j1-template 2022.2.2 → 2022.3.1

data/lib/starter_web/pages/public/jupyter/notebooks/textbooks/binder-launches.html

@@ -1,546 +0,0 @@
-  <div class="cell text_cell">
-    <button class="js-nbinteract-widget">
-      Loading widgets...
-    </button>
-  </div>
-
-
-
-<div class="cell border-box-sizing text_cell rendered"><div class="inner_cell">
-<div class="text_cell_render border-box-sizing rendered_html">
-<h1 id="Analysing-mybinder.org-launches">Analysing mybinder.org launches<a class="anchor-link" href="#Analysing-mybinder.org-launches">&#182;</a></h1><p>The first few cells download and massage the data. Later on we answer questions on which repositories are popular and such.</p>
-
-</div>
-</div>
-</div>
-
-  
-
-  <div class="
-      cell border-box-sizing code_cell rendered">
-    <div class="input">
-
-<div class="inner_cell">
-    <div class="input_area">
-<div class=" highlight hl-ipython3"><pre><span></span><span class="o">%</span><span class="k">matplotlib</span> inline
-
-<span class="kn">import</span> <span class="nn">matplotlib.pyplot</span> <span class="k">as</span> <span class="nn">plt</span>
-<span class="kn">import</span> <span class="nn">datetime</span>
-<span class="kn">import</span> <span class="nn">pandas</span> <span class="k">as</span> <span class="nn">pd</span>
-</pre></div>
-
-    </div>
-</div>
-</div>
-
-  </div>
-
-  
-
-  <div class="
-      cell border-box-sizing code_cell rendered">
-    <div class="input">
-
-<div class="inner_cell">
-    <div class="input_area">
-<div class=" highlight hl-ipython3"><pre><span></span><span class="n">index</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">read_json</span><span class="p">(</span><span class="s2">&quot;https://archive.analytics.mybinder.org/index.jsonl&quot;</span><span class="p">,</span>
-                     <span class="n">lines</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
-</pre></div>
-
-    </div>
-</div>
-</div>
-
-  </div>
-
-  
-
-  <div class="
-      cell border-box-sizing code_cell rendered">
-    <div class="input">
-
-<div class="inner_cell">
-    <div class="input_area">
-<div class=" highlight hl-ipython3"><pre><span></span><span class="c1"># get all days since start of 2019</span>
-<span class="n">now</span> <span class="o">=</span> <span class="n">datetime</span><span class="o">.</span><span class="n">datetime</span><span class="o">.</span><span class="n">now</span><span class="p">()</span>
-<span class="n">n</span> <span class="o">=</span> <span class="p">(</span><span class="n">now</span> <span class="o">-</span> <span class="n">datetime</span><span class="o">.</span><span class="n">datetime</span><span class="p">(</span><span class="mi">2019</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">))</span><span class="o">.</span><span class="n">days</span>
-
-<span class="c1"># small range for previewing</span>
-<span class="c1">#n = 30</span>
-
-<span class="n">frames</span> <span class="o">=</span> <span class="p">[]</span>
-<span class="k">for</span> <span class="n">idx</span><span class="p">,</span> <span class="n">day</span> <span class="ow">in</span> <span class="n">index</span><span class="o">.</span><span class="n">sort_index</span><span class="p">(</span><span class="n">ascending</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span><span class="o">.</span><span class="n">iterrows</span><span class="p">():</span>
-    <span class="n">df</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">read_json</span><span class="p">(</span><span class="s2">&quot;https://archive.analytics.mybinder.org/</span><span class="si">{}</span><span class="s2">&quot;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">day</span><span class="p">[</span><span class="s1">&#39;name&#39;</span><span class="p">]),</span>
-                      <span class="n">lines</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="p">)</span>
-    <span class="n">frames</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">df</span><span class="p">)</span>
-    <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">frames</span><span class="p">)</span> <span class="o">&gt;</span> <span class="n">n</span><span class="p">:</span>
