docs: document count_missing()

README.md

@@ -41,10 +41,11 @@ pip install git+https://github.com/moderndive/moderndive-python
   `engine="plotnine"` — same code, your choice of output.
 - **Theory-based wrapper tests**: `t_test`, `prop_test`, `chisq_test`,
   `t_stat`, `chisq_stat`, plus the `moderndive.theory` module.
-- **Regression helpers** mirroring R `moderndive`: `get_regression_table`,
+- **Regression & summary helpers** mirroring R `moderndive`: `get_regression_table`,
   `get_regression_points`, `get_regression_summaries`, `get_correlation`,
-  `pop_sd`, `tidy_summary` (built on `statsmodels`, returning `polars` frames),
-  plus the model plots `gg_parallel_slopes` / `geom_parallel_slopes` and
+  `pop_sd`, `tidy_summary`, `count_missing` (built on `statsmodels` where
+  relevant, returning `polars` frames), plus the model plots
+  `gg_parallel_slopes` / `geom_parallel_slopes` and
   `gg_categorical_model` / `geom_categorical_model`, and `pairplot`
   (the `GGally::ggpairs` analog).
 - **Sampling**: `rep_slice_sample` / `rep_sample_n` for sampling-distribution

doc/_build/html/_modules/moderndive/modeling.html

@@ -269,6 +269,7 @@ <h1>Source code for moderndive.modeling</h1><div class="highlight"><pre>
     <span class="s2">&quot;get_regression_points&quot;</span><span class="p">,</span>
     <span class="s2">&quot;get_regression_summaries&quot;</span><span class="p">,</span>
     <span class="s2">&quot;tidy_summary&quot;</span><span class="p">,</span>
+    <span class="s2">&quot;count_missing&quot;</span><span class="p">,</span>
 <span class="p">]</span>
 
 
@@ -442,6 +443,35 @@ <h1>Source code for moderndive.modeling</h1><div class="highlight"><pre>
     <span class="p">}</span>
     <span class="k">return</span> <span class="n">pl</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">(</span><span class="n">rows</span><span class="p">,</span> <span class="n">schema</span><span class="o">=</span><span class="n">schema</span><span class="p">)</span></div>
 
+
+
+<div class="viewcode-block" id="count_missing">
+<a class="viewcode-back" href="../../api.html#moderndive.count_missing">[docs]</a>
+<span class="k">def</span><span class="w"> </span><span class="nf">count_missing</span><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="n">columns</span><span class="p">:</span> <span class="nb">list</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">|</span> <span class="kc">None</span> <span class="o">=</span> <span class="kc">None</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">pl</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">:</span>
+<span class="w">    </span><span class="sd">&quot;&quot;&quot;Count missing (``null``) values in each column.</span>
+
+<span class="sd">    A beginner-friendly alternative to ``df.select(pl.all().is_null().sum())``:</span>
+<span class="sd">    it returns a tidy two-column data frame with one row per column</span>
+<span class="sd">    (``column``, ``n_missing``), sorted from most to fewest missing values so the</span>
+<span class="sd">    columns needing attention surface first.</span>
+
+<span class="sd">    Parameters</span>
+<span class="sd">    ----------</span>
+<span class="sd">    data:</span>
+<span class="sd">        A polars (or pandas) data frame.</span>
+<span class="sd">    columns:</span>
+<span class="sd">        Optional list of column names to check; defaults to every column.</span>
+<span class="sd">    &quot;&quot;&quot;</span>
+    <span class="n">df</span> <span class="o">=</span> <span class="n">data</span> <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="n">pl</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">)</span> <span class="k">else</span> <span class="n">pl</span><span class="o">.</span><span class="n">from_pandas</span><span class="p">(</span><span class="n">data</span><span class="p">)</span>
+    <span class="n">columns</span> <span class="o">=</span> <span class="n">columns</span> <span class="ow">or</span> <span class="n">df</span><span class="o">.</span><span class="n">columns</span>
+    <span class="k">return</span> <span class="n">pl</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">(</span>
+        <span class="p">{</span>
+            <span class="s2">&quot;column&quot;</span><span class="p">:</span> <span class="n">columns</span><span class="p">,</span>
+            <span class="s2">&quot;n_missing&quot;</span><span class="p">:</span> <span class="p">[</span><span class="nb">int</span><span class="p">(</span><span class="n">df</span><span class="p">[</span><span class="n">col</span><span class="p">]</span><span class="o">.</span><span class="n">null_count</span><span class="p">())</span> <span class="k">for</span> <span class="n">col</span> <span class="ow">in</span> <span class="n">columns</span><span class="p">],</span>
+        <span class="p">},</span>
+        <span class="n">schema</span><span class="o">=</span><span class="p">{</span><span class="s2">&quot;column&quot;</span><span class="p">:</span> <span class="n">pl</span><span class="o">.</span><span class="n">Utf8</span><span class="p">,</span> <span class="s2">&quot;n_missing&quot;</span><span class="p">:</span> <span class="n">pl</span><span class="o">.</span><span class="n">Int64</span><span class="p">},</span>
+    <span class="p">)</span><span class="o">.</span><span class="n">sort</span><span class="p">(</span><span class="s2">&quot;n_missing&quot;</span><span class="p">,</span> <span class="n">descending</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span></div>
+
 </pre></div>
         </article>
       </div>

