Add reference in data_loader

breimanntools · Sep 19, 2023 · 3507d78 · 3507d78
1 parent 736f0d5
commit 3507d78
Show file tree

Hide file tree

Showing 7 changed files with 40 additions and 41 deletions.
diff --git a/aaanalysis/data_loader/__pycache__/data_loader.cpython-39.pyc b/aaanalysis/data_loader/__pycache__/data_loader.cpython-39.pyc
diff --git a/aaanalysis/data_loader/data_loader.py b/aaanalysis/data_loader/data_loader.py
@@ -9,12 +9,14 @@
 from typing import Optional, Literal
 import aaanalysis.utils as ut
 
-
-# I Helper Functions
+# 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']
 NAME_SCALE_SETS_BASE = [ut.STR_SCALES, ut.STR_SCALES_RAW]
 NAMES_SCALE_SETS = NAME_SCALE_SETS_BASE + [ut.STR_SCALE_CAT, ut.STR_SCALES_PC, ut.STR_TOP60, ut.STR_TOP60_EVAL]
+FOLDER_BENCHMARKS = folder_in = ut.FOLDER_DATA + "benchmarks" + ut.SEP
+
+# I Helper Functions
 
 
 # II Main Functions
@@ -61,9 +63,8 @@ def load_dataset(name: str = "INFO",
     """
     Load protein benchmarking datasets.
 
-    The benchmarks are distinguished into residue/amino acid ('AA'), domain ('DOM'), and sequence ('SEQ') level
-    datasets. An overview table can be retrieved by using default setting (name='INFO'). A through analysis of
-    the residue and sequence datasets can be found in [Breimann23a].
+    The benchmarks are  distinguished into amino acid ('AA'), domain ('DOM'), and sequence ('SEQ') level
+    datasets. Use default settings (name='INFO') of an overview table. Detailed analysis is in :cite:`Breimann23a`.
 
     Parameters
     ----------
@@ -74,16 +75,16 @@ def load_dataset(name: str = "INFO",
     non_canonical_aa
         Options for modifying non-canonical amino acids:
 
-        - 'remove': Sequences containing non-canonical amino acids are removed.
+        - 'remove': Remove sequences containing non-canonical amino acids.
 
-        - 'keep': Sequences containing non-canonical amino acids are not removed.
+        - 'keep': Do not remove sequences containing non-canonical amino acids.
 
-        - 'gap': Sequences are kept and modified by replacing non-canonical amino acids by gap symbol ('X').
+        - 'gap': Non-canonical amino acids are replaced by gap symbol ('X').
 
     min_len
-        Minimum length of sequences for filtering. None to disable
+        Minimum length of sequences for filtering (disabled by default).
     max_len
-        Maximum length of sequences for filtering. None to disable
+        Maximum length of sequences for filtering (disabled by default).
 
     Returns
     -------
@@ -92,17 +93,16 @@ def load_dataset(name: str = "INFO",
 
     Notes
     -----
-    See further information on the benchmark datasets in
+    See further information on the benchmark datasets in ref table.
 
     """
     ut.check_non_negative_number(name="n", val=n, accept_none=True)
     ut.check_non_negative_number(name="min_len", val=min_len, accept_none=True)
-    folder_in = ut.FOLDER_DATA + "benchmarks" + ut.SEP
-    check_name_of_dataset(name=name, folder_in=folder_in)
+    check_name_of_dataset(name=name, folder_in=FOLDER_BENCHMARKS)
     # Load overview table
     if name == "INFO":
-        return pd.read_excel(folder_in + "INFO_benchmarks.xlsx")
-    df = pd.read_csv(folder_in + name + ".tsv", sep="\t")
+        return pd.read_excel(FOLDER_BENCHMARKS + "INFO_benchmarks.xlsx")
+    df = pd.read_csv(FOLDER_BENCHMARKS + name + ".tsv", sep="\t")
     # Filter Rdata
     if min_len is not None:
         mask = [len(x) >= min_len for x in df[ut.COL_SEQ]]

diff --git a/docs/build/doctrees/environment.pickle b/docs/build/doctrees/environment.pickle
diff --git a/docs/build/doctrees/generated/aaanalysis.load_dataset.doctree b/docs/build/doctrees/generated/aaanalysis.load_dataset.doctree
diff --git a/docs/build/html/_modules/aaanalysis/data_loader/data_loader.html b/docs/build/html/_modules/aaanalysis/data_loader/data_loader.html
@@ -104,12 +104,14 @@ <h1>Source code for aaanalysis.data_loader.data_loader</h1><div class="highlight
 <span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Optional</span><span class="p">,</span> <span class="n">Literal</span>
 <span class="kn">import</span> <span class="nn">aaanalysis.utils</span> <span class="k">as</span> <span class="nn">ut</span>
 