-        <span class="k">break</span>
-        
-<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">&quot;Fetched data for </span><span class="si">{</span><span class="n">n</span><span class="si">}</span><span class="s2"> days.&quot;</span><span class="p">)</span>
-</pre></div>
-
-    </div>
-</div>
-</div>
-
-  </div>
-
-  
-
-  <div class="
-      cell border-box-sizing code_cell rendered">
-    <div class="input">
-
-<div class="inner_cell">
-    <div class="input_area">
-<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">concat</span><span class="p">(</span><span class="n">frames</span><span class="p">)</span>
-</pre></div>
-
-    </div>
-</div>
-</div>
-
-  </div>
-
-  
-
-  <div class="
-      cell border-box-sizing code_cell rendered">
-    <div class="input">
-
-<div class="inner_cell">
-    <div class="input_area">
-<div class=" highlight hl-ipython3"><pre><span></span><span class="c1"># make it easier to grab the ref</span>
-<span class="k">def</span> <span class="nf">get_repo</span><span class="p">(</span><span class="n">spec</span><span class="p">):</span>
-    <span class="n">s</span> <span class="o">=</span> <span class="n">spec</span><span class="o">.</span><span class="n">rsplit</span><span class="p">(</span><span class="s2">&quot;/&quot;</span><span class="p">,</span> <span class="mi">1</span><span class="p">)[</span><span class="mi">0</span><span class="p">]</span>
-    <span class="k">if</span> <span class="n">s</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s1">&#39;.git&#39;</span><span class="p">):</span>
-        <span class="n">s</span> <span class="o">=</span> <span class="n">s</span><span class="p">[:</span><span class="o">-</span><span class="mi">4</span><span class="p">]</span>
-    <span class="k">return</span> <span class="n">s</span>
-<span class="n">df</span><span class="p">[</span><span class="s1">&#39;repo&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">df</span><span class="p">[</span><span class="s1">&#39;spec&#39;</span><span class="p">]</span><span class="o">.</span><span class="n">apply</span><span class="p">(</span><span class="n">get_repo</span><span class="p">)</span> <span class="c1">#lambda s: s.rsplit(&quot;/&quot;, 1)[0].replace(&quot;.git&quot;, &quot;&quot;))</span>
-<span class="n">df</span><span class="p">[</span><span class="s1">&#39;org&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">df</span><span class="p">[</span><span class="s1">&#39;spec&#39;</span><span class="p">]</span><span class="o">.</span><span class="n">apply</span><span class="p">(</span><span class="k">lambda</span> <span class="n">s</span><span class="p">:</span> <span class="n">s</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s2">&quot;/&quot;</span><span class="p">,</span> <span class="mi">1</span><span class="p">)[</span><span class="mi">0</span><span class="p">])</span>
-<span class="n">df</span><span class="p">[</span><span class="s1">&#39;ref&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">df</span><span class="p">[</span><span class="s1">&#39;spec&#39;</span><span class="p">]</span><span class="o">.</span><span class="n">apply</span><span class="p">(</span><span class="k">lambda</span> <span class="n">s</span><span class="p">:</span> <span class="n">s</span><span class="o">.</span><span class="n">rsplit</span><span class="p">(</span><span class="s2">&quot;/&quot;</span><span class="p">,</span> <span class="mi">1</span><span class="p">)[</span><span class="mi">1</span><span class="p">])</span>
-</pre></div>
-
-    </div>
-</div>
-</div>
-
-  </div>
-
-  
-
-  <div class="
-      cell border-box-sizing code_cell rendered">
-    <div class="input">
-
-<div class="inner_cell">
-    <div class="input_area">
-<div class=" highlight hl-ipython3"><pre><span></span><span class="c1"># take a look at the data, does it look sensible?</span>
-<span class="n">df</span><span class="o">.</span><span class="n">sample</span><span class="p">(</span><span class="mi">10</span><span class="p">)</span>
-</pre></div>
-
-    </div>
-</div>
-</div>
-
-  </div>
-
-  
-
-  <div class="