doc/_build/html/_sources/api.md.txt

@@ -42,7 +42,7 @@
    :members:
 ```
 
-## Regression helpers
+## Regression & summary helpers
 
 ```{eval-rst}
 .. autofunction:: moderndive.get_regression_table
@@ -51,6 +51,7 @@
 .. autofunction:: moderndive.get_correlation
 .. autofunction:: moderndive.pop_sd
 .. autofunction:: moderndive.tidy_summary
+.. autofunction:: moderndive.count_missing
 ```
 
 ## Sampling and plots

doc/_build/html/_sources/getting-started.md.txt

@@ -56,6 +56,15 @@ from moderndive import tidy_summary
 tidy_summary(md.load_almonds_sample_100(), columns=["weight"])
 ```
 
+`count_missing` reports how many `null` values each column has, sorted worst-first
+— handy for a quick data-quality check:
+
+```{code-cell} python
+from moderndive import count_missing
+
+count_missing(md.load_evals())
+```
+
 ## The inference pipeline
 
 The core grammar mirrors R `infer`. You build a pipeline and read it like a

doc/_build/html/api.html

@@ -804,8 +804,8 @@ <h2>Theory-based tests<a class="headerlink" href="#theory-based-tests" title="Li
 </dd></dl>
 
 </section>
-<section id="regression-helpers">
-<h2>Regression helpers<a class="headerlink" href="#regression-helpers" title="Link to this heading">¶</a></h2>
+<section id="regression-summary-helpers">
+<h2>Regression &amp; summary helpers<a class="headerlink" href="#regression-summary-helpers" title="Link to this heading">¶</a></h2>
 <dl class="py function">
 <dt class="sig sig-object py" id="moderndive.get_regression_table">
 <span class="sig-prename descclassname"><span class="pre">moderndive.</span></span><span class="sig-name descname"><span class="pre">get_regression_table</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">model</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">digits</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">3</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">conf_level</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">0.95</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/moderndive/modeling.html#get_regression_table"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#moderndive.get_regression_table" title="Link to this definition">¶</a></dt>
@@ -916,6 +916,27 @@ <h2>Regression helpers<a class="headerlink" href="#regression-helpers" title="Li
 </dl>
 </dd></dl>
 
