Updates for version 1.0 (#5)

* setup initial tests

* test: updated testing actions and test structure

* feat: added in some tests for utils

* feat: added in function for reading in population panel files separately

* draft: updated some tests

* test: population panel testing

* feat: new function to add in population handling

* test: added in test for verification of samples

* feat: vcf2frequency table now uses cyvcf2

* draft: small commit - still needs some fixing on docs

* test: some refactoring and some testing

* doc: some additional docstrings

* feat: updated to include data in installation

* feat: finally got cyvcf2 features working

* feat: not supporting windows due to cyvcf2

.github/workflows/macos.yml

@@ -35,7 +35,7 @@ jobs:
 
       - name: run tests
         run: |
-          pytest
+          python -m pytest tests/
 
       - name: run flake8
         run: |

.github/workflows/ubuntu.yml

@@ -35,7 +35,7 @@ jobs:
 
       - name: run tests
         run: |
-          pytest
+          python -m pytest tests/
 
       - name: run flake8
         run: |

.gitignore

@@ -1,3 +1,8 @@
 sandbox/*
 geovar/data/*.csv
 docsrc/_build/*
+.hypothesis/
+*.egg-info/
+*.coverage
+*.python-version
+build/

docs/_modules/geovar/binning.html

@@ -54,6 +54,7 @@ <h1>Source code for geovar.binning</h1><div class="highlight"><pre>
 <span class="sd">        &quot;&quot;&quot;</span>
         <span class="k">assert</span> <span class="n">np</span><span class="o">.</span><span class="n">all</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">bins</span><span class="p">)</span> <span class="o">&lt;=</span> <span class="mf">1.0</span><span class="p">)</span>
         <span class="k">assert</span> <span class="n">np</span><span class="o">.</span><span class="n">all</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">bins</span><span class="p">)</span> <span class="o">&gt;=</span> <span class="mf">0.0</span><span class="p">)</span>
+        <span class="k">assert</span> <span class="nb">len</span><span class="p">(</span><span class="n">bins</span><span class="p">)</span> <span class="o">&gt;</span> <span class="mi">0</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">bins</span> <span class="o">=</span> <span class="n">bins</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">freq_mat</span> <span class="o">=</span> <span class="kc">None</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">n_variants</span> <span class="o">=</span> <span class="kc">None</span>

docs/_sources/stubs/geovar.utils.rst.txt

@@ -13,9 +13,10 @@
 
    .. autosummary::
 
-      flip_alleles
+      read_pop_panel
       sep_freq_mat_pops
       vcf_to_freq_table
+      verify_sample_indices
 
 
 

docs/_static/pygments.css

@@ -54,7 +54,6 @@ span.linenos.special { color: #000000; background-color: #ffffc0; padding-left:
 .highlight .nt { color: #004461; font-weight: bold } /* Name.Tag */
 .highlight .nv { color: #000000 } /* Name.Variable */
 .highlight .ow { color: #004461; font-weight: bold } /* Operator.Word */
-.highlight .pm { color: #000000; font-weight: bold } /* Punctuation.Marker */
 .highlight .w { color: #f8f8f8; text-decoration: underline } /* Text.Whitespace */
 .highlight .mb { color: #990000 } /* Literal.Number.Bin */
 .highlight .mf { color: #990000 } /* Literal.Number.Float */

docs/genindex.html

@@ -37,9 +37,9 @@ <h1 id="index">Index</h1>
 
 <div class="genindex-jumpbox">
  <a href="#_"><strong>_</strong></a>
- | <a href="#F"><strong>F</strong></a>
  | <a href="#G"><strong>G</strong></a>
  | <a href="#M"><strong>M</strong></a>
+ | <a href="#R"><strong>R</strong></a>
  | <a href="#S"><strong>S</strong></a>
  | <a href="#V"><strong>V</strong></a>
 
@@ -56,14 +56,6 @@ <h2 id="_">_</h2>
   </ul></td>
 </tr></table>
 
-<h2 id="F">F</h2>
-<table style="width: 100%" class="indextable genindextable"><tr>
-  <td style="width: 33%; vertical-align: top;"><ul>
-      <li><a href="geovar.html#geovar.utils.flip_alleles">flip_alleles() (in module geovar.utils)</a>
-</li>
-  </ul></td>
-</tr></table>
-
 <h2 id="G">G</h2>
 <table style="width: 100%" class="indextable genindextable"><tr>
   <td style="width: 33%; vertical-align: top;"><ul>
@@ -96,6 +88,14 @@ <h2 id="M">M</h2>
   </ul></td>
 </tr></table>
 
