deploy: braindecode/braindecode@3fc8cd2

Author: bruAristimunha

master/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip

@@ -414,45 +414,6 @@ <h1>Source code for braindecode.preprocessing.preprocess</h1><div class="highlig
             <span class="nb">getattr</span><span class="p">(</span><span class="n">raw_or_epochs</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">fn</span><span class="p">)(</span><span class="o">**</span><span class="bp">self</span><span class="o">.</span><span class="n">kwargs</span><span class="p">)</span></div>
 
 
-<span class="nd">@deprecated</span><span class="p">(</span><span class="n">extra</span><span class="o">=</span><span class="s1">&#39;will be removed in 0.7.0. Use Preprocessor with &#39;</span>
-                  <span class="s1">&#39;`apply_on_array=False` instead.&#39;</span><span class="p">)</span>
-<span class="k">class</span> <span class="nc">MNEPreproc</span><span class="p">(</span><span class="n">Preprocessor</span><span class="p">):</span>
-    <span class="sd">&quot;&quot;&quot;Preprocessor for an MNE-raw/epoch.</span>
-
-<span class="sd">    Parameters</span>
-<span class="sd">    ----------</span>
-<span class="sd">    fn: str or callable</span>
-<span class="sd">        if str, the raw/epoch object must have a member function with that name.</span>
-<span class="sd">        if callable, directly apply the callable to the mne raw/epoch.</span>
-<span class="sd">    kwargs:</span>
-<span class="sd">        Keyword arguments will be forwarded to the mne function</span>
-<span class="sd">    &quot;&quot;&quot;</span>
-
-    <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">fn</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
-        <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">fn</span><span class="p">,</span> <span class="n">apply_on_array</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
-
-
-<span class="nd">@deprecated</span><span class="p">(</span><span class="n">extra</span><span class="o">=</span><span class="s1">&#39;will be removed in 0.7.0. Use Preprocessor with &#39;</span>
-                  <span class="s1">&#39;`apply_on_array=True` instead.&#39;</span><span class="p">)</span>
-<span class="k">class</span> <span class="nc">NumpyPreproc</span><span class="p">(</span><span class="n">Preprocessor</span><span class="p">):</span>
-    <span class="sd">&quot;&quot;&quot;Preprocessor that directly operates on the underlying numpy array of an mne raw/epoch.</span>
-
-<span class="sd">    Parameters</span>
-<span class="sd">    ----------</span>
-<span class="sd">    fn: callable</span>
-<span class="sd">        Function that preprocesses the numpy array</span>
-<span class="sd">    channel_wise: bool</span>
-<span class="sd">        Whether to apply the function channel-wise.</span>
-<span class="sd">    kwargs:</span>
-<span class="sd">        Keyword arguments will be forwarded to the function</span>
-<span class="sd">    &quot;&quot;&quot;</span>
-
-    <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">fn</span><span class="p">,</span> <span class="n">channel_wise</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
-        <span class="k">assert</span> <span class="n">callable</span><span class="p">(</span><span class="n">fn</span><span class="p">),</span> <span class="s1">&#39;fn must be callable.&#39;</span>
-        <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">fn</span><span class="p">,</span> <span class="n">apply_on_array</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">channel_wise</span><span class="o">=</span><span class="n">channel_wise</span><span class="p">,</span>
-                         <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
-
-
 <div class="viewcode-block" id="preprocess"><a class="viewcode-back" href="../../../generated/braindecode.preprocessing.preprocess.html#braindecode.preprocessing.preprocess">[docs]</a><span class="k">def</span> <span class="nf">preprocess</span><span class="p">(</span><span class="n">concat_ds</span><span class="p">,</span> <span class="n">preprocessors</span><span class="p">,</span> <span class="n">save_dir</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">overwrite</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
                <span class="n">n_jobs</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
     <span class="sd">&quot;&quot;&quot;Apply preprocessors to a concat dataset.</span>
@@ -701,35 +662,6 @@ <h1>Source code for braindecode.preprocessing.preprocess</h1><div class="highlig
     <span class="k">return</span> <span class="n">demeaned</span><span class="o">.</span><span class="n">T</span></div>
 
