-
Notifications
You must be signed in to change notification settings - Fork 6
/
exercise_4_solution.html
1062 lines (967 loc) · 68.1 KB
/
exercise_4_solution.html
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
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
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8" />
<meta name="generator" content="pandoc" />
<meta http-equiv="X-UA-Compatible" content="IE=EDGE" />
<title>Exercise Solutions</title>
<script src="site_libs/header-attrs-2.20/header-attrs.js"></script>
<script src="site_libs/jquery-3.6.0/jquery-3.6.0.min.js"></script>
<meta name="viewport" content="width=device-width, initial-scale=1" />
<link href="site_libs/bootstrap-3.3.5/css/flatly.min.css" rel="stylesheet" />
<script src="site_libs/bootstrap-3.3.5/js/bootstrap.min.js"></script>
<script src="site_libs/bootstrap-3.3.5/shim/html5shiv.min.js"></script>
<script src="site_libs/bootstrap-3.3.5/shim/respond.min.js"></script>
<style>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;}
code {color: inherit; background-color: rgba(0, 0, 0, 0.04);}
pre:not([class]) { background-color: white }</style>
<script src="site_libs/navigation-1.1/tabsets.js"></script>
<script src="site_libs/navigation-1.1/codefolding.js"></script>
<link href="site_libs/font-awesome-5.1.0/css/all.css" rel="stylesheet" />
<link href="site_libs/font-awesome-5.1.0/css/v4-shims.css" rel="stylesheet" />
<!-- Global site tag (gtag.js) - Google Analytics -->
<script async src="https://www.googletagmanager.com/gtag/js?id=UA-162377463-2"></script>
<script>
window.dataLayer = window.dataLayer || [];
function gtag(){dataLayer.push(arguments);}
gtag('js', new Date());
gtag('config', 'UA-162377463-2');
</script>
<style type="text/css">
code{white-space: pre-wrap;}
span.smallcaps{font-variant: small-caps;}
span.underline{text-decoration: underline;}
div.column{display: inline-block; vertical-align: top; width: 50%;}
div.hanging-indent{margin-left: 1.5em; text-indent: -1.5em;}
ul.task-list{list-style: none;}
</style>
<style type="text/css">
code {
white-space: pre;
}
.sourceCode {
overflow: visible;
}
</style>
<style type="text/css" data-origin="pandoc">
pre > code.sourceCode { white-space: pre; position: relative; }
pre > code.sourceCode > span { display: inline-block; line-height: 1.25; }
pre > code.sourceCode > span:empty { height: 1.2em; }
.sourceCode { overflow: visible; }
code.sourceCode > span { color: inherit; text-decoration: inherit; }
div.sourceCode { margin: 1em 0; }
pre.sourceCode { margin: 0; }
@media screen {
div.sourceCode { overflow: auto; }
}
@media print {
pre > code.sourceCode { white-space: pre-wrap; }
pre > code.sourceCode > span { text-indent: -5em; padding-left: 5em; }
}
pre.numberSource code
{ counter-reset: source-line 0; }
pre.numberSource code > span
{ position: relative; left: -4em; counter-increment: source-line; }
pre.numberSource code > span > a:first-child::before
{ content: counter(source-line);
position: relative; left: -1em; text-align: right; vertical-align: baseline;
border: none; display: inline-block;
-webkit-touch-callout: none; -webkit-user-select: none;
-khtml-user-select: none; -moz-user-select: none;
-ms-user-select: none; user-select: none;
padding: 0 4px; width: 4em;
color: #aaaaaa;
}
pre.numberSource { margin-left: 3em; border-left: 1px solid #aaaaaa; padding-left: 4px; }
div.sourceCode
{ background-color: #f8f8f8; }
@media screen {
pre > code.sourceCode > span > a:first-child::before { text-decoration: underline; }
}
code span.al { color: #ef2929; } /* Alert */
code span.an { color: #8f5902; font-weight: bold; font-style: italic; } /* Annotation */
code span.at { color: #204a87; } /* Attribute */
code span.bn { color: #0000cf; } /* BaseN */
code span.cf { color: #204a87; font-weight: bold; } /* ControlFlow */
code span.ch { color: #4e9a06; } /* Char */
code span.cn { color: #8f5902; } /* Constant */
code span.co { color: #8f5902; font-style: italic; } /* Comment */
code span.cv { color: #8f5902; font-weight: bold; font-style: italic; } /* CommentVar */
code span.do { color: #8f5902; font-weight: bold; font-style: italic; } /* Documentation */
code span.dt { color: #204a87; } /* DataType */
code span.dv { color: #0000cf; } /* DecVal */
code span.er { color: #a40000; font-weight: bold; } /* Error */
code span.ex { } /* Extension */
code span.fl { color: #0000cf; } /* Float */
code span.fu { color: #204a87; font-weight: bold; } /* Function */
code span.im { } /* Import */
code span.in { color: #8f5902; font-weight: bold; font-style: italic; } /* Information */
code span.kw { color: #204a87; font-weight: bold; } /* Keyword */
code span.op { color: #ce5c00; font-weight: bold; } /* Operator */
code span.ot { color: #8f5902; } /* Other */
code span.pp { color: #8f5902; font-style: italic; } /* Preprocessor */
code span.sc { color: #ce5c00; font-weight: bold; } /* SpecialChar */
code span.ss { color: #4e9a06; } /* SpecialString */
code span.st { color: #4e9a06; } /* String */
code span.va { color: #000000; } /* Variable */
code span.vs { color: #4e9a06; } /* VerbatimString */
code span.wa { color: #8f5902; font-weight: bold; font-style: italic; } /* Warning */
.sourceCode .row {
width: 100%;
}
.sourceCode {
overflow-x: auto;
}
.code-folding-btn {
margin-right: -30px;
}
</style>
<script>
// apply pandoc div.sourceCode style to pre.sourceCode instead
(function() {
var sheets = document.styleSheets;
for (var i = 0; i < sheets.length; i++) {
if (sheets[i].ownerNode.dataset["origin"] !== "pandoc") continue;
try { var rules = sheets[i].cssRules; } catch (e) { continue; }
var j = 0;
while (j < rules.length) {
var rule = rules[j];
// check if there is a div.sourceCode rule
if (rule.type !== rule.STYLE_RULE || rule.selectorText !== "div.sourceCode") {
j++;
continue;
}
var style = rule.style.cssText;
// check if color or background-color is set
if (rule.style.color === '' && rule.style.backgroundColor === '') {
j++;
continue;
}
// replace div.sourceCode by a pre.sourceCode rule
sheets[i].deleteRule(j);
sheets[i].insertRule('pre.sourceCode{' + style + '}', j);
}
}
})();
</script>
<style type = "text/css">
.main-container {
max-width: 940px;
margin-left: auto;
margin-right: auto;
}
img {
max-width:100%;
}
.tabbed-pane {
padding-top: 12px;
}
.html-widget {
margin-bottom: 20px;
}
button.code-folding-btn:focus {
outline: none;
}
summary {
display: list-item;
}
details > summary > p:only-child {
display: inline;
}
pre code {
padding: 0;
}
</style>
<style type="text/css">
.dropdown-submenu {
position: relative;
}
.dropdown-submenu>.dropdown-menu {
top: 0;
left: 100%;
margin-top: -6px;
margin-left: -1px;
border-radius: 0 6px 6px 6px;
}
.dropdown-submenu:hover>.dropdown-menu {
display: block;
}
.dropdown-submenu>a:after {
display: block;
content: " ";
float: right;
width: 0;
height: 0;
border-color: transparent;
border-style: solid;
border-width: 5px 0 5px 5px;
border-left-color: #cccccc;
margin-top: 5px;
margin-right: -10px;
}
.dropdown-submenu:hover>a:after {
border-left-color: #adb5bd;
}
.dropdown-submenu.pull-left {
float: none;
}
.dropdown-submenu.pull-left>.dropdown-menu {
left: -100%;
margin-left: 10px;
border-radius: 6px 0 6px 6px;
}
</style>
<script type="text/javascript">
// 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 the anchor link active (and if it's in a dropdown, also mark that active)
var dropdown = menuAnchor.closest('li.dropdown');
if (window.bootstrap) { // Bootstrap 4+
menuAnchor.addClass('active');
dropdown.find('> .dropdown-toggle').addClass('active');
} else { // Bootstrap 3
menuAnchor.parent().addClass('active');
dropdown.addClass('active');
}
// Navbar adjustments
var navHeight = $(".navbar").first().height() + 15;
var style = document.createElement('style');
var pt = "padding-top: " + navHeight + "px; ";
var mt = "margin-top: -" + navHeight + "px; ";
var css = "";
// offset scroll position for anchor links (for fixed navbar)
for (var i = 1; i <= 6; i++) {
css += ".section h" + i + "{ " + pt + mt + "}\n";
}
style.innerHTML = "body {" + pt + "padding-bottom: 40px; }\n" + css;
document.head.appendChild(style);
});
</script>
<!-- tabsets -->
<style type="text/css">
.tabset-dropdown > .nav-tabs {
display: inline-table;
max-height: 500px;
min-height: 44px;
overflow-y: auto;
border: 1px solid #ddd;
border-radius: 4px;
}
