-
Notifications
You must be signed in to change notification settings - Fork 0
/
README.html
516 lines (405 loc) · 29.5 KB
/
README.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
<!DOCTYPE html>
<!-- saved from url=(0014)about:internet -->
<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8"/>
<meta http-equiv="x-ua-compatible" content="IE=9" >
<title>Getting and Cleaning Data Project by George Drakulic</title>
<style type="text/css">
body, td {
font-family: sans-serif;
background-color: white;
font-size: 12px;
margin: 8px;
}
tt, code, pre {
font-family: 'DejaVu Sans Mono', 'Droid Sans Mono', 'Lucida Console', Consolas, Monaco, monospace;
}
h1 {
font-size:2.2em;
}
h2 {
font-size:1.8em;
}
h3 {
font-size:1.4em;
}
h4 {
font-size:1.0em;
}
h5 {
font-size:0.9em;
}
h6 {
font-size:0.8em;
}
a:visited {
color: rgb(50%, 0%, 50%);
}
pre {
margin-top: 0;
max-width: 95%;
border: 1px solid #ccc;
white-space: pre-wrap;
}
pre code {
display: block; padding: 0.5em;
}
code.r, code.cpp {
background-color: #F8F8F8;
}
table, td, th {
border: none;
}
blockquote {
color:#666666;
margin:0;
padding-left: 1em;
border-left: 0.5em #EEE solid;
}
hr {
height: 0px;
border-bottom: none;
border-top-width: thin;
border-top-style: dotted;
border-top-color: #999999;
}
@media print {
* {
background: transparent !important;
color: black !important;
filter:none !important;
-ms-filter: none !important;
}
body {
font-size:12pt;
max-width:100%;
}
a, a:visited {
text-decoration: underline;
}
hr {
visibility: hidden;
page-break-before: always;
}
pre, blockquote {
padding-right: 1em;
page-break-inside: avoid;
}
tr, img {
page-break-inside: avoid;
}
img {
max-width: 100% !important;
}
@page :left {
margin: 15mm 20mm 15mm 10mm;
}
@page :right {
margin: 15mm 10mm 15mm 20mm;
}
p, h2, h3 {
orphans: 3; widows: 3;
}
h2, h3 {
page-break-after: avoid;
}
}
</style>
<!-- Styles for R syntax highlighter -->
<style type="text/css">
pre .operator,
pre .paren {
color: rgb(104, 118, 135)
}
pre .literal {
color: rgb(88, 72, 246)
}
pre .number {
color: rgb(0, 0, 205);
}
pre .comment {
color: rgb(76, 136, 107);
}
pre .keyword {
color: rgb(0, 0, 255);
}
pre .identifier {
color: rgb(0, 0, 0);
}
pre .string {
color: rgb(3, 106, 7);
}
</style>
<!-- R syntax highlighter -->
<script type="text/javascript">
var hljs=new function(){function m(p){return p.replace(/&/gm,"&").replace(/</gm,"<")}function f(r,q,p){return RegExp(q,"m"+(r.cI?"i":"")+(p?"g":""))}function b(r){for(var p=0;p<r.childNodes.length;p++){var q=r.childNodes[p];if(q.nodeName=="CODE"){return q}if(!(q.nodeType==3&&q.nodeValue.match(/\s+/))){break}}}function h(t,s){var p="";for(var r=0;r<t.childNodes.length;r++){if(t.childNodes[r].nodeType==3){var q=t.childNodes[r].nodeValue;if(s){q=q.replace(/\n/g,"")}p+=q}else{if(t.childNodes[r].nodeName=="BR"){p+="\n"}else{p+=h(t.childNodes[r])}}}if(/MSIE [678]/.test(navigator.userAgent)){p=p.replace(/\r/g,"\n")}return p}function a(s){var r=s.className.split(/\s+/);r=r.concat(s.parentNode.className.split(/\s+/));for(var q=0;q<r.length;q++){var p=r[q].replace(/^language-/,"");if(e[p]){return p}}}function c(q){var p=[];(function(s,t){for(var r=0;r<s.childNodes.length;r++){if(s.childNodes[r].nodeType==3){t+=s.childNodes[r].nodeValue.length}else{if(s.childNodes[r].nodeName=="BR"){t+=1}else{if(s.childNodes[r].nodeType==1){p.push({event:"start",offset:t,node:s.childNodes[r]});t=arguments.callee(s.childNodes[r],t);p.push({event:"stop",offset:t,node:s.childNodes[r]})}}}}return t})(q,0);return p}function k(y,w,x){var q=0;var z="";var s=[];function u(){if(y.length&&w.length){if(y[0].offset!