<spanid="quapy-method-aggregative-module"></span><h2>quapy.method.aggregative module<aclass="headerlink"href="#module-quapy.method.aggregative"title="Link to this heading"></a></h2>
<emclass="property"><spanclass="pre">class</span><spanclass="w"></span></em><spanclass="sig-prename descclassname"><spanclass="pre">quapy.method.aggregative.</span></span><spanclass="sig-name descname"><spanclass="pre">ACC</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">classifier</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><spanclass="pre">BaseEstimator</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">val_split</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">5</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">n_jobs</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">None</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">solver</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">'minimize'</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#ACC"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.ACC"title="Link to this definition"></a></dt>
<p><aclass="reference external"href="https://link.springer.com/article/10.1007/s10618-008-0097-y">Adjusted Classify & Count</a>,
the “adjusted” variant of <aclass="reference internal"href="#quapy.method.aggregative.CC"title="quapy.method.aggregative.CC"><codeclass="xref py py-class docutils literal notranslate"><spanclass="pre">CC</span></code></a>, that corrects the predictions of CC
according to the <cite>misclassification rates</cite>.</p>
<li><p><strong>val_split</strong>– specifies the data used for generating classifier predictions. This specification
can be made as float in (0, 1) indicating the proportion of stratified held-out validation set to
be extracted from the training set; or as an integer (default 5), indicating that the predictions
are to be generated in a <cite>k</cite>-fold cross-validation manner (with this integer indicating the value
for <cite>k</cite>); or as a collection defining the specific set of data to use for validation.
Alternatively, this set can be specified at fit time by indicating the exact set of data
on which the predictions are to be generated.</p></li>
<li><p><strong>n_jobs</strong>– number of parallel workers</p></li>
<li><p><strong>solver</strong>– indicates the method to be used for obtaining the final estimates. The choice
‘exact’ comes down to solving the system of linear equations <spanclass="math notranslate nohighlight">\(Ax=B\)</span> where <cite>A</cite> is a
matrix containing the class-conditional probabilities of the predictions (e.g., the tpr and fpr in
binary) and <cite>B</cite> is the vector of prevalence values estimated via CC, as <spanclass="math notranslate nohighlight">\(x=A^{-1}B\)</span>. This solution
might not exist for degenerated classifiers, in which case the method defaults to classify and count
(i.e., does not attempt any adjustment).
Another option is to search for the prevalence vector that minimizes the L2 norm of <spanclass="math notranslate nohighlight">\(|Ax-B|\)</span>. The latter
is achieved by indicating solver=’minimize’. This one generally works better, and is the default parameter.
More details about this can be consulted in <aclass="reference external"href="https://lq-2022.github.io/proceedings/CompleteVolume.pdf">Bunse, M. “On Multi-Class Extensions of Adjusted Classify and
Count”, on proceedings of the 2nd International Workshop on Learning to Quantify: Methods and Applications
<spanclass="sig-name descname"><spanclass="pre">aggregate</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">classif_predictions</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#ACC.aggregate"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.ACC.aggregate"title="Link to this definition"></a></dt>
<spanclass="sig-name descname"><spanclass="pre">aggregation_fit</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">classif_predictions</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><spanclass="pre">LabelledCollection</span></a></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">data</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><spanclass="pre">LabelledCollection</span></a></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#ACC.aggregation_fit"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.ACC.aggregation_fit"title="Link to this definition"></a></dt>
<emclass="property"><spanclass="pre">classmethod</span><spanclass="w"></span></em><spanclass="sig-name descname"><spanclass="pre">getPteCondEstim</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">classes</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">y</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">y_</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#ACC.getPteCondEstim"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.ACC.getPteCondEstim"title="Link to this definition"></a></dt>
<emclass="property"><spanclass="pre">classmethod</span><spanclass="w"></span></em><spanclass="sig-name descname"><spanclass="pre">solve_adjustment</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">PteCondEstim</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">prevs_estim</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">solver</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">'exact'</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#ACC.solve_adjustment"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.ACC.solve_adjustment"title="Link to this definition"></a></dt>
<dd><p>Solves the system linear system <spanclass="math notranslate nohighlight">\(Ax = B\)</span> with <spanclass="math notranslate nohighlight">\(A\)</span> = <cite>PteCondEstim</cite> and <spanclass="math notranslate nohighlight">\(B\)</span> = <cite>prevs_estim</cite></p>
<li><p><strong>PteCondEstim</strong>– a <cite>np.ndarray</cite> of shape <cite>(n_classes,n_classes,)</cite> with entry <cite>(i,j)</cite> being the estimate
of <spanclass="math notranslate nohighlight">\(P(y_i|y_j)\)</span>, that is, the probability that an instance that belongs to <spanclass="math notranslate nohighlight">\(y_j\)</span> ends up being
classified as belonging to <spanclass="math notranslate nohighlight">\(y_i\)</span></p></li>
<li><p><strong>prevs_estim</strong>– a <cite>np.ndarray</cite> of shape <cite>(n_classes,)</cite> with the class prevalence estimates</p></li>
<spanclass="sig-prename descclassname"><spanclass="pre">quapy.method.aggregative.</span></span><spanclass="sig-name descname"><spanclass="pre">AdjustedClassifyAndCount</span></span><aclass="headerlink"href="#quapy.method.aggregative.AdjustedClassifyAndCount"title="Link to this definition"></a></dt>
<emclass="property"><spanclass="pre">class</span><spanclass="w"></span></em><spanclass="sig-prename descclassname"><spanclass="pre">quapy.method.aggregative.</span></span><spanclass="sig-name descname"><spanclass="pre">AggregativeCrispQuantifier</span></span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#AggregativeCrispQuantifier"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.AggregativeCrispQuantifier"title="Link to this definition"></a></dt>
<spanclass="sig-name descname"><spanclass="pre">fit</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">training</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><spanclass="pre">LabelledCollection</span></a></span></em>, <emclass="sig-param"><spanclass="o"><spanclass="pre">**</span></span><spanclass="n"><spanclass="pre">kwargs</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#AggregativeMedianEstimator.fit"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.AggregativeMedianEstimator.fit"title="Link to this definition"></a></dt>
<ddclass="field-odd"><p><strong>data</strong>– a <aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><codeclass="xref py py-class docutils literal notranslate"><spanclass="pre">quapy.data.base.LabelledCollection</span></code></a> consisting of the training data</p>
<spanclass="sig-name descname"><spanclass="pre">get_params</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">deep</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">True</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#AggregativeMedianEstimator.get_params"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.AggregativeMedianEstimator.get_params"title="Link to this definition"></a></dt>
<ddclass="field-odd"><p><strong>deep</strong> (<em>bool</em><em>, </em><em>default=True</em>) – If True, will return the parameters for this estimator and
<spanclass="sig-name descname"><spanclass="pre">quantify</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">instances</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#AggregativeMedianEstimator.quantify"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.AggregativeMedianEstimator.quantify"title="Link to this definition"></a></dt>
<dd><p>Generate class prevalence estimates for the sample’s instances</p>
<spanclass="sig-name descname"><spanclass="pre">set_params</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="o"><spanclass="pre">**</span></span><spanclass="n"><spanclass="pre">params</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#AggregativeMedianEstimator.set_params"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.AggregativeMedianEstimator.set_params"title="Link to this definition"></a></dt>
<dd><p>Set the parameters of this estimator.</p>
<p>The method works on simple estimators as well as on nested objects
(such as <codeclass="xref py py-class docutils literal notranslate"><spanclass="pre">Pipeline</span></code>). The latter have
parameters of the form <codeclass="docutils literal notranslate"><spanclass="pre"><component>__<parameter></span></code> so that it’s
possible to update each component of a nested object.</p>
<emclass="property"><spanclass="pre">class</span><spanclass="w"></span></em><spanclass="sig-prename descclassname"><spanclass="pre">quapy.method.aggregative.</span></span><spanclass="sig-name descname"><spanclass="pre">AggregativeQuantifier</span></span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#AggregativeQuantifier"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.AggregativeQuantifier"title="Link to this definition"></a></dt>
results. Aggregative quantifiers implement a pipeline that consists of generating classification predictions
and aggregating them. For this reason, the training phase is implemented by <codeclass="xref py py-meth docutils literal notranslate"><spanclass="pre">classification_fit()</span></code> followed
by <aclass="reference internal"href="#quapy.method.aggregative.AggregativeQuantifier.aggregation_fit"title="quapy.method.aggregative.AggregativeQuantifier.aggregation_fit"><codeclass="xref py py-meth docutils literal notranslate"><spanclass="pre">aggregation_fit()</span></code></a>, while the testing phase is implemented by <aclass="reference internal"href="#quapy.method.aggregative.AggregativeQuantifier.classify"title="quapy.method.aggregative.AggregativeQuantifier.classify"><codeclass="xref py py-meth docutils literal notranslate"><spanclass="pre">classify()</span></code></a> followed by
<aclass="reference internal"href="#quapy.method.aggregative.AggregativeQuantifier.aggregate"title="quapy.method.aggregative.AggregativeQuantifier.aggregate"><codeclass="xref py py-meth docutils literal notranslate"><spanclass="pre">aggregate()</span></code></a>. Subclasses of this abstract class must provide implementations for these methods.
