Remove load_dataset docstring for trouble shooting

aaanalysis/data_loader/data_loader.py

@@ -13,7 +13,6 @@
 from typing import Optional, Literal
 import aaanalysis.utils as ut
 
-# TODO add amino acid window selection
 # Constants
 STR_AA_GAP = "-"
 LIST_CANONICAL_AA = ['N', 'A', 'I', 'V', 'K', 'Q', 'R', 'M', 'H', 'F', 'E', 'D', 'C', 'G', 'L', 'T', 'S', 'Y', 'W', 'P']
@@ -142,58 +141,16 @@ def _filter_scales(df_cat=None, unclassified_in=False, just_aaindex=False):
 
 
 # II Main Functions
-def load_dataset(name: str = "INFO",
-                 n: Optional[int] = None,
-                 random: bool = False,
-                 non_canonical_aa: Literal["remove", "keep", "gap"] = "remove",
-                 min_len: Optional[int] = None,
-                 max_len: Optional[int] = None,
-                 aa_window_size: Optional[int] = 9,
-                 ) -> DataFrame:
+def load_dataset(name="INFO",
+                 n=None,
+                 random=False,
+                 non_canonical_aa="remove",
+                 min_len=None,
+                 max_len=None,
+                 aa_window_size=9):
     """
     Load protein benchmarking datasets.
 
-    The benchmarks are categorized into amino acid ('AA'), domain ('DOM'), and sequence ('SEQ') level
-    datasets. Use default settings (``name='INFO'``) for an overview table. Detailed analysis is in [Breimann23a]_.
-
-    Parameters
-    ----------
-    name
-        Name of the dataset. See 'Dataset' column in overview table.
-    n
-        Number of proteins per class, selected by index. If None, the whole dataset will be returned.
-    random
-        If True, ``n`` random selected proteins per class will be chosen.
-    non_canonical_aa
-        Options for modifying non-canonical amino acids:
-
-        - 'remove': Remove sequences containing non-canonical amino acids.
-
-        - 'keep': Dont remove sequences containing non-canonical amino acids.
-
-        - 'gap': Non-canonical amino acids are replaced by gap symbol ('X').
-
-    min_len
-        Minimum length of sequences for filtering, disabled by default.
-    max_len
-        Maximum length of sequences for filtering, disabled by default.
-    aa_window_size
-        Length of amino acid window, only used for amino acid dataset level (``name='AA_'``) and if ``n`` given.
-
-    Returns
-    -------
-    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
-    --------
-    >>> import aaanalysis as aa
-    >>> df_seq = aa.load_dataset(name="SEQ_AMYLO", n=100)
 
     """
     check_name_of_dataset(name=name, folder_in=FOLDER_BENCHMARKS)

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

@@ -125,47 +125,8 @@
 <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-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>
+<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#L144-L195"><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>
-<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>name</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.11)"><code class="xref py py-class docutils literal notranslate"><span class="pre">str</span></code></a>) – Name of the dataset. See ‘Dataset’ column in overview table.</p></li>
-<li><p><strong>n</strong> (<a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Optional" title="(in Python v3.11)"><code class="xref py py-data docutils literal notranslate"><span class="pre">Optional</span></code></a>[<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.11)"><code class="xref py py-class docutils literal notranslate"><span class="pre">int</span></code></a>]) – Number of proteins per class, selected by index. If None, the whole dataset will be returned.</p></li>
-<li><p><strong>random</strong> (<a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.11)"><code class="xref py py-class docutils literal notranslate"><span class="pre">bool</span></code></a>) – If True, <code class="docutils literal notranslate"><span class="pre">n</span></code> random selected proteins per class will be chosen.</p></li>
-<li><p><strong>non_canonical_aa</strong> (<a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Literal" title="(in Python v3.11)"><code class="xref py py-data docutils literal notranslate"><span class="pre">Literal</span></code></a>[‘remove’, ‘keep’, ‘gap’]) – <p>Options for modifying non-canonical amino acids:</p>
-<ul>
-<li><p>’remove’: Remove sequences containing non-canonical amino acids.</p></li>
-<li><p>’keep’: Dont remove sequences containing non-canonical amino acids.</p></li>
-<li><p>’gap’: Non-canonical amino acids are replaced by gap symbol (‘X’).</p></li>
-</ul>
-</p></li>
-<li><p><strong>min_len</strong> (<a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Optional" title="(in Python v3.11)"><code class="xref py py-data docutils literal notranslate"><span class="pre">Optional</span></code></a>[<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.11)"><code class="xref py py-class docutils literal notranslate"><span class="pre">int</span></code></a>]) – Minimum length of sequences for filtering, disabled by default.</p></li>
-<li><p><strong>max_len</strong> (<a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Optional" title="(in Python v3.11)"><code class="xref py py-data docutils literal notranslate"><span class="pre">Optional</span></code></a>[<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.11)"><code class="xref py py-class docutils literal notranslate"><span class="pre">int</span></code></a>]) – Maximum length of sequences for filtering, disabled by default.</p></li>
-<li><p><strong>aa_window_size</strong> (<a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Optional" title="(in Python v3.11)"><code class="xref py py-data docutils literal notranslate"><span class="pre">Optional</span></code></a>[<a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.11)"><code class="xref py py-class docutils literal notranslate"><span class="pre">int</span></code></a>]) – Length of amino acid window, only used for amino acid dataset level (<code class="docutils literal notranslate"><span class="pre">name='AA_'</span></code>) and if <code class="docutils literal notranslate"><span class="pre">n</span></code> given.</p></li>
-</ul>
-</dd>
-<dt class="field-even">Returns<span class="colon">:</span></dt>
-<dd class="field-even"><p>Dataframe (df_seq) containing the selected sequence dataset.</p>
-</dd>
-<dt class="field-odd">Return type<span class="colon">:</span></dt>
-<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>
-<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="s2">&quot;SEQ_AMYLO&quot;</span><span class="p">,</span> <span class="n">n</span><span class="o">=</span><span class="mi">100</span><span class="p">)</span>
-</pre></div>
-</div>
-</div>
 </dd></dl>
 
 </section>

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

@@ -125,7 +125,7 @@
 <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#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>
+<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#L199-L233"><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/requirements_docs.txt

@@ -1,5 +1,5 @@
 # Adjust these changes to the pyproject.toml
-sphinx>=5.3.0   # Newest version not campatible with myst_nb
+sphinx>=5.0,<7.0   # Newest version not campatible with myst_nb
 sphinx_rtd_theme>=1.3.0 # 1.1.1 # 0.5.2
 #sphinx_book_theme>=1.0.1
 #pydata_sphinx_theme>=0.13.3

pyproject.toml

@@ -58,7 +58,7 @@ threadpoolctl = "^3.1.0"
 
 #... (keep the other dependencies as they are)
 [tool.poetry.dev-dependencies]
-sphinx = "^5.3"
+sphinx = ">=5.0,<7.0"
 sphinx_rtd_theme = "^1.3.0"
 #sphinx_book_theme = "^1.0.1"
 #pydata_sphinx_theme = "^0.13.3"