Hope to solve sphinx problems

aaanalysis/cpp/feature.py

@@ -230,7 +230,7 @@ def get_df_parts(df_seq=None, list_parts=None, jmd_n_len=None, jmd_c_len=None, e
 
         >>> import aaanalysis as aa
         >>> sf = aa.SequenceFeature()
-        >>> df_seq = aa.load_dataset(name='DOM_GSE')
+        >>> df_seq = aa.load_dataset(name='DOM_GSEC')
         >>> df_parts = sf.get_df_parts(df_seq=df_seq, list_parts=["tmd_e", "tmd_jmd"], jmd_n_len=10, jmd_c_len=10)
         """
         ut.check_args_len(jmd_n_len=jmd_n_len, jmd_c_len=jmd_c_len, ext_len=ext_len, accept_tmd_none=True)

aaanalysis/data_loader/data_loader.py

@@ -185,6 +185,10 @@ def load_dataset(name: str = "INFO",
     DataFrame
         Dataframe (df_seq) containing the selected sequence dataset.
 
+    See also
+    --------
+    See an overview of all benchmarks in :ref:`1_overview_benchmarks` and a detailed usage tutorial in the
+    `data loader tutorial <tutorials/tutorial2_data_loader.ipynb>`_.
 
     Examples
     --------

docs/build/html/_sources/index/tables.rst.txt

@@ -1,4 +1,5 @@
-.. Developer Notes:
+..
+    Developer Notes:
     This is the index file for all tables of the AAanalysis documentation. Each table should be saved the /tables
     directory. This file will serve as template for tables.rst, which is automatically created on the information
     provided here and in the .csv tables from the /tables directory. Add a new table as .csv in the /tables directory,
@@ -39,13 +40,13 @@ Protein benchmark datasets
 Three types of benchmark datasets are provided:
 
 - Residue prediction (AA): Datasets used to predict residue (amino acid) specific properties.
-- Domain prediction (DOM): Dataset used to predict domain specific properties
-- Sequence prediction (SEQ): Datasets used to predict sequence specific properties
+- Domain prediction (DOM): Dataset used to predict domain specific properties.
+- Sequence prediction (SEQ): Datasets used to predict sequence specific properties.
 
 The classification of each dataset is indicated as first part of their name followed by an abbreviation for the
 specific dataset (e.g., 'AA_LDR', 'DOM_GSEC', 'SEQ_AMYLO'). For some datasets, an additional version of it is provided
 for positive-unlabeled (PU) learning containing only positive (1) and unlabeled (2) data samples, as indicated by
-*dataset_name*_PU (e.g., 'DOM_GSEC_PU').
+*dataset_name_PU* (e.g., 'DOM_GSEC_PU').
 
 .. _1_overview_benchmarks:
 .. list-table::

docs/build/html/_sources/tables_template.rst.txt

@@ -1,4 +1,5 @@
-.. Developer Notes:
+..
+    Developer Notes:
     This is the index file for all tables of the AAanalysis documentation. Each table should be saved the /tables
     directory. This file will serve as template for tables.rst, which is automatically created on the information
     provided here and in the .csv tables from the /tables directory. Add a new table as .csv in the /tables directory,
@@ -25,13 +26,13 @@ Protein benchmark datasets
 Three types of benchmark datasets are provided:
 
 - Residue prediction (AA): Datasets used to predict residue (amino acid) specific properties.
-- Domain prediction (DOM): Dataset used to predict domain specific properties
-- Sequence prediction (SEQ): Datasets used to predict sequence specific properties
+- Domain prediction (DOM): Dataset used to predict domain specific properties.
+- Sequence prediction (SEQ): Datasets used to predict sequence specific properties.
 
 The classification of each dataset is indicated as first part of their name followed by an abbreviation for the
 specific dataset (e.g., 'AA_LDR', 'DOM_GSEC', 'SEQ_AMYLO'). For some datasets, an additional version of it is provided
 for positive-unlabeled (PU) learning containing only positive (1) and unlabeled (2) data samples, as indicated by
-*dataset_name*_PU (e.g., 'DOM_GSEC_PU').
+*dataset_name_PU* (e.g., 'DOM_GSEC_PU').
 
