New blog post on Kaggle competition

This commit is contained in:
Bradlee Speice
2016-03-05 11:58:46 -05:00
parent e682eb2a35
commit f60cb5f8ef
31 changed files with 3765 additions and 210 deletions

View File

@ -28,6 +28,17 @@
<script src="https://oss.maxcdn.com/respond/1.4.2/respond.min.js"></script>
<![endif]-->
<!-- Google Analytics -->
<script>
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
(i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new Date();a=s.createElement(o),
m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m)
})(window,document,'script','//www.google-analytics.com/analytics.js','ga');
ga('create', 'UA-74711362-1', 'auto');
ga('send', 'pageview');
</script>
<!-- /Google Analytics -->
</head>
@ -81,7 +92,7 @@
<div class="prompt input_prompt">In&nbsp;[1]:</div>
<div class="inner_cell">
<div class="input_area">
<div class=" highlight hl-ipython3"><pre><span class="kn">from</span> <span class="nn">bokeh.plotting</span> <span class="k">import</span> <span class="n">figure</span><span class="p">,</span> <span class="n">output_notebook</span><span class="p">,</span> <span class="n">show</span>
<div class=" highlight hl-ipython3"><pre><span></span><span class="kn">from</span> <span class="nn">bokeh.plotting</span> <span class="k">import</span> <span class="n">figure</span><span class="p">,</span> <span class="n">output_notebook</span><span class="p">,</span> <span class="n">show</span>
<span class="kn">from</span> <span class="nn">bokeh.palettes</span> <span class="k">import</span> <span class="n">PuBuGn9</span> <span class="k">as</span> <span class="n">Palette</span>
<span class="kn">import</span> <span class="nn">pandas</span> <span class="k">as</span> <span class="nn">pd</span>
<span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
@ -341,7 +352,7 @@
<div class="prompt input_prompt">In&nbsp;[2]:</div>
<div class="inner_cell">
<div class="input_area">
<div class=" highlight hl-ipython3"><pre><span class="n">city_forecasts</span> <span class="o">=</span> <span class="n">pickle</span><span class="o">.</span><span class="n">load</span><span class="p">(</span><span class="nb">open</span><span class="p">(</span><span class="s1">&#39;city_forecasts.p&#39;</span><span class="p">,</span> <span class="s1">&#39;rb&#39;</span><span class="p">))</span>
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">city_forecasts</span> <span class="o">=</span> <span class="n">pickle</span><span class="o">.</span><span class="n">load</span><span class="p">(</span><span class="nb">open</span><span class="p">(</span><span class="s1">&#39;city_forecasts.p&#39;</span><span class="p">,</span> <span class="s1">&#39;rb&#39;</span><span class="p">))</span>
<span class="n">forecast_df</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">DataFrame</span><span class="o">.</span><span class="n">from_dict</span><span class="p">(</span><span class="n">city_forecasts</span><span class="p">)</span>
</pre></div>
@ -355,7 +366,7 @@
<div class="prompt input_prompt">In&nbsp;[3]:</div>
<div class="inner_cell">
<div class="input_area">
<div class=" highlight hl-ipython3"><pre><span class="n">cary_forecast</span> <span class="o">=</span> <span class="n">forecast_df</span><span class="p">[</span><span class="s1">&#39;cary&#39;</span><span class="p">]</span>
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">cary_forecast</span> <span class="o">=</span> <span class="n">forecast_df</span><span class="p">[</span><span class="s1">&#39;cary&#39;</span><span class="p">]</span>
<span class="n">years</span> <span class="o">=</span> <span class="nb">range</span><span class="p">(</span><span class="mi">1990</span><span class="p">,</span> <span class="mi">2016</span><span class="p">)</span>
<span class="n">months</span> <span class="o">=</span> <span class="nb">range</span><span class="p">(</span><span class="mi">7</span><span class="p">,</span> <span class="mi">12</span><span class="p">)</span>
<span class="n">months_str</span> <span class="o">=</span> <span class="p">[</span><span class="s1">&#39;July&#39;</span><span class="p">,</span> <span class="s1">&#39;August&#39;</span><span class="p">,</span> <span class="s1">&#39;September&#39;</span><span class="p">,</span> <span class="s1">&#39;October&#39;</span><span class="p">,</span> <span class="s1">&#39;November&#39;</span><span class="p">]</span>
@ -443,7 +454,7 @@
<div class="prompt input_prompt">In&nbsp;[4]:</div>
<div class="inner_cell">
<div class="input_area">
<div class=" highlight hl-ipython3"><pre><span class="k">def</span> <span class="nf">monthly_cloudy_days</span><span class="p">(</span><span class="n">year</span><span class="p">,</span> <span class="n">month</span><span class="p">):</span>
<div class=" highlight hl-ipython3"><pre><span></span><span class="k">def</span> <span class="nf">monthly_cloudy_days</span><span class="p">(</span><span class="n">year</span><span class="p">,</span> <span class="n">month</span><span class="p">):</span>