-
-<span class="c1"># I Helper Functions</span>
+<span class="c1"># Constants</span>
 <span class="n">STR_AA_GAP</span> <span class="o">=</span> <span class="s2">&quot;-&quot;</span>
 <span class="n">LIST_CANONICAL_AA</span> <span class="o">=</span> <span class="p">[</span><span class="s1">&#39;N&#39;</span><span class="p">,</span> <span class="s1">&#39;A&#39;</span><span class="p">,</span> <span class="s1">&#39;I&#39;</span><span class="p">,</span> <span class="s1">&#39;V&#39;</span><span class="p">,</span> <span class="s1">&#39;K&#39;</span><span class="p">,</span> <span class="s1">&#39;Q&#39;</span><span class="p">,</span> <span class="s1">&#39;R&#39;</span><span class="p">,</span> <span class="s1">&#39;M&#39;</span><span class="p">,</span> <span class="s1">&#39;H&#39;</span><span class="p">,</span> <span class="s1">&#39;F&#39;</span><span class="p">,</span> <span class="s1">&#39;E&#39;</span><span class="p">,</span> <span class="s1">&#39;D&#39;</span><span class="p">,</span> <span class="s1">&#39;C&#39;</span><span class="p">,</span> <span class="s1">&#39;G&#39;</span><span class="p">,</span> <span class="s1">&#39;L&#39;</span><span class="p">,</span> <span class="s1">&#39;T&#39;</span><span class="p">,</span> <span class="s1">&#39;S&#39;</span><span class="p">,</span> <span class="s1">&#39;Y&#39;</span><span class="p">,</span> <span class="s1">&#39;W&#39;</span><span class="p">,</span> <span class="s1">&#39;P&#39;</span><span class="p">]</span>
 <span class="n">NAME_SCALE_SETS_BASE</span> <span class="o">=</span> <span class="p">[</span><span class="n">ut</span><span class="o">.</span><span class="n">STR_SCALES</span><span class="p">,</span> <span class="n">ut</span><span class="o">.</span><span class="n">STR_SCALES_RAW</span><span class="p">]</span>
 <span class="n">NAMES_SCALE_SETS</span> <span class="o">=</span> <span class="n">NAME_SCALE_SETS_BASE</span> <span class="o">+</span> <span class="p">[</span><span class="n">ut</span><span class="o">.</span><span class="n">STR_SCALE_CAT</span><span class="p">,</span> <span class="n">ut</span><span class="o">.</span><span class="n">STR_SCALES_PC</span><span class="p">,</span> <span class="n">ut</span><span class="o">.</span><span class="n">STR_TOP60</span><span class="p">,</span> <span class="n">ut</span><span class="o">.</span><span class="n">STR_TOP60_EVAL</span><span class="p">]</span>
+<span class="n">FOLDER_BENCHMARKS</span> <span class="o">=</span> <span class="n">folder_in</span> <span class="o">=</span> <span class="n">ut</span><span class="o">.</span><span class="n">FOLDER_DATA</span> <span class="o">+</span> <span class="s2">&quot;benchmarks&quot;</span> <span class="o">+</span> <span class="n">ut</span><span class="o">.</span><span class="n">SEP</span>
+
+<span class="c1"># I Helper Functions</span>
 
 
 <span class="c1"># II Main Functions</span>
@@ -156,9 +158,8 @@ <h1>Source code for aaanalysis.data_loader.data_loader</h1><div class="highlight
 <span class="w">    </span><span class="sd">&quot;&quot;&quot;</span>
 <span class="sd">    Load protein benchmarking datasets.</span>
 
-<span class="sd">    The benchmarks are distinguished into residue/amino acid (&#39;AA&#39;), domain (&#39;DOM&#39;), and sequence (&#39;SEQ&#39;) level</span>
-<span class="sd">    datasets. An overview table can be retrieved by using default setting (name=&#39;INFO&#39;). A through analysis of</span>
-<span class="sd">    the residue and sequence datasets can be found in [Breimann23a].</span>
+<span class="sd">    The benchmarks are  distinguished into amino acid (&#39;AA&#39;), domain (&#39;DOM&#39;), and sequence (&#39;SEQ&#39;) level</span>
+<span class="sd">    datasets. Use default settings (name=&#39;INFO&#39;) of an overview table. Detailed analysis is in :cite:`Breimann23a`.</span>
 
 <span class="sd">    Parameters</span>
 <span class="sd">    ----------</span>
@@ -169,16 +170,16 @@ <h1>Source code for aaanalysis.data_loader.data_loader</h1><div class="highlight
 <span class="sd">    non_canonical_aa</span>
 <span class="sd">        Options for modifying non-canonical amino acids:</span>
 
-<span class="sd">        - &#39;remove&#39;: Sequences containing non-canonical amino acids are removed.</span>
+<span class="sd">        - &#39;remove&#39;: Remove sequences containing non-canonical amino acids.</span>
 
