Adjust CONTRIBUTING.rst

CONTRIBUTING.rst

@@ -368,7 +368,9 @@ To enhance the public interface or signature of your functions and classes, empl
 
 Testing
 -------
-For generating efficient tests with extensive coverage and considering edge cases, utilize the prompt template below:
+Generate efficient tests with extensive coverage and considering edge cases using the prompt template below,
+utilizing `our <https://github.com/breimanntools/aaanalysis/blob/master/tests/unit/data_loader_tests/test_load_dataset.py>`_
+or a custom  testing template:
 
 .. code-block:: none
 

aaanalysis/aaclust/aaclust_plot.py

@@ -1,5 +1,5 @@
 """
-This is a script for ...
+This is a script for the plotting class of AAclust.
 """
 import time
 import pandas as pd
@@ -14,17 +14,16 @@
 
 
 # II Main Functions
+class AAclustPlot:
+    """"""
+    def __int__(self):
+        pass
 
-# III Test/Caller Functions
+    @staticmethod
+    def eval():
+        """Plot eval output of dPULearn (n per component)"""
 
+    @staticmethod
+    def eval_cat(df_seq=None):
+        """Plot donut plot for proportion of categories"""
 
-# IV Main
-def main():
-    t0 = time.time()
-
-    t1 = time.time()
-    print("Time:", t1 - t0)
-
-
-if __name__ == "__main__":
-    main()

aaanalysis/cpp/cpp.py

@@ -315,7 +315,13 @@ def run(self, labels=None, parametric=False, n_filter=100,
             print(f"4. CPP returns df with {len(df_feat)} unique features including general information and statistics")
         return df_feat
 
+    # TODO get evaluation for any dataset for compelete
+    """
     @staticmethod
     def eval(df_feat=None, features=None):
-        """Get evaluation for provided dataset"""
-        # TODO get evaluation for any dataset for compelete
+    """
+    # TODO filter based on correlation of features
+    """
+    @staticmethod
+    def filter_corr(df_parts=None, df_feat=None, max_corr=None):
+    """

aaanalysis/cpp/cpp_plot.py

@@ -16,7 +16,7 @@
 
 # TODO simplify checks & interface (end-to-end check with tests & docu)
 # TODO plot_functions test & refactor (end-to-end)
-
+# TODO use decorator for redudant signatures (https://github.com/scverse/scanpy/blob/master/scanpy/preprocessing/_qc.py)
 
 # I Helper Functions
 def check_value_type(val_type=None, count_in=True):

aaanalysis/data_loader/data_loader.py

@@ -121,13 +121,13 @@ def post_check_df_seq(df_seq=None, n=None, name=None, n_match=True):
 
 
 # Helper functions for load_scales
-def _filter_scales(df_cat=None, unclassified_in=False, just_aaindex=False):
+def _filter_scales(df_cat=None, unclassified_out=False, just_aaindex=False):
     """Filter scales for unclassified and aaindex scales"""
     list_ids_not_in_aaindex = [x for x in df_cat[ut.COL_SCALE_ID] if "LINS" in x or "KOEH" in x]
     list_ids_unclassified = [x for x, cat, sub_cat in zip(df_cat[ut.COL_SCALE_ID], df_cat[ut.COL_CAT], df_cat[ut.COL_SUBCAT])
                              if "Unclassified" in sub_cat or cat == "Others"]
     list_ids_to_exclude = []
-    if not unclassified_in:
+    if unclassified_out:
         list_ids_to_exclude.extend(list_ids_unclassified)
     if just_aaindex:
         list_ids_to_exclude.extend(list_ids_not_in_aaindex)
@@ -269,7 +269,7 @@ def load_dataset(name: str = "INFO",
 # Load scales
 def load_scales(name: str = "scales",
                 just_aaindex: bool = False,
-                unclassified_in: bool = True,
+                unclassified_out: bool = False,
                 top60_n: Optional[int] = None
                 ) -> DataFrame:
     """
@@ -289,8 +289,8 @@ def load_scales(name: str = "scales",
         Name of the loaded dataset: 'scales', 'scales_raw', 'scales_cat', 'scales_pc', 'top60', 'top60_eval'.
     just_aaindex
         If True, returns only scales from AAindex. Relevant only for 'scales', 'scales_raw', or 'scales_cat'.
-    unclassified_in
-        Determines inclusion of unclassified scales. Relevant only for 'scales', 'scales_raw', or 'scales_cat'.
+    unclassified_out
+        Determines exclusion of unclassified scales. Relevant only for 'scales', 'scales_raw', or 'scales_cat'.
     top60_n
          Select the n-th scale set from top60 sets and return it for 'scales', 'scales_raw', or 'scales_cat'.
 