 
-<div class="viewcode-block" id="zscore"><a class="viewcode-back" href="../../../generated/braindecode.preprocessing.zscore.html#braindecode.preprocessing.zscore">[docs]</a><span class="nd">@deprecated</span><span class="p">(</span><span class="n">extra</span><span class="o">=</span><span class="s1">&#39;will be removed in 0.7.0. Use sklearn.preprocessing.scale &#39;</span>
-                  <span class="s1">&#39;instead.&#39;</span><span class="p">)</span>
-<span class="k">def</span> <span class="nf">zscore</span><span class="p">(</span><span class="n">data</span><span class="p">):</span>
-    <span class="sd">&quot;&quot;&quot;Zscore normalize continuous or windowed data in-place.</span>
-
-<span class="sd">    Parameters</span>
-<span class="sd">    ----------</span>
-<span class="sd">    data: np.ndarray (n_channels, n_times) or (n_windows, n_channels, n_times)</span>
-<span class="sd">        continuous or windowed signal</span>
-
-<span class="sd">    Returns</span>
-<span class="sd">    -------</span>
-<span class="sd">    zscored: np.ndarray (n_channels x n_times) or (n_windows x n_channels x</span>
-<span class="sd">    n_times)</span>
-<span class="sd">        normalized continuous or windowed data</span>
-
-<span class="sd">    ..note:</span>
-<span class="sd">        If this function is supposed to preprocess continuous data, it should be</span>
-<span class="sd">        given to raw.apply_function().</span>
-<span class="sd">    &quot;&quot;&quot;</span>
-    <span class="n">zscored</span> <span class="o">=</span> <span class="n">data</span> <span class="o">-</span> <span class="n">np</span><span class="o">.</span><span class="n">mean</span><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="n">keepdims</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">axis</span><span class="o">=-</span><span class="mi">1</span><span class="p">)</span>
-    <span class="n">zscored</span> <span class="o">=</span> <span class="n">zscored</span> <span class="o">/</span> <span class="n">np</span><span class="o">.</span><span class="n">std</span><span class="p">(</span><span class="n">zscored</span><span class="p">,</span> <span class="n">keepdims</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">axis</span><span class="o">=-</span><span class="mi">1</span><span class="p">)</span>
-    <span class="c1"># TODO: the overriding of protected &#39;_data&#39; should be implemented in the</span>
-    <span class="c1"># TODO: dataset when transforms are applied to windows</span>
-    <span class="k">if</span> <span class="nb">hasattr</span><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="s1">&#39;_data&#39;</span><span class="p">):</span>
-        <span class="n">data</span><span class="o">.</span><span class="n">_data</span> <span class="o">=</span> <span class="n">zscored</span>
-    <span class="k">return</span> <span class="n">zscored</span></div>
-
-
 <div class="viewcode-block" id="scale"><a class="viewcode-back" href="../../../generated/braindecode.preprocessing.scale.html#braindecode.preprocessing.scale">[docs]</a><span class="nd">@deprecated</span><span class="p">(</span><span class="n">extra</span><span class="o">=</span><span class="s1">&#39;will be removed in 0.7.0. Use numpy.multiply instead.&#39;</span><span class="p">)</span>
 <span class="k">def</span> <span class="nf">scale</span><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="n">factor</span><span class="p">):</span>
     <span class="sd">&quot;&quot;&quot;Scale continuous or windowed data in-place</span>

