<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0" xmlns:cc="http://cyber.law.harvard.edu/rss/creativeCommonsRssModule.html">
    <channel>
        <title><![CDATA[Stories by Peter Chang on Medium]]></title>
        <description><![CDATA[Stories by Peter Chang on Medium]]></description>
        <link>https://medium.com/@ThePeterChang?source=rss-281837ecce79------2</link>
        <image>
            <url>https://cdn-images-1.medium.com/fit/c/150/150/1*0tEVOa-qUos2qV8oHwCMRA.jpeg</url>
            <title>Stories by Peter Chang on Medium</title>
            <link>https://medium.com/@ThePeterChang?source=rss-281837ecce79------2</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Tue, 17 Nov 2026 17:48:06 GMT</lastBuildDate>
        <atom:link href="https://medium.com/@ThePeterChang/feed" rel="self" type="application/rss+xml"/>
        <webMaster><![CDATA[yourfriends@medium.com]]></webMaster>
        <atom:link href="http://medium.superfeedr.com/" rel="hub"/>
        <item>
            <title><![CDATA[Plotting Covid Stats]]></title>
            <link>https://medium.com/@ThePeterChang/plotting-covid-stats-ed1ec6c3fa06?source=rss-281837ecce79------2</link>
            <guid isPermaLink="false">https://medium.com/p/ed1ec6c3fa06</guid>
            <category><![CDATA[covid19]]></category>
            <category><![CDATA[bay-area]]></category>
            <category><![CDATA[california]]></category>
            <dc:creator><![CDATA[Peter Chang]]></dc:creator>
            <pubDate>Tue, 31 Mar 2020 04:49:33 GMT</pubDate>
            <atom:updated>2020-03-31T04:49:33.760Z</atom:updated>
            <content:encoded><![CDATA[<p>I wanted to create time-series plots of covid statistics to get a sense of how this virus was unfolding throughout the world. There are a number of people compiling data. The one that I found to be the most useful and accessible was <a href="https://coronadatascraper.com/#home">coronadatascraper.com</a>.</p><p>I created a <a href="https://colab.research.google.com/drive/1sfLaMzE-zoAHNF9dVCRJIJsVRNp7Qy8A">Jupyter Notebook and published it using Google Drive</a>. It’s shared so that you can copy it and manipulate it to your interest.</p><p>Here’s a brief walkthrough of some of the plots I’ve been looking at.</p><p><em>Note that most of the graphs below are log-scaled.</em></p><h3>Country-Level Graphs</h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/700/1*1MSpDzFQE5PdFJLxJ4uAqw.png" /></figure><p>If you’ve been following the news, there are some unsurprising aspects to this plot. Cases in China and South Korea have flattened. Everywhere else in the world, cases of covid continue to grow. Notably Italy and the US surpassed China around the 26th of March (with Spain being imminent).</p><p>In general, I’ve been wary of reading too much into case count. For the US, in particular, administration of tests have been subject to availability and conditional on whether it would impact the outcome of a patient. Also, for California in particular, many results are pending.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/700/1*nql480IBrKiv3k2Bo0KsYw.png" /></figure><p>Deaths are a more sobering statistic and is not reliant on a diagnostic. South Korea has notably reduced the rate of deaths considerably compared to the rest of the countries graphed here. Sadly, the number of deaths in Italy have been very high with Spain on a similar trajectory. France and the US are faring similarly at this point.</p><p>However, deaths are a lagging indicator. According to the <a href="https://wwwnc.cdc.gov/eid/article/26/6/20-0320_article">CDC</a>, “a median of 13 days passed from pneumonia confirmation to death.”</p><h3>State-Level Graph</h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/700/1*-JALzS7ruY_1QWL8x1PY9Q.png" /></figure><p>I took a look at a handful of states in the US. Washington, California, Massachusetts and Louisiana are within the same magnitude of cases and appear to be on similar trajectories for now.</p><p>New York is obviously the hottest spot in the US.</p><h3>Bay Area Graph</h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/700/1*jdl5lSPRIEz708WC7fslsg.png" /></figure><p>Finally, I wanted to take a closer look at how Bay Area counties were faring. While the growth rate looks similar, Santa Clara County has consistently had the highest number of cases. For some time, San Mateo County has the second most cases but San Francisco County surpassed it around the 24th of March.</p><p>As a reminder, this graph is log-scaled. If drawn linearly, bay area case counts look like this:</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/700/1*gskgztSAMr33-Pv_thSIZw.png" /></figure><h3>Final Notes</h3><p>As I mentioned earlier, it’s hard to have a lot of confidence in case counts, particularly in the US and California. However, as availability and processing improve, I would expect to have more confidence in the data.</p><p>Also, given that varies countries, states and counties have lockdown-ed fairly recently, I suspect the data will have more meaning in a couple more weeks.</p><p>If you’d like to plot your own data, feel free to copy <a href="https://colab.research.google.com/drive/1sfLaMzE-zoAHNF9dVCRJIJsVRNp7Qy8A">my notebook</a> or copy the <a href="https://colab.research.google.com/drive/1w-YaCRkhw2Zxwhz4BCiazIdKyRvG3JFZ#scrollTo=xbyVJ-ITT4Z5">one</a> from <a href="https://coronadatascraper.com/#home">Corona Data Scraper</a> which mine is heavily based on. The raw data contains a number of stats which allow for other kinds of exploration.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=ed1ec6c3fa06" width="1" height="1" alt="">]]></content:encoded>
        </item>
    </channel>
</rss>