Prepare for 3.4.4 release.

WORC/doc/_build/html/_modules/WORC/featureprocessing/Relief.html

@@ -165,7 +165,7 @@
   <h1>Source code for WORC.featureprocessing.Relief</h1><div class="highlight"><pre>
 <span></span><span class="ch">#!/usr/bin/env python</span>
 
-<span class="c1"># Copyright 2016-2019 Biomedical Imaging Group Rotterdam, Departments of</span>
+<span class="c1"># Copyright 2016-2021 Biomedical Imaging Group Rotterdam, Departments of</span>
 <span class="c1"># Medical Informatics and Radiology, Erasmus MC, Rotterdam, The Netherlands</span>
 <span class="c1">#</span>
 <span class="c1"># Licensed under the Apache License, Version 2.0 (the &quot;License&quot;);</span>
@@ -181,7 +181,7 @@ <h1>Source code for WORC.featureprocessing.Relief</h1><div class="highlight"><pr
 <span class="c1"># limitations under the License.</span>
 
 <span class="kn">from</span> <span class="nn">sklearn.base</span> <span class="k">import</span> <span class="n">BaseEstimator</span>
-<span class="kn">from</span> <span class="nn">sklearn.feature_selection.base</span> <span class="k">import</span> <span class="n">SelectorMixin</span>
+<span class="kn">from</span> <span class="nn">sklearn.feature_selection</span> <span class="k">import</span> <span class="n">SelectorMixin</span>
 <span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
 <span class="kn">import</span> <span class="nn">sklearn.neighbors</span> <span class="k">as</span> <span class="nn">nn</span>
 <span class="c1"># from skrebate import ReliefF</span>

WORC/doc/_build/html/_modules/WORC/featureprocessing/SelectGroups.html

@@ -165,7 +165,7 @@
   <h1>Source code for WORC.featureprocessing.SelectGroups</h1><div class="highlight"><pre>
 <span></span><span class="ch">#!/usr/bin/env python</span>
 
-<span class="c1"># Copyright 2016-2020 Biomedical Imaging Group Rotterdam, Departments of</span>
+<span class="c1"># Copyright 2016-2021 Biomedical Imaging Group Rotterdam, Departments of</span>
 <span class="c1"># Medical Informatics and Radiology, Erasmus MC, Rotterdam, The Netherlands</span>
 <span class="c1">#</span>
 <span class="c1"># Licensed under the Apache License, Version 2.0 (the &quot;License&quot;);</span>
@@ -181,7 +181,7 @@ <h1>Source code for WORC.featureprocessing.SelectGroups</h1><div class="highligh
 <span class="c1"># limitations under the License.</span>
 
 <span class="kn">from</span> <span class="nn">sklearn.base</span> <span class="k">import</span> <span class="n">BaseEstimator</span>
-<span class="kn">from</span> <span class="nn">sklearn.feature_selection.base</span> <span class="k">import</span> <span class="n">SelectorMixin</span>
+<span class="kn">from</span> <span class="nn">sklearn.feature_selection</span> <span class="k">import</span> <span class="n">SelectorMixin</span>
 <span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
 
 

WORC/doc/_build/html/_modules/WORC/featureprocessing/SelectIndividuals.html

@@ -181,7 +181,7 @@ <h1>Source code for WORC.featureprocessing.SelectIndividuals</h1><div class="hig
 <span class="c1"># limitations under the License.</span>
 
 <span class="kn">from</span> <span class="nn">sklearn.base</span> <span class="k">import</span> <span class="n">BaseEstimator</span>
-<span class="kn">from</span> <span class="nn">sklearn.feature_selection.base</span> <span class="k">import</span> <span class="n">SelectorMixin</span>
+<span class="kn">from</span> <span class="nn">sklearn.feature_selection</span> <span class="k">import</span> <span class="n">SelectorMixin</span>
 <span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
 
 

WORC/doc/_build/html/_modules/WORC/featureprocessing/StatisticalTestThreshold.html

@@ -181,7 +181,7 @@ <h1>Source code for WORC.featureprocessing.StatisticalTestThreshold</h1><div cla
 <span class="c1"># limitations under the License.</span>
 
 <span class="kn">from</span> <span class="nn">sklearn.base</span> <span class="k">import</span> <span class="n">BaseEstimator</span>
-<span class="kn">from</span> <span class="nn">sklearn.feature_selection.base</span> <span class="k">import</span> <span class="n">SelectorMixin</span>
+<span class="kn">from</span> <span class="nn">sklearn.feature_selection</span> <span class="k">import</span> <span class="n">SelectorMixin</span>
 <span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
 <span class="kn">from</span> <span class="nn">scipy.stats</span> <span class="k">import</span> <span class="n">ttest_ind</span><span class="p">,</span> <span class="n">ranksums</span><span class="p">,</span> <span class="n">mannwhitneyu</span>
 

WORC/doc/_build/html/_modules/WORC/featureprocessing/VarianceThreshold.html

@@ -182,7 +182,7 @@ <h1>Source code for WORC.featureprocessing.VarianceThreshold</h1><div class="hig
 
