PackageIntro.html">Package Introduction</a>

</li>

<li>

<a href="Project.html">Final Project</a>

</li>

</ul>

</li>

Resources

</a>

<li>

<a href="Provenance.html">Provenance</a>

</li>

<li>

<a href="Projects_2017.html">2017 Final Projects</a>

</li>

<li>

<a href="Resources.html">Resources</a>

</li>

<li>

<a href="GitSSHNotes.html">Setting up Github</a>

</li>

</ul>

</li>

</ul>

<li>

</a>

</li>

</ul>

</div>

</div>

</div>

<h1 class="title toc-ignore">Introduction to R</h1>

</div>

<h1>Logistics</h1>

<p><a href="presentations/PS_01_intro.html" target="_blank"><i class="fas fa-desktop fa-3x" aria-hidden="true"></i> Presentation</a></p>

<p><a href="scripts/01_Rintro.R" target="_blank"><i class="fa fa-file-code-o fa-3x" aria-hidden="true"></i> R Script</a> Download this file and open it (or copy-paste into a new script) with RStudio so you can follow along.</p>

</div>

<h1>First Steps</h1>

<h2>Variables</h2>

<pre class="r"><code>x=1

x</code></pre>

<p>We can also assign a vector to a variable:</p>

<pre class="r"><code>x=c(5,8,14,91,3,36,14,30)

x</code></pre>

<p>And do simple arithmetic:</p>

<p>Create a new variable called <code>y</code> and set it to <code>15</code></p>

Show Solution

</button>

</div>

<p>Note that <code>R</code> is case sensitive, if you ask for <code>X</code> instead of <code>x</code>, you will get an error</p>

<pre class="r"><code>X

Error: object 'X' not found</code></pre>

<h3>Variable naming conventions</h3>

<p>Naming your variables is your business, but there are <a href="http://www.r-bloggers.com/consistent-naming-conventions-in-r/">5 conventions</a> to be aware of:</p>

<ul>

<li><strong>alllowercase</strong>: <em>e.g.</em> <code>adjustcolor</code></li>

<li><strong>period.separated</strong>: <em>e.g.</em> <code>plot.new</code></li>

<li><strong>underscore_separated</strong>: <em>e.g.</em> <code>numeric_version</code></li>

<li><strong>lowerCamelCase</strong>: <em>e.g.</em> <code>addTaskCallback</code></li>

<li><strong>UpperCamelCase</strong>: <em>e.g.</em> <code>SignatureMethod</code></li>

</ul>

</div>

<h1>Subsetting</h1>

<p>Subset the vector using <code>x[ ]</code> notation</p>

<p>You can use a <code>:</code> to quickly generate a sequence:</p>

<p>and use that to subset as well:</p>

</div>

<h1>Using Functions</h1>

<p>To calculate the mean, you could do it <em>manually</em> like this</p>

<p>Or use a function:</p>

<p>Type <code>?functionname</code> to get the documentation (<code>?mean</code>) or <code>??"search parameters</code> (??“standard deviation”) to search the documentation. In RStudio, you can also search in the help panel. <code>mean</code> has other arguments too:</p>

<p><code>mean(x, trim = 0, na.rm = FALSE, ...)</code></p>

<p>In RStudio, if you press <code>TAB</code> after a function name (such as <code>mean(</code>), it will show function arguments.</p>

<p class="caption">Autocomplete screenshot</p>

</div>

<p>Calculate the standard deviation of <code>c(3,6,12,89)</code>.</p>

Show Solution

</button>

<pre class="r"><code>y=c(3,6,12,89)

sqrt((sum((y-mean(y))^2))/(length(y)-1))</code></pre>

<pre class="r"><code>#or

sd(y)</code></pre>

<pre class="r"><code>#or

sd(c(3,6,12,89))</code></pre>

</div>

<p>Writing functions in R is pretty easy. Let’s create one to calculate the mean of a vector by getting the sum and length. First think about how to break it down into parts:</p>

<pre class="r"><code>x1= sum(x)

x2=length(x)

x1/x2</code></pre>

<p>Then put it all back together and create a new function called <code>mymean</code>:</p>

<pre class="r"><code>mymean=function(f){

sum(f)/length(f)

}

mymean(f=x)</code></pre>

<p>Confirm it works:</p>

Any potential problems with the <code>mymean</code> function?

</div>

<h1>Missing data: dealing with <code>NA</code> values</h1>

" What do you think <code>mymean(x3)</code> will return?

</div>

<p>Calculate the mean using the new function</p>

<pre class="r"><code>mymean(x3)</code></pre>

<p>Use the built-in function (with and without na.rm=T)</p>

<p>Writing simple functions is easy, writing robust, reliable functions can be hard…</p>

<h2>Logical values</h2>

<p>R also has standard conditional tests to generate <code>TRUE</code> or <code>FALSE</code> values (which also behave as <code>0</code>s and <code>1</code>s. These are often useful for filtering data (e.g. identify all values greater than 5). The logical operators are <code><</code>, <code><=</code>, <code>></code>, <code>>=</code>, <code>==</code> for exact equality and <code>!=</code> for inequality.</p>