Aggregative quantifiers also maintain a <aclass="reference internal"href="#quapy.method.aggregative.AggregativeQuantifier.classifier"title="quapy.method.aggregative.AggregativeQuantifier.classifier"><codeclass="xref py py-attr docutils literal notranslate"><spanclass="pre">classifier</span></code></a> attribute.</p>
<p>The method <aclass="reference internal"href="#quapy.method.aggregative.AggregativeQuantifier.fit"title="quapy.method.aggregative.AggregativeQuantifier.fit"><codeclass="xref py py-meth docutils literal notranslate"><spanclass="pre">fit()</span></code></a> comes with a default implementation based on <codeclass="xref py py-meth docutils literal notranslate"><spanclass="pre">classification_fit()</span></code>
and <aclass="reference internal"href="#quapy.method.aggregative.AggregativeQuantifier.aggregation_fit"title="quapy.method.aggregative.AggregativeQuantifier.aggregation_fit"><codeclass="xref py py-meth docutils literal notranslate"><spanclass="pre">aggregation_fit()</span></code></a>.</p>
<p>The method <aclass="reference internal"href="#quapy.method.aggregative.AggregativeQuantifier.quantify"title="quapy.method.aggregative.AggregativeQuantifier.quantify"><codeclass="xref py py-meth docutils literal notranslate"><spanclass="pre">quantify()</span></code></a> comes with a default implementation based on <aclass="reference internal"href="#quapy.method.aggregative.AggregativeQuantifier.classify"title="quapy.method.aggregative.AggregativeQuantifier.classify"><codeclass="xref py py-meth docutils literal notranslate"><spanclass="pre">classify()</span></code></a>
and <aclass="reference internal"href="#quapy.method.aggregative.AggregativeQuantifier.aggregate"title="quapy.method.aggregative.AggregativeQuantifier.aggregate"><codeclass="xref py py-meth docutils literal notranslate"><spanclass="pre">aggregate()</span></code></a>.</p>
<emclass="property"><spanclass="pre">abstract</span><spanclass="w"></span></em><spanclass="sig-name descname"><spanclass="pre">aggregate</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">classif_predictions</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><spanclass="pre">ndarray</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#AggregativeQuantifier.aggregate"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.AggregativeQuantifier.aggregate"title="Link to this definition"></a></dt>
<emclass="property"><spanclass="pre">abstract</span><spanclass="w"></span></em><spanclass="sig-name descname"><spanclass="pre">aggregation_fit</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">classif_predictions</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><spanclass="pre">LabelledCollection</span></a></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">data</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><spanclass="pre">LabelledCollection</span></a></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#AggregativeQuantifier.aggregation_fit"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.AggregativeQuantifier.aggregation_fit"title="Link to this definition"></a></dt>
<li><p><strong>classif_predictions</strong>– a LabelledCollection containing the label predictions issued
by the classifier</p></li>
<li><p><strong>data</strong>– a <aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><codeclass="xref py py-class docutils literal notranslate"><spanclass="pre">quapy.data.base.LabelledCollection</span></code></a> consisting of the training data</p></li>
<emclass="property"><spanclass="pre">property</span><spanclass="w"></span></em><spanclass="sig-name descname"><spanclass="pre">classes_</span></span><aclass="headerlink"href="#quapy.method.aggregative.AggregativeQuantifier.classes_"title="Link to this definition"></a></dt>
<emclass="property"><spanclass="pre">property</span><spanclass="w"></span></em><spanclass="sig-name descname"><spanclass="pre">classifier</span></span><aclass="headerlink"href="#quapy.method.aggregative.AggregativeQuantifier.classifier"title="Link to this definition"></a></dt>
<spanclass="sig-name descname"><spanclass="pre">classifier_fit_predict</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">data</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><spanclass="pre">LabelledCollection</span></a></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">fit_classifier</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">True</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">predict_on</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">None</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#AggregativeQuantifier.classifier_fit_predict"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.AggregativeQuantifier.classifier_fit_predict"title="Link to this definition"></a></dt>
<dd><p>Trains the classifier if requested (<cite>fit_classifier=True</cite>) and generate the necessary predictions to
<li><p><strong>data</strong>– a <aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><codeclass="xref py py-class docutils literal notranslate"><spanclass="pre">quapy.data.base.LabelledCollection</span></code></a> consisting of the training data</p></li>
<li><p><strong>fit_classifier</strong>– whether to train the learner (default is True). Set to False if the
learner has been trained outside the quantifier.</p></li>
<li><p><strong>predict_on</strong>– specifies the set on which predictions need to be issued. This parameter can
be specified as None (default) to indicate no prediction is needed; a float in (0, 1) to
indicate the proportion of instances to be used for predictions (the remainder is used for
training); an integer >1 to indicate that the predictions must be generated via k-fold
cross-validation, using this integer as k; or the data sample itself on which to generate
<spanclass="sig-name descname"><spanclass="pre">classify</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">instances</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#AggregativeQuantifier.classify"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.AggregativeQuantifier.classify"title="Link to this definition"></a></dt>
<spanclass="sig-name descname"><spanclass="pre">fit</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">data</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><spanclass="pre">LabelledCollection</span></a></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">fit_classifier</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">True</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">val_split</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">None</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#AggregativeQuantifier.fit"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.AggregativeQuantifier.fit"title="Link to this definition"></a></dt>
<dd><p>Trains the aggregative quantifier. This comes down to training a classifier and an aggregation function.</p>
<li><p><strong>data</strong>– a <aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><codeclass="xref py py-class docutils literal notranslate"><spanclass="pre">quapy.data.base.LabelledCollection</span></code></a> consisting of the training data</p></li>
<spanclass="sig-name descname"><spanclass="pre">quantify</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">instances</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#AggregativeQuantifier.quantify"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.AggregativeQuantifier.quantify"title="Link to this definition"></a></dt>
<emclass="property"><spanclass="pre">property</span><spanclass="w"></span></em><spanclass="sig-name descname"><spanclass="pre">val_split</span></span><aclass="headerlink"href="#quapy.method.aggregative.AggregativeQuantifier.val_split"title="Link to this definition"></a></dt>
<spanclass="sig-name descname"><spanclass="pre">val_split_</span></span><emclass="property"><spanclass="w"></span><spanclass="p"><spanclass="pre">=</span></span><spanclass="w"></span><spanclass="pre">None</span></em><aclass="headerlink"href="#quapy.method.aggregative.AggregativeQuantifier.val_split_"title="Link to this definition"></a></dt>
<emclass="property"><spanclass="pre">class</span><spanclass="w"></span></em><spanclass="sig-prename descclassname"><spanclass="pre">quapy.method.aggregative.</span></span><spanclass="sig-name descname"><spanclass="pre">AggregativeSoftQuantifier</span></span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#AggregativeSoftQuantifier"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.AggregativeSoftQuantifier"title="Link to this definition"></a></dt>
<emclass="property"><spanclass="pre">class</span><spanclass="w"></span></em><spanclass="sig-prename descclassname"><spanclass="pre">quapy.method.aggregative.</span></span><spanclass="sig-name descname"><spanclass="pre">BinaryAggregativeQuantifier</span></span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#BinaryAggregativeQuantifier"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.BinaryAggregativeQuantifier"title="Link to this definition"></a></dt>
<spanclass="sig-name descname"><spanclass="pre">fit</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">data</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><spanclass="pre">LabelledCollection</span></a></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">fit_classifier</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">True</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">val_split</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">None</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#BinaryAggregativeQuantifier.fit"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.BinaryAggregativeQuantifier.fit"title="Link to this definition"></a></dt>
<dd><p>Trains the aggregative quantifier. This comes down to training a classifier and an aggregation function.</p>
<li><p><strong>data</strong>– a <aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><codeclass="xref py py-class docutils literal notranslate"><spanclass="pre">quapy.data.base.LabelledCollection</span></code></a> consisting of the training data</p></li>
<li><p><strong>fit_classifier</strong>– whether to train the learner (default is True). Set to False if the
learner has been trained outside the quantifier.</p></li>
<emclass="property"><spanclass="pre">property</span><spanclass="w"></span></em><spanclass="sig-name descname"><spanclass="pre">neg_label</span></span><aclass="headerlink"href="#quapy.method.aggregative.BinaryAggregativeQuantifier.neg_label"title="Link to this definition"></a></dt>
<emclass="property"><spanclass="pre">property</span><spanclass="w"></span></em><spanclass="sig-name descname"><spanclass="pre">pos_label</span></span><aclass="headerlink"href="#quapy.method.aggregative.BinaryAggregativeQuantifier.pos_label"title="Link to this definition"></a></dt>
<emclass="property"><spanclass="pre">class</span><spanclass="w"></span></em><spanclass="sig-prename descclassname"><spanclass="pre">quapy.method.aggregative.</span></span><spanclass="sig-name descname"><spanclass="pre">CC</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">classifier</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><spanclass="pre">BaseEstimator</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#CC"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.CC"title="Link to this definition"></a></dt>
<spanclass="sig-name descname"><spanclass="pre">aggregate</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">classif_predictions</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><spanclass="pre">ndarray</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#CC.aggregate"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.CC.aggregate"title="Link to this definition"></a></dt>
<spanclass="sig-name descname"><spanclass="pre">aggregation_fit</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">classif_predictions</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><spanclass="pre">LabelledCollection</span></a></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">data</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><spanclass="pre">LabelledCollection</span></a></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#CC.aggregation_fit"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.CC.aggregation_fit"title="Link to this definition"></a></dt>
<spanclass="sig-prename descclassname"><spanclass="pre">quapy.method.aggregative.</span></span><spanclass="sig-name descname"><spanclass="pre">ClassifyAndCount</span></span><aclass="headerlink"href="#quapy.method.aggregative.ClassifyAndCount"title="Link to this definition"></a></dt>
<spanclass="sig-name descname"><spanclass="pre">aggregate</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">posteriors</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><spanclass="pre">ndarray</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#DMy.aggregate"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.DMy.aggregate"title="Link to this definition"></a></dt>
<spanclass="sig-name descname"><spanclass="pre">aggregation_fit</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">classif_predictions</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><spanclass="pre">LabelledCollection</span></a></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">data</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><spanclass="pre">LabelledCollection</span></a></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#DMy.aggregation_fit"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.DMy.aggregation_fit"title="Link to this definition"></a></dt>
<spanclass="sig-prename descclassname"><spanclass="pre">quapy.method.aggregative.</span></span><spanclass="sig-name descname"><spanclass="pre">DistributionMatchingY</span></span><aclass="headerlink"href="#quapy.method.aggregative.DistributionMatchingY"title="Link to this definition"></a></dt>
<dd><p>alias of <aclass="reference internal"href="#quapy.method.aggregative.DMy"title="quapy.method.aggregative.DMy"><codeclass="xref py py-class docutils literal notranslate"><spanclass="pre">DMy</span></code></a></p>
DyS is a generalization of HDy method, using a Ternary Search in order to find the prevalence that
minimizes the distance between distributions.