 .. _1_overview_benchmarks:
 

docs/build/html/_sources/usage_principles.rst.txt

@@ -10,4 +10,13 @@ Import AAanalysis as:
 
 .. code-block:: python
 
-    import aaanalysis as aa
+    import aaanalysis as aa
+
+.. toctree::
+   :maxdepth: 1
+
+   index/usage_principles/data_flow_entry_points
+   index/usage_principles/aaontology
+   index/usage_principles/feature_identification
+   index/usage_principles/pu_learning
+   index/usage_principles/xai

docs/build/html/generated/aaanalysis.SequenceFeature.html

@@ -219,7 +219,7 @@ <h1>aaanalysis.SequenceFeature<a class="headerlink" href="#aaanalysis-sequencefe
 <p>Get sequence parts from df_seq with ‘tmd_e’, and ‘tmd_jmd’ as parts and jmd length of 10:</p>
 <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="kn">import</span> <span class="nn">aaanalysis</span> <span class="k">as</span> <span class="nn">aa</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">sf</span> <span class="o">=</span> <span class="n">aa</span><span class="o">.</span><span class="n">SequenceFeature</span><span class="p">()</span>
-<span class="gp">&gt;&gt;&gt; </span><span class="n">df_seq</span> <span class="o">=</span> <span class="n">aa</span><span class="o">.</span><span class="n">load_dataset</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s1">&#39;DOM_GSE&#39;</span><span class="p">)</span>
+<span class="gp">&gt;&gt;&gt; </span><span class="n">df_seq</span> <span class="o">=</span> <span class="n">aa</span><span class="o">.</span><span class="n">load_dataset</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s1">&#39;DOM_GSEC&#39;</span><span class="p">)</span>
 <span class="gp">&gt;&gt;&gt; </span><span class="n">df_parts</span> <span class="o">=</span> <span class="n">sf</span><span class="o">.</span><span class="n">get_df_parts</span><span class="p">(</span><span class="n">df_seq</span><span class="o">=</span><span class="n">df_seq</span><span class="p">,</span> <span class="n">list_parts</span><span class="o">=</span><span class="p">[</span><span class="s2">&quot;tmd_e&quot;</span><span class="p">,</span> <span class="s2">&quot;tmd_jmd&quot;</span><span class="p">],</span> <span class="n">jmd_n_len</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span> <span class="n">jmd_c_len</span><span class="o">=</span><span class="mi">10</span><span class="p">)</span>
 </pre></div>
 </div>

docs/build/html/generated/aaanalysis.load_dataset.html

@@ -120,7 +120,7 @@
 <h1>aaanalysis.load_dataset<a class="headerlink" href="#aaanalysis-load-dataset" title="Permalink to this heading"></a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="aaanalysis.load_dataset">
-<span class="sig-prename descclassname"><span class="pre">aaanalysis.</span></span><span class="sig-name descname"><span class="pre">load_dataset</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'INFO'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n</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">random</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">non_canonical_aa</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'remove'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_len</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">max_len</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">aa_window_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">9</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/breimanntools/aaanalysis/tree/master/aaanalysis/data_loader/data_loader.py#L145-L234"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#aaanalysis.load_dataset" title="Permalink to this definition"></a></dt>
+<span class="sig-prename descclassname"><span class="pre">aaanalysis.</span></span><span class="sig-name descname"><span class="pre">load_dataset</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'INFO'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">n</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">random</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">non_canonical_aa</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'remove'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_len</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">max_len</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">aa_window_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">9</span></span></em><span class="sig-paren">)</span><a class="reference external" href="https://github.com/breimanntools/aaanalysis/tree/master/aaanalysis/data_loader/data_loader.py#L145-L238"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#aaanalysis.load_dataset" title="Permalink to this definition"></a></dt>
 <dd><p>Load protein benchmarking datasets.</p>
 <p>The benchmarks are categorized into amino acid (‘AA’), domain (‘DOM’), and sequence (‘SEQ’) level
 datasets. Use default settings (<code class="docutils literal notranslate"><span class="pre">name='INFO'</span></code>) for an overview table. Detailed analysis is in <a class="reference internal" href="../index/references.html#breimann23a" id="id1"><span>[Breimann23a]</span></a>.</p>
@@ -149,6 +149,11 @@ <h1>aaanalysis.load_dataset<a class="headerlink" href="#aaanalysis-load-dataset"
 <dd class="field-odd"><p>DataFrame</p>
 </dd>
 </dl>
+<div class="admonition seealso">
+<p class="admonition-title">See also</p>
+<p>See an overview of all benchmarks in <a class="reference internal" href="../tables_template.html#overview-benchmarks"><span class="std std-ref">Amino acid scale datasets</span></a> and a detailed usage tutorial in the
+<a class="reference external" href="tutorials/tutorial2_data_loader.ipynb">data loader tutorial</a>.</p>
+</div>
 <div class="admonition-examples admonition">
 <p class="admonition-title">Examples</p>
 <div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="kn">import</span> <span class="nn">aaanalysis</span> <span class="k">as</span> <span class="nn">aa</span>