.tabset-dropdown > .nav-tabs > li.active:before, .tabset-dropdown > .nav-tabs.nav-tabs-open:before {
content: "\e259";
font-family: 'Glyphicons Halflings';
display: inline-block;
padding: 10px;
border-right: 1px solid #ddd;
}
.tabset-dropdown > .nav-tabs.nav-tabs-open > li.active:before {
content: "\e258";
font-family: 'Glyphicons Halflings';
border: none;
}
.tabset-dropdown > .nav-tabs > li.active {
display: block;
}
.tabset-dropdown > .nav-tabs > li > a,
.tabset-dropdown > .nav-tabs > li > a:focus,
.tabset-dropdown > .nav-tabs > li > a:hover {
border: none;
display: inline-block;
border-radius: 4px;
background-color: transparent;
}
.tabset-dropdown > .nav-tabs.nav-tabs-open > li {
display: block;
float: none;
}
.tabset-dropdown > .nav-tabs > li {
display: none;
}
</style>
<!-- code folding -->
<style type="text/css">
.code-folding-btn { margin-bottom: 4px; }
</style>
</head>
<body>
<div class="container-fluid main-container">
<div class="navbar navbar-default navbar-fixed-top" role="navigation">
<div class="container">
<div class="navbar-header">
<button type="button" class="navbar-toggle collapsed" data-toggle="collapse" data-bs-toggle="collapse" data-target="#navbar" data-bs-target="#navbar">
<span class="icon-bar"></span>
<span class="icon-bar"></span>
<span class="icon-bar"></span>
</button>
<a class="navbar-brand" href="index.html">Intro2R</a>
</div>
<div id="navbar" class="navbar-collapse collapse">
<ul class="nav navbar-nav">
<li>
<a href="setup.html">
<span class="fa fa-cog"></span>
Setup
</a>
</li>
<li class="dropdown">
<a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" data-bs-toggle="dropdown" aria-expanded="false">
<span class="fa fa-book"></span>
R Book
<span class="caret"></span>
</a>
<ul class="dropdown-menu" role="menu">
<li>
<a href="https://intro2r.com">
<span class="fa fa-firefox"></span>
Web book
</a>
</li>
<li class="divider"></li>
<li>
<a href="https://github.com/alexd106/Rbook/raw/master/docs/Rbook.pdf">
<span class="fa fa-file-pdf"></span>
PDF book
</a>
</li>
</ul>
</li>
<li class="dropdown">
<a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" data-bs-toggle="dropdown" aria-expanded="false">
<span class="fa fa-university"></span>
Learn R
<span class="caret"></span>
</a>
<ul class="dropdown-menu" role="menu">
<li>
<a href="howto.html">
<span class="fa fa-tv"></span>
How-to
</a>
</li>
<li class="divider"></li>
<li>
<a href="lectures.html">
<span class="fa fa-chalkboard"></span>
Lectures
</a>
</li>
</ul>
</li>
<li class="dropdown">
<a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" data-bs-toggle="dropdown" aria-expanded="false">
<span class="fa fa-file-contract"></span>
Exercises
<span class="caret"></span>
</a>
<ul class="dropdown-menu" role="menu">
<li>
<a href="exercises.html">
<span class="fa fa-folder"></span>
Excercises
</a>
</li>
<li class="divider"></li>
<li>
<a href="exercise_solutions.html">
<span class="fa fa-folder"></span>
Exercise solutions
</a>
</li>
</ul>
</li>
<li>
<a href="data.html">
<span class="fa fa-download"></span>
Data
</a>
</li>
<li>
<a href="Tutorials.html">
<span class="fa fa-desktop"></span>
Tutorials
</a>
</li>
<li class="dropdown">
<a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" data-bs-toggle="dropdown" aria-expanded="false">
<span class="fa fa-question-circle"></span>
Info
<span class="caret"></span>
</a>
<ul class="dropdown-menu" role="menu">
<li>
<a href="syllabus.html">
<span class="fa fa-graduation-cap"></span>
Syllabus
</a>
</li>
<li class="divider"></li>
<li>
<a href="People.html">
<span class="fa fa-user-friends"></span>
People
</a>
</li>
<li class="divider"></li>
<li>
<a href="resources.html">
<span class="fa fa-book"></span>
Resources
</a>
</li>
<li>
<a href="https://forms.gle/U7MbyhRWyLomjyFY7">
<span class="fa fa-commenting"></span>
Feedback
</a>
</li>
<li class="divider"></li>
<li>
<a href="People.html">
<span class="fa fa-envelope fa-lg"></span>
Contact
</a>
</li>
<li>
<a href="https://github.com/alexd106/intro2R">
<span class="fa fa-github fa-lg"></span>
Source code
</a>
</li>
<li>
<a href="https://twitter.com/Scedacity">
<span class="fa fa-twitter fa-lg"></span>
Twitter
</a>
</li>
</ul>
</li>
</ul>
<ul class="nav navbar-nav navbar-right">
</ul>
</div><!--/.nav-collapse -->
</div><!--/.container -->
</div><!--/.navbar -->
<div id="header">
<div class="btn-group pull-right float-right">
<button type="button" class="btn btn-default btn-xs btn-secondary btn-sm dropdown-toggle" data-toggle="dropdown" data-bs-toggle="dropdown" aria-haspopup="true" aria-expanded="false"><span>Code</span> <span class="caret"></span></button>
<ul class="dropdown-menu dropdown-menu-right" style="min-width: 50px;">
<li><a id="rmd-show-all-code" href="#">Show All Code</a></li>
<li><a id="rmd-hide-all-code" href="#">Hide All Code</a></li>
</ul>
</div>
<h1 class="title toc-ignore">Exercise Solutions</h1>
</div>
<p> </p>
<div id="exercise-4-visualising-data-using-base-r-and-lattice-graphics"
class="section level2">
<h2>Exercise 4: Visualising data using base R and lattice graphics</h2>
<p> </p>
<p>Read <a href="https://intro2r.com/graphics-base-r.html">Chapter 4</a>
to help you complete the questions in this exercise.</p>
<p> </p>
<p>1. As in previous exercises, either create a new R script or continue
with your previous R script in your RStudio Project. Again, make sure
you include any metadata you feel is appropriate (title, description of
task, date of creation etc) and don’t forget to comment out your
metadata with a <code>#</code> at the beginning of the line.</p>
<p> </p>
<p>2. Download the data file <em>‘squid1.xlsx’</em> from the <strong><a
href="data.html"><i class="fa fa-download"></i> Data</a></strong> link
and save it to the <code>data</code> directory you created during
exercise 1. Open this file in Microsoft Excel (or even better use an
open source equivalent - <a
href="https://www.libreoffice.org/download/download/">LibreOffice</a> is
a good free alternative) and save it as a tab delimited file type. Name
the file <em>‘squid1.txt’</em> and save it to the <code>data</code>
directory.</p>
<p> </p>
<p>3. These data were originally collected as part of a study published
in Aquatic Living Resources<sup>1</sup> in 2005. The aim of the study
was to investigate the seasonal patterns of investment in somatic and
reproductive tissues in the long finned squid <em>Loligo forbesi</em>
caught in Scottish waters. Squid were caught monthly from December 1989
- July 1991 (<code>month</code> and <code>year</code> variables). After
capture, each squid was given a unique <code>specimen</code> code,
weighed (<code>weight</code>) and the sex determined (<code>sex</code> -
only female squid are included here). The size of individuals was also
measured as the dorsal mantle length (<code>DML</code>) and the mantle
weight measured without internal organs
(<code>eviscerate.weight</code>). The gonads were weighed
(<code>ovary.weight</code>) along with the accessory reproductive organ
(the nidamental gland, <code>nid.weight</code>,
<code>nid.length</code>). Each individual was also assigned a
categorical measure of maturity (<code>maturity.stage</code>, ranging
from 1 to 5 with 1 = immature, 5 = mature). The digestive gland weight
(<code>dig.weight</code>) was also recorded to assess nutritional status
of the individual. If you’re not familiar with squid morphology and are
interested in finding out more see <a
href="https://en.wikipedia.org/wiki/Cephalopod_size">here</a>.</p>
<p> </p>
<p>4. Import the <em>‘squid1.txt’</em> file into R using the
<code>read.table()</code> function and assign it to a variable named
<code>squid</code>. Use the <code>str()</code> function to display the
structure of the dataset and the <code>summary()</code> function to
summarise the dataset. How many observations are in this dataset? How
many variables? The <code>year</code>, <code>month</code> and
<code>maturity.stage</code> variables were coded as integers in the
original dataset. Here we would like to code them as factors. Create a
new variable for each of these variables in the <code>squid</code>
dataframe and recode them as factors. Use the <code>str()</code>
function again to check the coding of these new variables.</p>