-      cell border-box-sizing code_cell rendered">
-    <div class="input">
-
-<div class="inner_cell">
-    <div class="input_area">
-<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df</span> <span class="o">=</span> <span class="n">df</span><span class="o">.</span><span class="n">drop</span><span class="p">(</span><span class="n">columns</span><span class="o">=</span><span class="p">[</span><span class="s1">&#39;schema&#39;</span><span class="p">,</span> <span class="s1">&#39;version&#39;</span><span class="p">,</span> <span class="s1">&#39;spec&#39;</span><span class="p">,</span> <span class="s1">&#39;status&#39;</span><span class="p">])</span>
-</pre></div>
-
-    </div>
-</div>
-</div>
-
-  </div>
-
-  
-
-  <div class="
-      cell border-box-sizing code_cell rendered">
-    <div class="input">
-
-<div class="inner_cell">
-    <div class="input_area">
-<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df</span><span class="o">.</span><span class="n">head</span><span class="p">()</span>
-</pre></div>
-
-    </div>
-</div>
-</div>
-
-  </div>
-<div class="cell border-box-sizing text_cell rendered"><div class="inner_cell">
-<div class="text_cell_render border-box-sizing rendered_html">
-<h2 id="Monthly,-weekly,-daily-active-repos">Monthly, weekly, daily active repos<a class="anchor-link" href="#Monthly,-weekly,-daily-active-repos">&#182;</a></h2>
-</div>
-</div>
-</div>
-
-  
-
-  <div class="
-      cell border-box-sizing code_cell rendered">
-    <div class="input">
-
-<div class="inner_cell">
-    <div class="input_area">
-<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df_</span> <span class="o">=</span> <span class="n">df</span><span class="o">.</span><span class="n">set_index</span><span class="p">(</span><span class="s2">&quot;timestamp&quot;</span><span class="p">)</span>
-</pre></div>
-
-    </div>
-</div>
-</div>
-
-  </div>
-
-  
-
-  <div class="
-      cell border-box-sizing code_cell rendered">
-    <div class="input">
-
-<div class="inner_cell">
-    <div class="input_area">
-<div class=" highlight hl-ipython3"><pre><span></span><span class="k">def</span> <span class="nf">n_active_repos</span><span class="p">(</span><span class="n">period</span><span class="o">=</span><span class="mi">30</span><span class="p">):</span>
-    <span class="sd">&quot;&quot;&quot;Unique active repos over the period</span>
-<span class="sd">    </span>
-<span class="sd">    With period=30 this gives monthly active repos</span>
-<span class="sd">    With period=1 you get daily active repos</span>
-<span class="sd">    &quot;&quot;&quot;</span>
-    <span class="n">now</span> <span class="o">=</span> <span class="n">datetime</span><span class="o">.</span><span class="n">datetime</span><span class="o">.</span><span class="n">now</span><span class="p">()</span>
-    <span class="n">start</span> <span class="o">=</span> <span class="n">datetime</span><span class="o">.</span><span class="n">datetime</span><span class="p">(</span><span class="mi">2019</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
-    <span class="n">days_since_start</span> <span class="o">=</span> <span class="p">(</span><span class="n">now</span> <span class="o">-</span> <span class="n">start</span><span class="p">)</span><span class="o">.</span><span class="n">days</span>
-
-    <span class="n">data</span> <span class="o">=</span> <span class="p">[]</span>
-
-    <span class="k">for</span> <span class="n">n</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="n">days_since_start</span><span class="p">):</span>
-        <span class="n">s</span> <span class="o">=</span> <span class="n">start</span> <span class="o">+</span> <span class="n">datetime</span><span class="o">.</span><span class="n">timedelta</span><span class="p">(</span><span class="n">days</span><span class="o">=</span><span class="n">n</span><span class="p">)</span>
-        <span class="n">e</span> <span class="o">=</span> <span class="n">start</span> <span class="o">+</span> <span class="n">datetime</span><span class="o">.</span><span class="n">timedelta</span><span class="p">(</span><span class="n">days</span><span class="o">=</span><span class="n">n</span><span class="o">+</span><span class="n">period</span><span class="p">)</span>