=w[0].offset){return(y[0].offset<w[0].offset)?y:w}else{return w[0].event=="start"?y:w}}else{return y.length?y:w}}function t(D){var A="<"+D.nodeName.toLowerCase();for(var B=0;B<D.attributes.length;B++){var C=D.attributes[B];A+=" "+C.nodeName.toLowerCase();if(C.value!==undefined&&C.value!==false&&C.value!==null){A+='="'+m(C.value)+'"'}}return A+">"}while(y.length||w.length){var v=u().splice(0,1)[0];z+=m(x.substr(q,v.offset-q));q=v.offset;if(v.event=="start"){z+=t(v.node);s.push(v.node)}else{if(v.event=="stop"){var p,r=s.length;do{r--;p=s[r];z+=("</"+p.nodeName.toLowerCase()+">")}while(p!=v.node);s.splice(r,1);while(r<s.length){z+=t(s[r]);r++}}}}return z+m(x.substr(q))}function j(){function q(x,y,v){if(x.compiled){return}var u;var s=[];if(x.k){x.lR=f(y,x.l||hljs.IR,true);for(var w in x.k){if(!x.k.hasOwnProperty(w)){continue}if(x.k[w] instanceof Object){u=x.k[w]}else{u=x.k;w="keyword"}for(var r in u){if(!u.hasOwnProperty(r)){continue}x.k[r]=[w,u[r]];s.push(r)}}}if(!v){if(x.bWK){x.b="\\b("+s.join("|")+")\\s"}x.bR=f(y,x.b?x.b:"\\B|\\b");if(!x.e&&!x.eW){x.e="\\B|\\b"}if(x.e){x.eR=f(y,x.e)}}if(x.i){x.iR=f(y,x.i)}if(x.r===undefined){x.r=1}if(!x.c){x.c=[]}x.compiled=true;for(var t=0;t<x.c.length;t++){if(x.c[t]=="self"){x.c[t]=x}q(x.c[t],y,false)}if(x.starts){q(x.starts,y,false)}}for(var p in e){if(!e.hasOwnProperty(p)){continue}q(e[p].dM,e[p],true)}}function d(B,C){if(!j.called){j();j.called=true}function q(r,M){for(var L=0;L<M.c.length;L++){if((M.c[L].bR.exec(r)||[null])[0]==r){return M.c[L]}}}function v(L,r){if(D[L].e&&D[L].eR.test(r)){return 1}if(D[L].eW){var M=v(L-1,r);return M?M+1:0}return 0}function w(r,L){return L.i&&L.iR.test(r)}function K(N,O){var M=[];for(var L=0;L<N.c.length;L++){M.push(N.c[L].b)}var r=D.length-1;do{if(D[r].e){M.push(D[r].e)}r--}while(D[r+1].eW);if(N.i){M.push(N.i)}return f(O,M.join("|"),true)}function p(M,L){var N=D[D.length-1];if(!N.t){N.t=K(N,E)}N.t.lastIndex=L;var r=N.t.exec(M);return r?[M.substr(L,r.index-L),r[0],false]:[M.substr(L),"",true]}function z(N,r){var L=E.cI?r[0].toLowerCase():r[0];var M=N.k[L];if(M&&M instanceof Array){return M}return false}function F(L,P){L=m(L);if(!P.k){return L}var r="";var O=0;P.lR.lastIndex=0;var M=P.lR.exec(L);while(M){r+=L.substr(O,M.index-O);var N=z(P,M);if(N){x+=N[1];r+='<span class="'+N[0]+'">'+M[0]+"</span>"}else{r+=M[0]}O=P.lR.lastIndex;M=P.lR.exec(L)}return r+L.substr(O,L.length-O)}function J(L,M){if(M.sL&&e[M.sL]){var r=d(M.sL,L);x+=r.keyword_count;return r.value}else{return F(L,M)}}function I(M,r){var L=M.cN?'<span class="'+M.cN+'">':"";if(M.rB){y+=L;M.buffer=""}else{if(M.eB){y+=m(r)+L;M.buffer=""}else{y+=L;M.buffer=r}}D.push(M);A+=M.r}function G(N,M,Q){var R=D[D.length-1];if(Q){y+=J(R.buffer+N,R);return false}var P=q(M,R);if(P){y+=J(R.buffer+N,R);I(P,M);return P.rB}var L=v(D.length-1,M);if(L){var O=R.cN?"</span>":"";if(R.rE){y+=J(R.buffer+N,R)+O}else{if(R.eE){y+=J(R.buffer+N,R)+O+m(M)}else{y+=J(R.buffer+N+M,R)+O}}while(L>1){O=D[D.length-2].cN?"