Skip to content

Commit 0a0352b

Browse files
twitwitwitwi
committed
[DOI: 10.5281/zenodo.278222] Rebuilt HTML files for release 2017.02
jekyll version: jekyll 3.2.1
1 parent e979465 commit 0a0352b

File tree

21 files changed

+11745
-0
lines changed

21 files changed

+11745
-0
lines changed

‎01-numpy/index.html

Lines changed: 1362 additions & 0 deletions
Large diffs are not rendered by default.

‎02-loop/index.html

Lines changed: 610 additions & 0 deletions
Large diffs are not rendered by default.

‎03-lists/index.html

Lines changed: 742 additions & 0 deletions
Large diffs are not rendered by default.

‎04-files/index.html

Lines changed: 390 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,390 @@
1+
<!doctype html>
2+
<html lang="en">
3+
<head>
4+
<meta charset="utf-8">
5+
<meta http-equiv="X-UA-Compatible" content="IE=edge">
6+
<meta http-equiv="last-modified" content="2017-02-08 23:51:37 +0100">
7+
<meta name="viewport" content="width=device-width, initial-scale=1">
8+
<!-- meta "search-domain" used for google site search function google_search() -->
9+
<meta name="search-domain" value="/swc-releases/2017.02/python-novice-inflammation">
10+
<link rel="stylesheet" type="text/css" href="../assets/css/bootstrap.css" />
11+
<link rel="stylesheet" type="text/css" href="../assets/css/bootstrap-theme.css" />
12+
<link rel="stylesheet" type="text/css" href="../assets/css/lesson.css" />
13+
14+
<link rel="shortcut icon" type="image/x-icon" href="/favicon-swc.ico" />
15+
16+
17+
<!-- HTML5 shim and Respond.js for IE8 support of HTML5 elements and media queries -->
18+
<!-- WARNING: Respond.js doesn't work if you view the page via file:// -->
19+
<!--[if lt IE 9]>
20+
<script src="https://oss.maxcdn.com/html5shiv/3.7.2/html5shiv.min.js"></script>
21+
<script src="https://oss.maxcdn.com/respond/1.4.2/respond.min.js"></script>
22+
<![endif]-->
23+
<title>Programming with Python: Analyzing Data from Multiple Files</title>
24+
</head>
25+
<body>
26+
<div class="container">
27+
<nav class="navbar navbar-default">
28+
<div class="container-fluid">
29+
<div class="navbar-header">
30+
<button type="button" class="navbar-toggle collapsed" data-toggle="collapse" data-target="#bs-example-navbar-collapse-1" aria-expanded="false">
31+
<span class="sr-only">Toggle navigation</span>
32+
<span class="icon-bar"></span>
33+
<span class="icon-bar"></span>
34+
<span class="icon-bar"></span>
35+
</button>
36+
37+
38+
39+
<a href="https://software-carpentry.org" class="pull-left">
40+
<img class="navbar-logo" src="../assets/img/swc-icon-blue.svg" alt="Software Carpentry logo" />
41+
</a>
42+
43+
44+
45+
<a class="navbar-brand" href="../">Home</a>
46+
47+
</div>
48+
<div class="collapse navbar-collapse" id="bs-example-navbar-collapse-1">
49+
<ul class="nav navbar-nav">
50+
51+
52+
<li><a href="../conduct/">Code of Conduct</a></li>
53+
54+
55+
56+
<li><a href="../setup/">Setup</a></li>
57+
<li><a href="../reference/">Reference</a></li>
58+
<li class="dropdown">
59+
<a href="../" class="dropdown-toggle" data-toggle="dropdown" role="button" aria-haspopup="true" aria-expanded="false">Episodes <span class="caret"></span></a>
60+
<ul class="dropdown-menu">
61+
62+
<li><a href="../01-numpy/">Analyzing Patient Data</a></li>
63+
64+
<li><a href="../02-loop/">Repeating Actions with Loops</a></li>
65+
66+
<li><a href="../03-lists/">Storing Multiple Values in Lists</a></li>
67+
68+
<li><a href="../04-files/">Analyzing Data from Multiple Files</a></li>
69+
70+