Details for the ternary search have been got from <<aclass="reference external"href="https://dl.acm.org/doi/pdf/10.1145/3219819.3220059">https://dl.acm.org/doi/pdf/10.1145/3219819.3220059</a>></p>
validation distribution, or a <aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><codeclass="xref py py-class docutils literal notranslate"><spanclass="pre">quapy.data.base.LabelledCollection</span></code></a> (the split itself), or an integer indicating the number of folds (default 5)..</p></li>
<spanclass="sig-name descname"><spanclass="pre">aggregate</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">classif_posteriors</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#DyS.aggregate"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.DyS.aggregate"title="Link to this definition"></a></dt>
<spanclass="sig-name descname"><spanclass="pre">aggregation_fit</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">classif_predictions</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><spanclass="pre">LabelledCollection</span></a></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">data</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><spanclass="pre">LabelledCollection</span></a></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#DyS.aggregation_fit"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.DyS.aggregation_fit"title="Link to this definition"></a></dt>
<li><p><strong>data</strong>– a <aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><codeclass="xref py py-class docutils literal notranslate"><spanclass="pre">quapy.data.base.LabelledCollection</span></code></a> consisting of the training data</p></li>
<p>This implementation also gives access to the heuristics proposed by <aclass="reference external"href="http://proceedings.mlr.press/v119/alexandari20a.html">Alexandari et al. paper</a>. These heuristics consist of using, as the training
prevalence, an estimate of it obtained via k-fold cross validation (instead of the true training prevalence),
and to recalibrate the posterior probabilities of the classifier.</p>
<emclass="property"><spanclass="pre">classmethod</span><spanclass="w"></span></em><spanclass="sig-name descname"><spanclass="pre">EM</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">tr_prev</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">posterior_probabilities</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">epsilon</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">0.0001</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#EMQ.EM"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.EMQ.EM"title="Link to this definition"></a></dt>
<emclass="property"><spanclass="pre">classmethod</span><spanclass="w"></span></em><spanclass="sig-name descname"><spanclass="pre">EMQ_BCTS</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">classifier</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><spanclass="pre">BaseEstimator</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">n_jobs</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">None</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#EMQ.EMQ_BCTS"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.EMQ.EMQ_BCTS"title="Link to this definition"></a></dt>
<dd><p>Constructs an instance of EMQ using the best configuration found in the <aclass="reference external"href="http://proceedings.mlr.press/v119/alexandari20a.html">Alexandari et al. paper</a>, i.e., one that relies on Bias-Corrected Temperature
Scaling (BCTS) as a recalibration function, and that uses an estimate of the training prevalence instead of
<spanclass="sig-name descname"><spanclass="pre">EPSILON</span></span><emclass="property"><spanclass="w"></span><spanclass="p"><spanclass="pre">=</span></span><spanclass="w"></span><spanclass="pre">0.0001</span></em><aclass="headerlink"href="#quapy.method.aggregative.EMQ.EPSILON"title="Link to this definition"></a></dt>
<spanclass="sig-name descname"><spanclass="pre">MAX_ITER</span></span><emclass="property"><spanclass="w"></span><spanclass="p"><spanclass="pre">=</span></span><spanclass="w"></span><spanclass="pre">1000</span></em><aclass="headerlink"href="#quapy.method.aggregative.EMQ.MAX_ITER"title="Link to this definition"></a></dt>
<spanclass="sig-name descname"><spanclass="pre">aggregate</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">classif_posteriors</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">epsilon</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">0.0001</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#EMQ.aggregate"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.EMQ.aggregate"title="Link to this definition"></a></dt>
<spanclass="sig-name descname"><spanclass="pre">aggregation_fit</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">classif_predictions</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><spanclass="pre">LabelledCollection</span></a></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">data</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><spanclass="pre">LabelledCollection</span></a></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#EMQ.aggregation_fit"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.EMQ.aggregation_fit"title="Link to this definition"></a></dt>
<li><p><strong>data</strong>– a <aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><codeclass="xref py py-class docutils literal notranslate"><spanclass="pre">quapy.data.base.LabelledCollection</span></code></a> consisting of the training data</p></li>
<spanclass="sig-name descname"><spanclass="pre">classify</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">instances</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#EMQ.classify"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.EMQ.classify"title="Link to this definition"></a></dt>
<dd><p>Provides the posterior probabilities for the given instances. If the classifier was required
to be recalibrated, then these posteriors are recalibrated accordingly.</p>
<spanclass="sig-name descname"><spanclass="pre">predict_proba</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">instances</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">epsilon</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">0.0001</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#EMQ.predict_proba"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.EMQ.predict_proba"title="Link to this definition"></a></dt>
<dd><p>Returns the posterior probabilities updated by the EM algorithm.</p>
<spanclass="sig-prename descclassname"><spanclass="pre">quapy.method.aggregative.</span></span><spanclass="sig-name descname"><spanclass="pre">ExpectationMaximizationQuantifier</span></span><aclass="headerlink"href="#quapy.method.aggregative.ExpectationMaximizationQuantifier"title="Link to this definition"></a></dt>
<emclass="property"><spanclass="pre">class</span><spanclass="w"></span></em><spanclass="sig-prename descclassname"><spanclass="pre">quapy.method.aggregative.</span></span><spanclass="sig-name descname"><spanclass="pre">HDy</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">classifier</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><spanclass="pre">BaseEstimator</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">val_split</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">5</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#HDy"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.HDy"title="Link to this definition"></a></dt>
validation distribution, or a <aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><codeclass="xref py py-class docutils literal notranslate"><spanclass="pre">quapy.data.base.LabelledCollection</span></code></a> (the split itself), or an integer indicating the number of folds (default 5)..</p></li>
<spanclass="sig-name descname"><spanclass="pre">aggregate</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">classif_posteriors</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#HDy.aggregate"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.HDy.aggregate"title="Link to this definition"></a></dt>
<spanclass="sig-name descname"><spanclass="pre">aggregation_fit</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">classif_predictions</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><spanclass="pre">LabelledCollection</span></a></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">data</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><spanclass="pre">LabelledCollection</span></a></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#HDy.aggregation_fit"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.HDy.aggregation_fit"title="Link to this definition"></a></dt>
<spanclass="sig-prename descclassname"><spanclass="pre">quapy.method.aggregative.</span></span><spanclass="sig-name descname"><spanclass="pre">HellingerDistanceY</span></span><aclass="headerlink"href="#quapy.method.aggregative.HellingerDistanceY"title="Link to this definition"></a></dt>
<emclass="property"><spanclass="pre">class</span><spanclass="w"></span></em><spanclass="sig-prename descclassname"><spanclass="pre">quapy.method.aggregative.</span></span><spanclass="sig-name descname"><spanclass="pre">OneVsAllAggregative</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">binary_quantifier</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">n_jobs</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">None</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">parallel_backend</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">'multiprocessing'</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#OneVsAllAggregative"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.OneVsAllAggregative"title="Link to this definition"></a></dt>
<p>Allows any binary quantifier to perform quantification on single-label datasets.
The method maintains one binary quantifier for each class, and then l1-normalizes the outputs so that the
class prevelences sum up to 1.
This variant was used, along with the <aclass="reference internal"href="#quapy.method.aggregative.EMQ"title="quapy.method.aggregative.EMQ"><codeclass="xref py py-class docutils literal notranslate"><spanclass="pre">EMQ</span></code></a> quantifier, in
<aclass="reference external"href="https://link.springer.com/content/pdf/10.1007/s13278-016-0327-z.pdf">Gao and Sebastiani, 2016</a>.</p>
<spanclass="sig-name descname"><spanclass="pre">aggregate</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">classif_predictions</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#OneVsAllAggregative.aggregate"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.OneVsAllAggregative.aggregate"title="Link to this definition"></a></dt>
<dd><p>Implements the aggregation of label predictions.</p>
<spanclass="sig-name descname"><spanclass="pre">classify</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">instances</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#OneVsAllAggregative.classify"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.OneVsAllAggregative.classify"title="Link to this definition"></a></dt>
<emclass="property"><spanclass="pre">class</span><spanclass="w"></span></em><spanclass="sig-prename descclassname"><spanclass="pre">quapy.method.aggregative.</span></span><spanclass="sig-name descname"><spanclass="pre">PACC</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">classifier</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><spanclass="pre">BaseEstimator</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">val_split</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">5</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">n_jobs</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">None</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">solver</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">'minimize'</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#PACC"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.PACC"title="Link to this definition"></a></dt>
<li><p><strong>solver</strong>–<p>indicates the method to be used for obtaining the final estimates. The choice
‘exact’ comes down to solving the system of linear equations <spanclass="math notranslate nohighlight">\(Ax=B\)</span> where <cite>A</cite> is a
matrix containing the class-conditional probabilities of the predictions (e.g., the tpr and fpr in
binary) and <cite>B</cite> is the vector of prevalence values estimated via CC, as <spanclass="math notranslate nohighlight">\(x=A^{-1}B\)</span>. This solution
might not exist for degenerated classifiers, in which case the method defaults to classify and count
(i.e., does not attempt any adjustment).
Another option is to search for the prevalence vector that minimizes the L2 norm of <spanclass="math notranslate nohighlight">\(|Ax-B|\)</span>. The latter
is achieved by indicating solver=’minimize’. This one generally works better, and is the default parameter.