<div class="sourceCode" id="cb1"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb1-1"><a href="#cb1-1" tabindex="-1"></a>squid <span class="ot"><-</span> <span class="fu">read.table</span>(<span class="st">'workshop/data/squid1.txt'</span>, <span class="at">header =</span><span class="cn">TRUE</span>,</span>
<span id="cb1-2"><a href="#cb1-2" tabindex="-1"></a> <span class="at">stringsAsFactors =</span> <span class="cn">TRUE</span>)</span>
<span id="cb1-3"><a href="#cb1-3" tabindex="-1"></a></span>
<span id="cb1-4"><a href="#cb1-4" tabindex="-1"></a><span class="fu">str</span>(squid)</span>
<span id="cb1-5"><a href="#cb1-5" tabindex="-1"></a><span class="co"># 'data.frame': 519 obs. of 13 variables:</span></span>
<span id="cb1-6"><a href="#cb1-6" tabindex="-1"></a><span class="co"># $ sample.no : int 105128901 105128901 105128901 105128901 ...</span></span>
<span id="cb1-7"><a href="#cb1-7" tabindex="-1"></a><span class="co"># $ specimen : int 1002 1003 1005 1007 1008 1009 1011 1013 ...</span></span>
<span id="cb1-8"><a href="#cb1-8" tabindex="-1"></a><span class="co"># $ year : int 1989 1989 1989 1989 1989 1989 1989 1989 ...</span></span>
<span id="cb1-9"><a href="#cb1-9" tabindex="-1"></a><span class="co"># $ month : int 12 12 12 12 12 12 12 12 12 12 ...</span></span>
<span id="cb1-10"><a href="#cb1-10" tabindex="-1"></a><span class="co"># $ weight : num 152 106 138 141 126 ...</span></span>
<span id="cb1-11"><a href="#cb1-11" tabindex="-1"></a><span class="co"># $ sex : int 2 2 2 2 2 2 2 2 2 2 ...</span></span>
<span id="cb1-12"><a href="#cb1-12" tabindex="-1"></a><span class="co"># $ maturity.stage : int 3 1 2 2 3 1 2 3 3 4 ...</span></span>
<span id="cb1-13"><a href="#cb1-13" tabindex="-1"></a><span class="co"># $ DML : int 174 153 169 175 169 116 135 192 170 205 ...</span></span>
<span id="cb1-14"><a href="#cb1-14" tabindex="-1"></a><span class="co"># $ eviscerate.weight: num 87.5 62.6 79.4 83.1 72.2 ...</span></span>
<span id="cb1-15"><a href="#cb1-15" tabindex="-1"></a><span class="co"># $ dig.weight : num 4.648 3.138 0.307 4.123 3.605 ...</span></span>
<span id="cb1-16"><a href="#cb1-16" tabindex="-1"></a><span class="co"># $ nid.length : num 39.4 24.1 39 41.4 39.8 20 14 55 44 53 ...</span></span>
<span id="cb1-17"><a href="#cb1-17" tabindex="-1"></a><span class="co"># $ nid.weight : num 2.46 0.319 1.169 1.631 2.03 ...</span></span>
<span id="cb1-18"><a href="#cb1-18" tabindex="-1"></a><span class="co"># $ ovary.weight : num 1.68 0.103 0.289 0.252 0.86 ...</span></span>
<span id="cb1-19"><a href="#cb1-19" tabindex="-1"></a></span>
<span id="cb1-20"><a href="#cb1-20" tabindex="-1"></a><span class="fu">summary</span>(squid)</span>
<span id="cb1-21"><a href="#cb1-21" tabindex="-1"></a></span>
<span id="cb1-22"><a href="#cb1-22" tabindex="-1"></a><span class="co"># convert variables to factors</span></span>
<span id="cb1-23"><a href="#cb1-23" tabindex="-1"></a>squid<span class="sc">$</span>Fmaturity <span class="ot"><-</span> <span class="fu">factor</span>(squid<span class="sc">$</span>maturity.stage)</span>
<span id="cb1-24"><a href="#cb1-24" tabindex="-1"></a>squid<span class="sc">$</span>Fmonth <span class="ot"><-</span> <span class="fu">factor</span>(squid<span class="sc">$</span>month) </span>
<span id="cb1-25"><a href="#cb1-25" tabindex="-1"></a>squid<span class="sc">$</span>Fyear <span class="ot"><-</span> <span class="fu">factor</span>(squid<span class="sc">$</span>year)</span>
<span id="cb1-26"><a href="#cb1-26" tabindex="-1"></a></span>
<span id="cb1-27"><a href="#cb1-27" tabindex="-1"></a><span class="fu">str</span>(squid)</span>
<span id="cb1-28"><a href="#cb1-28" tabindex="-1"></a><span class="co"># 'data.frame': 519 obs. of 16 variables:</span></span>
<span id="cb1-29"><a href="#cb1-29" tabindex="-1"></a><span class="co"># $ sample.no : int 105128901 105128901 105128901 ...</span></span>
<span id="cb1-30"><a href="#cb1-30" tabindex="-1"></a><span class="co"># $ specimen : int 1002 1003 1005 1007 1008 1009 ...</span></span>
<span id="cb1-31"><a href="#cb1-31" tabindex="-1"></a><span class="co"># $ year : int 1989 1989 1989 1989 1989 1989 ...</span></span>
<span id="cb1-32"><a href="#cb1-32" tabindex="-1"></a><span class="co"># $ month : int 12 12 12 12 12 12 12 12 12 12 ...</span></span>
<span id="cb1-33"><a href="#cb1-33" tabindex="-1"></a><span class="co"># $ weight : num 152 106 138 141 126 ...</span></span>
<span id="cb1-34"><a href="#cb1-34" tabindex="-1"></a><span class="co"># $ sex : int 2 2 2 2 2 2 2 2 2 2 ...</span></span>
<span id="cb1-35"><a href="#cb1-35" tabindex="-1"></a><span class="co"># $ maturity.stage : int 3 1 2 2 3 1 2 3 3 4 ...</span></span>
<span id="cb1-36"><a href="#cb1-36" tabindex="-1"></a><span class="co"># $ DML : int 174 153 169 175 169 116 135 ...</span></span>
<span id="cb1-37"><a href="#cb1-37" tabindex="-1"></a><span class="co"># $ eviscerate.weight: num 87.5 62.6 79.4 83.1 72.2 ...</span></span>
<span id="cb1-38"><a href="#cb1-38" tabindex="-1"></a><span class="co"># $ dig.weight : num 4.648 3.138 0.307 4.123 3.605 ...</span></span>
<span id="cb1-39"><a href="#cb1-39" tabindex="-1"></a><span class="co"># $ nid.length : num 39.4 24.1 39 41.4 39.8 20 14 ...</span></span>
<span id="cb1-40"><a href="#cb1-40" tabindex="-1"></a><span class="co"># $ nid.weight : num 2.46 0.319 1.169 1.631 2.03 ...</span></span>
<span id="cb1-41"><a href="#cb1-41" tabindex="-1"></a><span class="co"># $ ovary.weight : num 1.68 0.103 0.289 0.252 0.86 ...</span></span>
<span id="cb1-42"><a href="#cb1-42" tabindex="-1"></a><span class="co"># $ Fmaturity : Factor w/ 5 levels "1","2","3","4" "5"...</span></span>
<span id="cb1-43"><a href="#cb1-43" tabindex="-1"></a><span class="co"># $ Fmonth : Factor w/ 12 levels "1","2","3","4" ...</span></span>
<span id="cb1-44"><a href="#cb1-44" tabindex="-1"></a><span class="co"># $ Fyear : Factor w/ 3 levels "1989","1990",..1 ...</span></span></code></pre></div>
<p> </p>
<p>5. How many observations are there per month and year combination
(hint: remember the <code>table()</code> or <code>xtabs()</code>
functions?)? Don’t forget to use the factor recoded versions of these
variables. Do you have data for each month in each year? Which years
have the most observations? (optional) Use a combination of the
<code>xtabs()</code> and <code>ftable()</code> functions to create a
flattened table of the number of observations for each year, maturity
stage and month (aka a contingency table).</p>
<div class="sourceCode" id="cb2"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb2-1"><a href="#cb2-1" tabindex="-1"></a><span class="fu">table</span>(squid<span class="sc">$</span>Fmonth, squid<span class="sc">$</span>Fyear)</span>
<span id="cb2-2"><a href="#cb2-2" tabindex="-1"></a></span>
<span id="cb2-3"><a href="#cb2-3" tabindex="-1"></a> <span class="co"># 1989 1990 1991</span></span>
<span id="cb2-4"><a href="#cb2-4" tabindex="-1"></a> <span class="co"># 1 0 3 37</span></span>
<span id="cb2-5"><a href="#cb2-5" tabindex="-1"></a> <span class="co"># 2 0 0 30</span></span>
<span id="cb2-6"><a href="#cb2-6" tabindex="-1"></a> <span class="co"># 3 0 40 29</span></span>
<span id="cb2-7"><a href="#cb2-7" tabindex="-1"></a> <span class="co"># 4 0 10 33</span></span>
<span id="cb2-8"><a href="#cb2-8" tabindex="-1"></a> <span class="co"># 5 0 1 30</span></span>
<span id="cb2-9"><a href="#cb2-9" tabindex="-1"></a> <span class="co"># 6 0 0 14</span></span>
<span id="cb2-10"><a href="#cb2-10" tabindex="-1"></a> <span class="co"># 7 0 42 1</span></span>
<span id="cb2-11"><a href="#cb2-11" tabindex="-1"></a> <span class="co"># 8 0 29 0</span></span>
<span id="cb2-12"><a href="#cb2-12" tabindex="-1"></a> <span class="co"># 9 0 82 0</span></span>
<span id="cb2-13"><a href="#cb2-13" tabindex="-1"></a> <span class="co"># 10 0 19 0</span></span>
<span id="cb2-14"><a href="#cb2-14" tabindex="-1"></a> <span class="co"># 11 0 76 0</span></span>
<span id="cb2-15"><a href="#cb2-15" tabindex="-1"></a> <span class="co"># 12 12 31 0</span></span>
<span id="cb2-16"><a href="#cb2-16" tabindex="-1"></a> </span>
<span id="cb2-17"><a href="#cb2-17" tabindex="-1"></a><span class="fu">ftable</span>(<span class="fu">xtabs</span>(<span class="sc">~</span> Fyear <span class="sc">+</span> Fmaturity <span class="sc">+</span> Fmonth, <span class="at">data =</span> squid))</span>
<span id="cb2-18"><a href="#cb2-18" tabindex="-1"></a></span>