<li><a href="../05-cond/">Making Choices</a></li>
71+
72+
<li><a href="../06-func/">Creating Functions</a></li>
73+
74+
<li><a href="../07-errors/">Errors and Exceptions</a></li>
75+
76+
<li><a href="../08-defensive/">Defensive Programming</a></li>
77+
78+
<li><a href="../09-debugging/">Debugging</a></li>
79+
80+
<li><a href="../10-cmdline/">Command-Line Programs</a></li>
81+
82+
</ul>
83+
</li>
84+
85+
86+
87+
88+
<li class="dropdown">
89+
<a href="../" class="dropdown-toggle" data-toggle="dropdown" role="button" aria-haspopup="true" aria-expanded="false">Extras <span class="caret"></span></a>
90+
<ul class="dropdown-menu">
91+
92+
<li><a href="../about/">About</a></li>
93+
94+
<li><a href="../discuss/">Discussion</a></li>
95+
96+
<li><a href="../figures/">Figures</a></li>
97+
98+
<li><a href="../guide/">Instructor Notes</a></li>
99+
100+
</ul>
101+
</li>
102+
103+
104+
105+
<li><a href="../license/">License</a></li>
106+
</ul>
107+
<form class="navbar-form navbar-right" role="search" id="search" onsubmit="google_search(); return false;">
108+
<div class="form-group">
109+
<input type="text" id="google-search" placeholder="Search..." aria-label="Google site search">
110+
</div>
111+
</form>
112+
</div>
113+
</div>
114+
</nav>
115+
116+
117+
118+
119+
120+
<div class="row">
121+
<div class="col-md-1">
122+
<h3>
123+
124+
<a href="../03-lists/"><span class="glyphicon glyphicon-menu-left" aria-hidden="true"></span><span class="sr-only">previous episode</span></a>
125+
126+
</h3>
127+
</div>
128+
<div class="col-md-10">
129+
130+
<h3 class="maintitle"><a href="../">Programming with Python</a></h3>
131+
<h1 class="maintitle">Analyzing Data from Multiple Files</h1>
132+
133+
</div>
134+
<div class="col-md-1">
135+
<h3>
136+
137+
<a href="../05-cond/"><span class="glyphicon glyphicon-menu-right" aria-hidden="true"></span><span class="sr-only">next episode</span></a>
138+
139+
</h3>
140+
</div>
141+
</div>
142+
143+
144+
<blockquote class="objectives">
145+
<h2>Overview</h2>
146+
147+
<div class="row">
148+
<div class="col-md-3">
149+
<strong>Teaching:</strong> 20 min
150+
<br/>
151+
<strong>Exercises:</strong> 0 min
152+
</div>
153+
<div class="col-md-9">
154+
<strong>Questions</strong>
155+
<ul>
156+
157+
<li><p>How can I do the same operations on many different files?</p>
158+
</li>
159+
160+
</ul>
161+
</div>
162+
</div>
163+
164+
<div class="row">
165+
<div class="col-md-3">
166+
</div>
167+
<div class="col-md-9">
168+
<strong>Objectives</strong>
169+
<ul>
170+
171+
<li><p>Use a library function to get a list of filenames that match a simple wildcard pattern.</p>
172+
</li>
173+
174+
<li><p>Write a for loop to process multiple files.</p>
175+
</li>
176+
177+
</ul>
178+
</div>
179+
</div>
180+
181+
</blockquote>
182+
183+
<p>We now have almost everything we need to process all our data files.
184+
The only thing that’s missing is a library with a rather unpleasant name:</p>
185+
186+
<div class="python highlighter-rouge"><pre class="highlight"><code>import glob
187+
</code></pre>
188+
</div>
189+
190+
<p>The <code class="highlighter-rouge">glob</code> library contains a function, also called <code class="highlighter-rouge">glob</code>,
191+
that finds files and directories whose names match a pattern.
192+
We provide those patterns as strings:
193+
the character <code class="highlighter-rouge">*</code> matches zero or more characters,
194+
while <code class="highlighter-rouge">?</code> matches any one character.
195+