More details about this can be consulted in <aclass="reference external"href="https://lq-2022.github.io/proceedings/CompleteVolume.pdf">Bunse, M. “On Multi-Class Extensions of Adjusted Classify and
Count”, on proceedings of the 2nd International Workshop on Learning to Quantify: Methods and Applications
<spanclass="sig-name descname"><spanclass="pre">aggregate</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">classif_posteriors</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#PACC.aggregate"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.PACC.aggregate"title="Link to this definition"></a></dt>
<spanclass="sig-name descname"><spanclass="pre">aggregation_fit</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">classif_predictions</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><spanclass="pre">LabelledCollection</span></a></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">data</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><spanclass="pre">LabelledCollection</span></a></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#PACC.aggregation_fit"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.PACC.aggregation_fit"title="Link to this definition"></a></dt>
<emclass="property"><spanclass="pre">classmethod</span><spanclass="w"></span></em><spanclass="sig-name descname"><spanclass="pre">getPteCondEstim</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">classes</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">y</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">y_</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#PACC.getPteCondEstim"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.PACC.getPteCondEstim"title="Link to this definition"></a></dt>
<emclass="property"><spanclass="pre">class</span><spanclass="w"></span></em><spanclass="sig-prename descclassname"><spanclass="pre">quapy.method.aggregative.</span></span><spanclass="sig-name descname"><spanclass="pre">PCC</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">classifier</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><spanclass="pre">BaseEstimator</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#PCC"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.PCC"title="Link to this definition"></a></dt>
<spanclass="sig-name descname"><spanclass="pre">aggregate</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">classif_posteriors</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#PCC.aggregate"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.PCC.aggregate"title="Link to this definition"></a></dt>
<spanclass="sig-name descname"><spanclass="pre">aggregation_fit</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">classif_predictions</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><spanclass="pre">LabelledCollection</span></a></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">data</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><spanclass="pre">LabelledCollection</span></a></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#PCC.aggregation_fit"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.PCC.aggregation_fit"title="Link to this definition"></a></dt>
<spanclass="sig-prename descclassname"><spanclass="pre">quapy.method.aggregative.</span></span><spanclass="sig-name descname"><spanclass="pre">ProbabilisticAdjustedClassifyAndCount</span></span><aclass="headerlink"href="#quapy.method.aggregative.ProbabilisticAdjustedClassifyAndCount"title="Link to this definition"></a></dt>
<spanclass="sig-prename descclassname"><spanclass="pre">quapy.method.aggregative.</span></span><spanclass="sig-name descname"><spanclass="pre">ProbabilisticClassifyAndCount</span></span><aclass="headerlink"href="#quapy.method.aggregative.ProbabilisticClassifyAndCount"title="Link to this definition"></a></dt>
<spanclass="sig-prename descclassname"><spanclass="pre">quapy.method.aggregative.</span></span><spanclass="sig-name descname"><spanclass="pre">SLD</span></span><aclass="headerlink"href="#quapy.method.aggregative.SLD"title="Link to this definition"></a></dt>
<emclass="property"><spanclass="pre">class</span><spanclass="w"></span></em><spanclass="sig-prename descclassname"><spanclass="pre">quapy.method.aggregative.</span></span><spanclass="sig-name descname"><spanclass="pre">SMM</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">classifier</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><spanclass="pre">BaseEstimator</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">val_split</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">5</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#SMM"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.SMM"title="Link to this definition"></a></dt>
validation distribution, or a <aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><codeclass="xref py py-class docutils literal notranslate"><spanclass="pre">quapy.data.base.LabelledCollection</span></code></a> (the split itself), or an integer indicating the number of folds (default 5)..</p></li>
<spanclass="sig-name descname"><spanclass="pre">aggregate</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">classif_posteriors</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#SMM.aggregate"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.SMM.aggregate"title="Link to this definition"></a></dt>
<spanclass="sig-name descname"><spanclass="pre">aggregation_fit</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">classif_predictions</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><spanclass="pre">LabelledCollection</span></a></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">data</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><spanclass="pre">LabelledCollection</span></a></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#SMM.aggregation_fit"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.SMM.aggregation_fit"title="Link to this definition"></a></dt>
<li><p><strong>data</strong>– a <aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><codeclass="xref py py-class docutils literal notranslate"><spanclass="pre">quapy.data.base.LabelledCollection</span></code></a> consisting of the training data</p></li>
<spanclass="sig-prename descclassname"><spanclass="pre">quapy.method.aggregative.</span></span><spanclass="sig-name descname"><spanclass="pre">newELM</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">svmperf_base</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">None</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">loss</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">'01'</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">C</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">1</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#newELM"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.newELM"title="Link to this definition"></a></dt>
<li><p><strong>svmperf_base</strong>– path to the folder containing the binary files of <cite>SVM perf</cite>; if set to None (default)
this path will be obtained from qp.environ[‘SVMPERF_HOME’]</p></li>
<li><p><strong>loss</strong>– the loss to optimize (see <aclass="reference internal"href="quapy.classification.html#quapy.classification.svmperf.SVMperf.valid_losses"title="quapy.classification.svmperf.SVMperf.valid_losses"><codeclass="xref py py-attr docutils literal notranslate"><spanclass="pre">quapy.classification.svmperf.SVMperf.valid_losses</span></code></a>)</p></li>
<li><p><strong>C</strong>– trade-off between training error and margin (default 0.01)</p></li>
<spanclass="sig-prename descclassname"><spanclass="pre">quapy.method.aggregative.</span></span><spanclass="sig-name descname"><spanclass="pre">newSVMAE</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">svmperf_base</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">None</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">C</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">1</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#newSVMAE"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.newSVMAE"title="Link to this definition"></a></dt>
<spanclass="sig-prename descclassname"><spanclass="pre">quapy.method.aggregative.</span></span><spanclass="sig-name descname"><spanclass="pre">newSVMKLD</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">svmperf_base</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">None</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">C</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">1</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#newSVMKLD"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.newSVMKLD"title="Link to this definition"></a></dt>
<spanclass="sig-prename descclassname"><spanclass="pre">quapy.method.aggregative.</span></span><spanclass="sig-name descname"><spanclass="pre">newSVMQ</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">svmperf_base</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">None</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">C</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">1</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#newSVMQ"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.newSVMQ"title="Link to this definition"></a></dt>
<spanclass="sig-prename descclassname"><spanclass="pre">quapy.method.aggregative.</span></span><spanclass="sig-name descname"><spanclass="pre">newSVMRAE</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">svmperf_base</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">None</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">C</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">1</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/aggregative.html#newSVMRAE"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.aggregative.newSVMRAE"title="Link to this definition"></a></dt>
<emclass="property"><spanclass="pre">class</span><spanclass="w"></span></em><spanclass="sig-prename descclassname"><spanclass="pre">quapy.method._kdey.</span></span><spanclass="sig-name descname"><spanclass="pre">KDEBase</span></span><aclass="reference internal"href="_modules/quapy/method/_kdey.html#KDEBase"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method._kdey.KDEBase"title="Link to this definition"></a></dt>
<spanclass="sig-name descname"><spanclass="pre">BANDWIDTH_METHOD</span></span><emclass="property"><spanclass="w"></span><spanclass="p"><spanclass="pre">=</span></span><spanclass="w"></span><spanclass="pre">['scott',</span><spanclass="pre">'silverman']</span></em><aclass="headerlink"href="#quapy.method._kdey.KDEBase.BANDWIDTH_METHOD"title="Link to this definition"></a></dt>
<spanclass="sig-name descname"><spanclass="pre">get_kde_function</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">X</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">bandwidth</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/_kdey.html#KDEBase.get_kde_function"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method._kdey.KDEBase.get_kde_function"title="Link to this definition"></a></dt>
<dd><p>Wraps the KDE function from scikit-learn.</p>
<spanclass="sig-name descname"><spanclass="pre">get_mixture_components</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">X</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">y</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">n_classes</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">bandwidth</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/_kdey.html#KDEBase.get_mixture_components"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method._kdey.KDEBase.get_mixture_components"title="Link to this definition"></a></dt>
<dd><p>Returns an array containing the mixture components, i.e., the KDE functions for each class.</p>
<spanclass="sig-name descname"><spanclass="pre">pdf</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">kde</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">X</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/_kdey.html#KDEBase.pdf"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method._kdey.KDEBase.pdf"title="Link to this definition"></a></dt>
<dd><p>Wraps the density evalution of scikit-learn’s KDE. Scikit-learn returns log-scores (s), so this
function returns <spanclass="math notranslate nohighlight">\(e^{s}\)</span></p>
<emclass="property"><spanclass="pre">class</span><spanclass="w"></span></em><spanclass="sig-prename descclassname"><spanclass="pre">quapy.method._kdey.</span></span><spanclass="sig-name descname"><spanclass="pre">KDEyCS</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">classifier</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><spanclass="pre">BaseEstimator</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">val_split</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">10</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">bandwidth</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">0.1</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">n_jobs</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">None</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/_kdey.html#KDEyCS"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method._kdey.KDEyCS"title="Link to this definition"></a></dt>
<p>where <spanclass="math notranslate nohighlight">\(p_{\alpha}\)</span> is the mixture of class-specific KDEs with mixture parameter (hence class prevalence)
<spanclass="math notranslate nohighlight">\(\alpha\)</span> defined by</p>
<spanclass="sig-name descname"><spanclass="pre">aggregate</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">posteriors</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><spanclass="pre">ndarray</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/_kdey.html#KDEyCS.aggregate"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method._kdey.KDEyCS.aggregate"title="Link to this definition"></a></dt>
<dd><p>Implements the aggregation of label predictions.</p>
<spanclass="sig-name descname"><spanclass="pre">aggregation_fit</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">classif_predictions</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><spanclass="pre">LabelledCollection</span></a></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">data</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><spanclass="pre">LabelledCollection</span></a></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/_kdey.html#KDEyCS.aggregation_fit"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method._kdey.KDEyCS.aggregation_fit"title="Link to this definition"></a></dt>
<li><p><strong>classif_predictions</strong>– a LabelledCollection containing the label predictions issued
by the classifier</p></li>
<li><p><strong>data</strong>– a <aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><codeclass="xref py py-class docutils literal notranslate"><spanclass="pre">quapy.data.base.LabelledCollection</span></code></a> consisting of the training data</p></li>
<spanclass="sig-name descname"><spanclass="pre">gram_matrix_mix_sum</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">X</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">Y</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">None</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/_kdey.html#KDEyCS.gram_matrix_mix_sum"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method._kdey.KDEyCS.gram_matrix_mix_sum"title="Link to this definition"></a></dt>
<p>where <spanclass="math notranslate nohighlight">\(p_{\alpha}\)</span> is the mixture of class-specific KDEs with mixture parameter (hence class prevalence)
<spanclass="math notranslate nohighlight">\(\alpha\)</span> defined by</p>
<p>where the datapoints (trials) <spanclass="math notranslate nohighlight">\(x_1,\ldots,x_t\sim_{\mathrm{iid}} r\)</span> with <spanclass="math notranslate nohighlight">\(r\)</span> the
<spanclass="sig-name descname"><spanclass="pre">aggregate</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">posteriors</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><spanclass="pre">ndarray</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/_kdey.html#KDEyHD.aggregate"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method._kdey.KDEyHD.aggregate"title="Link to this definition"></a></dt>
<dd><p>Implements the aggregation of label predictions.</p>
<spanclass="sig-name descname"><spanclass="pre">aggregation_fit</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">classif_predictions</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><spanclass="pre">LabelledCollection</span></a></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">data</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><spanclass="pre">LabelledCollection</span></a></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/_kdey.html#KDEyHD.aggregation_fit"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method._kdey.KDEyHD.aggregation_fit"title="Link to this definition"></a></dt>
<li><p><strong>classif_predictions</strong>– a LabelledCollection containing the label predictions issued
by the classifier</p></li>
<li><p><strong>data</strong>– a <aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><codeclass="xref py py-class docutils literal notranslate"><spanclass="pre">quapy.data.base.LabelledCollection</span></code></a> consisting of the training data</p></li>
<p>where <spanclass="math notranslate nohighlight">\(p_{\alpha}\)</span> is the mixture of class-specific KDEs with mixture parameter (hence class prevalence)
<spanclass="math notranslate nohighlight">\(\alpha\)</span> defined by</p>
<spanclass="sig-name descname"><spanclass="pre">aggregate</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">posteriors</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><spanclass="pre">ndarray</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/_kdey.html#KDEyML.aggregate"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method._kdey.KDEyML.aggregate"title="Link to this definition"></a></dt>
<dd><p>Searches for the mixture model parameter (the sought prevalence values) that maximizes the likelihood
of the data (i.e., that minimizes the negative log-likelihood)</p>
<spanclass="sig-name descname"><spanclass="pre">aggregation_fit</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">classif_predictions</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><spanclass="pre">LabelledCollection</span></a></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">data</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><spanclass="pre">LabelledCollection</span></a></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/_kdey.html#KDEyML.aggregation_fit"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method._kdey.KDEyML.aggregation_fit"title="Link to this definition"></a></dt>
<li><p><strong>classif_predictions</strong>– a LabelledCollection containing the label predictions issued
by the classifier</p></li>
<li><p><strong>data</strong>– a <aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><codeclass="xref py py-class docutils literal notranslate"><spanclass="pre">quapy.data.base.LabelledCollection</span></code></a> consisting of the training data</p></li>
<p>Implements the <aclass="reference external"href="https://dl.acm.org/doi/abs/10.1145/3269206.3269287">QuaNet</a> forward pass.