<span id="cb2-19"><a href="#cb2-19" tabindex="-1"></a><span class="co"># Fmonth 1 2 3 4 5 6 7 8 9 10 11 12</span></span>
<span id="cb2-20"><a href="#cb2-20" tabindex="-1"></a><span class="co"># Fyear Fmaturity </span></span>
<span id="cb2-21"><a href="#cb2-21" tabindex="-1"></a><span class="co"># 1989 1 0 0 0 0 0 0 0 0 0 0 0 2</span></span>
<span id="cb2-22"><a href="#cb2-22" tabindex="-1"></a><span class="co"># 2 0 0 0 0 0 0 0 0 0 0 0 3</span></span>
<span id="cb2-23"><a href="#cb2-23" tabindex="-1"></a><span class="co"># 3 0 0 0 0 0 0 0 0 0 0 0 5</span></span>
<span id="cb2-24"><a href="#cb2-24" tabindex="-1"></a><span class="co"># 4 0 0 0 0 0 0 0 0 0 0 0 2</span></span>
<span id="cb2-25"><a href="#cb2-25" tabindex="-1"></a><span class="co"># 5 0 0 0 0 0 0 0 0 0 0 0 0</span></span>
<span id="cb2-26"><a href="#cb2-26" tabindex="-1"></a><span class="co"># 1990 1 0 0 0 0 0 0 8 0 1 1 1 2</span></span>
<span id="cb2-27"><a href="#cb2-27" tabindex="-1"></a><span class="co"># 2 0 0 0 0 0 0 22 21 76 17 31 4</span></span>
<span id="cb2-28"><a href="#cb2-28" tabindex="-1"></a><span class="co"># 3 0 0 0 0 0 0 0 5 5 1 31 6</span></span>
<span id="cb2-29"><a href="#cb2-29" tabindex="-1"></a><span class="co"># 4 2 0 15 7 0 0 4 3 0 0 10 13</span></span>
<span id="cb2-30"><a href="#cb2-30" tabindex="-1"></a><span class="co"># 5 1 0 25 3 1 0 8 0 0 0 3 6</span></span>
<span id="cb2-31"><a href="#cb2-31" tabindex="-1"></a><span class="co"># 1991 1 0 0 0 2 0 4 0 0 0 0 0 0</span></span>
<span id="cb2-32"><a href="#cb2-32" tabindex="-1"></a><span class="co"># 2 1 1 0 1 0 6 0 0 0 0 0 0</span></span>
<span id="cb2-33"><a href="#cb2-33" tabindex="-1"></a><span class="co"># 3 2 0 0 1 1 0 0 0 0 0 0 0</span></span>
<span id="cb2-34"><a href="#cb2-34" tabindex="-1"></a><span class="co"># 4 16 8 6 13 6 1 1 0 0 0 0 0</span></span>
<span id="cb2-35"><a href="#cb2-35" tabindex="-1"></a><span class="co"># 5 18 21 23 16 23 3 0 0 0 0 0 0</span></span></code></pre></div>
<p> </p>
<p>6. The humble cleveland dotplot is a great way of identifying if you
have potential outliers in continuous variables (See <a
href="https://intro2r.com/simple-base-r-plots.html#dotcharts">Section
4.2.4</a>). Create dotplots (using the <code>dotchart()</code> function)
for the following variables; <code>DML</code>, <code>weight</code>,
<code>nid.length</code> and <code>ovary.weight</code>. Do these
variables contain any unusually large or small observations? Don’t
forget, if you prefer to create a single figure with all 4 plots you can
always split your plotting device into 2 rows and 2 columns (see <a
href="https://intro2r.com/mult_graphs.html#mult_graphs">Section 4.4</a>
of the book). Use the <code>pdf()</code> function to save a pdf version
of your plot(s) in your <code>output</code> directory you created in
Exercise 1 (see <a
href="https://intro2r.com/export_plots.html#export_plots">Section
4.5</a> of the book to see how the <code>pdf()</code> function works). I
have also included some alternative code in the <a
href="exercise_4_solution.html">solutions for this exercise</a> using
the <code>dotplot()</code> function from the <code>lattice</code>
package.</p>
<div class="sourceCode" id="cb3"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb3-1"><a href="#cb3-1" tabindex="-1"></a><span class="fu">pdf</span>(<span class="st">'figures/ex4_dotplots.pdf'</span>)</span>
<span id="cb3-2"><a href="#cb3-2" tabindex="-1"></a><span class="fu">par</span>(<span class="at">mfrow =</span> <span class="fu">c</span>(<span class="dv">2</span>, <span class="dv">2</span>))</span>
<span id="cb3-3"><a href="#cb3-3" tabindex="-1"></a><span class="fu">dotchart</span>(squid<span class="sc">$</span>DML, <span class="at">main =</span> <span class="st">"DML"</span>)</span>
<span id="cb3-4"><a href="#cb3-4" tabindex="-1"></a><span class="fu">dotchart</span>(squid<span class="sc">$</span>weight, <span class="at">main =</span> <span class="st">"weight"</span>)</span>
<span id="cb3-5"><a href="#cb3-5" tabindex="-1"></a><span class="fu">dotchart</span>(squid<span class="sc">$</span>nid.length, <span class="at">main =</span> <span class="st">"nid length"</span>)</span>
<span id="cb3-6"><a href="#cb3-6" tabindex="-1"></a><span class="fu">dotchart</span>(squid<span class="sc">$</span>ovary.weight, <span class="at">main =</span> <span class="st">"ovary weight"</span>)</span>
<span id="cb3-7"><a href="#cb3-7" tabindex="-1"></a><span class="fu">dev.off</span>()</span>
<span id="cb3-8"><a href="#cb3-8" tabindex="-1"></a></span>
<span id="cb3-9"><a href="#cb3-9" tabindex="-1"></a><span class="co"># alternative code using dotplot function from lattice package</span></span>
<span id="cb3-10"><a href="#cb3-10" tabindex="-1"></a><span class="fu">library</span>(lattice)</span>
<span id="cb3-11"><a href="#cb3-11" tabindex="-1"></a><span class="fu">dotplot</span>(<span class="fu">as.matrix</span>(squid[,<span class="fu">c</span>(<span class="st">"DML"</span>, <span class="st">"weight"</span>, <span class="st">"nid.length"</span>, <span class="st">"ovary.weight"</span>)]),</span>
<span id="cb3-12"><a href="#cb3-12" tabindex="-1"></a> <span class="at">groups=</span><span class="cn">FALSE</span>,</span>
<span id="cb3-13"><a href="#cb3-13" tabindex="-1"></a> <span class="at">strip =</span> <span class="fu">strip.custom</span>(<span class="at">bg =</span> <span class="st">'white'</span>,</span>
<span id="cb3-14"><a href="#cb3-14" tabindex="-1"></a> <span class="at">par.strip.text =</span> <span class="fu">list</span>(<span class="at">cex =</span> <span class="fl">0.8</span>)),</span>
<span id="cb3-15"><a href="#cb3-15" tabindex="-1"></a> <span class="at">scales =</span> <span class="fu">list</span>(<span class="at">x =</span> <span class="fu">list</span>(<span class="at">relation =</span> <span class="st">"free"</span>),</span>
<span id="cb3-16"><a href="#cb3-16" tabindex="-1"></a> <span class="at">y =</span> <span class="fu">list</span>(<span class="at">relation =</span> <span class="st">"free"</span>),</span>
<span id="cb3-17"><a href="#cb3-17" tabindex="-1"></a> <span class="at">draw =</span> <span class="cn">FALSE</span>),</span>
<span id="cb3-18"><a href="#cb3-18" tabindex="-1"></a> <span class="at">col=</span><span class="dv">1</span>, <span class="at">cex =</span><span class="fl">0.5</span>, <span class="at">pch =</span> <span class="dv">16</span>,</span>
<span id="cb3-19"><a href="#cb3-19" tabindex="-1"></a> <span class="at">xlab =</span> <span class="st">"Value of the variable"</span>,</span>
<span id="cb3-20"><a href="#cb3-20" tabindex="-1"></a> <span class="at">ylab =</span> <span class="st">"Order of the data from text file"</span>)</span></code></pre></div>
<p> </p>
<p>7. It looks like the variable <code>nid.length</code> contains an
unusually large value. Actually, this value is biologically implausible
and clearly an error. The researchers were asked to go back and check
their field notebooks and sure enough they discover a typo. It looks
like a tired researcher accidentally inserted a zero by mistake when
transcribing these data (mistakes in data are very common and why we
<strong>always</strong> explore, check and validate any data we are
working on). We can clearly see this value is over 400 so we can use the
<code>which()</code> function to identify which observation this is
<code>which(squid$nid.length > 400)</code>. It looks like this is the
11<sup>th</sup> observation of the <code>squid$nid.length</code>
variable. Use your skill with the square brackets <code>[ ]</code> to
first confirm the this is the correct value (you should get 430.2) and
then change this value to 43.2. Now redo the dotchart to visualise your
correction. Caution: You can only do this because you have confirmed
that this is an transcribing error. You should <strong>not</strong>
remove or change values in your data just because you feel like it or
they look ‘unusual’. This is scientific fraud! Also, the advantage of
making this change in your R script rather than in Excel is that you now
have a permanent record of the change you made and can state a clear
reason for the change.</p>
<div class="sourceCode" id="cb4"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb4-1"><a href="#cb4-1" tabindex="-1"></a><span class="fu">which</span>(squid<span class="sc">$</span>nid.length <span class="sc">></span> <span class="dv">400</span>)</span>