</span>":"";y+=O;L--;D.length--}var r=D[D.length-1];D.length--;D[D.length-1].buffer="";if(r.starts){I(r.starts,"")}return R.rE}if(w(M,R)){throw"Illegal"}}var E=e[B];var D=[E.dM];var A=0;var x=0;var y="";try{var s,u=0;E.dM.buffer="";do{s=p(C,u);var t=G(s[0],s[1],s[2]);u+=s[0].length;if(!t){u+=s[1].length}}while(!s[2]);if(D.length>1){throw"Illegal"}return{r:A,keyword_count:x,value:y}}catch(H){if(H=="Illegal"){return{r:0,keyword_count:0,value:m(C)}}else{throw H}}}function g(t){var p={keyword_count:0,r:0,value:m(t)};var r=p;for(var q in e){if(!e.hasOwnProperty(q)){continue}var s=d(q,t);s.language=q;if(s.keyword_count+s.r>r.keyword_count+r.r){r=s}if(s.keyword_count+s.r>p.keyword_count+p.r){r=p;p=s}}if(r.language){p.second_best=r}return p}function i(r,q,p){if(q){r=r.replace(/^((<[^>]+>|\t)+)/gm,function(t,w,v,u){return w.replace(/\t/g,q)})}if(p){r=r.replace(/\n/g,"<br>")}return r}function n(t,w,r){var x=h(t,r);var v=a(t);var y,s;if(v){y=d(v,x)}else{return}var q=c(t);if(q.length){s=document.createElement("pre");s.innerHTML=y.value;y.value=k(q,c(s),x)}y.value=i(y.value,w,r);var u=t.className;if(!u.match("(\\s|^)(language-)?"+v+"(\\s|$)")){u=u?(u+" "+v):v}if(/MSIE [678]/.test(navigator.userAgent)&&t.tagName=="CODE"&&t.parentNode.tagName=="PRE"){s=t.parentNode;var p=document.createElement("div");p.innerHTML="<pre><code>"+y.value+"</code></pre>";t=p.firstChild.firstChild;p.firstChild.cN=s.cN;s.parentNode.replaceChild(p.firstChild,s)}else{t.innerHTML=y.value}t.className=u;t.result={language:v,kw:y.keyword_count,re:y.r};if(y.second_best){t.second_best={language:y.second_best.language,kw:y.second_best.keyword_count,re:y.second_best.r}}}function o(){if(o.called){return}o.called=true;var r=document.getElementsByTagName("pre");for(var p=0;p<r.length;p++){var q=b(r[p]);if(q){n(q,hljs.tabReplace)}}}function l(){if(window.addEventListener){window.addEventListener("DOMContentLoaded",o,false);window.addEventListener("load",o,false)}else{if(window.attachEvent){window.attachEvent("onload",o)}else{window.onload=o}}}var e={};this.LANGUAGES=e;this.highlight=d;this.highlightAuto=g;this.fixMarkup=i;this.highlightBlock=n;this.initHighlighting=o;this.initHighlightingOnLoad=l;this.IR="[a-zA-Z][a-zA-Z0-9_]*";this.UIR="[a-zA-Z_][a-zA-Z0-9_]*";this.NR="\\b\\d+(\\.\\d+)?";this.CNR="\\b(0[xX][a-fA-F0-9]+|(\\d+(\\.\\d*)?|\\.\\d+)([eE][-+]?\\d+)?)";this.BNR="\\b(0b[01]+)";this.RSR="!|!=|!==|%|%=|&|&&|&=|\\*|\\*=|\\+|\\+=|,|\\.|-|-=|/|/=|:|;|<|<<|<<=|<=|=|==|===|>|>=|>>|>>=|>>>|>>>=|\\?|\\[|\\{|\\(|\\^|\\^=|\\||\\|=|\\|\\||~";this.ER="(?![\\s\\S])";this.BE={b:"\\\\.",r:0};this.ASM={cN:"string",b:"'",e:"'",i:"\\n",c:[this.BE],r:0};this.QSM={cN:"string",b:'"',e:'"',i:"\\n",c:[this.BE],r:0};this.CLCM={cN:"comment",b:"//",e:"$"};this.CBLCLM={cN:"comment",b:"/\\*",e:"\\*/"};this.HCM={cN:"comment",b:"#",e:"$"};this.NM={cN:"number",b:this.NR,r:0};this.CNM={cN:"number",b:this.CNR,r:0};this.BNM={cN:"number",b:this.BNR,r:0};this.inherit=function(r,s){var p={};for(var q in r){p[q]=r[q]}if(s){for(var q in s){p[q]=s[q]}}return p}}();hljs.LANGUAGES.cpp=function(){var