See <aclass="reference internal"href="#quapy.method._neural.QuaNetTrainer"title="quapy.method._neural.QuaNetTrainer"><codeclass="xref py py-class docutils literal notranslate"><spanclass="pre">QuaNetTrainer</span></code></a> for training QuaNet.</p>
<emclass="property"><spanclass="pre">property</span><spanclass="w"></span></em><spanclass="sig-name descname"><spanclass="pre">device</span></span><aclass="headerlink"href="#quapy.method._neural.QuaNetModule.device"title="Link to this definition"></a></dt>
<spanclass="sig-name descname"><spanclass="pre">forward</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">doc_embeddings</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">doc_posteriors</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">statistics</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/_neural.html#QuaNetModule.forward"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method._neural.QuaNetModule.forward"title="Link to this definition"></a></dt>
<dd><p>Defines the computation performed at every call.</p>
<p>Should be overridden by all subclasses.</p>
<divclass="admonition note">
<pclass="admonition-title">Note</p>
<p>Although the recipe for forward pass needs to be defined within
this function, one should call the <codeclass="xref py py-class docutils literal notranslate"><spanclass="pre">Module</span></code> instance afterwards
instead of this since the former takes care of running the
registered hooks while the latter silently ignores them.</p>
<emclass="property"><spanclass="pre">property</span><spanclass="w"></span></em><spanclass="sig-name descname"><spanclass="pre">classes_</span></span><aclass="headerlink"href="#quapy.method._neural.QuaNetTrainer.classes_"title="Link to this definition"></a></dt>
<spanclass="sig-name descname"><spanclass="pre">clean_checkpoint</span></span><spanclass="sig-paren">(</span><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/_neural.html#QuaNetTrainer.clean_checkpoint"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method._neural.QuaNetTrainer.clean_checkpoint"title="Link to this definition"></a></dt>
<spanclass="sig-name descname"><spanclass="pre">clean_checkpoint_dir</span></span><spanclass="sig-paren">(</span><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/_neural.html#QuaNetTrainer.clean_checkpoint_dir"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method._neural.QuaNetTrainer.clean_checkpoint_dir"title="Link to this definition"></a></dt>
<dd><p>Removes anything contained in the checkpoint directory</p>
<spanclass="sig-name descname"><spanclass="pre">fit</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">data</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><spanclass="pre">LabelledCollection</span></a></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">fit_classifier</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">True</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/_neural.html#QuaNetTrainer.fit"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method._neural.QuaNetTrainer.fit"title="Link to this definition"></a></dt>
<spanclass="sig-name descname"><spanclass="pre">get_params</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">deep</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">True</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/_neural.html#QuaNetTrainer.get_params"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method._neural.QuaNetTrainer.get_params"title="Link to this definition"></a></dt>
<ddclass="field-odd"><p><strong>deep</strong> (<em>bool</em><em>, </em><em>default=True</em>) – If True, will return the parameters for this estimator and
<spanclass="sig-name descname"><spanclass="pre">quantify</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">instances</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/_neural.html#QuaNetTrainer.quantify"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method._neural.QuaNetTrainer.quantify"title="Link to this definition"></a></dt>
<dd><p>Generate class prevalence estimates for the sample’s instances</p>
<spanclass="sig-name descname"><spanclass="pre">set_params</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="o"><spanclass="pre">**</span></span><spanclass="n"><spanclass="pre">parameters</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/_neural.html#QuaNetTrainer.set_params"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method._neural.QuaNetTrainer.set_params"title="Link to this definition"></a></dt>
<dd><p>Set the parameters of this estimator.</p>
<p>The method works on simple estimators as well as on nested objects
(such as <codeclass="xref py py-class docutils literal notranslate"><spanclass="pre">Pipeline</span></code>). The latter have
parameters of the form <codeclass="docutils literal notranslate"><spanclass="pre"><component>__<parameter></span></code> so that it’s
possible to update each component of a nested object.</p>
<spanclass="sig-prename descclassname"><spanclass="pre">quapy.method._neural.</span></span><spanclass="sig-name descname"><spanclass="pre">mae_loss</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">output</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">target</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/_neural.html#mae_loss"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method._neural.mae_loss"title="Link to this definition"></a></dt>
<dd><p>Torch-like wrapper for the Mean Absolute Error</p>
<emclass="property"><spanclass="pre">class</span><spanclass="w"></span></em><spanclass="sig-prename descclassname"><spanclass="pre">quapy.method._threshold_optim.</span></span><spanclass="sig-name descname"><spanclass="pre">MAX</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">classifier</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><spanclass="pre">BaseEstimator</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">val_split</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">5</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/_threshold_optim.html#MAX"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method._threshold_optim.MAX"title="Link to this definition"></a></dt>
<spanclass="sig-name descname"><spanclass="pre">condition</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">tpr</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">fpr</span></span></em><spanclass="sig-paren">)</span><spanclass="sig-return"><spanclass="sig-return-icon">→</span><spanclass="sig-return-typehint"><spanclass="pre">float</span></span></span><aclass="reference internal"href="_modules/quapy/method/_threshold_optim.html#MAX.condition"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method._threshold_optim.MAX.condition"title="Link to this definition"></a></dt>
<dd><p>Implements the criterion according to which the threshold should be selected.
This function should return the (float) score to be minimized.</p>
<emclass="property"><spanclass="pre">class</span><spanclass="w"></span></em><spanclass="sig-prename descclassname"><spanclass="pre">quapy.method._threshold_optim.</span></span><spanclass="sig-name descname"><spanclass="pre">MS</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">classifier</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><spanclass="pre">BaseEstimator</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">val_split</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">5</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/_threshold_optim.html#MS"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method._threshold_optim.MS"title="Link to this definition"></a></dt>
<p>Median Sweep. Threshold Optimization variant for <codeclass="xref py py-class docutils literal notranslate"><spanclass="pre">ACC</span></code> as proposed by
<aclass="reference external"href="https://dl.acm.org/doi/abs/10.1145/1150402.1150423">Forman 2006</a> and
<aclass="reference external"href="https://link.springer.com/article/10.1007/s10618-008-0097-y">Forman 2008</a> that generates
class prevalence estimates for all decision thresholds and returns the median of them all.
The goal is to bring improved stability to the denominator of the adjustment.</p>
<spanclass="sig-name descname"><spanclass="pre">aggregate</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">classif_predictions</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><spanclass="pre">ndarray</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/_threshold_optim.html#MS.aggregate"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method._threshold_optim.MS.aggregate"title="Link to this definition"></a></dt>
<dd><p>Implements the aggregation of label predictions.</p>
<spanclass="sig-name descname"><spanclass="pre">aggregation_fit</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">classif_predictions</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><spanclass="pre">LabelledCollection</span></a></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">data</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><spanclass="pre">LabelledCollection</span></a></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/_threshold_optim.html#MS.aggregation_fit"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method._threshold_optim.MS.aggregation_fit"title="Link to this definition"></a></dt>
<li><p><strong>classif_predictions</strong>– a LabelledCollection containing the label predictions issued
by the classifier</p></li>
<li><p><strong>data</strong>– a <aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><codeclass="xref py py-class docutils literal notranslate"><spanclass="pre">quapy.data.base.LabelledCollection</span></code></a> consisting of the training data</p></li>
<spanclass="sig-name descname"><spanclass="pre">condition</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">tpr</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">fpr</span></span></em><spanclass="sig-paren">)</span><spanclass="sig-return"><spanclass="sig-return-icon">→</span><spanclass="sig-return-typehint"><spanclass="pre">float</span></span></span><aclass="reference internal"href="_modules/quapy/method/_threshold_optim.html#MS.condition"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method._threshold_optim.MS.condition"title="Link to this definition"></a></dt>
<dd><p>Implements the criterion according to which the threshold should be selected.