 <span class="kn">from</span> <span class="nn">sklearn.feature_selection</span> <span class="k">import</span> <span class="n">VarianceThreshold</span>
 <span class="kn">from</span> <span class="nn">sklearn.base</span> <span class="k">import</span> <span class="n">BaseEstimator</span>
-<span class="kn">from</span> <span class="nn">sklearn.feature_selection.base</span> <span class="k">import</span> <span class="n">SelectorMixin</span>
+<span class="kn">from</span> <span class="nn">sklearn.feature_selection</span> <span class="k">import</span> <span class="n">SelectorMixin</span>
 <span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
 <span class="kn">import</span> <span class="nn">WORC.addexceptions</span> <span class="k">as</span> <span class="nn">ae</span>
 

WORC/doc/_build/html/_sources/static/quick_start.rst.txt

@@ -181,7 +181,7 @@ After defining the inputs, the following code can be used to run your first expe
     experiment.segmentations_from_this_directory(imagedatadir,
                                         segmentation_file_name=segmentation_file_name)
     experiment.labels_from_this_file(label_file)
-    experiment.predict_labels([label_name])
+    experiment.predict_labels(label_name)
 
     # Use the standard workflow for your specific modus
     if modus == 'binary_classification':

WORC/doc/_build/html/static/changelog.html

@@ -325,6 +325,8 @@ <h2>3.4.4 - 2021-07-01<a class="headerlink" href="#id1" title="Permalink to this
 <h3>Fixed<a class="headerlink" href="#fixed" title="Permalink to this headline">¶</a></h3>
 <ul class="simple">
 <li><p>Bug where most recent added estimators were not valid in SimpleWORC.</p></li>
+<li><p>SelectorMixin is now imported directly from sklearn.feature_selection,
+as sklearn.feature_selection.base is deprecated and will be removed.</p></li>
 </ul>
 </div>
 <div class="section" id="changed">

WORC/doc/_build/html/static/quick_start.html

@@ -345,7 +345,7 @@ <h3>The actual experiment<a class="headerlink" href="#the-actual-experiment" tit
 <span class="n">experiment</span><span class="o">.</span><span class="n">segmentations_from_this_directory</span><span class="p">(</span><span class="n">imagedatadir</span><span class="p">,</span>
                                     <span class="n">segmentation_file_name</span><span class="o">=</span><span class="n">segmentation_file_name</span><span class="p">)</span>
 <span class="n">experiment</span><span class="o">.</span><span class="n">labels_from_this_file</span><span class="p">(</span><span class="n">label_file</span><span class="p">)</span>
-<span class="n">experiment</span><span class="o">.</span><span class="n">predict_labels</span><span class="p">([</span><span class="n">label_name</span><span class="p">])</span>
+<span class="n">experiment</span><span class="o">.</span><span class="n">predict_labels</span><span class="p">(</span><span class="n">label_name</span><span class="p">)</span>
 
 <span class="c1"># Use the standard workflow for your specific modus</span>
 <span class="k">if</span> <span class="n">modus</span> <span class="o">==</span> <span class="s1">&#39;binary_classification&#39;</span><span class="p">:</span>

WORC/doc/static/quick_start.rst

@@ -181,7 +181,7 @@ After defining the inputs, the following code can be used to run your first expe
     experiment.segmentations_from_this_directory(imagedatadir,
                                         segmentation_file_name=segmentation_file_name)
     experiment.labels_from_this_file(label_file)
-    experiment.predict_labels([label_name])
+    experiment.predict_labels(label_name)
 
     # Use the standard workflow for your specific modus
     if modus == 'binary_classification':

WORC/facade/simpleworc.py

@@ -366,6 +366,9 @@ def predict_labels(self, label_names: list):
             raise TypeError(f'label_names is of type {type(label_names)} while list is expected')
 
         for label in label_names:
+            if not isinstance(label, str):
+                raise TypeError(f'label {label} is of type {type(label)} while str is expected')
+
             if len(label.strip()) == 0:
                 raise ValueError('Invalid label, length = 0')
 

WORC/tests/WORCTutorialSimple_travis_regression.py

@@ -80,13 +80,17 @@ def main():
     label_file = os.path.join(data_path, 'Examplefiles', 'pinfo_HN.csv')
 
     # Name of the label you want to predict
-    if modus == 'classification':
+    if modus == 'binary_classification':
         # Classification: predict a binary (0 or 1) label
-        label_name = 'imaginary_label_1'
+        label_name = ['imaginary_label_1']
 
     elif modus == 'regression':
         # Regression: predict a continuous label
-        label_name = 'Age'
+        label_name = ['Age']
+
+    elif modus == 'multiclass_classification':
+        # Multiclass classification: predict several mutually exclusive binaru labels together
+        label_name = ['imaginary_label_1', 'complement_label_1']
 
     # Determine whether we want to do a coarse quick experiment, or a full lengthy
     # one. Again, change this accordingly if you use your own data.
@@ -126,7 +130,7 @@ def main():
 
     # Labels
     experiment.labels_from_this_file(label_file)
-    experiment.predict_labels([label_name])
+    experiment.predict_labels(label_name)
 
     # Use the standard workflow for binary classification
     if modus == 'classification':