<span class="n">dates</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">DatetimeIndex</span><span class="p">(</span><span class="n">start</span><span class="o">=</span><span class="n">datetime</span><span class="p">(</span><span class="n">year</span><span class="p">,</span> <span class="n">month</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">12</span><span class="p">),</span>
<span class="n">end</span><span class="o">=</span><span class="n">datetime</span><span class="p">(</span><span class="n">year</span><span class="p">,</span> <span class="n">month</span> <span class="o">+</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">12</span><span class="p">),</span>
<span class="n">freq</span><span class="o">=</span><span class="s1">&#39;D&#39;</span><span class="p">,</span> <span class="n">closed</span><span class="o">=</span><span class="s1">&#39;left&#39;</span><span class="p">)</span>
@ -559,7 +570,7 @@
<div class="prompt input_prompt">In&nbsp;[5]:</div>
<div class="inner_cell">
<div class="input_area">
<div class=" highlight hl-ipython3"><pre><span class="k">def</span> <span class="nf">safe_precip</span><span class="p">(</span><span class="n">frame</span><span class="p">):</span>
<div class=" highlight hl-ipython3"><pre><span></span><span class="k">def</span> <span class="nf">safe_precip</span><span class="p">(</span><span class="n">frame</span><span class="p">):</span>
<span class="k">if</span> <span class="n">frame</span> <span class="ow">and</span> <span class="s1">&#39;precipProbability&#39;</span> <span class="ow">in</span> <span class="n">frame</span><span class="p">:</span>
<span class="k">return</span> <span class="n">frame</span><span class="p">[</span><span class="s1">&#39;precipProbability&#39;</span><span class="p">]</span>
<span class="k">else</span><span class="p">:</span>
@ -640,7 +651,7 @@
<div class="prompt input_prompt">In&nbsp;[6]:</div>
<div class="inner_cell">
<div class="input_area">
<div class=" highlight hl-ipython3"><pre><span class="k">def</span> <span class="nf">monthly_rainy_days</span><span class="p">(</span><span class="n">year</span><span class="p">,</span> <span class="n">month</span><span class="p">):</span>
<div class=" highlight hl-ipython3"><pre><span></span><span class="k">def</span> <span class="nf">monthly_rainy_days</span><span class="p">(</span><span class="n">year</span><span class="p">,</span> <span class="n">month</span><span class="p">):</span>
<span class="n">dates</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">DatetimeIndex</span><span class="p">(</span><span class="n">start</span><span class="o">=</span><span class="n">datetime</span><span class="p">(</span><span class="n">year</span><span class="p">,</span> <span class="n">month</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">12</span><span class="p">),</span>
<span class="n">end</span><span class="o">=</span><span class="n">datetime</span><span class="p">(</span><span class="n">year</span><span class="p">,</span> <span class="n">month</span> <span class="o">+</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">12</span><span class="p">),</span>
<span class="n">freq</span><span class="o">=</span><span class="s1">&#39;D&#39;</span><span class="p">,</span> <span class="n">closed</span><span class="o">=</span><span class="s1">&#39;left&#39;</span><span class="p">)</span>
@ -759,7 +770,7 @@
<div class="inner_cell">
<div class="text_cell_render border-box-sizing rendered_html">
<h1 id="Generating-the-Forecast-file">Generating the Forecast file<a class="anchor-link" href="#Generating-the-Forecast-file">&#182;</a></h1><p>The following code was generates the file that was used throughout the blog post. Please note that I'm retrieving data for other cities to use in a future blog post, only Cary data was used for this post.</p>
<div class="highlight"><pre><span class="kn">import</span> <span class="nn">pandas</span> <span class="kn">as</span> <span class="nn">pd</span>
<div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">pandas</span> <span class="kn">as</span> <span class="nn">pd</span>
<span class="kn">from</span> <span class="nn">functools</span> <span class="kn">import</span> <span class="nb">reduce</span>
<span class="kn">import</span> <span class="nn">requests</span>
<span class="kn">from</span> <span class="nn">datetime</span> <span class="kn">import</span> <span class="n">datetime</span>
@ -834,6 +845,20 @@ MathJax.Hub.Config({tex2jax: {inlineMath: [['$','$'], ['\(','\)']]}});
<script async src='https://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS_CHTML'></script>
<div class="comments">
<div id="disqus_thread"></div>
<script type="text/javascript">
var disqus_shortname = 'bradleespeice';
var disqus_identifier = 'complaining-about-the-weather.html';
var disqus_url = 'https://bspeice.github.io/complaining-about-the-weather.html';
(function() {
var dsq = document.createElement('script'); dsq.type = 'text/javascript'; dsq.async = true;
dsq.src = '//' + disqus_shortname + '.disqus.com/embed.js';
(document.getElementsByTagName('head')[0] || document.getElementsByTagName('body')[0]).appendChild(dsq);
})();
</script>
<noscript>Please enable JavaScript to view the comments.</noscript>
</div>
</div>
<!-- /Content -->