This function should return the (float) score to be minimized.</p>
<emclass="property"><spanclass="pre">class</span><spanclass="w"></span></em><spanclass="sig-prename descclassname"><spanclass="pre">quapy.method._threshold_optim.</span></span><spanclass="sig-name descname"><spanclass="pre">MS2</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">classifier</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><spanclass="pre">BaseEstimator</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">val_split</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">5</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/_threshold_optim.html#MS2"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method._threshold_optim.MS2"title="Link to this definition"></a></dt>
<spanclass="sig-name descname"><spanclass="pre">discard</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">tpr</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">fpr</span></span></em><spanclass="sig-paren">)</span><spanclass="sig-return"><spanclass="sig-return-icon">→</span><spanclass="sig-return-typehint"><spanclass="pre">bool</span></span></span><aclass="reference internal"href="_modules/quapy/method/_threshold_optim.html#MS2.discard"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method._threshold_optim.MS2.discard"title="Link to this definition"></a></dt>
<dd><p>Indicates whether a combination of tpr and fpr should be discarded</p>
<emclass="property"><spanclass="pre">class</span><spanclass="w"></span></em><spanclass="sig-prename descclassname"><spanclass="pre">quapy.method._threshold_optim.</span></span><spanclass="sig-name descname"><spanclass="pre">T50</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">classifier</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><spanclass="pre">BaseEstimator</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">val_split</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">5</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/_threshold_optim.html#T50"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method._threshold_optim.T50"title="Link to this definition"></a></dt>
<spanclass="sig-name descname"><spanclass="pre">condition</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">tpr</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">fpr</span></span></em><spanclass="sig-paren">)</span><spanclass="sig-return"><spanclass="sig-return-icon">→</span><spanclass="sig-return-typehint"><spanclass="pre">float</span></span></span><aclass="reference internal"href="_modules/quapy/method/_threshold_optim.html#T50.condition"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method._threshold_optim.T50.condition"title="Link to this definition"></a></dt>
<dd><p>Implements the criterion according to which the threshold should be selected.
This function should return the (float) score to be minimized.</p>
<emclass="property"><spanclass="pre">class</span><spanclass="w"></span></em><spanclass="sig-prename descclassname"><spanclass="pre">quapy.method._threshold_optim.</span></span><spanclass="sig-name descname"><spanclass="pre">ThresholdOptimization</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">classifier</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><spanclass="pre">BaseEstimator</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">val_split</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">5</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">n_jobs</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">None</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/_threshold_optim.html#ThresholdOptimization"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method._threshold_optim.ThresholdOptimization"title="Link to this definition"></a></dt>
<p>Abstract class of Threshold Optimization variants for <codeclass="xref py py-class docutils literal notranslate"><spanclass="pre">ACC</span></code> as proposed by
<aclass="reference external"href="https://dl.acm.org/doi/abs/10.1145/1150402.1150423">Forman 2006</a> and
<spanclass="sig-name descname"><spanclass="pre">aggregate</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">classif_predictions</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><spanclass="pre">ndarray</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/_threshold_optim.html#ThresholdOptimization.aggregate"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method._threshold_optim.ThresholdOptimization.aggregate"title="Link to this definition"></a></dt>
<dd><p>Implements the aggregation of label predictions.</p>
<spanclass="sig-name descname"><spanclass="pre">aggregate_with_threshold</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">classif_predictions</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">tprs</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">fprs</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">thresholds</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/_threshold_optim.html#ThresholdOptimization.aggregate_with_threshold"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method._threshold_optim.ThresholdOptimization.aggregate_with_threshold"title="Link to this definition"></a></dt>
<spanclass="sig-name descname"><spanclass="pre">aggregation_fit</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">classif_predictions</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><spanclass="pre">LabelledCollection</span></a></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">data</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><spanclass="pre">LabelledCollection</span></a></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/_threshold_optim.html#ThresholdOptimization.aggregation_fit"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method._threshold_optim.ThresholdOptimization.aggregation_fit"title="Link to this definition"></a></dt>
<li><p><strong>classif_predictions</strong>– a LabelledCollection containing the label predictions issued
by the classifier</p></li>
<li><p><strong>data</strong>– a <aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><codeclass="xref py py-class docutils literal notranslate"><spanclass="pre">quapy.data.base.LabelledCollection</span></code></a> consisting of the training data</p></li>
<emclass="property"><spanclass="pre">abstract</span><spanclass="w"></span></em><spanclass="sig-name descname"><spanclass="pre">condition</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">tpr</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">fpr</span></span></em><spanclass="sig-paren">)</span><spanclass="sig-return"><spanclass="sig-return-icon">→</span><spanclass="sig-return-typehint"><spanclass="pre">float</span></span></span><aclass="reference internal"href="_modules/quapy/method/_threshold_optim.html#ThresholdOptimization.condition"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method._threshold_optim.ThresholdOptimization.condition"title="Link to this definition"></a></dt>
<dd><p>Implements the criterion according to which the threshold should be selected.
This function should return the (float) score to be minimized.</p>
<spanclass="sig-name descname"><spanclass="pre">discard</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">tpr</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">fpr</span></span></em><spanclass="sig-paren">)</span><spanclass="sig-return"><spanclass="sig-return-icon">→</span><spanclass="sig-return-typehint"><spanclass="pre">bool</span></span></span><aclass="reference internal"href="_modules/quapy/method/_threshold_optim.html#ThresholdOptimization.discard"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method._threshold_optim.ThresholdOptimization.discard"title="Link to this definition"></a></dt>
<dd><p>Indicates whether a combination of tpr and fpr should be discarded</p>
<emclass="property"><spanclass="pre">class</span><spanclass="w"></span></em><spanclass="sig-prename descclassname"><spanclass="pre">quapy.method._threshold_optim.</span></span><spanclass="sig-name descname"><spanclass="pre">X</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">classifier</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><spanclass="pre">BaseEstimator</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">val_split</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">5</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/_threshold_optim.html#X"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method._threshold_optim.X"title="Link to this definition"></a></dt>
<spanclass="sig-name descname"><spanclass="pre">condition</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">tpr</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">fpr</span></span></em><spanclass="sig-paren">)</span><spanclass="sig-return"><spanclass="sig-return-icon">→</span><spanclass="sig-return-typehint"><spanclass="pre">float</span></span></span><aclass="reference internal"href="_modules/quapy/method/_threshold_optim.html#X.condition"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method._threshold_optim.X.condition"title="Link to this definition"></a></dt>
<dd><p>Implements the criterion according to which the threshold should be selected.
This function should return the (float) score to be minimized.</p>
<ddclass="field-even"><p>float, a score for the given <cite>tpr</cite> and <cite>fpr</cite></p>
</dd>
</dl>
</dd></dl>
</dd></dl>
</section>
<sectionid="module-quapy.method.base">
<spanid="quapy-method-base-module"></span><h2>quapy.method.base module<aclass="headerlink"href="#module-quapy.method.base"title="Link to this heading"></a></h2>
<emclass="property"><spanclass="pre">class</span><spanclass="w"></span></em><spanclass="sig-prename descclassname"><spanclass="pre">quapy.method.base.</span></span><spanclass="sig-name descname"><spanclass="pre">BaseQuantifier</span></span><aclass="reference internal"href="_modules/quapy/method/base.html#BaseQuantifier"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.base.BaseQuantifier"title="Link to this definition"></a></dt>
<p>Abstract Quantifier. A quantifier is defined as an object of a class that implements the method <aclass="reference internal"href="#quapy.method.base.BaseQuantifier.fit"title="quapy.method.base.BaseQuantifier.fit"><codeclass="xref py py-meth docutils literal notranslate"><spanclass="pre">fit()</span></code></a> on
<aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><codeclass="xref py py-class docutils literal notranslate"><spanclass="pre">quapy.data.base.LabelledCollection</span></code></a>, the method <aclass="reference internal"href="#quapy.method.base.BaseQuantifier.quantify"title="quapy.method.base.BaseQuantifier.quantify"><codeclass="xref py py-meth docutils literal notranslate"><spanclass="pre">quantify()</span></code></a>, and the <codeclass="xref py py-meth docutils literal notranslate"><spanclass="pre">set_params()</span></code> and
<codeclass="xref py py-meth docutils literal notranslate"><spanclass="pre">get_params()</span></code> for model selection (see <aclass="reference internal"href="quapy.html#quapy.model_selection.GridSearchQ"title="quapy.model_selection.GridSearchQ"><codeclass="xref py py-meth docutils literal notranslate"><spanclass="pre">quapy.model_selection.GridSearchQ()</span></code></a>)</p>
<emclass="property"><spanclass="pre">abstract</span><spanclass="w"></span></em><spanclass="sig-name descname"><spanclass="pre">fit</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">data</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><spanclass="pre">LabelledCollection</span></a></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/base.html#BaseQuantifier.fit"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.base.BaseQuantifier.fit"title="Link to this definition"></a></dt>
<ddclass="field-odd"><p><strong>data</strong>– a <aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><codeclass="xref py py-class docutils literal notranslate"><spanclass="pre">quapy.data.base.LabelledCollection</span></code></a> consisting of the training data</p>
<emclass="property"><spanclass="pre">abstract</span><spanclass="w"></span></em><spanclass="sig-name descname"><spanclass="pre">quantify</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">instances</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/base.html#BaseQuantifier.quantify"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.base.BaseQuantifier.quantify"title="Link to this definition"></a></dt>
<dd><p>Generate class prevalence estimates for the sample’s instances</p>