<span id="cb4-2"><a href="#cb4-2" tabindex="-1"></a><span class="co"># [1] 11</span></span>
<span id="cb4-3"><a href="#cb4-3" tabindex="-1"></a></span>
<span id="cb4-4"><a href="#cb4-4" tabindex="-1"></a>squid<span class="sc">$</span>nid.length[<span class="dv">11</span>]</span>
<span id="cb4-5"><a href="#cb4-5" tabindex="-1"></a><span class="co"># [1] 430.2</span></span>
<span id="cb4-6"><a href="#cb4-6" tabindex="-1"></a></span>
<span id="cb4-7"><a href="#cb4-7" tabindex="-1"></a>squid<span class="sc">$</span>nid.length[<span class="dv">11</span>] <span class="ot"><-</span> <span class="fl">43.2</span></span>
<span id="cb4-8"><a href="#cb4-8" tabindex="-1"></a>squid<span class="sc">$</span>nid.length[<span class="dv">11</span>]</span>
<span id="cb4-9"><a href="#cb4-9" tabindex="-1"></a><span class="co"># [1] 43.2</span></span>
<span id="cb4-10"><a href="#cb4-10" tabindex="-1"></a></span>
<span id="cb4-11"><a href="#cb4-11" tabindex="-1"></a><span class="fu">dotchart</span>(squid<span class="sc">$</span>nid.length, <span class="at">main =</span> <span class="st">"nid length"</span>)</span></code></pre></div>
<p> </p>
<p>8. When exploring your data it is often useful to visualise the
distribution of continuous variables. Take a look at <a
href="https://intro2r.com/simple-base-r-plots.html#histograms">Section
4.2.2</a> and then create histograms for the variables;
<code>DML</code>, <code>weight</code>, <code>eviscerate.weight</code>
and <code>ovary.weight</code>. Again, its up to you if you want to plot
all 4 plots separately or in the same figure. Export your plot(s) as pdf
file(s) to the <code>output</code> directory. One potential problem with
histograms is that the distribution of data can look quite different
depending on the number of ‘breaks’ used. The <code>hist()</code>
function does it’s best to create appropriate ‘breaks’ for your plots
(it uses the <a href="https://en.wikipedia.org/wiki/Histogram">Sturges
algorithm</a> for those that want to know) but experiment with changing
the number of breaks for the <code>DML</code> variable to see how the
shape of the distribution changes (see <a
href="https://intro2r.com/simple-base-r-plots.html#histograms">Section
4.2.2</a> of the book for further details of how to change the
breaks).</p>
<div class="sourceCode" id="cb5"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb5-1"><a href="#cb5-1" tabindex="-1"></a><span class="fu">pdf</span>(<span class="st">'workshop/figures/ex4_hist.pdf'</span>)</span>
<span id="cb5-2"><a href="#cb5-2" tabindex="-1"></a><span class="fu">par</span>(<span class="at">mfrow =</span> <span class="fu">c</span>(<span class="dv">2</span>,<span class="dv">2</span>))</span>
<span id="cb5-3"><a href="#cb5-3" tabindex="-1"></a><span class="fu">hist</span>(squid<span class="sc">$</span>DML, <span class="at">main=</span><span class="st">""</span>, <span class="at">xlab =</span> <span class="st">"DML"</span>)</span>
<span id="cb5-4"><a href="#cb5-4" tabindex="-1"></a><span class="fu">hist</span>(squid<span class="sc">$</span>weight, <span class="at">main=</span><span class="st">""</span>, <span class="at">xlab =</span> <span class="st">"weight"</span>)</span>
<span id="cb5-5"><a href="#cb5-5" tabindex="-1"></a><span class="fu">hist</span>(squid<span class="sc">$</span>eviscerate.weight, <span class="at">main=</span><span class="st">""</span>, <span class="at">xlab =</span> <span class="st">"eviscerate weight"</span>)</span>
<span id="cb5-6"><a href="#cb5-6" tabindex="-1"></a><span class="fu">hist</span>(squid<span class="sc">$</span>ovary.weight, <span class="at">main=</span><span class="st">""</span>, <span class="at">xlab =</span> <span class="st">"ovary weight"</span>)</span>
<span id="cb5-7"><a href="#cb5-7" tabindex="-1"></a><span class="fu">dev.off</span>()</span>
<span id="cb5-8"><a href="#cb5-8" tabindex="-1"></a></span>
<span id="cb5-9"><a href="#cb5-9" tabindex="-1"></a><span class="co"># need to get the min and max values for DML</span></span>
<span id="cb5-10"><a href="#cb5-10" tabindex="-1"></a><span class="co"># to work out the limits for the breaks</span></span>
<span id="cb5-11"><a href="#cb5-11" tabindex="-1"></a></span>
<span id="cb5-12"><a href="#cb5-12" tabindex="-1"></a><span class="fu">summary</span>(squid<span class="sc">$</span>DML)</span>
<span id="cb5-13"><a href="#cb5-13" tabindex="-1"></a><span class="co"># Min. 1st Qu. Median Mean 3rd Qu. Max. </span></span>
<span id="cb5-14"><a href="#cb5-14" tabindex="-1"></a><span class="co"># 88 187 217 215 240 323 </span></span>
<span id="cb5-15"><a href="#cb5-15" tabindex="-1"></a> </span>
<span id="cb5-16"><a href="#cb5-16" tabindex="-1"></a><span class="co"># experimenting with different breaks</span></span>
<span id="cb5-17"><a href="#cb5-17" tabindex="-1"></a><span class="fu">par</span>(<span class="at">mfrow =</span> <span class="fu">c</span>(<span class="dv">2</span>,<span class="dv">2</span>))</span>
<span id="cb5-18"><a href="#cb5-18" tabindex="-1"></a>brk1 <span class="ot"><-</span> <span class="fu">seq</span>(<span class="at">from =</span> <span class="dv">80</span>, <span class="at">to =</span> <span class="dv">340</span>, <span class="at">by =</span> <span class="dv">20</span>) </span>
<span id="cb5-19"><a href="#cb5-19" tabindex="-1"></a><span class="fu">hist</span>(squid<span class="sc">$</span>DML, <span class="at">xlab =</span> <span class="st">"DML"</span>, <span class="at">breaks =</span> brk1, <span class="at">main =</span> <span class="st">"brk: 20"</span>)</span>
<span id="cb5-20"><a href="#cb5-20" tabindex="-1"></a></span>
<span id="cb5-21"><a href="#cb5-21" tabindex="-1"></a>brk2 <span class="ot"><-</span> <span class="fu">seq</span>(<span class="at">from =</span> <span class="dv">80</span>, <span class="at">to =</span> <span class="dv">340</span>, <span class="at">by =</span> <span class="dv">10</span>) </span>
<span id="cb5-22"><a href="#cb5-22" tabindex="-1"></a><span class="fu">hist</span>(squid<span class="sc">$</span>DML, <span class="at">xlab =</span> <span class="st">"DML"</span>, <span class="at">breaks =</span> brk2, <span class="at">main =</span> <span class="st">"brk: 10"</span>)</span>
<span id="cb5-23"><a href="#cb5-23" tabindex="-1"></a></span>
<span id="cb5-24"><a href="#cb5-24" tabindex="-1"></a>brk3 <span class="ot"><-</span> <span class="fu">seq</span>(<span class="at">from =</span> <span class="dv">80</span>, <span class="at">to =</span> <span class="dv">340</span>, <span class="at">by =</span> <span class="dv">5</span>) </span>
<span id="cb5-25"><a href="#cb5-25" tabindex="-1"></a><span class="fu">hist</span>(squid<span class="sc">$</span>DML, <span class="at">xlab =</span> <span class="st">"DML"</span>, <span class="at">breaks =</span> brk3, <span class="at">main =</span> <span class="st">"brk: 5"</span>)</span>
<span id="cb5-26"><a href="#cb5-26" tabindex="-1"></a></span>
<span id="cb5-27"><a href="#cb5-27" tabindex="-1"></a>brk4 <span class="ot"><-</span> <span class="fu">seq</span>(<span class="at">from =</span> <span class="dv">80</span>, <span class="at">to =</span> <span class="dv">340</span>, <span class="at">by =</span> <span class="dv">2</span>) </span>
<span id="cb5-28"><a href="#cb5-28" tabindex="-1"></a><span class="fu">hist</span>(squid<span class="sc">$</span>DML, <span class="at">xlab =</span> <span class="st">"DML"</span>, <span class="at">breaks =</span> brk4, <span class="at">main =</span> <span class="st">"brk: 2"</span>)</span></code></pre></div>
<p> </p>
<p>9. Scatterplots are great for visualising relationships between two
continuous variables (<a
href="https://intro2r.com/simple-base-r-plots.html#scatterplot">Section
4.2.1</a>). Plot the relationship between <code>DML</code> on the x axis
and <code>weight</code> on the y axis. How would you describe this
relationship? Is it linear? One approach to linearising relationships is
to apply a transformation on one or both variables. Try transforming the
<code>weight</code> variable with either a natural log
(<code>log()</code>) or square root (<code>sqrt()</code>)
transformation. I suggest you create new variables in the
<code>squid</code> dataframe for your transformed variables and use
these variables when creating your new plots (ask if you’re not sure how
to do this). Which transformation best linearises this relationship?