+<dl class="py function">
+<dt class="sig sig-object py" id="moderndive.count_missing">
+<span class="sig-prename descclassname"><span class="pre">moderndive.</span></span><span class="sig-name descname"><span class="pre">count_missing</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">columns</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/moderndive/modeling.html#count_missing"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#moderndive.count_missing" title="Link to this definition">¶</a></dt>
+<dd><p>Count missing (<code class="docutils literal notranslate"><span class="pre">null</span></code>) values in each column.</p>
+<p>A beginner-friendly alternative to <code class="docutils literal notranslate"><span class="pre">df.select(pl.all().is_null().sum())</span></code>:
+it returns a tidy two-column data frame with one row per column
+(<code class="docutils literal notranslate"><span class="pre">column</span></code>, <code class="docutils literal notranslate"><span class="pre">n_missing</span></code>), sorted from most to fewest missing values so the
+columns needing attention surface first.</p>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters<span class="colon">:</span></dt>
+<dd class="field-odd"><ul class="simple">
+<li><p><strong>data</strong> – A polars (or pandas) data frame.</p></li>
+<li><p><strong>columns</strong> (<span class="sphinx_autodoc_typehints-type"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">list</span></code></a>[<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.14)"><code class="xref py py-class docutils literal notranslate"><span class="pre">str</span></code></a>] | <a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.14)"><code class="xref py py-obj docutils literal notranslate"><span class="pre">None</span></code></a></span>) – Optional list of column names to check; defaults to every column.</p></li>
+</ul>
+</dd>
+<dt class="field-even">Return type<span class="colon">:</span></dt>
+<dd class="field-even"><p><span class="sphinx_autodoc_typehints-type"><code class="xref py py-class docutils literal notranslate"><span class="pre">DataFrame</span></code></span></p>
+</dd>
+</dl>
+</dd></dl>
+
 </section>
 <section id="sampling-and-plots">
 <h2>Sampling and plots<a class="headerlink" href="#sampling-and-plots" title="Link to this heading">¶</a></h2>
@@ -1166,13 +1187,14 @@ <h2>Datasets<a class="headerlink" href="#datasets" title="Link to this heading">
 <li><a class="reference internal" href="#moderndive.theory.prop_test_two_sample"><code class="docutils literal notranslate"><span class="pre">prop_test_two_sample()</span></code></a></li>
 </ul>
 </li>
-<li><a class="reference internal" href="#regression-helpers">Regression helpers</a><ul>
+<li><a class="reference internal" href="#regression-summary-helpers">Regression &amp; summary helpers</a><ul>
 <li><a class="reference internal" href="#moderndive.get_regression_table"><code class="docutils literal notranslate"><span class="pre">get_regression_table()</span></code></a></li>
 <li><a class="reference internal" href="#moderndive.get_regression_points"><code class="docutils literal notranslate"><span class="pre">get_regression_points()</span></code></a></li>
 <li><a class="reference internal" href="#moderndive.get_regression_summaries"><code class="docutils literal notranslate"><span class="pre">get_regression_summaries()</span></code></a></li>
 <li><a class="reference internal" href="#moderndive.get_correlation"><code class="docutils literal notranslate"><span class="pre">get_correlation()</span></code></a></li>
 <li><a class="reference internal" href="#moderndive.pop_sd"><code class="docutils literal notranslate"><span class="pre">pop_sd()</span></code></a></li>
 <li><a class="reference internal" href="#moderndive.tidy_summary"><code class="docutils literal notranslate"><span class="pre">tidy_summary()</span></code></a></li>
+<li><a class="reference internal" href="#moderndive.count_missing"><code class="docutils literal notranslate"><span class="pre">count_missing()</span></code></a></li>
 </ul>
 </li>
 <li><a class="reference internal" href="#sampling-and-plots">Sampling and plots</a><ul>

doc/_build/html/genindex.html

@@ -282,6 +282,8 @@ <h2>C</h2>
         <li><a href="api.html#moderndive.chisq_stat">chisq_stat() (in module moderndive)</a>
 </li>
         <li><a href="api.html#moderndive.chisq_test">chisq_test() (in module moderndive)</a>
+</li>
+        <li><a href="api.html#moderndive.count_missing">count_missing() (in module moderndive)</a>
 </li>
     </ul></td>
   </tr></table>