a={keyword:{"false":1,"int":1,"float":1,"while":1,"private":1,"char":1,"catch":1,"export":1,virtual:1,operator:2,sizeof:2,dynamic_cast:2,typedef:2,const_cast:2,"const":1,struct:1,"for":1,static_cast:2,union:1,namespace:1,unsigned:1,"long":1,"throw":1,"volatile":2,"static":1,"protected":1,bool:1,template:1,mutable:1,"if":1,"public":1,friend:2,"do":1,"return":1,"goto":1,auto:1,"void":2,"enum":1,"else":1,"break":1,"new":1,extern:1,using:1,"true":1,"class":1,asm:1,"case":1,typeid:1,"short":1,reinterpret_cast:2,"default":1,"double":1,register:1,explicit:1,signed:1,typename:1,"try":1,"this":1,"switch":1,"continue":1,wchar_t:1,inline:1,"delete":1,alignof:1,char16_t:1,char32_t:1,constexpr:1,decltype:1,noexcept:1,nullptr:1,static_assert:1,thread_local:1,restrict:1,_Bool:1,complex:1},built_in:{std:1,string:1,cin:1,cout:1,cerr:1,clog:1,stringstream:1,istringstream:1,ostringstream:1,auto_ptr:1,deque:1,list:1,queue:1,stack:1,vector:1,map:1,set:1,bitset:1,multiset:1,multimap:1,unordered_set:1,unordered_map:1,unordered_multiset:1,unordered_multimap:1,array:1,shared_ptr:1}};return{dM:{k:a,i:"</",c:[hljs.CLCM,hljs.CBLCLM,hljs.QSM,{cN:"string",b:"'\\\\?.",e:"'",i:"."},{cN:"number",b:"\\b(\\d+(\\.\\d*)?|\\.\\d+)(u|U|l|L|ul|UL|f|F)"},hljs.CNM,{cN:"preprocessor",b:"#",e:"$"},{cN:"stl_container",b:"\\b(deque|list|queue|stack|vector|map|set|bitset|multiset|multimap|unordered_map|unordered_set|unordered_multiset|unordered_multimap|array)\\s*<",e:">",k:a,r:10,c:["self"]}]}}}();hljs.LANGUAGES.r={dM:{c:[hljs.HCM,{cN:"number",b:"\\b0[xX][0-9a-fA-F]+[Li]?\\b",e:hljs.IMMEDIATE_RE,r:0},{cN:"number",b:"\\b\\d+(?:[eE][+\\-]?\\d*)?L\\b",e:hljs.IMMEDIATE_RE,r:0},{cN:"number",b:"\\b\\d+\\.(?!\\d)(?:i\\b)?",e:hljs.IMMEDIATE_RE,r:1},{cN:"number",b:"\\b\\d+(?:\\.\\d*)?(?:[eE][+\\-]?\\d*)?i?\\b",e:hljs.IMMEDIATE_RE,r:0},{cN:"number",b:"\\.\\d+(?:[eE][+\\-]?\\d*)?i?\\b",e:hljs.IMMEDIATE_RE,r:1},{cN:"keyword",b:"(?:tryCatch|library|setGeneric|setGroupGeneric)\\b",e:hljs.IMMEDIATE_RE,r:10},{cN:"keyword",b:"\\.\\.\\.",e:hljs.IMMEDIATE_RE,r:10},{cN:"keyword",b:"\\.\\.\\d+(?![\\w.])",e:hljs.IMMEDIATE_RE,r:10},{cN:"keyword",b:"\\b(?:function)",e:hljs.IMMEDIATE_RE,r:2},{cN:"keyword",b:"(?:if|in|break|next|repeat|else|for|return|switch|while|try|stop|warning|require|attach|detach|source|setMethod|setClass)\\b",e:hljs.IMMEDIATE_RE,r:1},{cN:"literal",b:"(?:NA|NA_integer_|NA_real_|NA_character_|NA_complex_)\\b",e:hljs.IMMEDIATE_RE,r:10},{cN:"literal",b:"(?:NULL|TRUE|FALSE|T|F|Inf|NaN)\\b",e:hljs.IMMEDIATE_RE,r:1},{cN:"identifier",b:"[a-zA-Z.][a-zA-Z0-9._]*\\b",e:hljs.IMMEDIATE_RE,r:0},{cN:"operator",b:"<\\-(?!\\s*\\d)",e:hljs.IMMEDIATE_RE,r:2},{cN:"operator",b:"\\->|<\\-",e:hljs.IMMEDIATE_RE,r:1},{cN:"operator",b:"%%|~",e:hljs.IMMEDIATE_RE},{cN:"operator",b:">=|<=|==|!=|\\|\\||&&|=|\\+|\\-|\\*|/|\\^|>|<|!|&|\\||\\$|:",e:hljs.IMMEDIATE_RE,r:0},{cN:"operator",b:"%",e:"%",i:"\\n",r:1},{cN:"identifier",b:"`",e:"`",r:0},{cN:"string",b:'"',e:'"',c:[hljs.BE],r:0},{cN:"string",b:"'",e:"'",c:[hljs.BE],r:0},{cN:"paren",b:"[[({\\])}]",e:hljs.IMMEDIATE_RE,r:0}]}};
hljs.initHighlightingOnLoad();
</script>
</head>
<body>
<h1>Getting and Cleaning Data Project by George Drakulic</h1>
<h2>download data from</h2>
<h2><a href="http://archive.ics.uci.edu/ml/datasets/Human+Activity+Recognition+Using+Smartphones">http://archive.ics.uci.edu/ml/datasets/Human+Activity+Recognition+Using+Smartphones</a></h2>
<h2>unzip it at your working directory</h2>
<h2>it will create directoy called “UCI HAR Dataset”</h2>
<h2>in that directory there are two other directories: “test” and “train”,</h2>