Again, save your plots as a pdf file (or try saving in your
<code>output</code> directory as jpeg or png format using the
<code>jpeg()</code> or <code>png()</code> functions - <a
href="https://intro2r.com/export_plots.html#export_plots">Section
4.5</a> if you feel the need for a change!).</p>
<div class="sourceCode" id="cb6"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb6-1"><a href="#cb6-1" tabindex="-1"></a><span class="co"># clearly not linear</span></span>
<span id="cb6-2"><a href="#cb6-2" tabindex="-1"></a><span class="fu">plot</span>(squid<span class="sc">$</span>DML, squid<span class="sc">$</span>weight)</span>
<span id="cb6-3"><a href="#cb6-3" tabindex="-1"></a></span>
<span id="cb6-4"><a href="#cb6-4" tabindex="-1"></a><span class="co"># natural log and sqrt tranform weight</span></span>
<span id="cb6-5"><a href="#cb6-5" tabindex="-1"></a>squid<span class="sc">$</span>weight.sqrt <span class="ot"><-</span> <span class="fu">sqrt</span>(squid<span class="sc">$</span>weight)</span>
<span id="cb6-6"><a href="#cb6-6" tabindex="-1"></a>squid<span class="sc">$</span>weight.log <span class="ot"><-</span> <span class="fu">log</span>(squid<span class="sc">$</span>weight)</span>
<span id="cb6-7"><a href="#cb6-7" tabindex="-1"></a></span>
<span id="cb6-8"><a href="#cb6-8" tabindex="-1"></a><span class="fu">par</span>(<span class="at">mfrow =</span> <span class="fu">c</span>(<span class="dv">1</span>,<span class="dv">2</span>))</span>
<span id="cb6-9"><a href="#cb6-9" tabindex="-1"></a><span class="fu">plot</span>(squid<span class="sc">$</span>DML, squid<span class="sc">$</span>weight.sqrt)</span>
<span id="cb6-10"><a href="#cb6-10" tabindex="-1"></a><span class="fu">plot</span>(squid<span class="sc">$</span>DML, squid<span class="sc">$</span>weight.log)</span>
<span id="cb6-11"><a href="#cb6-11" tabindex="-1"></a></span>
<span id="cb6-12"><a href="#cb6-12" tabindex="-1"></a><span class="co"># the square root transformation looks</span></span>
<span id="cb6-13"><a href="#cb6-13" tabindex="-1"></a><span class="co"># most appropriate</span></span>
<span id="cb6-14"><a href="#cb6-14" tabindex="-1"></a><span class="fu">jpeg</span>(<span class="st">'output/ex4_transf_plot.jpeg'</span>)</span>
<span id="cb6-15"><a href="#cb6-15" tabindex="-1"></a><span class="fu">plot</span>(squid<span class="sc">$</span>DML, squid<span class="sc">$</span>weight.sqrt)</span>
<span id="cb6-16"><a href="#cb6-16" tabindex="-1"></a><span class="fu">dev.off</span>()</span>
<span id="cb6-17"><a href="#cb6-17" tabindex="-1"></a></span>
<span id="cb6-18"><a href="#cb6-18" tabindex="-1"></a><span class="fu">png</span>(<span class="st">'output/ex4_transf_plot.png'</span>)</span>
<span id="cb6-19"><a href="#cb6-19" tabindex="-1"></a><span class="fu">plot</span>(squid<span class="sc">$</span>DML, squid<span class="sc">$</span>weight.sqrt)</span>
<span id="cb6-20"><a href="#cb6-20" tabindex="-1"></a><span class="fu">dev.off</span>()</span></code></pre></div>
<p> </p>
<p>10. When visualising differences in a continuous variable between
levels of a factor (categorical variable) then a boxplot is your friend
(avoid using bar plots - Google ‘bar plots are evil’ for more info).
Create a boxplot to visualise the differences in DML at each maturity
stage (don’t forget to use the recoded version of this variable you
created in Q4) . Include x and y axes labels in your plot. Make sure you
understand the anatomy of a boxplot before moving on - please ask if
you’re not sure (also see <a
href="https://intro2r.com/simple-base-r-plots.html#box-and-violin-plots">Section
4.2.3</a> of the book). An alternative to the boxplot is the violin
plot. A violin plot is a combination of a boxplot and a <a
href="https://www.statmethods.net/graphs/density.html">kernel density
plot</a> and is great at visualising the distribution of a variable. To
create a violin plot you will first need to install the
<code>vioplot</code> package from CRAN and make it available using
<code>library(vioplot)</code>. You can now use the
<code>vioplot()</code> function in pretty much the same way as you
created your boxplot (again <a
href="https://intro2r.com/simple-base-r-plots.html#box-and-violin-plots">Section
4.2.3</a> of the book walks you through this).</p>
<div class="sourceCode" id="cb7"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb7-1"><a href="#cb7-1" tabindex="-1"></a><span class="co"># note: Fmaturity is the recoded maturity.stage variable cerated in Q4</span></span>
<span id="cb7-2"><a href="#cb7-2" tabindex="-1"></a><span class="fu">boxplot</span>(DML <span class="sc">~</span> Fmaturity, <span class="at">data =</span> squid, <span class="at">xlab =</span> <span class="st">"maturity stage"</span>, <span class="at">ylab =</span> <span class="st">"DML"</span>)</span>
<span id="cb7-3"><a href="#cb7-3" tabindex="-1"></a></span>
<span id="cb7-4"><a href="#cb7-4" tabindex="-1"></a><span class="co"># violin plot</span></span>
<span id="cb7-5"><a href="#cb7-5" tabindex="-1"></a><span class="fu">library</span>(vioplot)</span>
<span id="cb7-6"><a href="#cb7-6" tabindex="-1"></a><span class="fu">vioplot</span>(DML <span class="sc">~</span> Fmaturity, <span class="at">data =</span> squid, <span class="at">xlab =</span> <span class="st">"maturity stage"</span>, <span class="at">ylab =</span> <span class="st">"DML"</span>, <span class="at">col =</span> <span class="st">"lightblue"</span>)</span></code></pre></div>
<p> </p>
<p>11. To visualise the relationship between two continuous variables
but for different levels of a factor variable you can create a
conditional scatterplot. Use the <code>coplot()</code> function (<a
href="https://intro2r.com/simple-base-r-plots.html#coplots">Section
4.2.6</a>) to plot the relationship between DML on the x axis and square
root transformed weight on the y axis (you created this variable in Q8)
for each level of maturity stage. Does the relationship between DML and
weight look different for each maturity stage (suggesting an
interaction)? If you prefer, you can also create a similar plot using
the <code>xyplot()</code> function (<a
href="https://intro2r.com/simple-base-r-plots.html#lattice-plots">Section
4.2.7</a>) from the <code>lattice</code> package (don’t forget to make
the function available by using <code>library(lattice)</code>
first).</p>
<div class="sourceCode" id="cb8"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb8-1"><a href="#cb8-1" tabindex="-1"></a><span class="fu">coplot</span>(weight.sqrt <span class="sc">~</span> DML <span class="sc">|</span> Fmaturity, <span class="at">data =</span> squid)</span>
<span id="cb8-2"><a href="#cb8-2" tabindex="-1"></a></span>
<span id="cb8-3"><a href="#cb8-3" tabindex="-1"></a><span class="co"># using xyplot from the lattice package</span></span>
<span id="cb8-4"><a href="#cb8-4" tabindex="-1"></a><span class="fu">library</span>(lattice)</span>
<span id="cb8-5"><a href="#cb8-5" tabindex="-1"></a><span class="fu">xyplot</span>(weight.sqrt <span class="sc">~</span> DML <span class="sc">|</span> Fmaturity, <span class="at">data =</span> squid)</span></code></pre></div>
<p> </p>
<p>12. To explore the relationships between multiple continuous
variables it’s hard to beat a pairs plot. Create a pairs plot for the
variables; <code>DML</code>, <code>weight</code>,
<code>eviscerate.weight</code>, <code>ovary.weight</code>,