<emclass="property"><spanclass="pre">class</span><spanclass="w"></span></em><spanclass="sig-prename descclassname"><spanclass="pre">quapy.method.base.</span></span><spanclass="sig-name descname"><spanclass="pre">BinaryQuantifier</span></span><aclass="reference internal"href="_modules/quapy/method/base.html#BinaryQuantifier"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.base.BinaryQuantifier"title="Link to this definition"></a></dt>
<emclass="property"><spanclass="pre">class</span><spanclass="w"></span></em><spanclass="sig-prename descclassname"><spanclass="pre">quapy.method.base.</span></span><spanclass="sig-name descname"><spanclass="pre">OneVsAll</span></span><aclass="reference internal"href="_modules/quapy/method/base.html#OneVsAll"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.base.OneVsAll"title="Link to this definition"></a></dt>
<emclass="property"><spanclass="pre">class</span><spanclass="w"></span></em><spanclass="sig-prename descclassname"><spanclass="pre">quapy.method.base.</span></span><spanclass="sig-name descname"><spanclass="pre">OneVsAllGeneric</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">binary_quantifier</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">n_jobs</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">None</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/base.html#OneVsAllGeneric"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.base.OneVsAllGeneric"title="Link to this definition"></a></dt>
<emclass="property"><spanclass="pre">property</span><spanclass="w"></span></em><spanclass="sig-name descname"><spanclass="pre">classes_</span></span><aclass="headerlink"href="#quapy.method.base.OneVsAllGeneric.classes_"title="Link to this definition"></a></dt>
<spanclass="sig-name descname"><spanclass="pre">fit</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">data</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><spanclass="pre">LabelledCollection</span></a></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">fit_classifier</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">True</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/base.html#OneVsAllGeneric.fit"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.base.OneVsAllGeneric.fit"title="Link to this definition"></a></dt>
<ddclass="field-odd"><p><strong>data</strong>– a <aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><codeclass="xref py py-class docutils literal notranslate"><spanclass="pre">quapy.data.base.LabelledCollection</span></code></a> consisting of the training data</p>
<spanclass="sig-name descname"><spanclass="pre">quantify</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">instances</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/base.html#OneVsAllGeneric.quantify"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.base.OneVsAllGeneric.quantify"title="Link to this definition"></a></dt>
<dd><p>Generate class prevalence estimates for the sample’s instances</p>
<spanclass="sig-prename descclassname"><spanclass="pre">quapy.method.base.</span></span><spanclass="sig-name descname"><spanclass="pre">newOneVsAll</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">binary_quantifier</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">n_jobs</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">None</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/base.html#newOneVsAll"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.base.newOneVsAll"title="Link to this definition"></a></dt>
<dd></dd></dl>
</section>
<sectionid="module-quapy.method.meta">
<spanid="quapy-method-meta-module"></span><h2>quapy.method.meta module<aclass="headerlink"href="#module-quapy.method.meta"title="Link to this heading"></a></h2>
<spanclass="sig-prename descclassname"><spanclass="pre">quapy.method.meta.</span></span><spanclass="sig-name descname"><spanclass="pre">EACC</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">classifier</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">param_grid</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">None</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">optim</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">None</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">param_mod_sel</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">None</span></span></em>, <emclass="sig-param"><spanclass="o"><spanclass="pre">**</span></span><spanclass="n"><spanclass="pre">kwargs</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/meta.html#EACC"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.meta.EACC"title="Link to this definition"></a></dt>
<dd><p>Implements an ensemble of <aclass="reference internal"href="#quapy.method.aggregative.ACC"title="quapy.method.aggregative.ACC"><codeclass="xref py py-class docutils literal notranslate"><spanclass="pre">quapy.method.aggregative.ACC</span></code></a> quantifiers, as used by
<li><p><strong>kwargs</strong>– kwargs for the class <aclass="reference internal"href="#quapy.method.meta.Ensemble"title="quapy.method.meta.Ensemble"><codeclass="xref py py-class docutils literal notranslate"><spanclass="pre">Ensemble</span></code></a></p></li>
<dd><p>Implements an ensemble of <aclass="reference internal"href="#quapy.method.aggregative.CC"title="quapy.method.aggregative.CC"><codeclass="xref py py-class docutils literal notranslate"><spanclass="pre">quapy.method.aggregative.CC</span></code></a> quantifiers, as used by
<aclass="reference external"href="https://www.sciencedirect.com/science/article/pii/S1566253517303652">Pérez-Gállego et al., 2019</a>.</p>
<li><p><strong>kwargs</strong>– kwargs for the class <aclass="reference internal"href="#quapy.method.meta.Ensemble"title="quapy.method.meta.Ensemble"><codeclass="xref py py-class docutils literal notranslate"><spanclass="pre">Ensemble</span></code></a></p></li>
<li><p><strong>kwargs</strong>– kwargs for the class <aclass="reference internal"href="#quapy.method.meta.Ensemble"title="quapy.method.meta.Ensemble"><codeclass="xref py py-class docutils literal notranslate"><spanclass="pre">Ensemble</span></code></a></p></li>
<dd><p>Implements an ensemble of <aclass="reference internal"href="#quapy.method.aggregative.HDy"title="quapy.method.aggregative.HDy"><codeclass="xref py py-class docutils literal notranslate"><spanclass="pre">quapy.method.aggregative.HDy</span></code></a> quantifiers, as used by
<aclass="reference external"href="https://www.sciencedirect.com/science/article/pii/S1566253517303652">Pérez-Gállego et al., 2019</a>.</p>
<li><p><strong>kwargs</strong>– kwargs for the class <aclass="reference internal"href="#quapy.method.meta.Ensemble"title="quapy.method.meta.Ensemble"><codeclass="xref py py-class docutils literal notranslate"><spanclass="pre">Ensemble</span></code></a></p></li>
<li><p><strong>kwargs</strong>– kwargs for the class <aclass="reference internal"href="#quapy.method.meta.Ensemble"title="quapy.method.meta.Ensemble"><codeclass="xref py py-class docutils literal notranslate"><spanclass="pre">Ensemble</span></code></a></p></li>
<spanclass="sig-name descname"><spanclass="pre">VALID_POLICIES</span></span><emclass="property"><spanclass="w"></span><spanclass="p"><spanclass="pre">=</span></span><spanclass="w"></span><spanclass="pre">{'ave',</span><spanclass="pre">'ds',</span><spanclass="pre">'mae',</span><spanclass="pre">'mkld',</span><spanclass="pre">'mnae',</span><spanclass="pre">'mnkld',</span><spanclass="pre">'mnrae',</span><spanclass="pre">'mrae',</span><spanclass="pre">'mse',</span><spanclass="pre">'ptr'}</span></em><aclass="headerlink"href="#quapy.method.meta.Ensemble.VALID_POLICIES"title="Link to this definition"></a></dt>
<li><p><strong>quantifier</strong>– base quantification member of the ensemble</p></li>
<li><p><strong>size</strong>– number of members</p></li>
<li><p><strong>red_size</strong>– number of members to retain after selection (depending on the policy)</p></li>
<li><p><strong>min_pos</strong>– minimum number of positive instances to consider a sample as valid</p></li>
<li><p><strong>policy</strong>– the selection policy; available policies include: <cite>ave</cite> (default), <cite>ptr</cite>, <cite>ds</cite>, and accuracy
(which is instantiated via a valid error name, e.g., <cite>mae</cite>)</p></li>
<li><p><strong>max_sample_size</strong>– maximum number of instances to consider in the samples (set to None
to indicate no limit, default)</p></li>
<li><p><strong>val_split</strong>– a float in range (0,1) indicating the proportion of data to be used as a stratified held-out
validation split, or a <aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><codeclass="xref py py-class docutils literal notranslate"><spanclass="pre">quapy.data.base.LabelledCollection</span></code></a> (the split itself).</p></li>
<li><p><strong>n_jobs</strong>– number of parallel workers (default 1)</p></li>
<li><p><strong>verbose</strong>– set to True (default is False) to get some information in standard output</p></li>
<emclass="property"><spanclass="pre">property</span><spanclass="w"></span></em><spanclass="sig-name descname"><spanclass="pre">aggregative</span></span><aclass="headerlink"href="#quapy.method.meta.Ensemble.aggregative"title="Link to this definition"></a></dt>
<dd><p>Indicates that the quantifier is not aggregative.</p>
<spanclass="sig-name descname"><spanclass="pre">fit</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">data</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><spanclass="pre">LabelledCollection</span></a></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">val_split</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><spanclass="pre">LabelledCollection</span></a><spanclass="w"></span><spanclass="p"><spanclass="pre">|</span></span><spanclass="w"></span><spanclass="pre">float</span><spanclass="w"></span><spanclass="p"><spanclass="pre">|</span></span><spanclass="w"></span><spanclass="pre">None</span></span><spanclass="w"></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="w"></span><spanclass="default_value"><spanclass="pre">None</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/meta.html#Ensemble.fit"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.meta.Ensemble.fit"title="Link to this definition"></a></dt>
<ddclass="field-odd"><p><strong>data</strong>– a <aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><codeclass="xref py py-class docutils literal notranslate"><spanclass="pre">quapy.data.base.LabelledCollection</span></code></a> consisting of the training data</p>
<spanclass="sig-name descname"><spanclass="pre">get_params</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">deep</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">True</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/meta.html#Ensemble.get_params"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.meta.Ensemble.get_params"title="Link to this definition"></a></dt>
<dd><p>This function should not be used within <aclass="reference internal"href="quapy.html#quapy.model_selection.GridSearchQ"title="quapy.model_selection.GridSearchQ"><codeclass="xref py py-class docutils literal notranslate"><spanclass="pre">quapy.model_selection.GridSearchQ</span></code></a> (is here for compatibility
with the abstract class).
Instead, use <cite>Ensemble(GridSearchQ(q),…)</cite>, with <cite>q</cite> a Quantifier (recommended), or
<cite>Ensemble(Q(GridSearchCV(l)))</cite> with <cite>Q</cite> a quantifier class that has a classifier <cite>l</cite> optimized for
<emclass="property"><spanclass="pre">property</span><spanclass="w"></span></em><spanclass="sig-name descname"><spanclass="pre">probabilistic</span></span><aclass="headerlink"href="#quapy.method.meta.Ensemble.probabilistic"title="Link to this definition"></a></dt>
<dd><p>Indicates that the quantifier is not probabilistic.</p>
<spanclass="sig-name descname"><spanclass="pre">quantify</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">instances</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/meta.html#Ensemble.quantify"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.meta.Ensemble.quantify"title="Link to this definition"></a></dt>
<dd><p>Generate class prevalence estimates for the sample’s instances</p>
<spanclass="sig-name descname"><spanclass="pre">set_params</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="o"><spanclass="pre">**</span></span><spanclass="n"><spanclass="pre">parameters</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/meta.html#Ensemble.set_params"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.meta.Ensemble.set_params"title="Link to this definition"></a></dt>
<dd><p>This function should not be used within <aclass="reference internal"href="quapy.html#quapy.model_selection.GridSearchQ"title="quapy.model_selection.GridSearchQ"><codeclass="xref py py-class docutils literal notranslate"><spanclass="pre">quapy.model_selection.GridSearchQ</span></code></a> (is here for compatibility
with the abstract class).
