Change INFO to Overview inf load_dataset

aaanalysis/data_handling/_load_dataset.py

@@ -19,16 +19,17 @@
 
 # I Helper Functions
 # Check functions
-def check_name_of_dataset(name="INFO", folder_in=None):
+def check_name_of_dataset(name="Overview", folder_in=None):
     """"""
-    if name == "INFO":
+    if name == "Overview":
         return
-    list_datasets = [x.split(".")[0] for x in os.listdir(folder_in) if "." in x]
+    list_datasets = [x.split(".")[0] for x in os.listdir(folder_in)
+                     if "." in x and not x.startswith(".")]
     if name not in list_datasets:
         list_aa = [x for x in list_datasets if 'AA' in x]
         list_seq = [x for x in list_datasets if 'SEQ' in x]
         list_dom = [x for x in list_datasets if 'DOM' in x]
-        raise ValueError(f"'name' ({name}) is not valid."
+        raise ValueError(f"'name' ({name}) is not valid. Chose one of the following:"
                          f"\n Amino acid datasets: {list_aa}"
                          f"\n Sequence datasets: {list_seq}"
                          f"\n Domain datasets: {list_dom}")
@@ -119,7 +120,7 @@ def _get_aa_window(df_seq=None, aa_window_size=9):
 
 
 # II Main Functions
-def load_dataset(name: str = "INFO",
+def load_dataset(name: str = "Overview",
                  n: Optional[int] = None,
                  random: bool = False,
                  non_canonical_aa: Literal["remove", "keep", "gap"] = "remove",
@@ -131,7 +132,7 @@ def load_dataset(name: str = "INFO",
     Loads protein benchmarking datasets.
 
     The benchmarks are categorized into amino acid ('AA'), domain ('DOM'), and sequence ('SEQ') level datasets.
-    By default, an overview table is provided (``name='INFO'``). For in-depth details, refer to [Breimann23a]_.
+    By default, an overview table is provided (``name='Overview'``). For in-depth details, refer to [Breimann23a]_.
 
     Parameters
     ----------
@@ -159,7 +160,7 @@ def load_dataset(name: str = "INFO",
     -------
     pandas.DataFrame
         A DataFrame of either the selected sequence dataset (``df_seq``) or
-        general info on all benchmark datasets (``df_info``).
+        overview on all benchmark datasets (``df_overview``).
 
     Notes
     -----
@@ -188,8 +189,8 @@ def load_dataset(name: str = "INFO",
     check_min_max_val(min_len=min_len, max_len=max_len)
     check_aa_window_size(aa_window_size=aa_window_size)
     # Load overview table
-    if name == "INFO":
-        return ut.read_excel_cached(FOLDER_BENCHMARKS + "INFO_benchmarks.xlsx")
+    if name == "Overview":
+        return ut.read_excel_cached(FOLDER_BENCHMARKS + "Overview.xlsx")
     df = ut.read_csv_cached(FOLDER_BENCHMARKS + name + ".tsv", sep="\t")
     # Filter data
     if min_len is not None:

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

@@ -126,10 +126,10 @@
 <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_handling/_load_dataset.py#L122-L224"><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">'Overview'</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_handling/_load_dataset.py#L123-L225"><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>Loads protein benchmarking datasets.</p>
 <p>The benchmarks are categorized into amino acid (‘AA’), domain (‘DOM’), and sequence (‘SEQ’) level datasets.
-By default, an overview table is provided (<code class="docutils literal notranslate"><span class="pre">name='INFO'</span></code>). For in-depth details, refer to <a class="reference internal" href="../index/references.html#breimann23a" id="id1"><span>[Breimann23a]</span></a>.</p>
+By default, an overview table is provided (<code class="docutils literal notranslate"><span class="pre">name='Overview'</span></code>). For in-depth details, refer to <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">
@@ -150,7 +150,7 @@ <h1>aaanalysis.load_dataset<a class="headerlink" href="#aaanalysis-load-dataset"
 </dd>
 <dt class="field-even">Returns<span class="colon">:</span></dt>
 <dd class="field-even"><p>A DataFrame of either the selected sequence dataset (<code class="docutils literal notranslate"><span class="pre">df_seq</span></code>) or
-general info on all benchmark datasets (<code class="docutils literal notranslate"><span class="pre">df_info</span></code>).</p>
+overview on all benchmark datasets (<code class="docutils literal notranslate"><span class="pre">df_overview</span></code>).</p>
 </dd>
 <dt class="field-odd">Return type<span class="colon">:</span></dt>
 <dd class="field-odd"><p><a class="reference external" href="https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.html#pandas.DataFrame" title="(in pandas v2.1.1)">pandas.DataFrame</a></p>