<code>nid.length</code>, and <code>nid.weight</code> (see <a
href="https://intro2r.com/simple-base-r-plots.html#pairs-plots">Section
4.2.5</a> of the book for more details). If it looks a little cramped in
RStudio then click on the ‘zoom’ button in the plot viewer to see a
larger version. One of the great things about the <code>pairs()</code>
function is that you can customise what goes into each panel. Modify
your pairs plot to include a histogram of the variables on the diagonal
panel and include a correlation coefficient for each relationship on the
upper triangle panels. Also include a smoother (wiggly line) in the
lower triangle panels to help visualise these relationships. Take a look
at the Introduction to R book to see how to do all this (or
<code>?pairs</code>).</p>
<div class="sourceCode" id="cb9"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb9-1"><a href="#cb9-1" tabindex="-1"></a><span class="co"># vanilla pairs plot</span></span>
<span id="cb9-2"><a href="#cb9-2" tabindex="-1"></a><span class="fu">pairs</span>(squid[, <span class="fu">c</span>(<span class="dv">5</span>, <span class="dv">8</span>, <span class="dv">9</span>, <span class="dv">11</span>, <span class="dv">12</span>, <span class="dv">13</span>)])</span>
<span id="cb9-3"><a href="#cb9-3" tabindex="-1"></a></span>
<span id="cb9-4"><a href="#cb9-4" tabindex="-1"></a><span class="co"># customise the plot. You will need to define the panel.hist and panel.cor functions first. see the</span></span>
<span id="cb9-5"><a href="#cb9-5" tabindex="-1"></a><span class="co"># course manual or ?pairs help file</span></span>
<span id="cb9-6"><a href="#cb9-6" tabindex="-1"></a></span>
<span id="cb9-7"><a href="#cb9-7" tabindex="-1"></a><span class="fu">pairs</span>(squid[, <span class="fu">c</span>(<span class="dv">5</span>, <span class="dv">8</span>, <span class="dv">9</span>, <span class="dv">11</span>, <span class="dv">12</span>, <span class="dv">13</span>)], <span class="at">diag.panel =</span> panel.hist, <span class="at">upper.panel =</span> panel.cor, <span class="at">lower.panel =</span> panel.smooth)</span></code></pre></div>
<p> </p>
<p>13. Almost every aspect of the figures you create in R is
customisable. Learning how to get your plot looking just right is not
only rewarding but also means that you will never have to include a plot
in your paper/thesis that you’re not completely happy with. When you
start learning how to use R it can sometimes seem to take a lot of work
to customise your plots. Don’t worry, it gets easier with experience
(most of the time anyway) and you will always have your code if you want
to create a similar plot in the future. Use the <code>plot()</code>
function to produce a scatterplot of DML on the x axis and ovary weight
on the y axis (you might need to apply a transformation on the variable
<code>ovary.weight</code>). Use a different colour to highlight points
for each level of maturity stage. Produce a legend explaining the
different colours and place it in a suitable position on the plot.
Format the graph further to make it suitable for inclusion into your
paper/thesis (i.e. add axes labels, change the axes scales etc). See <a
href="https://intro2r.com/custom_plot.html#custom_plot">Section 4.3</a>
for more details about customising plots. I have given you a few
different solutions in the code below. give them a go!</p>
<div class="sourceCode" id="cb10"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb10-1"><a href="#cb10-1" tabindex="-1"></a><span class="co"># quick and dirty way</span></span>
<span id="cb10-2"><a href="#cb10-2" tabindex="-1"></a><span class="co"># need to transform ovary.weight first</span></span>
<span id="cb10-3"><a href="#cb10-3" tabindex="-1"></a>squid<span class="sc">$</span>ovary.weight.sqrt <span class="ot"><-</span> <span class="fu">sqrt</span>(squid<span class="sc">$</span>ovary.weight)</span>
<span id="cb10-4"><a href="#cb10-4" tabindex="-1"></a></span>
<span id="cb10-5"><a href="#cb10-5" tabindex="-1"></a><span class="co"># create the plot</span></span>
<span id="cb10-6"><a href="#cb10-6" tabindex="-1"></a><span class="fu">with</span>(squid, <span class="fu">plot</span>(DML, ovary.weight.sqrt, <span class="at">xlab =</span> <span class="st">"DML (mm)"</span>, </span>
<span id="cb10-7"><a href="#cb10-7" tabindex="-1"></a> <span class="at">ylab =</span> <span class="st">"square root ovary weight (g)"</span>, </span>
<span id="cb10-8"><a href="#cb10-8" tabindex="-1"></a> <span class="at">col =</span> <span class="fu">as.numeric</span>(Fmaturity), </span>
<span id="cb10-9"><a href="#cb10-9" tabindex="-1"></a> <span class="at">xlim =</span> <span class="fu">c</span>(<span class="dv">60</span>, <span class="dv">350</span>), <span class="at">ylim =</span> <span class="fu">c</span>(<span class="dv">0</span>, <span class="fl">8.5</span>)))</span>
<span id="cb10-10"><a href="#cb10-10" tabindex="-1"></a></span>
<span id="cb10-11"><a href="#cb10-11" tabindex="-1"></a><span class="co"># create the legend</span></span>
<span id="cb10-12"><a href="#cb10-12" tabindex="-1"></a>labs <span class="ot"><-</span> <span class="fu">c</span>(<span class="st">"stage 1"</span>, <span class="st">"stage 2"</span>, <span class="st">"stage 3"</span>, <span class="st">"stage 4"</span>,<span class="st">"stage 5"</span>)</span>
<span id="cb10-13"><a href="#cb10-13" tabindex="-1"></a>cols <span class="ot"><-</span> <span class="fu">as.numeric</span>(<span class="fu">levels</span>(squid<span class="sc">$</span>Fmaturity))</span>
<span id="cb10-14"><a href="#cb10-14" tabindex="-1"></a><span class="fu">legend</span>(<span class="st">"topleft"</span>, labs,<span class="at">col =</span> cols, <span class="at">pch =</span> <span class="dv">1</span>)</span></code></pre></div>
<div class="sourceCode" id="cb11"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb11-1"><a href="#cb11-1" tabindex="-1"></a><span class="co"># longer but more control</span></span>
<span id="cb11-2"><a href="#cb11-2" tabindex="-1"></a></span>
<span id="cb11-3"><a href="#cb11-3" tabindex="-1"></a><span class="co"># need to scales package to set transparency of points</span></span>
<span id="cb11-4"><a href="#cb11-4" tabindex="-1"></a><span class="co"># will the alpha function</span></span>
<span id="cb11-5"><a href="#cb11-5" tabindex="-1"></a><span class="fu">library</span>(scales)</span>
<span id="cb11-6"><a href="#cb11-6" tabindex="-1"></a></span>
<span id="cb11-7"><a href="#cb11-7" tabindex="-1"></a><span class="co">#setup the axes but dont plot the points</span></span>
<span id="cb11-8"><a href="#cb11-8" tabindex="-1"></a><span class="fu">with</span>(squid, <span class="fu">plot</span>(DML, ovary.weight.sqrt, <span class="at">xlab =</span> <span class="st">"DML (mm)"</span>, </span>
<span id="cb11-9"><a href="#cb11-9" tabindex="-1"></a> <span class="at">ylab =</span> <span class="st">"square root ovary weight (g)"</span>,</span>
<span id="cb11-10"><a href="#cb11-10" tabindex="-1"></a> <span class="at">type =</span> <span class="st">"n"</span>, <span class="at">xlim =</span> <span class="fu">c</span>(<span class="dv">60</span>, <span class="dv">350</span>), <span class="at">ylim =</span> <span class="fu">c</span>(<span class="dv">0</span>, <span class="fl">8.5</span>)))</span>
<span id="cb11-11"><a href="#cb11-11" tabindex="-1"></a></span>