<h2>as well as labels of variour columns of the data in txt files</h2>
<h2>create a data frame “subject” by reading subject_test.txt, which has rows of a subject's number,</h2>
<h2>and name the column “subject”</h2>
<pre><code class="r">subject <- read.table("UCI HAR Dataset/test/subject_test.txt")
colnames(subject) <- c("subject")
</code></pre>
<h2>create a data frame “activity” by reading y_test.txt, which has rows of an activity's number,</h2>
<h2>and name the column “activity”</h2>
<pre><code class="r">activity <- read.table("UCI HAR Dataset/test/y_test.txt")
colnames(activity) <- c("activity")
</code></pre>
<h2>change the numbers in activity data frame into textual activities listed in “activity_labels.txt”</h2>
<pre><code class="r">activity <- factor(activity$activity, levels = c(1, 2, 3, 4, 5, 6), labels = c("walking",
"walking_upstairs", "walking_downstairs", "sitting", "standing", "laying"))
</code></pre>
<h2>merge two data frames into one (subject and activity into dat1)</h2>
<pre><code class="r">dat1 <- cbind(subject, activity)
</code></pre>
<h2>read X_test data with 561 columns</h2>
<pre><code class="r">X_test <- read.table("UCI HAR Dataset/test/X_test.txt")
</code></pre>
<h2>get the names of the features (which will be column names of X_test data)</h2>
<pre><code class="r">features <- read.table("UCI HAR Dataset/features.txt")
</code></pre>
<h1>rows should be columns, so we will transpose rows and columns, and get just the names of the features</h1>
<pre><code class="r">feature_name <- t(features)[2, ]
</code></pre>
<h2>rename the columns of X_test data with the column names of the features from features.txt</h2>
<pre><code class="r">colnames(X_test) <- feature_name
</code></pre>
<h2>get the index of columns that have “mean()” in them, and also “meanFreq()</h2>
<pre><code class="r">g_mean <- grep("mean()", feature_name)
</code></pre>
<h2>get the index of columns that have "std()” in them</h2>
<pre><code class="r">g_std <- grep("std()", feature_name)
</code></pre>
<h2>combine those indices into one</h2>
<pre><code class="r">g_all <- append(g_mean, g_std)
</code></pre>
<h2>sort the indices</h2>
<h2>these are the indices we need in our data</h2>
<pre><code class="r">sorted_indices <- sort(g_all)
</code></pre>
<h2>the data set with columns of needed data of mean, and std computations</h2>
<pre><code class="r">X_test_mean_and_std <- X_test[, sorted_indices]
</code></pre>
<h2>merge subject + activity (dat1), and X_test_mean_std</h2>
<pre><code class="r">X_test_merged <- cbind(dat1, X_test_mean_and_std)
</code></pre>
<h2>just to check the final result: nrow(X_test_merged) gives me 2947,</h2>
<h2>ncol(X_test_merged) gives me 81, so the test merged data frame is 2947 x 81</h2>
<h2>Do the same for the train data</h2>
<pre><code class="r">subjectTrain <- read.table("UCI HAR Dataset/train/subject_train.txt")
colnames(subjectTrain) <- c("subject")
activityTrain <- read.table("UCI HAR Dataset/train/y_train.txt")
colnames(activityTrain) <- c("activity")
activityTrain <- factor(activityTrain$activity, levels = c(1, 2, 3, 4, 5, 6),
labels = c("walking", "walking_upstairs", "walking_downstairs", "sitting",
"standing", "laying"))
dat2 <- cbind(subjectTrain, activityTrain)
colnames(dat2) <- c("subject", "activity")