Instead, use <cite>Ensemble(GridSearchQ(q),…)</cite>, with <cite>q</cite> a Quantifier (recommended), or
<cite>Ensemble(Q(GridSearchCV(l)))</cite> with <cite>Q</cite> a quantifier class that has a classifier <cite>l</cite> optimized for
<spanclass="sig-name descname"><spanclass="pre">fit</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">training</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><spanclass="pre">LabelledCollection</span></a></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/meta.html#MedianEstimator.fit"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.meta.MedianEstimator.fit"title="Link to this definition"></a></dt>
<ddclass="field-odd"><p><strong>data</strong>– a <aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><codeclass="xref py py-class docutils literal notranslate"><spanclass="pre">quapy.data.base.LabelledCollection</span></code></a> consisting of the training data</p>
<spanclass="sig-name descname"><spanclass="pre">get_params</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">deep</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">True</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/meta.html#MedianEstimator.get_params"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.meta.MedianEstimator.get_params"title="Link to this definition"></a></dt>
<ddclass="field-odd"><p><strong>deep</strong> (<em>bool</em><em>, </em><em>default=True</em>) – If True, will return the parameters for this estimator and
<spanclass="sig-name descname"><spanclass="pre">quantify</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">instances</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/meta.html#MedianEstimator.quantify"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.meta.MedianEstimator.quantify"title="Link to this definition"></a></dt>
<dd><p>Generate class prevalence estimates for the sample’s instances</p>
<spanclass="sig-name descname"><spanclass="pre">set_params</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="o"><spanclass="pre">**</span></span><spanclass="n"><spanclass="pre">params</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/meta.html#MedianEstimator.set_params"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.meta.MedianEstimator.set_params"title="Link to this definition"></a></dt>
<dd><p>Set the parameters of this estimator.</p>
<p>The method works on simple estimators as well as on nested objects
(such as <codeclass="xref py py-class docutils literal notranslate"><spanclass="pre">Pipeline</span></code>). The latter have
parameters of the form <codeclass="docutils literal notranslate"><spanclass="pre"><component>__<parameter></span></code> so that it’s
possible to update each component of a nested object.</p>
<spanclass="sig-name descname"><spanclass="pre">fit</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">training</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><spanclass="pre">LabelledCollection</span></a></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/meta.html#MedianEstimator2.fit"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.meta.MedianEstimator2.fit"title="Link to this definition"></a></dt>
<ddclass="field-odd"><p><strong>data</strong>– a <aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><codeclass="xref py py-class docutils literal notranslate"><spanclass="pre">quapy.data.base.LabelledCollection</span></code></a> consisting of the training data</p>
<spanclass="sig-name descname"><spanclass="pre">get_params</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">deep</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">True</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/meta.html#MedianEstimator2.get_params"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.meta.MedianEstimator2.get_params"title="Link to this definition"></a></dt>
<ddclass="field-odd"><p><strong>deep</strong> (<em>bool</em><em>, </em><em>default=True</em>) – If True, will return the parameters for this estimator and
<spanclass="sig-name descname"><spanclass="pre">quantify</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">instances</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/meta.html#MedianEstimator2.quantify"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.meta.MedianEstimator2.quantify"title="Link to this definition"></a></dt>
<spanclass="sig-name descname"><spanclass="pre">set_params</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="o"><spanclass="pre">**</span></span><spanclass="n"><spanclass="pre">params</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/meta.html#MedianEstimator2.set_params"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.meta.MedianEstimator2.set_params"title="Link to this definition"></a></dt>
<dd><p>Set the parameters of this estimator.</p>
<p>The method works on simple estimators as well as on nested objects
(such as <codeclass="xref py py-class docutils literal notranslate"><spanclass="pre">Pipeline</span></code>). The latter have
parameters of the form <codeclass="docutils literal notranslate"><spanclass="pre"><component>__<parameter></span></code> so that it’s
possible to update each component of a nested object.</p>
<dd><p>Ensemble factory. Provides a unified interface for instantiating ensembles that can be optimized (via model
selection for quantification) for a given evaluation metric using <aclass="reference internal"href="quapy.html#quapy.model_selection.GridSearchQ"title="quapy.model_selection.GridSearchQ"><codeclass="xref py py-class docutils literal notranslate"><spanclass="pre">quapy.model_selection.GridSearchQ</span></code></a>.
If the evaluation metric is classification-oriented
(instead of quantification-oriented), then the optimization will be carried out via sklearn’s
<p>Example to instantiate an <aclass="reference internal"href="#quapy.method.meta.Ensemble"title="quapy.method.meta.Ensemble"><codeclass="xref py py-class docutils literal notranslate"><spanclass="pre">Ensemble</span></code></a> based on <aclass="reference internal"href="#quapy.method.aggregative.PACC"title="quapy.method.aggregative.PACC"><codeclass="xref py py-class docutils literal notranslate"><spanclass="pre">quapy.method.aggregative.PACC</span></code></a>
in which the base members are optimized for <aclass="reference internal"href="quapy.html#quapy.error.mae"title="quapy.error.mae"><codeclass="xref py py-meth docutils literal notranslate"><spanclass="pre">quapy.error.mae()</span></code></a> via
<aclass="reference internal"href="quapy.html#quapy.model_selection.GridSearchQ"title="quapy.model_selection.GridSearchQ"><codeclass="xref py py-class docutils literal notranslate"><spanclass="pre">quapy.model_selection.GridSearchQ</span></code></a>. The ensemble follows the policy <cite>Accuracy</cite> based
on <aclass="reference internal"href="quapy.html#quapy.error.mae"title="quapy.error.mae"><codeclass="xref py py-meth docutils literal notranslate"><spanclass="pre">quapy.error.mae()</span></code></a> (the same measure being optimized),
meaning that a static selection of members of the ensemble is made based on their performance
<li><p><strong>kwargs</strong>– kwargs for the class <aclass="reference internal"href="#quapy.method.meta.Ensemble"title="quapy.method.meta.Ensemble"><codeclass="xref py py-class docutils literal notranslate"><spanclass="pre">Ensemble</span></code></a></p></li>
<spanclass="sig-prename descclassname"><spanclass="pre">quapy.method.meta.</span></span><spanclass="sig-name descname"><spanclass="pre">get_probability_distribution</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">posterior_probabilities</span></span></em>, <emclass="sig-param"><spanclass="n"><spanclass="pre">bins</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">8</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/meta.html#get_probability_distribution"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.meta.get_probability_distribution"title="Link to this definition"></a></dt>
<spanid="quapy-method-non-aggregative-module"></span><h2>quapy.method.non_aggregative module<aclass="headerlink"href="#module-quapy.method.non_aggregative"title="Link to this heading"></a></h2>
<emclass="property"><spanclass="pre">classmethod</span><spanclass="w"></span></em><spanclass="sig-name descname"><spanclass="pre">HDx</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">n_jobs</span></span><spanclass="o"><spanclass="pre">=</span></span><spanclass="default_value"><spanclass="pre">None</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/non_aggregative.html#DMx.HDx"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.non_aggregative.DMx.HDx"title="Link to this definition"></a></dt>
<spanclass="sig-name descname"><spanclass="pre">fit</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">data</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><spanclass="pre">LabelledCollection</span></a></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/non_aggregative.html#DMx.fit"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.non_aggregative.DMx.fit"title="Link to this definition"></a></dt>
<dd><p>Generates the validation distributions out of the training data (covariates).
The validation distributions have shape <cite>(n, nfeats, nbins)</cite>, with <cite>n</cite> the number of classes, <cite>nfeats</cite>
the number of features, and <cite>nbins</cite> the number of bins.
In particular, let <cite>V</cite> be the validation distributions; then <cite>di=V[i]</cite> are the distributions obtained from
training data labelled with class <cite>i</cite>; while <cite>dij = di[j]</cite> is the discrete distribution for feature j in
training data labelled with class <cite>i</cite>, and <cite>dij[k]</cite> is the fraction of instances with a value in the <cite>k</cite>-th bin.</p>
<spanclass="sig-name descname"><spanclass="pre">quantify</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">instances</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/non_aggregative.html#DMx.quantify"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.non_aggregative.DMx.quantify"title="Link to this definition"></a></dt>
<dd><p>Searches for the mixture model parameter (the sought prevalence values) that yields a validation distribution
(the mixture) that best matches the test distribution, in terms of the divergence measure of choice.
The matching is computed as the average dissimilarity (in terms of the dissimilarity measure of choice)
between all feature-specific discrete distributions.</p>
<spanclass="sig-prename descclassname"><spanclass="pre">quapy.method.non_aggregative.</span></span><spanclass="sig-name descname"><spanclass="pre">DistributionMatchingX</span></span><aclass="headerlink"href="#quapy.method.non_aggregative.DistributionMatchingX"title="Link to this definition"></a></dt>
<dd><p>alias of <aclass="reference internal"href="#quapy.method.non_aggregative.DMx"title="quapy.method.non_aggregative.DMx"><codeclass="xref py py-class docutils literal notranslate"><spanclass="pre">DMx</span></code></a></p>
<emclass="property"><spanclass="pre">class</span><spanclass="w"></span></em><spanclass="sig-prename descclassname"><spanclass="pre">quapy.method.non_aggregative.</span></span><spanclass="sig-name descname"><spanclass="pre">MaximumLikelihoodPrevalenceEstimation</span></span><aclass="reference internal"href="_modules/quapy/method/non_aggregative.html#MaximumLikelihoodPrevalenceEstimation"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.non_aggregative.MaximumLikelihoodPrevalenceEstimation"title="Link to this definition"></a></dt>
<spanclass="sig-name descname"><spanclass="pre">fit</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">data</span></span><spanclass="p"><spanclass="pre">:</span></span><spanclass="w"></span><spanclass="n"><aclass="reference internal"href="quapy.data.html#quapy.data.base.LabelledCollection"title="quapy.data.base.LabelledCollection"><spanclass="pre">LabelledCollection</span></a></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/non_aggregative.html#MaximumLikelihoodPrevalenceEstimation.fit"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.non_aggregative.MaximumLikelihoodPrevalenceEstimation.fit"title="Link to this definition"></a></dt>
<spanclass="sig-name descname"><spanclass="pre">quantify</span></span><spanclass="sig-paren">(</span><emclass="sig-param"><spanclass="n"><spanclass="pre">instances</span></span></em><spanclass="sig-paren">)</span><aclass="reference internal"href="_modules/quapy/method/non_aggregative.html#MaximumLikelihoodPrevalenceEstimation.quantify"><spanclass="viewcode-link"><spanclass="pre">[source]</span></span></a><aclass="headerlink"href="#quapy.method.non_aggregative.MaximumLikelihoodPrevalenceEstimation.quantify"title="Link to this definition"></a></dt>