<span id="cb11-12"><a href="#cb11-12" tabindex="-1"></a><span class="co"># plot the points with custom colours</span></span>
<span id="cb11-13"><a href="#cb11-13" tabindex="-1"></a><span class="fu">with</span>(squid, <span class="fu">points</span>(DML[Fmaturity <span class="sc">==</span> <span class="st">"1"</span>], ovary.weight.sqrt[Fmaturity <span class="sc">==</span> <span class="st">"1"</span>], </span>
<span id="cb11-14"><a href="#cb11-14" tabindex="-1"></a> <span class="at">col =</span> <span class="fu">alpha</span>(<span class="st">"deepskyblue3"</span>, <span class="fl">0.7</span>), <span class="at">pch =</span> <span class="dv">16</span>))</span>
<span id="cb11-15"><a href="#cb11-15" tabindex="-1"></a><span class="fu">with</span>(squid, <span class="fu">points</span>(DML[Fmaturity <span class="sc">==</span> <span class="st">"2"</span>], ovary.weight.sqrt[Fmaturity <span class="sc">==</span> <span class="st">"2"</span>], </span>
<span id="cb11-16"><a href="#cb11-16" tabindex="-1"></a> <span class="at">col =</span> <span class="fu">alpha</span>(<span class="st">"darkolivegreen3"</span>, <span class="fl">0.7</span>), <span class="at">pch =</span> <span class="dv">16</span>))</span>
<span id="cb11-17"><a href="#cb11-17" tabindex="-1"></a><span class="fu">with</span>(squid, <span class="fu">points</span>(DML[Fmaturity <span class="sc">==</span> <span class="st">"3"</span>], ovary.weight.sqrt[Fmaturity <span class="sc">==</span> <span class="st">"3"</span>], </span>
<span id="cb11-18"><a href="#cb11-18" tabindex="-1"></a> <span class="at">col =</span> <span class="fu">alpha</span>(<span class="st">"coral3"</span>, <span class="fl">0.7</span>), <span class="at">pch =</span> <span class="dv">16</span>))</span>
<span id="cb11-19"><a href="#cb11-19" tabindex="-1"></a><span class="fu">with</span>(squid, <span class="fu">points</span>(DML[Fmaturity <span class="sc">==</span> <span class="st">"4"</span>], ovary.weight.sqrt[Fmaturity <span class="sc">==</span> <span class="st">"4"</span>], </span>
<span id="cb11-20"><a href="#cb11-20" tabindex="-1"></a> <span class="at">col =</span> <span class="fu">alpha</span>(<span class="st">"lemonchiffon3"</span>, <span class="fl">0.7</span>), <span class="at">pch =</span> <span class="dv">16</span>))</span>
<span id="cb11-21"><a href="#cb11-21" tabindex="-1"></a><span class="fu">with</span>(squid, <span class="fu">points</span>(DML[Fmaturity <span class="sc">==</span> <span class="st">"5"</span>], ovary.weight.sqrt[Fmaturity <span class="sc">==</span> <span class="st">"5"</span>], </span>
<span id="cb11-22"><a href="#cb11-22" tabindex="-1"></a> <span class="at">col =</span> <span class="fu">alpha</span>(<span class="st">"darkorchid3"</span>, <span class="fl">0.7</span>), <span class="at">pch =</span> <span class="dv">16</span>))</span>
<span id="cb11-23"><a href="#cb11-23" tabindex="-1"></a> </span>
<span id="cb11-24"><a href="#cb11-24" tabindex="-1"></a><span class="co"># include the legend</span></span>
<span id="cb11-25"><a href="#cb11-25" tabindex="-1"></a>labs <span class="ot"><-</span> <span class="fu">c</span>(<span class="st">"stage 1"</span>, <span class="st">"stage 2"</span>, <span class="st">"stage 3"</span>, <span class="st">"stage 4"</span>,<span class="st">"stage 5"</span>)</span>
<span id="cb11-26"><a href="#cb11-26" tabindex="-1"></a>cols <span class="ot"><-</span> <span class="fu">c</span>(<span class="st">"deepskyblue3"</span>, <span class="st">"darkolivegreen3"</span>, <span class="st">"coral3"</span>, </span>
<span id="cb11-27"><a href="#cb11-27" tabindex="-1"></a> <span class="st">"lemonchiffon3"</span>, <span class="st">"darkorchid3"</span>)</span>
<span id="cb11-28"><a href="#cb11-28" tabindex="-1"></a><span class="fu">legend</span>(<span class="dv">55</span>, <span class="fl">8.2</span>, labs,<span class="at">col =</span> <span class="fu">alpha</span>(cols, <span class="fl">0.7</span>), <span class="at">pch =</span> <span class="dv">16</span>, <span class="at">bty =</span> <span class="st">"n"</span>)</span></code></pre></div>
<div class="sourceCode" id="cb12"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb12-1"><a href="#cb12-1" tabindex="-1"></a><span class="co"># or use the ggplot2 package</span></span>
<span id="cb12-2"><a href="#cb12-2" tabindex="-1"></a><span class="co"># square root transform ovary weight</span></span>
<span id="cb12-3"><a href="#cb12-3" tabindex="-1"></a>squid<span class="sc">$</span>ovary.weight.sqrt <span class="ot"><-</span> <span class="fu">sqrt</span>(squid<span class="sc">$</span>ovary.weight)</span>
<span id="cb12-4"><a href="#cb12-4" tabindex="-1"></a></span>
<span id="cb12-5"><a href="#cb12-5" tabindex="-1"></a><span class="fu">library</span>(ggplot2)</span>
<span id="cb12-6"><a href="#cb12-6" tabindex="-1"></a><span class="fu">ggplot</span>(<span class="at">data =</span> squid) <span class="sc">+</span></span>
<span id="cb12-7"><a href="#cb12-7" tabindex="-1"></a> <span class="fu">geom_point</span>(<span class="fu">aes</span>(<span class="at">x =</span> DML, <span class="at">y =</span> ovary.weight.sqrt, <span class="at">colour =</span> Fmaturity), </span>
<span id="cb12-8"><a href="#cb12-8" tabindex="-1"></a> <span class="at">alpha =</span> <span class="fl">0.8</span>, <span class="at">size =</span> <span class="dv">2</span>) <span class="sc">+</span></span>
<span id="cb12-9"><a href="#cb12-9" tabindex="-1"></a> <span class="fu">scale_colour_manual</span>(<span class="at">values =</span> <span class="fu">c</span>(<span class="st">"deepskyblue3"</span>, <span class="st">"darkolivegreen3"</span>, <span class="st">"coral3"</span>, </span>
<span id="cb12-10"><a href="#cb12-10" tabindex="-1"></a> <span class="st">"lemonchiffon3"</span>, <span class="st">"darkorchid3"</span>), </span>
<span id="cb12-11"><a href="#cb12-11" tabindex="-1"></a> <span class="at">labels =</span> <span class="fu">c</span>(<span class="st">"stage 1"</span>, <span class="st">"stage 2"</span>, <span class="st">"stage 3"</span>, </span>
<span id="cb12-12"><a href="#cb12-12" tabindex="-1"></a> <span class="st">"stage 4"</span>, <span class="st">"stage 5"</span>)) <span class="sc">+</span></span>
<span id="cb12-13"><a href="#cb12-13" tabindex="-1"></a> <span class="fu">theme_classic</span>(<span class="at">base_size =</span> <span class="dv">12</span>) <span class="sc">+</span></span>
<span id="cb12-14"><a href="#cb12-14" tabindex="-1"></a> <span class="fu">labs</span>(<span class="at">colour =</span> <span class="st">""</span>, <span class="at">x =</span> <span class="st">"DML (mm)"</span>, <span class="at">y =</span> <span class="st">"square root ovary weight (g)"</span>)</span>
<span id="cb12-15"><a href="#cb12-15" tabindex="-1"></a></span>
<span id="cb12-16"><a href="#cb12-16" tabindex="-1"></a><span class="co"># OR</span></span>
<span id="cb12-17"><a href="#cb12-17" tabindex="-1"></a><span class="fu">ggplot</span>(<span class="at">data =</span> squid) <span class="sc">+</span></span>
<span id="cb12-18"><a href="#cb12-18" tabindex="-1"></a> <span class="fu">geom_point</span>(<span class="fu">aes</span>(<span class="at">x =</span> DML, <span class="at">y =</span> ovary.weight.sqrt, <span class="at">colour =</span> Fmaturity), </span>
<span id="cb12-19"><a href="#cb12-19" tabindex="-1"></a> <span class="at">alpha =</span> <span class="fl">0.8</span>, <span class="at">size =</span> <span class="dv">2</span>) <span class="sc">+</span></span>