X_train <- read.table("UCI HAR Dataset/train/X_train.txt")
colnames(X_train) <- feature_name
X_train_mean_and_std <- X_train[, sorted_indices]
X_train_merged <- cbind(dat2, X_train_mean_and_std)
</code></pre>
<h2>just to check the final result: nrow(X_train_merged) gives me 7352,</h2>
<h2>ncol(X_train_merged) gives me 81, so the train merged data frame is 7352 x 81</h2>
<h2>merging the test and the training sets should give me (2947 + 7352) x 81 data frame</h2>
<h2>i.e. 10299 x 81</h2>
<pre><code class="r">X_final <- rbind(X_test_merged, X_train_merged)
</code></pre>
<h2>nrow(X_final) gives me 10299, which is as expected, ncol(X_final) is 81 as well</h2>
<h2>empty data frame for tidy data</h2>
<pre><code class="r">X_tidy <- data.frame()
</code></pre>
<h1>the data is split by subject, activity, and other variables, so it computes</h1>
<h1>the mean of each variable for each subject and his/her activity,</h1>
<h1>e.g. subject 1, activity 1, all means of variables; subject 2, activity 1, means,</h1>
<h1>up to last subject, activity 1</h1>
<h1>then, it starts with subject 1, activity 2 …, last s, act 2 and so on</h1>
<pre><code class="r">data_split <- split(X_final[, 3:81], list(X_final$subject, X_final$activity))
X_tidy <- sapply(data_split, colMeans)
</code></pre>
<h1>nrow(X_tidy) = 79, ncol(X_tidy) = 180</h1>
<h1>output with row.names=F so the data is properly aligned in MS Excel, but the row names</h1>
<h1>are, of course, missing</h1>
<pre><code class="r">write.table(X_tidy, file = "./X_tidy.txt", sep = "\t", row.names = FALSE)
</code></pre>
<h1>output with row.names=T so the data is NOT properly aligned in MS Excel</h1>
<pre><code class="r">write.table(X_tidy, file = "./X_tidy_with_row_names.txt", sep = "\t")
</code></pre>
<pre><code class="r">head(X_tidy, 2)
</code></pre>
<pre><code>## 1.walking 2.walking 3.walking 4.walking 5.walking
## tBodyAcc-mean()-X 0.27733 0.27643 0.27557 0.27858 0.27784
## tBodyAcc-mean()-Y -0.01738 -0.01859 -0.01718 -0.01484 -0.01729
## 6.walking 7.walking 8.walking 9.walking 10.walking
## tBodyAcc-mean()-X 0.2837 0.27559 0.27469 0.27850 0.27857
## tBodyAcc-mean()-Y -0.0169 -0.01865 -0.01866 -0.01809 -0.01702
## 11.walking 12.walking 13.walking 14.walking 15.walking
## tBodyAcc-mean()-X 0.27182 0.27713 0.27588 0.27196 0.27390
## tBodyAcc-mean()-Y -0.01665 -0.01556 -0.01857 -0.02178 -0.01708
## 16.walking 17.walking 18.walking 19.walking 20.walking
## tBodyAcc-mean()-X 0.27602 0.27234 0.2739 0.27393 0.2726
## tBodyAcc-mean()-Y -0.02043 -0.01849 -0.0178 -0.01918 -0.0212
## 21.walking 22.walking 23.walking 24.walking 25.walking
## tBodyAcc-mean()-X 0.27918 0.27886 0.27321 0.27698 0.27899
## tBodyAcc-mean()-Y -0.01816 -0.01672 -0.01836 -0.02254 -0.01865
## 26.walking 27.walking 28.walking 29.walking 30.walking
## tBodyAcc-mean()-X 0.27926 0.27685 0.28123 0.27200 0.27641
## tBodyAcc-mean()-Y -0.01543 -0.01665 -0.01568 -0.01629 -0.01759
## 1.walking_upstairs 2.walking_upstairs 3.walking_upstairs
## tBodyAcc-mean()-X 0.25546 0.24716 0.26082
## tBodyAcc-mean()-Y -0.02395 -0.02141 -0.03241
## 4.walking_upstairs 5.walking_upstairs 6.walking_upstairs
## tBodyAcc-mean()-X 0.27088 0.26846 0.26823
## tBodyAcc-mean()-Y -0.03198 -0.03253 -0.02724
## 7.walking_upstairs 8.walking_upstairs 9.walking_upstairs