We can use this to get the names of all the CSV files in the current directory:</p>
196+
197+
<div class="python highlighter-rouge"><pre class="highlight"><code>print(glob.glob('data/inflammation*.csv'))
198+
</code></pre>
199+
</div>
200+
201+
<div class="output highlighter-rouge"><pre class="highlight"><code>['data/inflammation-05.csv', 'data/inflammation-11.csv', 'data/inflammation-12.csv', 'data/inflammation-08.csv', 'data/inflammation-03.csv', 'data/inflammation-06.csv', 'data/inflammation-09.csv', 'data/inflammation-07.csv', 'data/inflammation-10.csv', 'data/inflammation-02.csv', 'data/inflammation-04.csv', 'data/inflammation-01.csv']
202+
</code></pre>
203+
</div>
204+
205+
<p>As these examples show,
206+
<code class="highlighter-rouge">glob.glob</code>’s result is a list of file and directory paths in arbitrary order.
207+
This means we can loop over it
208+
to do something with each filename in turn.
209+
In our case,
210+
the “something” we want to do is generate a set of plots for each file in our inflammation dataset.
211+
If we want to start by analyzing just the first three files in alphabetical order, we can use the <code class="highlighter-rouge">sorted</code> built-in function to generate a new sorted list from the <code class="highlighter-rouge">glob.glob</code> output:</p>
212+
213+
<div class="python highlighter-rouge"><pre class="highlight"><code>import numpy
214+
import matplotlib.pyplot
215+
216+
filenames = sorted(glob.glob('data/inflammation*.csv'))
217+
filenames = filenames[0:3]
218+
for f in filenames:
219+
print(f)
220+
221+
data = numpy.loadtxt(fname=f, delimiter=',')
222+
223+
fig = matplotlib.pyplot.figure(figsize=(10.0, 3.0))
224+
225+
axes1 = fig.add_subplot(1, 3, 1)
226+
axes2 = fig.add_subplot(1, 3, 2)
227+
axes3 = fig.add_subplot(1, 3, 3)
228+
229+
axes1.set_ylabel('average')
230+
axes1.plot(numpy.mean(data, axis=0))
231+
232+
axes2.set_ylabel('max')
233+
axes2.plot(numpy.max(data, axis=0))
234+
235+
axes3.set_ylabel('min')
236+
axes3.plot(numpy.min(data, axis=0))
237+
238+
fig.tight_layout()
239+
matplotlib.pyplot.show()
240+
</code></pre>
241+
</div>
242+
243+
<div class="output highlighter-rouge"><pre class="highlight"><code>inflammation-01.csv
244+
</code></pre>
245+
</div>
246+
247+
<p><img src="../fig/03-loop_49_1.png" alt="Analysis of inflammation-01.csv" /></p>
248+
249+
<div class="output highlighter-rouge"><pre class="highlight"><code>inflammation-02.csv
250+
</code></pre>
251+
</div>
252+
253+
<p><img src="../fig/03-loop_49_3.png" alt="Analysis of inflammation-02.csv" /></p>
254+
255+
<div class="output highlighter-rouge"><pre class="highlight"><code>inflammation-03.csv
256+
</code></pre>
257+
</div>
258+
259+
<p><img src="../fig/03-loop_49_5.png" alt="Analysis of inflammation-03.csv" /></p>
260+
261+
<p>Sure enough,
262+
the maxima of the first two data sets show exactly the same ramp as the first,
263+
and their minima show the same staircase structure;
264+
a different situation has been revealed in the third dataset,
265+
where the maxima are a bit less regular, but the minima are consistently zero.</p>
266+
267+
<blockquote class="challenge">
268+
<h2 id="plotting-differences">Plotting Differences</h2>
269+
270+
<p>Plot the difference between the average of the first dataset
271+
and the average of the second dataset,
272+
i.e., the difference between the leftmost plot of the first two figures.</p>
273+
274+
<blockquote class="solution">
275+
<h2 id="solution">Solution</h2>
276+
