daviddoji/numpy-100
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Add confidence intervals exercise

Browse Source
This commit is contained in:
Jessica B. Hamrick 2016-07-14 14:54:03 -05:00
parent 03ccfbdd33
commit 1be7effea7
2 changed files with 27 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
README.html
View File

@ -4,12 +4,12 @@
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
<meta name="generator" content="Docutils 0.12: http://docutils.sourceforge.net/" />
<title>100 numpy exercises</title>
<title>100 numpy exercises</title>
<link rel="stylesheet" href="numpy.css" type="text/css" />
</head>
<body>
<div class="document" id="numpy-exercises">
<h1 class="title">100 numpy exercises</h1>
<h1 class="title">100 numpy exercises</h1>
<h2 class="subtitle" id="a-joint-effort-of-the-numpy-community">A joint effort of the numpy community</h2>
<p>The goal is both to offer a quick reference for new and old users and to
@ -949,7 +949,20 @@ the rows which only contain integers and which sum to n. (★★★)</p>
<span class="keyword">print</span><span class="punctuation">(</span><span class="name">X</span><span class="punctuation">[</span><span class="name">M</span><span class="punctuation">])</span>
</pre>
</li>
<li><p class="first">Compute bootstrapped 95% confidence intervals for the mean of a 1D array X (i.e., resample the elements of an array with replacement N times, compute the mean of each sample, and then compute percentiles over the means).</p>
</li>
</ol>
<blockquote>
<pre class="code python literal-block">
<span class="comment single"># Author: Jessica B. Hamrick</span>
<span class="name">N</span> <span class="operator">=</span> <span class="literal number integer">1000</span> <span class="comment single"># number of bootstrap samples</span>
<span class="name">idx</span> <span class="operator">=</span> <span class="name">np</span><span class="operator">.</span><span class="name">random</span><span class="operator">.</span><span class="name">randint</span><span class="punctuation">(</span><span class="literal number integer">0</span><span class="punctuation">,</span> <span class="name">X</span><span class="operator">.</span><span class="name">size</span><span class="punctuation">,</span> <span class="punctuation">(</span><span class="name">N</span><span class="punctuation">,</span> <span class="name">X</span><span class="operator">.</span><span class="name">size</span><span class="punctuation">))</span>
<span class="name">means</span> <span class="operator">=</span> <span class="name">X</span><span class="punctuation">[</span><span class="name">idx</span><span class="punctuation">]</span><span class="operator">.</span><span class="name">mean</span><span class="punctuation">(</span><span class="name">axis</span><span class="operator">=</span><span class="literal number integer">1</span><span class="punctuation">)</span>
<span class="name">confint</span> <span class="operator">=</span> <span class="name">np</span><span class="operator">.</span><span class="name">percentile</span><span class="punctuation">(</span><span class="name">means</span><span class="punctuation">,</span> <span class="punctuation">[</span><span class="literal number float">2.5</span><span class="punctuation">,</span> <span class="literal number float">97.5</span><span class="punctuation">])</span>
<span class="keyword">print</span><span class="punctuation">(</span><span class="name">confint</span><span class="punctuation">)</span>
</pre>
</blockquote>
</div>
</body>
</html>

12
README.rst
View File

@ -1106,3 +1106,15 @@ Thanks to Michiaki Ariga, there is now a
M = np.logical_and.reduce(np.mod(X, 1) == 0, axis=-1)
M &= (X.sum(axis=-1) == n)
print(X[M])
#. Compute bootstrapped 95% confidence intervals for the mean of a 1D array X (i.e., resample the elements of an array with replacement N times, compute the mean of each sample, and then compute percentiles over the means).
.. code-block:: python
# Author: Jessica B. Hamrick
N = 1000 # number of bootstrap samples
idx = np.random.randint(0, X.size, (N, X.size))
means = X[idx].mean(axis=1)
confint = np.percentile(means, [2.5, 97.5])
print(confint)