@@ -326,7 +326,7 @@ def load_scales(name: str = "scales",
     """
     check_name_of_scale(name=name)
     ut.check_bool(name="just_aaindex", val=just_aaindex)
-    ut.check_bool(name="unclassified_in", val=unclassified_in)
+    ut.check_bool(name="unclassified_in", val=unclassified_out)
     check_top60_n(name=name, top60_n=top60_n)
 
     # Load and filter top60 scales
@@ -344,7 +344,7 @@ def load_scales(name: str = "scales",
             raise ValueError(f"Wrong 'name' ('{name}') for 'top60_n")
 
     # Load unfiltered data
-    if unclassified_in and not just_aaindex:
+    if not unclassified_out and not just_aaindex:
         if name == ut.STR_SCALE_CAT:
             df_cat = ut.read_excel_cached(ut.FOLDER_DATA + f"{ut.STR_SCALE_CAT}.xlsx")
             return df_cat
@@ -353,7 +353,7 @@ def load_scales(name: str = "scales",
 
     # Load and filter scale categories
     df_cat = ut.read_excel_cached(ut.FOLDER_DATA + f"{ut.STR_SCALE_CAT}.xlsx")
-    df_cat = _filter_scales(df_cat=df_cat, unclassified_in=unclassified_in, just_aaindex=just_aaindex)
+    df_cat = _filter_scales(df_cat=df_cat, unclassified_out=unclassified_out, just_aaindex=just_aaindex)
     if name == ut.STR_SCALE_CAT:
         return df_cat.reset_index(drop=True)
 

aaanalysis/dpulearn/dpulearn_plot.py

@@ -1,5 +1,5 @@
 """
-This is a script for ...
+This is a script for the plotting class of dPULearn.
 """
 import time
 import pandas as pd
@@ -14,18 +14,18 @@
 
 
 # II Main Functions
+class dPULearnPlot:
+    """"""
+    def __int__(self):
+        pass
 
+    @staticmethod
+    def eval():
+        """Plot eval output of dPULearn (n per component)"""
 
-# III Test/Caller Functions
+    @staticmethod
+    def components(df_seq=None, x="PC1", y="PC2", show_mean_x=False, show_mean_y=False):
+        """Plot PC map for PC analysis """
 
 
-# IV Main
-def main():
-    t0 = time.time()
 
-    t1 = time.time()
-    print("Time:", t1 - t0)
-
-
-if __name__ == "__main__":
-    main()

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

@@ -368,7 +368,9 @@ To enhance the public interface or signature of your functions and classes, empl
 
 Testing
 -------
-For generating efficient tests with extensive coverage and considering edge cases, utilize the prompt template below:
+Generate efficient tests with extensive coverage and considering edge cases using the prompt template below,
+utilizing `our <https://github.com/breimanntools/aaanalysis/blob/master/tests/unit/data_loader_tests/test_load_dataset.py>`_
+or a custom  testing template:
 
 .. code-block:: none
 

docs/build/html/generated/aaanalysis.CPP.html

@@ -128,7 +128,7 @@
 <h1>aaanalysis.CPP<a class="headerlink" href="#aaanalysis-cpp" title="Permalink to this heading"></a></h1>
 <dl class="py class">
 <dt class="sig sig-object py" id="aaanalysis.CPP">
-<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">aaanalysis.</span></span><span class="sig-name descname"><span class="pre">CPP</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">df_scales</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">df_cat</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">df_parts</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">split_kws</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">accept_gaps</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">verbose</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/cpp/cpp.py#L32-L321"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#aaanalysis.CPP" title="Permalink to this definition"></a></dt>
+<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">aaanalysis.</span></span><span class="sig-name descname"><span class="pre">CPP</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">df_scales</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">df_cat</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">df_parts</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">split_kws</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">accept_gaps</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">verbose</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/cpp/cpp.py#L32-L327"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#aaanalysis.CPP" title="Permalink to this definition"></a></dt>
 <dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">Tool</span></code></p>
 <p>Create and filter features that are most discriminant between two sets of sequences.</p>
 <dl class="field-list simple">
@@ -158,8 +158,8 @@ <h1>aaanalysis.CPP<a class="headerlink" href="#aaanalysis-cpp" title="Permalink
 <tr class="row-odd"><td><p><a class="reference internal" href="#aaanalysis.CPP.__init__" title="aaanalysis.CPP.__init__"><code class="xref py py-obj docutils literal notranslate"><span class="pre">__init__</span></code></a>([df_scales, df_cat, df_parts, ...])</p></td>
 <td><p></p></td>
 </tr>
-<tr class="row-even"><td><p><a class="reference internal" href="#aaanalysis.CPP.eval" title="aaanalysis.CPP.eval"><code class="xref py py-obj docutils literal notranslate"><span class="pre">eval</span></code></a>([df_feat, features])</p></td>
-<td><p>Get evaluation for provided dataset</p></td>
+<tr class="row-even"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">eval</span></code>()</p></td>
+<td><p>Evaluate the output generated by the tool.</p></td>
 </tr>
 <tr class="row-odd"><td><p><a class="reference internal" href="#aaanalysis.CPP.run" title="aaanalysis.CPP.run"><code class="xref py py-obj docutils literal notranslate"><span class="pre">run</span></code></a>([labels, parametric, n_filter, tmd_len, ...])</p></td>
 <td><p>Perform CPP pipeline by creation and two-step filtering of features.</p></td>
@@ -221,12 +221,6 @@ <h1>aaanalysis.CPP<a class="headerlink" href="#aaanalysis-cpp" title="Permalink
 </div>
 </dd></dl>
 