-        <span class="k">if</span> <span class="n">e</span> <span class="o">&gt;</span> <span class="n">now</span><span class="p">:</span>
-            <span class="k">break</span>
-
-        <span class="c1"># our &quot;monthly&quot; data</span>
-        <span class="n">monthly</span> <span class="o">=</span> <span class="n">df_</span><span class="o">.</span><span class="n">loc</span><span class="p">[</span><span class="n">s</span><span class="o">.</span><span class="n">isoformat</span><span class="p">():</span><span class="n">e</span><span class="o">.</span><span class="n">isoformat</span><span class="p">()]</span>
-        <span class="n">data</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="nb">dict</span><span class="p">(</span><span class="n">timestamp</span><span class="o">=</span><span class="n">e</span><span class="p">,</span> <span class="n">repos</span><span class="o">=</span><span class="nb">len</span><span class="p">(</span><span class="nb">set</span><span class="p">(</span><span class="n">monthly</span><span class="o">.</span><span class="n">repo</span><span class="p">))))</span>
-        
-    <span class="k">return</span> <span class="n">pd</span><span class="o">.</span><span class="n">DataFrame</span><span class="o">.</span><span class="n">from_records</span><span class="p">(</span><span class="n">data</span><span class="p">)</span><span class="o">.</span><span class="n">set_index</span><span class="p">(</span><span class="s2">&quot;timestamp&quot;</span><span class="p">)</span>
-</pre></div>
-
-    </div>
-</div>
-</div>
-
-  </div>
-
-  
-
-  <div class="
-      cell border-box-sizing code_cell rendered">
-    <div class="input">
-
-<div class="inner_cell">
-    <div class="input_area">
-<div class=" highlight hl-ipython3"><pre><span></span><span class="n">monthly_active</span> <span class="o">=</span> <span class="n">n_active_repos</span><span class="p">(</span><span class="mi">30</span><span class="p">)</span>
-<span class="n">weekly_active</span> <span class="o">=</span> <span class="n">n_active_repos</span><span class="p">(</span><span class="mi">7</span><span class="p">)</span>
-<span class="n">daily_active</span> <span class="o">=</span> <span class="n">n_active_repos</span><span class="p">(</span><span class="mi">1</span><span class="p">)</span>
-</pre></div>
-
-    </div>
-</div>
-</div>
-
-  </div>
-
-  
-
-  <div class="
-      cell border-box-sizing code_cell rendered">
-    <div class="input">
-
-<div class="inner_cell">
-    <div class="input_area">
-<div class=" highlight hl-ipython3"><pre><span></span><span class="n">activity</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">merge</span><span class="p">(</span><span class="n">monthly_active</span><span class="p">,</span> <span class="n">daily_active</span><span class="p">,</span>
-                    <span class="n">suffixes</span><span class="o">=</span><span class="p">(</span><span class="s2">&quot;_monthly&quot;</span><span class="p">,</span> <span class="s2">&quot;_daily&quot;</span><span class="p">),</span> <span class="n">left_index</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">right_index</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
-<span class="n">activity</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">merge</span><span class="p">(</span><span class="n">activity</span><span class="p">,</span> <span class="n">weekly_active</span><span class="p">,</span> <span class="n">left_index</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">right_index</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
-
-<span class="n">activity</span><span class="o">.</span><span class="n">columns</span> <span class="o">=</span> <span class="p">[</span><span class="s1">&#39;30day active&#39;</span><span class="p">,</span> <span class="s1">&#39;1d active&#39;</span><span class="p">,</span> <span class="s1">&#39;7d active&#39;</span><span class="p">]</span>
-<span class="n">activity</span><span class="o">.</span><span class="n">plot</span><span class="p">();</span>