docs/build/html/generated/aaanalysis.load_scales.html

@@ -120,7 +120,7 @@
 <h1>aaanalysis.load_scales<a class="headerlink" href="#aaanalysis-load-scales" title="Permalink to this heading"></a></h1>
 <dl class="py function">
 <dt class="sig sig-object py" id="aaanalysis.load_scales">
-<span class="sig-prename descclassname"><span class="pre">aaanalysis.</span></span><span class="sig-name descname"><span class="pre">load_scales</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'scales'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">just_aaindex</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">unclassified_in</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 external" href="https://github.com/breimanntools/aaanalysis/tree/master/aaanalysis/data_loader/data_loader.py#L238-L272"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#aaanalysis.load_scales" title="Permalink to this definition"></a></dt>
+<span class="sig-prename descclassname"><span class="pre">aaanalysis.</span></span><span class="sig-name descname"><span class="pre">load_scales</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'scales'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">just_aaindex</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">unclassified_in</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 external" href="https://github.com/breimanntools/aaanalysis/tree/master/aaanalysis/data_loader/data_loader.py#L242-L276"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#aaanalysis.load_scales" title="Permalink to this definition"></a></dt>
 <dd><p>Load amino acid scales, scale classification (AAontology), or scale evaluation.</p>
 <p>A thorough analysis of the residue and sequence datasets can be found in <a class="reference internal" href="../index/references.html#breimann23a" id="id1"><span>[Breimann23a]</span></a>.</p>
 <dl class="field-list simple">

docs/build/html/index/CONTRIBUTING_COPY.html

@@ -40,7 +40,7 @@
     <link rel="index" title="Index" href="../genindex.html" />
     <link rel="search" title="Search" href="../search.html" />
     <link rel="next" title="Tutorials" href="../tutorials.html" />
-    <link rel="prev" title="Usage Principles" href="../usage_principles.html" /> 
+    <link rel="prev" title="Explainable AI at Sequence Level" href="usage_principles/xai.html" /> 
 </head>
 
 <body class="wy-body-for-nav"> 
@@ -360,7 +360,7 @@ <h3>Building the Docs<a class="headerlink" href="#building-the-docs" title="Perm
            </div>
           </div>
           <footer><div class="rst-footer-buttons" role="navigation" aria-label="Footer">
-        <a href="../usage_principles.html" class="btn btn-neutral float-left" title="Usage Principles" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left" aria-hidden="true"></span> Previous</a>
+        <a href="usage_principles/xai.html" class="btn btn-neutral float-left" title="Explainable AI at Sequence Level" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left" aria-hidden="true"></span> Previous</a>
         <a href="../tutorials.html" class="btn btn-neutral float-right" title="Tutorials" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right" aria-hidden="true"></span></a>
     </div>
 