-<span class="sd">        - &#39;keep&#39;: Sequences containing non-canonical amino acids are not removed.</span>
+<span class="sd">        - &#39;keep&#39;: Do not remove sequences containing non-canonical amino acids.</span>
 
-<span class="sd">        - &#39;gap&#39;: Sequences are kept and modified by replacing non-canonical amino acids by gap symbol (&#39;X&#39;).</span>
+<span class="sd">        - &#39;gap&#39;: Non-canonical amino acids are replaced by gap symbol (&#39;X&#39;).</span>
 
 <span class="sd">    min_len</span>
-<span class="sd">        Minimum length of sequences for filtering. None to disable</span>
+<span class="sd">        Minimum length of sequences for filtering (disabled by default).</span>
 <span class="sd">    max_len</span>
-<span class="sd">        Maximum length of sequences for filtering. None to disable</span>
+<span class="sd">        Maximum length of sequences for filtering (disabled by default).</span>
 
 <span class="sd">    Returns</span>
 <span class="sd">    -------</span>
@@ -187,17 +188,16 @@ <h1>Source code for aaanalysis.data_loader.data_loader</h1><div class="highlight
 
 <span class="sd">    Notes</span>
 <span class="sd">    -----</span>
-<span class="sd">    See further information on the benchmark datasets in</span>
+<span class="sd">    See further information on the benchmark datasets in ref table.</span>
 
 <span class="sd">    &quot;&quot;&quot;</span>
     <span class="n">ut</span><span class="o">.</span><span class="n">check_non_negative_number</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s2">&quot;n&quot;</span><span class="p">,</span> <span class="n">val</span><span class="o">=</span><span class="n">n</span><span class="p">,</span> <span class="n">accept_none</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
     <span class="n">ut</span><span class="o">.</span><span class="n">check_non_negative_number</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s2">&quot;min_len&quot;</span><span class="p">,</span> <span class="n">val</span><span class="o">=</span><span class="n">min_len</span><span class="p">,</span> <span class="n">accept_none</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
-    <span class="n">folder_in</span> <span class="o">=</span> <span class="n">ut</span><span class="o">.</span><span class="n">FOLDER_DATA</span> <span class="o">+</span> <span class="s2">&quot;benchmarks&quot;</span> <span class="o">+</span> <span class="n">ut</span><span class="o">.</span><span class="n">SEP</span>
-    <span class="n">check_name_of_dataset</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="n">name</span><span class="p">,</span> <span class="n">folder_in</span><span class="o">=</span><span class="n">folder_in</span><span class="p">)</span>
+    <span class="n">check_name_of_dataset</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="n">name</span><span class="p">,</span> <span class="n">folder_in</span><span class="o">=</span><span class="n">FOLDER_BENCHMARKS</span><span class="p">)</span>
     <span class="c1"># Load overview table</span>
     <span class="k">if</span> <span class="n">name</span> <span class="o">==</span> <span class="s2">&quot;INFO&quot;</span><span class="p">:</span>
-        <span class="k">return</span> <span class="n">pd</span><span class="o">.</span><span class="n">read_excel</span><span class="p">(</span><span class="n">folder_in</span> <span class="o">+</span> <span class="s2">&quot;INFO_benchmarks.xlsx&quot;</span><span class="p">)</span>
-    <span class="n">df</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">read_csv</span><span class="p">(</span><span class="n">folder_in</span> <span class="o">+</span> <span class="n">name</span> <span class="o">+</span> <span class="s2">&quot;.tsv&quot;</span><span class="p">,</span> <span class="n">sep</span><span class="o">=</span><span class="s2">&quot;</span><span class="se">\t</span><span class="s2">&quot;</span><span class="p">)</span>
+        <span class="k">return</span> <span class="n">pd</span><span class="o">.</span><span class="n">read_excel</span><span class="p">(</span><span class="n">FOLDER_BENCHMARKS</span> <span class="o">+</span> <span class="s2">&quot;INFO_benchmarks.xlsx&quot;</span><span class="p">)</span>
+    <span class="n">df</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">read_csv</span><span class="p">(</span><span class="n">FOLDER_BENCHMARKS</span> <span class="o">+</span> <span class="n">name</span> <span class="o">+</span> <span class="s2">&quot;.tsv&quot;</span><span class="p">,</span> <span class="n">sep</span><span class="o">=</span><span class="s2">&quot;</span><span class="se">\t</span><span class="s2">&quot;</span><span class="p">)</span>
     <span class="c1"># Filter Rdata</span>
     <span class="k">if</span> <span class="n">min_len</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
         <span class="n">mask</span> <span class="o">=</span> <span class="p">[</span><span class="nb">len</span><span class="p">(</span><span class="n">x</span><span class="p">)</span> <span class="o">&gt;=</span> <span class="n">min_len</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">df</span><span class="p">[</span><span class="n">ut</span><span class="o">.</span><span class="n">COL_SEQ</span><span class="p">]]</span>