-</pre></div>
-
-    </div>
-</div>
-</div>
-
-  </div>
-<div class="cell border-box-sizing text_cell rendered"><div class="inner_cell">
-<div class="text_cell_render border-box-sizing rendered_html">
-<h2 id="Total-launches">Total launches<a class="anchor-link" href="#Total-launches">&#182;</a></h2>
-</div>
-</div>
-</div>
-
-  
-
-  <div class="
-      cell border-box-sizing code_cell rendered">
-    <div class="input">
-
-<div class="inner_cell">
-    <div class="input_area">
-<div class=" highlight hl-ipython3"><pre><span></span><span class="c1"># Sneak peek: total launches!</span>
-<span class="n">df</span><span class="o">.</span><span class="n">shape</span>
-</pre></div>
-
-    </div>
-</div>
-</div>
-
-  </div>
-<div class="cell border-box-sizing text_cell rendered"><div class="inner_cell">
-<div class="text_cell_render border-box-sizing rendered_html">
-<h2 id="Launches-per-day">Launches per day<a class="anchor-link" href="#Launches-per-day">&#182;</a></h2>
-</div>
-</div>
-</div>
-
-  
-
-  <div class="
-      cell border-box-sizing code_cell rendered">
-    <div class="input">
-
-<div class="inner_cell">
-    <div class="input_area">
-<div class=" highlight hl-ipython3"><pre><span></span><span class="n">daily</span> <span class="o">=</span> <span class="n">df</span><span class="o">.</span><span class="n">set_index</span><span class="p">(</span><span class="s2">&quot;timestamp&quot;</span><span class="p">)</span><span class="o">.</span><span class="n">resample</span><span class="p">(</span><span class="s1">&#39;D&#39;</span><span class="p">)</span><span class="o">.</span><span class="n">count</span><span class="p">()</span>
-</pre></div>
-
-    </div>
-</div>
-</div>
-
-  </div>
-
-  
-
-  <div class="
-      cell border-box-sizing code_cell rendered">
-    <div class="input">
-
-<div class="inner_cell">
-    <div class="input_area">
-<div class=" highlight hl-ipython3"><pre><span></span><span class="n">daily</span><span class="p">[</span><span class="s1">&#39;repo&#39;</span><span class="p">]</span><span class="o">.</span><span class="n">plot</span><span class="p">()</span>
-</pre></div>
-
-    </div>
-</div>
-</div>
-
-  </div>
-<div class="cell border-box-sizing text_cell rendered"><div class="inner_cell">
-<div class="text_cell_render border-box-sizing rendered_html">
-<h2 id="Estimate-number-of-unique-repositories">Estimate number of unique repositories<a class="anchor-link" href="#Estimate-number-of-unique-repositories">&#182;</a></h2><p>Expect the raw number of launches to be bigger than the number of repositories launched more than once. Those launched only once might have been accidents.</p>
-
-</div>
-</div>
-</div>
-
-  
-
-  <div class="
-      cell border-box-sizing code_cell rendered">
-    <div class="input">
-
-<div class="inner_cell">
-    <div class="input_area">
-<div class=" highlight hl-ipython3"><pre><span></span><span class="nb">len</span><span class="p">(</span><span class="nb">set</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">repo</span><span class="p">))</span>
-</pre></div>
-
-    </div>
-</div>
-</div>
-
-  </div>
-
-  
-
-  <div class="
-      cell border-box-sizing code_cell rendered">
-    <div class="input">
-
-<div class="inner_cell">
-    <div class="input_area">
-<div class=" highlight hl-ipython3"><pre><span></span><span class="kn">from</span> <span class="nn">collections</span> <span class="kn">import</span> <span class="n">Counter</span>
-
-<span class="nb">sum</span><span class="p">(</span><span class="mi">1</span> <span class="k">for</span> <span class="n">k</span><span class="p">,</span><span class="n">v</span> <span class="ow">in</span> <span class="n">Counter</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">repo</span><span class="p">)</span><span class="o">.</span><span class="n">items</span><span class="p">()</span> <span class="k">if</span> <span class="n">v</span> <span class="o">&gt;</span> <span class="mi">3</span><span class="p">)</span>
-</pre></div>
-
-    </div>
-</div>
-</div>
-
-  </div>
-<div class="cell border-box-sizing text_cell rendered"><div class="inner_cell">