-<dl class="py method">
-<dt class="sig sig-object py" id="aaanalysis.CPP.eval">
-<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">eval</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">df_feat</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">features</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 external" href="https://github.com/breimanntools/aaanalysis/tree/master/aaanalysis/cpp/cpp.py#L318-L321"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#aaanalysis.CPP.eval" title="Permalink to this definition"></a></dt>
-<dd><p>Get evaluation for provided dataset</p>
-</dd></dl>
-
 </dd></dl>
 
 </section>

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

@@ -126,7 +126,7 @@
 <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>, <em class="sig-param"><span class="n"><span class="pre">top60_n</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 external" href="https://github.com/breimanntools/aaanalysis/tree/master/aaanalysis/data_loader/data_loader.py#L270-L365"><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_out</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">top60_n</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 external" href="https://github.com/breimanntools/aaanalysis/tree/master/aaanalysis/data_loader/data_loader.py#L270-L365"><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 classifications (AAontology), or scale evaluations.</p>
 <p>The amino acid scales (<code class="docutils literal notranslate"><span class="pre">name='scales_raw'</span></code>) encompass all scales from AAindex (<a class="reference internal" href="../index/references.html#kawashima08" id="id1"><span>[Kawashima08]</span></a>) along with two
 additional data sources. These scales were min-max normalized (<code class="docutils literal notranslate"><span class="pre">name='scales'</span></code>) and organized in a two-level
@@ -140,7 +140,7 @@ <h1>aaanalysis.load_scales<a class="headerlink" href="#aaanalysis-load-scales" t
 <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 loaded dataset: ‘scales’, ‘scales_raw’, ‘scales_cat’, ‘scales_pc’, ‘top60’, ‘top60_eval’.</p></li>
 <li><p><strong>just_aaindex</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, returns only scales from AAindex. Relevant only for ‘scales’, ‘scales_raw’, or ‘scales_cat’.</p></li>
-<li><p><strong>unclassified_in</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>) – Determines inclusion of unclassified scales. Relevant only for ‘scales’, ‘scales_raw’, or ‘scales_cat’.</p></li>
+<li><p><strong>unclassified_out</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>) – Determines exclusion of unclassified scales. Relevant only for ‘scales’, ‘scales_raw’, or ‘scales_cat’.</p></li>
 <li><p><strong>top60_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>]) – Select the n-th scale set from top60 sets and return it for ‘scales’, ‘scales_raw’, or ‘scales_cat’.</p></li>
 </ul>
 </dd>

docs/build/html/genindex.html

@@ -186,8 +186,6 @@ <h2 id="E">E</h2>
       <li><a href="generated/aaanalysis.AAclust.html#aaanalysis.AAclust.eval">eval() (aaanalysis.AAclust method)</a>
 
       <ul>
-        <li><a href="generated/aaanalysis.CPP.html#aaanalysis.CPP.eval">(aaanalysis.CPP static method)</a>
-</li>
         <li><a href="generated/aaanalysis.dPULearn.html#aaanalysis.dPULearn.eval">(aaanalysis.dPULearn method)</a>
 </li>
       </ul></li>

docs/build/html/index/CONTRIBUTING_COPY.html

@@ -478,7 +478,9 @@ <h3>Interface optimization<a class="headerlink" href="#interface-optimization" t
 </section>
 <section id="testing">
 <h3>Testing<a class="headerlink" href="#testing" title="Permalink to this heading"></a></h3>
-<p>For generating efficient tests with extensive coverage and considering edge cases, utilize the prompt template below:</p>
+<p>Generate efficient tests with extensive coverage and considering edge cases using the prompt template below,
+utilizing <a class="reference external" href="https://github.com/breimanntools/aaanalysis/blob/master/tests/unit/data_loader_tests/test_load_dataset.py">our</a>
+or a custom  testing template:</p>
 <div class="highlight-none notranslate"><div class="highlight"><pre><span></span>&quot;
 Generate test functions for a given TARGET FUNCTION using the style of the provided TESTING TEMPLATE.