## tBodyAcc-mean()-X 0.24871 0.25888 0.26244
## tBodyAcc-mean()-Y -0.02756 -0.02824 -0.01951
## 10.walking_upstairs 11.walking_upstairs
## tBodyAcc-mean()-X 0.26712 0.26378
## tBodyAcc-mean()-Y -0.01439 -0.03032
## 12.walking_upstairs 13.walking_upstairs
## tBodyAcc-mean()-X 0.27297 0.25820
## tBodyAcc-mean()-Y -0.02636 -0.02774
## 14.walking_upstairs 15.walking_upstairs
## tBodyAcc-mean()-X 0.26242 0.27019
## tBodyAcc-mean()-Y -0.02044 -0.02875
## 16.walking_upstairs 17.walking_upstairs
## tBodyAcc-mean()-X 0.25599 0.25260
## tBodyAcc-mean()-Y -0.01437 -0.02286
## 18.walking_upstairs 19.walking_upstairs
## tBodyAcc-mean()-X 0.26540 0.2421
## tBodyAcc-mean()-Y -0.02221 -0.0304
## 20.walking_upstairs 21.walking_upstairs
## tBodyAcc-mean()-X 0.25210 0.26519
## tBodyAcc-mean()-Y -0.02823 -0.02372
## 22.walking_upstairs 23.walking_upstairs
## tBodyAcc-mean()-X 0.24839 0.25000
## tBodyAcc-mean()-Y -0.02686 -0.03238
## 24.walking_upstairs 25.walking_upstairs
## tBodyAcc-mean()-X 0.2699 0.27800
## tBodyAcc-mean()-Y -0.0252 -0.02699
## 26.walking_upstairs 27.walking_upstairs
## tBodyAcc-mean()-X 0.27269 0.2658
## tBodyAcc-mean()-Y -0.02816 -0.0201
## 28.walking_upstairs 29.walking_upstairs
## tBodyAcc-mean()-X 0.26201 0.26542
## tBodyAcc-mean()-Y -0.02794 -0.02995
## 30.walking_upstairs 1.walking_downstairs
## tBodyAcc-mean()-X 0.27142 0.289188
## tBodyAcc-mean()-Y -0.02533 -0.009919
## 2.walking_downstairs 3.walking_downstairs
## tBodyAcc-mean()-X 0.27762 0.29242
## tBodyAcc-mean()-Y -0.02266 -0.01936
## 4.walking_downstairs 5.walking_downstairs
## tBodyAcc-mean()-X 0.279965 0.293544
## tBodyAcc-mean()-Y -0.009802 -0.008501
## 6.walking_downstairs 7.walking_downstairs
## tBodyAcc-mean()-X 0.27705 0.28031
## tBodyAcc-mean()-Y -0.01954 -0.01663
## 8.walking_downstairs 9.walking_downstairs
## tBodyAcc-mean()-X 0.28348 0.2959
## tBodyAcc-mean()-Y -0.02111 -0.0204
## 10.walking_downstairs 11.walking_downstairs
## tBodyAcc-mean()-X 0.29040 0.29161
## tBodyAcc-mean()-Y -0.02001 -0.01781
## 12.walking_downstairs 13.walking_downstairs
## tBodyAcc-mean()-X 0.28152 0.29491
## tBodyAcc-mean()-Y -0.01808 -0.01437
## 14.walking_downstairs 15.walking_downstairs
## tBodyAcc-mean()-X 0.29342 0.28020
## tBodyAcc-mean()-Y -0.02001 -0.00563
## 16.walking_downstairs 17.walking_downstairs
## tBodyAcc-mean()-X 0.29559 0.29392
## tBodyAcc-mean()-Y -0.01839 -0.01674
## 18.walking_downstairs 19.walking_downstairs
## tBodyAcc-mean()-X 0.28844 0.26269
## tBodyAcc-mean()-Y -0.01687 -0.01459
## 20.walking_downstairs 21.walking_downstairs
## tBodyAcc-mean()-X 0.296144 0.30146
## tBodyAcc-mean()-Y -0.009641 -0.01732
## 22.walking_downstairs 23.walking_downstairs
## tBodyAcc-mean()-X 0.2845 0.28990
## tBodyAcc-mean()-Y -0.0198 -0.01621
## 24.walking_downstairs 25.walking_downstairs
## tBodyAcc-mean()-X 0.28863 0.29133
## tBodyAcc-mean()-Y -0.01457 -0.02102
## 26.walking_downstairs 27.walking_downstairs
## tBodyAcc-mean()-X 0.27928 0.29754
## tBodyAcc-mean()-Y -0.01263 -0.01356
## 28.walking_downstairs 29.walking_downstairs
## tBodyAcc-mean()-X 0.29364 0.29314
## tBodyAcc-mean()-Y -0.02202 -0.01494
## 30.walking_downstairs 1.sitting 2.sitting 3.sitting
## tBodyAcc-mean()-X 0.28319 0.261238 0.27709 0.257198
## tBodyAcc-mean()-Y -0.01744 -0.001308 -0.01569 -0.003503
## 4.sitting 