-<div class="text_cell_render border-box-sizing rendered_html">
-<h2 id="Popular-repositories-and-their-branches">Popular repositories and their branches<a class="anchor-link" href="#Popular-repositories-and-their-branches">&#182;</a></h2><p>Twenty most popular repos:</p>
-
-</div>
-</div>
-</div>
-
-  
-
-  <div class="
-      cell border-box-sizing code_cell rendered">
-    <div class="input">
-
-<div class="inner_cell">
-    <div class="input_area">
-<div class=" highlight hl-ipython3"><pre><span></span><span class="n">top20</span> <span class="o">=</span> <span class="n">df</span><span class="o">.</span><span class="n">groupby</span><span class="p">(</span><span class="s2">&quot;repo&quot;</span><span class="p">)</span><span class="o">.</span><span class="n">count</span><span class="p">()</span><span class="o">.</span><span class="n">sort_values</span><span class="p">(</span><span class="s2">&quot;timestamp&quot;</span><span class="p">,</span> <span class="n">ascending</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span><span class="o">.</span><span class="n">head</span><span class="p">(</span><span class="mi">20</span><span class="p">)</span>
-<span class="n">top20</span>
-</pre></div>
-
-    </div>
-</div>
-</div>
-
-  </div>
-
-  
-
-  <div class="
-      cell border-box-sizing code_cell rendered">
-    <div class="input">
-
-<div class="inner_cell">
-    <div class="input_area">
-<div class=" highlight hl-ipython3"><pre><span></span><span class="nb">print</span><span class="p">(</span><span class="s2">&quot;Cumulative top20 launches:&quot;</span><span class="p">,</span> <span class="n">top20</span><span class="p">[</span><span class="s1">&#39;ref&#39;</span><span class="p">]</span><span class="o">.</span><span class="n">sum</span><span class="p">())</span>
-<span class="nb">print</span><span class="p">(</span><span class="s2">&quot;The top20 repos are </span><span class="si">{:.1f}% o</span><span class="s2">f all &quot;</span>
-      <span class="s2">&quot;launches.&quot;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="mi">100</span> <span class="o">*</span> <span class="n">top20</span><span class="p">[</span><span class="s1">&#39;ref&#39;</span><span class="p">]</span><span class="o">.</span><span class="n">sum</span><span class="p">()</span> <span class="o">/</span> <span class="n">df</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]))</span>
-</pre></div>
-
-    </div>
-</div>
-</div>
-
-  </div>
-<div class="cell border-box-sizing text_cell rendered"><div class="inner_cell">
-<div class="text_cell_render border-box-sizing rendered_html">
-<h2 id="Per-org-stats">Per org stats<a class="anchor-link" href="#Per-org-stats">&#182;</a></h2><p>Needs more RAM than mybinder.org gives us for now</p>
-
-</div>
-</div>
-</div>
-
-  
-
-  <div class="
-      cell border-box-sizing code_cell rendered">
-    <div class="input">
-
-<div class="inner_cell">
-    <div class="input_area">
-<div class=" highlight hl-ipython3"><pre><span></span><span class="c1"># add a new column showing total launches per repo</span>
-<span class="n">totals_per_repo</span> <span class="o">=</span> <span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">groupby</span><span class="p">([</span><span class="s2">&quot;repo&quot;</span><span class="p">])</span>
- <span class="o">.</span><span class="n">size</span><span class="p">()</span>
- <span class="o">.</span><span class="n">reset_index</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s1">&#39;repo_counts&#39;</span><span class="p">))</span>
-</pre></div>
-
-    </div>
-</div>
-</div>
-
-  </div>
-
-  
-
-  <div class="
-      cell border-box-sizing code_cell rendered">
-    <div class="input">
-
-<div class="inner_cell">
-    <div class="input_area">
-<div class=" highlight hl-ipython3"><pre><span></span><span class="c1"># add a nnew column showing total launches per org</span>
-<span class="n">totals_per_org</span> <span class="o">=</span> <span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">groupby</span><span class="p">([</span><span class="s2">&quot;org&quot;</span><span class="p">])</span>
- <span class="o">.</span><span class="n">size</span><span class="p">()</span>