master/_downloads/6f1e7a639e0699d6164445b55e6c116d/auto_examples_jupyter.zip

@@ -546,11 +546,6 @@
    braindecode.preprocessing.exponential_moving_standardize
   </a>
  </li>
- <li class="toctree-l1">
-  <a class="reference internal" href="generated/braindecode.preprocessing.zscore.html">
-   braindecode.preprocessing.zscore
-  </a>
- </li>
  <li class="toctree-l1">
   <a class="reference internal" href="generated/braindecode.preprocessing.scale.html">
    braindecode.preprocessing.scale
@@ -1035,19 +1030,16 @@ <h2><a class="toc-backref" href="#id11">Preprocessing</a><a class="headerlink" h
 <tr class="row-odd"><td><p><a class="reference internal" href="generated/braindecode.preprocessing.exponential_moving_standardize.html#braindecode.preprocessing.exponential_moving_standardize" title="braindecode.preprocessing.exponential_moving_standardize"><code class="xref py py-obj docutils literal notranslate"><span class="pre">exponential_moving_standardize</span></code></a>(data[, ...])</p></td>
 <td><p>Perform exponential moving standardization.</p></td>
 </tr>
-<tr class="row-even"><td><p><a class="reference internal" href="generated/braindecode.preprocessing.zscore.html#braindecode.preprocessing.zscore" title="braindecode.preprocessing.zscore"><code class="xref py py-obj docutils literal notranslate"><span class="pre">zscore</span></code></a>(data)</p></td>
-<td><p>DEPRECATED: will be removed in 0.7.0.</p></td>
-</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="generated/braindecode.preprocessing.scale.html#braindecode.preprocessing.scale" title="braindecode.preprocessing.scale"><code class="xref py py-obj docutils literal notranslate"><span class="pre">scale</span></code></a>(data, factor)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="generated/braindecode.preprocessing.scale.html#braindecode.preprocessing.scale" title="braindecode.preprocessing.scale"><code class="xref py py-obj docutils literal notranslate"><span class="pre">scale</span></code></a>(data, factor)</p></td>
 <td><p>DEPRECATED: will be removed in 0.7.0.</p></td>
 </tr>
-<tr class="row-even"><td><p><a class="reference internal" href="generated/braindecode.preprocessing.filterbank.html#braindecode.preprocessing.filterbank" title="braindecode.preprocessing.filterbank"><code class="xref py py-obj docutils literal notranslate"><span class="pre">filterbank</span></code></a>(raw, frequency_bands[, ...])</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="generated/braindecode.preprocessing.filterbank.html#braindecode.preprocessing.filterbank" title="braindecode.preprocessing.filterbank"><code class="xref py py-obj docutils literal notranslate"><span class="pre">filterbank</span></code></a>(raw, frequency_bands[, ...])</p></td>
 <td><p>Applies multiple bandpass filters to the signals in raw.</p></td>
 </tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="generated/braindecode.preprocessing.preprocess.html#braindecode.preprocessing.preprocess" title="braindecode.preprocessing.preprocess"><code class="xref py py-obj docutils literal notranslate"><span class="pre">preprocess</span></code></a>(concat_ds, preprocessors[, ...])</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="generated/braindecode.preprocessing.preprocess.html#braindecode.preprocessing.preprocess" title="braindecode.preprocessing.preprocess"><code class="xref py py-obj docutils literal notranslate"><span class="pre">preprocess</span></code></a>(concat_ds, preprocessors[, ...])</p></td>
 <td><p>Apply preprocessors to a concat dataset.</p></td>
 </tr>
-<tr class="row-even"><td><p><a class="reference internal" href="generated/braindecode.preprocessing.Preprocessor.html#braindecode.preprocessing.Preprocessor" title="braindecode.preprocessing.Preprocessor"><code class="xref py py-obj docutils literal notranslate"><span class="pre">Preprocessor</span></code></a>(fn, *[, apply_on_array])</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="generated/braindecode.preprocessing.Preprocessor.html#braindecode.preprocessing.Preprocessor" title="braindecode.preprocessing.Preprocessor"><code class="xref py py-obj docutils literal notranslate"><span class="pre">Preprocessor</span></code></a>(fn, *[, apply_on_array])</p></td>
 <td><p>Preprocessor for an MNE Raw or Epochs object.</p></td>
 </tr>
 </tbody>

master/_images/sphx_glr_plot_bcic_iv_2a_moabb_cropped_001.png

@@ -465,7 +465,7 @@
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/usr/share/miniconda/envs/braindecode/lib/python3.7/site-packages/sklearn/utils/deprecation.py:87: FutureWarning: Function scale is deprecated; will be removed in 0.7.0. Use numpy.multiply instead.
   warnings.warn(msg, category=FutureWarning)
 
-&lt;braindecode.datasets.moabb.MOABBDataset object at 0x7f7d77298390&gt;
+&lt;braindecode.datasets.moabb.MOABBDataset object at 0x7f8f1bfa7ed0&gt;
 </pre></div>
 </div>
 <section id="create-model-and-compute-windowing-parameters">
@@ -634,10 +634,10 @@ <h2>Split the dataset<a class="headerlink" href="#split-the-dataset" title="Perm
   warnings.warn(warning_msg, SkorchWarning)
   epoch    train_accuracy    train_loss    valid_accuracy    valid_loss      lr      dur
 -------  ----------------  ------------  ----------------  ------------  ------  -------
-      1            0.2500        1.4486            0.2500        5.4385  0.0006  16.8113
-      2            0.2569        1.2315            0.2500        3.6823  0.0005  16.5741
-      3            0.3958        1.1476            0.3611        2.2702  0.0002  16.5465
-      4            0.4340        1.1225            0.4410        1.4375  0.0000  16.5769
+      1            0.2500        1.4486            0.2500        5.4386  0.0006  20.5234
+      2            0.2569        1.2315            0.2500        3.6824  0.0005  19.9409
+      3            0.3958        1.1476            0.3611        2.2702  0.0002  19.8328
+      4            0.4340        1.1225            0.4410        1.4375  0.0000  19.7846
 