<div class="python highlighter-rouge"><pre class="highlight"><code>import glob
277+
import numpy
278+
import matplotlib.pyplot
279+
280+
filenames = glob.glob('data/inflammation*.csv')
281+
282+
data0 = numpy.loadtxt(fname=filenames[0], delimiter=',')
283+
data1 = numpy.loadtxt(fname=filenames[1], delimiter=',')
284+
285+
fig = matplotlib.pyplot.figure(figsize=(10.0, 3.0))
286+
287+
matplotlib.pyplot.ylabel('Difference in average')
288+
matplotlib.pyplot.plot(data0.mean(axis=0) - data1.mean(axis=0))
289+
290+
fig.tight_layout()
291+
matplotlib.pyplot.show()
292+
</code></pre>
293+
</div>
294+
</blockquote>
295+
</blockquote>
296+
297+
<blockquote class="challenge">
298+
<h2 id="generate-composite-statistics">Generate Composite Statistics</h2>
299+
300+
<p>Use each of the files once to generate a dataset containing values averaged over all patients:</p>
301+
302+
<div class="python highlighter-rouge"><pre class="highlight"><code>filenames = glob.glob('data/inflammation*.csv')
303+
composite_data = numpy.zeros((60,40))
304+
for f in filenames:
305+
# sum each new file's data into as it's read
306+
# and then divide the composite_data by number of samples
307+
composite_data /= len(filenames)
308+
</code></pre>
309+
</div>
310+
311+
<p>Then use pyplot to generate average, max, and min for all patients.</p>
312+
313+
</blockquote>
314+
315+
<blockquote class="keypoints">
316+
<h2>Key Points</h2>
317+
<ul>
318+
319+
<li><p>Use <code class="highlighter-rouge">glob.glob(pattern)</code> to create a list of files whose names match a pattern.</p>
320+
</li>
321+
322+
<li><p>Use <code class="highlighter-rouge">*</code> in a pattern to match zero or more characters, and <code class="highlighter-rouge">?</code> to match any single character.</p>
323+
</li>
324+
325+
</ul>
326+
</blockquote>
327+
328+
329+
330+
331+
332+
<div class="row">
333+
<div class="col-md-1">
334+
<h3>
335+
336+
<a href="../03-lists/"><span class="glyphicon glyphicon-menu-left" aria-hidden="true"></span><span class="sr-only">previous episode</span></a>
337+
338+
</h3>
339+
</div>
340+
<div class="col-md-10">
341+
342+
</div>
343+
<div class="col-md-1">
344+
<h3>
345+
346+
<a href="../05-cond/"><span class="glyphicon glyphicon-menu-right" aria-hidden="true"></span><span class="sr-only">next episode</span></a>
347+
348+
</h3>
349+
</div>
350+
</div>
351+
352+
353+
354+
<footer>
355+
<div class="row">
356+
<div class="col-md-6" align="left">
357+
<h4>
358+
Copyright &copy; 2016
359+
<a href="https://software-carpentry.org">Software Carpentry Foundation</a>
360+
361+
</h4>
362+
</div>
363+
<div class="col-md-6" align="right">
364+
<h4>
365+
<a href="/">Source</a>
366+
/
367+
<a href="/blob/gh-pages/CONTRIBUTING.md">Contributing</a>
368+
/
369+
<a href="mailto:[email protected]">Contact</a>
370+
</h4>
371+
</div>
372+
</div>
373+
</footer>
374+
375+
376+
</div>
377+
<script src="../assets/js/jquery.min.js"></script>
378+
<script src="../assets/js/bootstrap.min.js"></script>
379+
<script src="../assets/js/lesson.js"></script>
380+
<script>
381+
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
382+
(i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new Date();a=s.createElement(o),
383+
m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m)
384+
})(window,document,'script','https://www.google-analytics.com/analytics.js','ga');
385+
ga('create', 'UA-37305346-2', 'auto');
386+
ga('send', 'pageview');
387+
</script>
388+
389+
</body>
390+
</html>

0 commit comments

Comments
 (0)