- <span class="o">.</span><span class="n">reset_index</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s1">&#39;org_counts&#39;</span><span class="p">))</span>
-</pre></div>
-
-    </div>
-</div>
-</div>
-
-  </div>
-
-  
-
-  <div class="
-      cell border-box-sizing code_cell rendered">
-    <div class="input">
-
-<div class="inner_cell">
-    <div class="input_area">
-<div class=" highlight hl-ipython3"><pre><span></span><span class="n">df_</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">merge</span><span class="p">(</span><span class="n">df</span><span class="p">,</span> <span class="n">totals_per_repo</span><span class="p">,</span> <span class="n">on</span><span class="o">=</span><span class="s1">&#39;repo&#39;</span><span class="p">)</span>
-<span class="n">df_</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">merge</span><span class="p">(</span><span class="n">df_</span><span class="p">,</span> <span class="n">totals_per_org</span><span class="p">,</span> <span class="n">on</span><span class="o">=</span><span class="s1">&#39;org&#39;</span><span class="p">)</span>
-<span class="c1">#df_.sample(10)</span>
-</pre></div>
-
-    </div>
-</div>
-</div>
-
-  </div>
-
-  
-
-  <div class="
-      cell border-box-sizing code_cell rendered">
-    <div class="input">
-
-<div class="inner_cell">
-    <div class="input_area">
-<div class=" highlight hl-ipython3"><pre><span></span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">groupby</span><span class="p">(</span><span class="s2">&quot;provider&quot;</span><span class="p">)</span>
-   <span class="o">.</span><span class="n">size</span><span class="p">()</span>
-   <span class="o">.</span><span class="n">reset_index</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s1">&#39;Launches&#39;</span><span class="p">)</span>
-   <span class="o">.</span><span class="n">sort_values</span><span class="p">(</span><span class="s1">&#39;Launches&#39;</span><span class="p">,</span> <span class="n">ascending</span><span class="o">=</span><span class="kc">False</span><span class="p">))</span>
-</pre></div>
-
-    </div>
-</div>
-</div>
-
-  </div>
-
-  
-
-  <div class="
-      cell border-box-sizing code_cell rendered">
-    <div class="input">
-
-<div class="inner_cell">
-    <div class="input_area">
-<div class=" highlight hl-ipython3"><pre><span></span><span class="p">(</span><span class="n">df_</span><span class="o">.</span><span class="n">groupby</span><span class="p">([</span><span class="s2">&quot;org&quot;</span><span class="p">,</span> <span class="s2">&quot;repo&quot;</span><span class="p">,</span> <span class="s2">&quot;ref&quot;</span><span class="p">,</span> <span class="s2">&quot;repo_counts&quot;</span><span class="p">,</span> <span class="s2">&quot;org_counts&quot;</span><span class="p">])</span>
- <span class="o">.</span><span class="n">size</span><span class="p">()</span>
- <span class="c1"># give the column a nice name</span>
- <span class="o">.</span><span class="n">reset_index</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s1">&#39;ref_counts&#39;</span><span class="p">)</span>
- <span class="c1"># sort first by total launches, then within a repo by ref launches</span>
- <span class="o">.</span><span class="n">sort_values</span><span class="p">([</span><span class="s1">&#39;org_counts&#39;</span><span class="p">,</span> <span class="s1">&#39;repo_counts&#39;</span><span class="p">,</span> <span class="s1">&#39;ref_counts&#39;</span><span class="p">],</span>
-              <span class="n">ascending</span><span class="o">=</span><span class="p">[</span><span class="kc">False</span><span class="p">,</span><span class="kc">False</span><span class="p">,</span> <span class="kc">False</span><span class="p">])</span>
- <span class="o">.</span><span class="n">set_index</span><span class="p">([</span><span class="s2">&quot;org&quot;</span><span class="p">,</span> <span class="s1">&#39;repo&#39;</span><span class="p">,</span> <span class="s1">&#39;ref&#39;</span><span class="p">])</span>
-<span class="p">)</span>
-</pre></div>
-
-    </div>
-</div>
-</div>
-
-  </div>
-