<pre><code>## [1] FALSE FALSE NA TRUE FALSE NA FALSE FALSE TRUE</code></pre>

<pre><code>## [1] FALSE FALSE NA FALSE FALSE NA FALSE FALSE FALSE</code></pre>

<pre><code>## [1] FALSE FALSE NA TRUE FALSE NA FALSE TRUE TRUE</code></pre>

<p>And you can perform operations on those results:</p>

<p>or save the results as variables:</p>

<pre class="r"><code>result = x3 > 3

result</code></pre>

<pre><code>## [1] TRUE TRUE NA TRUE FALSE NA TRUE TRUE TRUE</code></pre>

<p>Define a function that counts how many values in a vector are less than or equal (<code><=</code>) to 12.</p>

Show Solution

</button>

<pre class="r"><code>mycount=function(x){

sum(x<=12)

}</code></pre>

<pre class="r"><code>mycount(x3)</code></pre>

<pre class="r"><code>mycount=function(x){

sum(x<=12,na.rm=T)

}</code></pre>

<pre class="r"><code>mycount(x3)</code></pre>

</div>

<h1>Generating Data</h1>

<p>There are many ways to generate data in R such as sequences:</p>

<p>and random numbers that follow a statistical distribution (such as the normal):</p>

<pre class="r"><code>a=rnorm(100,mean=0,sd=10)</code></pre>

<p>Let’s visualize those values in a histogram:</p>

<p>We’ll cover much more sophisticated graphics later…</p>

</div>

<h1>Data Types</h1>

<h2>Matrices</h2>

<p>You can also use matrices (2-dimensional arrays of numbers):</p>

<pre class="r"><code>y=matrix(1:9,ncol=3)

y</code></pre>

<pre><code>## [,1] [,2] [,3]

## [1,] 1 4 7

## [2,] 2 5 8

## [3,] 3 6 9</code></pre>

<p>Matrices behave much like vectors:</p>

<pre><code>## [,1] [,2] [,3]

## [1,] 3 6 9

## [2,] 4 7 10

## [3,] 5 8 11</code></pre>

<p>and have 2-dimensional indexing:</p>

<p>Create a 3x3 matrix full of random numbers. Hint: <code>rnorm(5)</code> will generate 5 random numbers</p>

Show Solution

</button>

<pre class="r"><code>matrix(rnorm(9),nrow=3)</code></pre>

<pre><code>## [,1] [,2] [,3]

## [1,] 0.05710626 -1.15878801 0.2178735

## [2,] 0.90820862 0.01480023 0.2220378

## [3,] -0.40504985 1.23441876 0.8151335</code></pre>

</div>

<h2>Data Frames</h2>

<p>Data frames are similar to matrices, but more flexible. Matrices must be all the same type (e.g. all numbers), while a data frame can include multiple data types (e.g. text, factors, numbers). Dataframes are commonly used when doing statistical modeling in R.</p>

<pre class="r"><code>data = data.frame( x = c(11,12,14),

y = c("a","b","b"),

z = c(T,F,T))

data</code></pre>

<pre><code>## x y z

## 1 11 a TRUE

## 2 12 b FALSE

## 3 14 b TRUE</code></pre>

<p>You can subset in several ways</p>

</div>

<h1>Loading Packages</h1>

<p>For installed packages: <code>library(packagename)</code>.</p>

<p>New packages: <code>install.packages()</code> or use the package manager.</p>

<pre class="r"><code>library(ggplot2)</code></pre>

<p>R may ask you to choose a CRAN mirror. CRAN is the distributed network of servers that provides access to R’s software. It doesn’t really matter which you chose, but closer ones are likely to be faster. From RStudio, you can select the mirror under Tools→Options or just wait until it asks you.</p>

</blockquote>

<p>If you don’t have the packages above, install them in the package manager or by running <code>install.packages("raster")</code>.</p>

</div>

<h1>Today’s task</h1>

<p>Now <a href="CS_01.html">complete the first task here</a> by yourself or in small groups.</p>

</div>

(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){

(i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new Date();a=s.createElement(o),

m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m)

})(window,document,'script','https://www.google-analytics.com/analytics.js','ga');

ga('create', 'UA-2684666-2', 'auto');

ga('send', 'pageview');

</script>

<!-- disqus

/* * * CONFIGURATION VARIABLES: EDIT BEFORE PASTING INTO YOUR WEBPAGE * * */

var disqus_shortname = 'rdataanalysis'; // required: replace example with your forum shortname

var disqus_identifier = "{{ page.url }}";

/* * * DON'T EDIT BELOW THIS LINE * * */

(function() {

var dsq = document.createElement('script'); dsq.type = 'text/javascript'; dsq.async = true;

dsq.src = '//' + disqus_shortname + '.disqus.com/embed.js';

(document.getElementsByTagName('head')[0] || document.getElementsByTagName('body')[0]).appendChild(dsq );

})();

</script>

comments powered by Disqus.</a>

</noscript>

-->

<br/>

</div>

</div>

</footer>

</div>

// add bootstrap table styles to pandoc tables

function bootstrapStylePandocTables() {

$('tr.header').parent('thead').parent('table').addClass('table table-condensed');

}

$(document).ready(function () {

bootstrapStylePandocTables();

});

</script>

</body>

</html>

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

FilesExpand file tree

01_Rintro.html

Latest commit

History

01_Rintro.html

File metadata and controls