doc/_build/html/getting-started.html

@@ -313,6 +313,26 @@ <h2>A first summary<a class="headerlink" href="#a-first-summary" title="Link to
 </style>
 <small>shape: (1, 11)</small><table border="1" class="dataframe"><thead><tr><th>column</th><th>n</th><th>group</th><th>type</th><th>min</th><th>Q1</th><th>mean</th><th>median</th><th>Q3</th><th>max</th><th>sd</th></tr><tr><td>str</td><td>i64</td><td>str</td><td>str</td><td>f64</td><td>f64</td><td>f64</td><td>f64</td><td>f64</td><td>f64</td><td>f64</td></tr></thead><tbody><tr><td>&quot;weight&quot;</td><td>100</td><td>null</td><td>&quot;numeric&quot;</td><td>2.9</td><td>3.4</td><td>3.682</td><td>3.7</td><td>3.9</td><td>4.5</td><td>0.362</td></tr></tbody></table></div></div></div>
 </div>
+<p><code class="docutils literal notranslate"><span class="pre">count_missing</span></code> reports how many <code class="docutils literal notranslate"><span class="pre">null</span></code> values each column has, sorted worst-first
+— handy for a quick data-quality check:</p>
+<div class="cell docutils container">
+<div class="cell_input docutils container">
+<div class="highlight-ipython3 notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span><span class="w"> </span><span class="nn">moderndive</span><span class="w"> </span><span class="kn">import</span> <span class="n">count_missing</span>
+
+<span class="n">count_missing</span><span class="p">(</span><span class="n">md</span><span class="o">.</span><span class="n">load_evals</span><span class="p">())</span>
+</pre></div>
+</div>
+</div>
+<div class="cell_output docutils container">
+<div class="output text_html"><div><style>
+.dataframe > thead > tr,
+.dataframe > tbody > tr {
+  text-align: right;
+  white-space: pre-wrap;
+}
+</style>
+<small>shape: (14, 2)</small><table border="1" class="dataframe"><thead><tr><th>column</th><th>n_missing</th></tr><tr><td>str</td><td>i64</td></tr></thead><tbody><tr><td>&quot;ID&quot;</td><td>0</td></tr><tr><td>&quot;prof_ID&quot;</td><td>0</td></tr><tr><td>&quot;score&quot;</td><td>0</td></tr><tr><td>&quot;age&quot;</td><td>0</td></tr><tr><td>&quot;bty_avg&quot;</td><td>0</td></tr><tr><td>&hellip;</td><td>&hellip;</td></tr><tr><td>&quot;pic_outfit&quot;</td><td>0</td></tr><tr><td>&quot;pic_color&quot;</td><td>0</td></tr><tr><td>&quot;cls_did_eval&quot;</td><td>0</td></tr><tr><td>&quot;cls_students&quot;</td><td>0</td></tr><tr><td>&quot;cls_level&quot;</td><td>0</td></tr></tbody></table></div></div></div>
+</div>
 </section>
 <section id="the-inference-pipeline">
 <h2>The inference pipeline<a class="headerlink" href="#the-inference-pipeline" title="Link to this heading">¶</a></h2>

doc/_build/html/index.html

@@ -389,7 +389,7 @@ <h2>Where to next<a class="headerlink" href="#where-to-next" title="Link to this
 <li class="toctree-l2"><a class="reference internal" href="api.html#inference-grammar">Inference grammar</a></li>
 <li class="toctree-l2"><a class="reference internal" href="api.html#getters-and-visualization">Getters and visualization</a></li>
 <li class="toctree-l2"><a class="reference internal" href="api.html#theory-based-tests">Theory-based tests</a></li>
-<li class="toctree-l2"><a class="reference internal" href="api.html#regression-helpers">Regression helpers</a></li>
+<li class="toctree-l2"><a class="reference internal" href="api.html#regression-summary-helpers">Regression &amp; summary helpers</a></li>
 <li class="toctree-l2"><a class="reference internal" href="api.html#sampling-and-plots">Sampling and plots</a></li>
 <li class="toctree-l2"><a class="reference internal" href="api.html#datasets">Datasets</a></li>
 </ul>

doc/_build/jupyter_execute/datasets.ipynb

@@ -3,7 +3,7 @@
   {
    "cell_type": "code",
    "execution_count": 1,
-   "id": "a9e6fc06",
+   "id": "b560106b",
    "metadata": {
     "tags": [
      "remove-input"
@@ -19,7 +19,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "599ae5ce",
+   "id": "d4e61ded",
    "metadata": {},
    "source": [
     "# Datasets\n",
@@ -31,7 +31,7 @@
   {
    "cell_type": "code",
    "execution_count": 2,
-   "id": "c158a621",
+   "id": "79c08466",
    "metadata": {},
    "outputs": [
     {
@@ -82,7 +82,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "37ccb1db",
+   "id": "9f6c7c7c",
    "metadata": {},
    "source": [
     "## By topic\n",