+<h2 id="R">R</h2>
+<table style="width: 100%" class="indextable genindextable"><tr>
+  <td style="width: 33%; vertical-align: top;"><ul>
+      <li><a href="geovar.html#geovar.utils.read_pop_panel">read_pop_panel() (in module geovar.utils)</a>
+</li>
+  </ul></td>
+</tr></table>
+
 <h2 id="S">S</h2>
 <table style="width: 100%" class="indextable genindextable"><tr>
   <td style="width: 33%; vertical-align: top;"><ul>
@@ -108,6 +108,10 @@ <h2 id="V">V</h2>
 <table style="width: 100%" class="indextable genindextable"><tr>
   <td style="width: 33%; vertical-align: top;"><ul>
       <li><a href="geovar.html#geovar.utils.vcf_to_freq_table">vcf_to_freq_table() (in module geovar.utils)</a>
+</li>
+  </ul></td>
+  <td style="width: 33%; vertical-align: top;"><ul>
+      <li><a href="geovar.html#geovar.utils.verify_sample_indices">verify_sample_indices() (in module geovar.utils)</a>
 </li>
   </ul></td>
 </tr></table>

docs/geovar.html

@@ -62,9 +62,14 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 </table>
 <span class="target" id="module-geovar.utils"></span><p>Utilities for file conversions for GeoVar.</p>
 <dl class="py function">
-<dt class="sig sig-object py" id="geovar.utils.flip_alleles">
-<span class="sig-prename descclassname"><span class="pre">geovar.utils.</span></span><span class="sig-name descname"><span class="pre">flip_alleles</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">acnt</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">flip</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/geovar/utils.html#flip_alleles"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#geovar.utils.flip_alleles" title="Permalink to this definition">¶</a></dt>
-<dd><p>Flip alleles if based on being the minor allele.</p>
+<dt class="sig sig-object py" id="geovar.utils.read_pop_panel">
+<span class="sig-prename descclassname"><span class="pre">geovar.utils.</span></span><span class="sig-name descname"><span class="pre">read_pop_panel</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">pop_panel_file</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/geovar/utils.html#read_pop_panel"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#geovar.utils.read_pop_panel" title="Permalink to this definition">¶</a></dt>
+<dd><p>Read in a population panel file.</p>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters<span class="colon">:</span></dt>
+<dd class="field-odd"><p><strong>(</strong> (<em>pop_panel_files</em>) – obj: <cite>string</cite>): list of population</p>
+</dd>
+</dl>
 </dd></dl>
 
 <dl class="py function">
@@ -83,20 +88,34 @@ <h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this
 
 <dl class="py function">
 <dt class="sig sig-object py" id="geovar.utils.vcf_to_freq_table">
-<span class="sig-prename descclassname"><span class="pre">geovar.utils.</span></span><span class="sig-name descname"><span class="pre">vcf_to_freq_table</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">vcf_file</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pop_panel</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">outfile</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">minor_allele</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/geovar/utils.html#vcf_to_freq_table"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#geovar.utils.vcf_to_freq_table" title="Permalink to this definition">¶</a></dt>
+<span class="sig-prename descclassname"><span class="pre">geovar.utils.</span></span><span class="sig-name descname"><span class="pre">vcf_to_freq_table</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">vcf_file</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">pop_df</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">outfile</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">minor_allele</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/geovar/utils.html#vcf_to_freq_table"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#geovar.utils.vcf_to_freq_table" title="Permalink to this definition">¶</a></dt>
 <dd><p>Convert a VCF File to a frequency table to be used as input to a GeoVar object.</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>vcf_file</strong> (<a class="reference external" href="https://docs.python.org/3/library/string.html#module-string" title="(in Python v3.10)"><code class="xref py py-obj docutils literal notranslate"><span class="pre">string</span></code></a>) – filepath to VCF file (can be bgzipped).</p></li>
-<li><p><strong>pop_panel</strong> (<a class="reference external" href="https://docs.python.org/3/library/string.html#module-string" title="(in Python v3.10)"><code class="xref py py-obj docutils literal notranslate"><span class="pre">string</span></code></a>) – filepath to population panel file.</p></li>
+<li><p><strong>pop_df</strong> (<code class="xref py py-obj docutils literal notranslate"><span class="pre">pandas.DataFrame</span></code>) – population data frame in pandas format.</p></li>
 <li><p><strong>outfile</strong> (<a class="reference external" href="https://docs.python.org/3/library/string.html#module-string" title="(in Python v3.10)"><code class="xref py py-obj docutils literal notranslate"><span class="pre">string</span></code></a>) – file to write output allele frequency table to.</p></li>
 <li><p><strong>minor_allele</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.10)"><code class="xref py py-obj docutils literal notranslate"><span class="pre">bool</span></code></a>) – flag to indicate if we want to polarize to the minor allele.</p></li>
 </ul>
 </dd>
 </dl>
 </dd></dl>
 
+<dl class="py function">
+<dt class="sig sig-object py" id="geovar.utils.verify_sample_indices">
+<span class="sig-prename descclassname"><span class="pre">geovar.utils.</span></span><span class="sig-name descname"><span class="pre">verify_sample_indices</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">pop_df</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">samples</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/geovar/utils.html#verify_sample_indices"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#geovar.utils.verify_sample_indices" title="Permalink to this definition">¶</a></dt>
+<dd><p>Generate the sample indices from a list of sample IDs stratified by population.</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>pop_df</strong> (<code class="xref py py-obj docutils literal notranslate"><span class="pre">pandas.DataFrame</span></code>) – population data frame in pandas format.Must have <cite>pop</cite> and <cite>sample</cite> columns available.</p></li>
+<li><p><strong>samples</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.10)"><code class="xref py py-obj docutils literal notranslate"><span class="pre">list</span></code></a>) – list of sample IDs (strings) that are ready to be indexed.</p></li>
+</ul>
+</dd>
+</dl>
+</dd></dl>
+
 </section>
 </section>