 &lt;class &#39;braindecode.classifier.EEGClassifier&#39;&gt;[initialized](
   module_=ShallowFBCSPNet(
@@ -734,8 +734,8 @@ <h2>Plot Confusion Matrix<a class="headerlink" href="#plot-confusion-matrix" tit
 <img src="../_images/sphx_glr_plot_bcic_iv_2a_moabb_cropped_002.png" srcset="../_images/sphx_glr_plot_bcic_iv_2a_moabb_cropped_002.png" alt="plot bcic iv 2a moabb cropped" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>&lt;Figure size 800x550 with 1 Axes&gt;
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  33.969 seconds)</p>
-<p><strong>Estimated memory usage:</strong>  1195 MB</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes  52.548 seconds)</p>
+<p><strong>Estimated memory usage:</strong>  991 MB</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-auto-examples-plot-bcic-iv-2a-moabb-cropped-py">
 <div class="sphx-glr-download sphx-glr-download-python docutils container">
 <p><a class="reference download internal" download="" href="../_downloads/995f58ef1b3d29dce64caee24e5bf457/plot_bcic_iv_2a_moabb_cropped.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">plot_bcic_iv_2a_moabb_cropped.py</span></code></a></p>

master/_images/sphx_glr_plot_bcic_iv_2a_moabb_cropped_thumb.png

@@ -435,7 +435,7 @@ <h3>Preprocessing<a class="headerlink" href="#preprocessing" title="Permalink to
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/usr/share/miniconda/envs/braindecode/lib/python3.7/site-packages/sklearn/utils/deprecation.py:87: FutureWarning: Function scale is deprecated; will be removed in 0.7.0. Use numpy.multiply instead.
   warnings.warn(msg, category=FutureWarning)
 
-&lt;braindecode.datasets.moabb.MOABBDataset object at 0x7f7d53f94d50&gt;
+&lt;braindecode.datasets.moabb.MOABBDataset object at 0x7f8f36ce8f50&gt;
 </pre></div>
 </div>
 </section>
@@ -568,10 +568,10 @@ <h2>Training<a class="headerlink" href="#training" title="Permalink to this head
 </div>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>  epoch    train_accuracy    train_loss    valid_accuracy    valid_loss      lr     dur
 -------  ----------------  ------------  ----------------  ------------  ------  ------
-      1            0.2604        1.6159            0.2465        5.6120  0.0006  6.4000
-      2            0.2535        1.2103            0.2535        6.3209  0.0005  6.2357
-      3            0.2535        1.0746            0.2535        5.2375  0.0002  6.4500
-      4            0.2674        1.0589            0.2535        3.9899  0.0000  6.4442
+      1            0.2604        1.6159            0.2465        5.6117  0.0006  8.1866
+      2            0.2535        1.2103            0.2535        6.3208  0.0005  8.1967
+      3            0.2535        1.0746            0.2535        5.2375  0.0002  8.3569
+      4            0.2674        1.0589            0.2535        3.9899  0.0000  8.2435
 
 &lt;class &#39;braindecode.classifier.EEGClassifier&#39;&gt;[initialized](
   module_=ShallowFBCSPNet(
@@ -662,8 +662,8 @@ <h2>Plot Confusion Matrix<a class="headerlink" href="#plot-confusion-matrix" tit
 <img src="../_images/sphx_glr_plot_bcic_iv_2a_moabb_trial_002.png" srcset="../_images/sphx_glr_plot_bcic_iv_2a_moabb_trial_002.png" alt="plot bcic iv 2a moabb trial" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>&lt;Figure size 800x550 with 1 Axes&gt;
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes  40.226 seconds)</p>
-<p><strong>Estimated memory usage:</strong>  1080 MB</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes  50.477 seconds)</p>
+<p><strong>Estimated memory usage:</strong>  789 MB</p>
 <div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-auto-examples-plot-bcic-iv-2a-moabb-trial-py">
 <div class="sphx-glr-download sphx-glr-download-python docutils container">
 <p><a class="reference download internal" download="" href="../_downloads/475edf2d5ed60b15717de3100f3551a5/plot_bcic_iv_2a_moabb_trial.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">plot_bcic_iv_2a_moabb_trial.py</span></code></a></p>