5.sitting 6.sitting 7.sitting 8.sitting
## tBodyAcc-mean()-X 0.271538 0.273694 0.27678 0.28467 0.267491
## tBodyAcc-mean()-Y -0.007163 -0.009901 -0.01459 -0.01461 -0.006726
## 9.sitting 10.sitting 11.sitting 12.sitting 13.sitting
## tBodyAcc-mean()-X 0.24833 0.27061 0.27659 0.27501 0.274328
## tBodyAcc-mean()-Y -0.02702 -0.01504 -0.01492 -0.01579 -0.005877
## 14.sitting 15.sitting 16.sitting 17.sitting 18.sitting
## tBodyAcc-mean()-X 0.279991 0.27290 0.28077 0.27736 0.27727
## tBodyAcc-mean()-Y -0.008706 -0.01172 -0.01025 -0.01416 -0.01287
## 19.sitting 20.sitting 21.sitting 22.sitting 23.sitting
## tBodyAcc-mean()-X 0.27383 0.27805 0.2775 0.27358 0.27335
## tBodyAcc-mean()-Y -0.01674 -0.01472 -0.0144 -0.01235 -0.01339
## 24.sitting 25.sitting 26.sitting 27.sitting 28.sitting
## tBodyAcc-mean()-X 0.27348 0.27854 0.258244 0.27394 0.27698
## tBodyAcc-mean()-Y -0.01313 -0.01477 -0.007134 -0.01553 -0.01854
## 29.sitting 30.sitting 1.standing 2.standing 3.standing
## tBodyAcc-mean()-X 0.27718 0.268336 0.27892 0.27791 0.28005
## tBodyAcc-mean()-Y -0.01663 -0.008047 -0.01614 -0.01842 -0.01434
## 4.standing 5.standing 6.standing 7.standing 8.standing
## tBodyAcc-mean()-X 0.280500 0.282544 0.28035 0.28272 0.27962
## tBodyAcc-mean()-Y -0.009489 -0.007004 -0.01812 -0.01457 -0.01481
## 9.standing 10.standing 11.standing 12.standing
## tBodyAcc-mean()-X 0.28231 0.27665 0.2777 0.2774
## tBodyAcc-mean()-Y -0.02005 -0.01554 -0.0172 -0.0169
## 13.standing 14.standing 15.standing 16.standing
## tBodyAcc-mean()-X 0.27776 0.28055 0.27892 0.2835
## tBodyAcc-mean()-Y -0.01679 -0.01521 -0.01835 -0.0166
## 17.standing 18.standing 19.standing 20.standing
## tBodyAcc-mean()-X 0.27794 0.27846 0.27817 0.27808
## tBodyAcc-mean()-Y -0.01741 -0.01664 -0.01542 -0.01807
## 21.standing 22.standing 23.standing 24.standing
## tBodyAcc-mean()-X 0.27695 0.27905 0.27790 0.28035
## tBodyAcc-mean()-Y -0.01671 -0.01586 -0.01775 -0.01448
## 25.standing 26.standing 27.standing 28.standing
## tBodyAcc-mean()-X 0.27801 0.28113 0.27957 0.27780
## tBodyAcc-mean()-Y -0.01636 -0.01666 -0.01659 -0.01726
## 29.standing 30.standing 1.laying 2.laying 3.laying
## tBodyAcc-mean()-X 0.27797 0.27711 0.22160 0.28137 0.27552
## tBodyAcc-mean()-Y -0.01726 -0.01702 -0.04051 -0.01816 -0.01896
## 4.laying 5.laying 6.laying 7.laying 8.laying 9.laying
## tBodyAcc-mean()-X 0.2636 0.2783 0.24866 0.25018 0.26125 0.25920
## tBodyAcc-mean()-Y -0.0150 -0.0183 -0.01025 -0.02044 -0.02123 -0.02053
## 10.laying 11.laying 12.laying 13.laying 14.laying
## tBodyAcc-mean()-X 0.28023 0.28059 0.26011 0.27672 0.23328
## tBodyAcc-mean()-Y -0.02429 -0.01766 -0.01752 -0.02044 -0.01134
## 15.laying 16.laying 17.laying 18.laying 19.laying
## tBodyAcc-mean()-X 0.28948 0.27423 0.26978 0.27469 0.27265
## tBodyAcc-mean()-Y -0.01663 -0.01661 -0.01685 -0.01739 -0.01714
## 20.laying 21.laying 22.laying 23.laying 24.laying
## tBodyAcc-mean()-X 0.23951 0.27133 0.27996 0.27404 0.27285
## tBodyAcc-mean()-Y -0.01444 -0.01842 -0.01426 -0.02166 -0.01736
## 25.laying 26.laying 27.laying 28.laying 29.laying
## tBodyAcc-mean()-X 0.25079 0.27165 0.27410 0.27591 0.2873
## tBodyAcc-mean()-Y -0.01889 -0.01919 -0.01799 -0.01675 -0.0172
## 30.laying
## tBodyAcc-mean()-X 0.28103
## tBodyAcc-mean()-Y -0.01945
</code></pre>
</body>
</html>