docs/build/html/index/tables.html

@@ -114,13 +114,13 @@
 <h1>Tables<a class="headerlink" href="#tables" title="Permalink to this heading"></a></h1>
 <div class="contents local topic" id="contents">
 <ul class="simple">
-<li><p><a class="reference internal" href="#overview-table" id="id3">Overview Table</a></p></li>
-<li><p><a class="reference internal" href="#protein-benchmark-datasets" id="id4">Protein benchmark datasets</a></p></li>
-<li><p><a class="reference internal" href="#amino-acid-scale-datasets" id="id5">Amino acid scale datasets</a></p></li>
+<li><p><a class="reference internal" href="#overview-table" id="id1">Overview Table</a></p></li>
+<li><p><a class="reference internal" href="#protein-benchmark-datasets" id="id2">Protein benchmark datasets</a></p></li>
+<li><p><a class="reference internal" href="#amino-acid-scale-datasets" id="id3">Amino acid scale datasets</a></p></li>
 </ul>
 </div>
 <div class="section" id="overview-table">
-<h2><a class="toc-backref" href="#id3">Overview Table</a><a class="headerlink" href="#overview-table" title="Permalink to this heading"></a></h2>
+<h2><a class="toc-backref" href="#id1">Overview Table</a><a class="headerlink" href="#overview-table" title="Permalink to this heading"></a></h2>
 <p>All tables from the AAanalysis documentation are given here in chronological order of the project history.</p>
 <table class="colwidths-given docutils align-default" id="mapper">
 <colgroup>
@@ -147,17 +147,17 @@ <h2><a class="toc-backref" href="#id3">Overview Table</a><a class="headerlink" h
 </table>
 </div>
 <div class="section" id="protein-benchmark-datasets">
-<h2><a class="toc-backref" href="#id4">Protein benchmark datasets</a><a class="headerlink" href="#protein-benchmark-datasets" title="Permalink to this heading"></a></h2>
+<h2><a class="toc-backref" href="#id2">Protein benchmark datasets</a><a class="headerlink" href="#protein-benchmark-datasets" title="Permalink to this heading"></a></h2>
 <p>Three types of benchmark datasets are provided:</p>
 <ul class="simple">
 <li><p>Residue prediction (AA): Datasets used to predict residue (amino acid) specific properties.</p></li>
-<li><p>Domain prediction (DOM): Dataset used to predict domain specific properties</p></li>
-<li><p>Sequence prediction (SEQ): Datasets used to predict sequence specific properties</p></li>
+<li><p>Domain prediction (DOM): Dataset used to predict domain specific properties.</p></li>
+<li><p>Sequence prediction (SEQ): Datasets used to predict sequence specific properties.</p></li>
 </ul>
 <p>The classification of each dataset is indicated as first part of their name followed by an abbreviation for the
 specific dataset (e.g., ‘AA_LDR’, ‘DOM_GSEC’, ‘SEQ_AMYLO’). For some datasets, an additional version of it is provided
 for positive-unlabeled (PU) learning containing only positive (1) and unlabeled (2) data samples, as indicated by
-<a href="#id1"><span class="problematic" id="id2">*</span></a>dataset_name*_PU (e.g., ‘DOM_GSEC_PU’).</p>
+<em>dataset_name_PU</em> (e.g., ‘DOM_GSEC_PU’).</p>
 <table class="colwidths-given docutils align-default" id="overview-benchmarks">
 <colgroup>
 <col style="width: 10%" />
@@ -343,7 +343,7 @@ <h2><a class="toc-backref" href="#id4">Protein benchmark datasets</a><a class="h
 </table>
 </div>
 <div class="section" id="amino-acid-scale-datasets">
-<h2><a class="toc-backref" href="#id5">Amino acid scale datasets</a><a class="headerlink" href="#amino-acid-scale-datasets" title="Permalink to this heading"></a></h2>
+<h2><a class="toc-backref" href="#id3">Amino acid scale datasets</a><a class="headerlink" href="#amino-acid-scale-datasets" title="Permalink to this heading"></a></h2>
 <p>Different amino acid scale datasets are provided</p>
 <table class="colwidths-given docutils align-default" id="overview-scales">
 <colgroup>