Merge branch 'adapt-python:master' into master

Author: antoinedemathelin

README.md

@@ -18,32 +18,32 @@ The purpose of the ADAPT library is to facilitate the access to transfer leanrin
 <table>
   <tr valign="top">
     <td width="50%" >
-        <a href="doc/examples/Sample_bias_example.html">
+        <a href="https://adapt-python.github.io/adapt/examples/Sample_bias_example.html">
             <br>
             <b>Sample bias correction</b>
             <br>
             <br>
-            <img src="src_docs/_static/images/sample_bias_corr_img.png">
+            <img src="https://github.com/adapt-python/adapt/blob/41c13055facc0733faf49c4e3979709e82be10e5/docs/_static/images/sample_bias_corr_img.png">
         </a>
     </td>
     <td width="50%">
-        <a href="doc/examples/Flowers_example.html">
+        <a href="https://adapt-python.github.io/adapt/examples/Flowers_example.html">
             <br>
             <b>Model-based Transfer</b>
             <br>
             <br>
-            <img src="src_docs/_static/images/finetuned.png">
+            <img src="https://github.com/adapt-python/adapt/blob/41c13055facc0733faf49c4e3979709e82be10e5/docs/_static/images/finetuned.png">
         </a>
     </td>
   </tr>
   <tr valign="top">
     <td width="50%">
-        <a href="doc/examples/Flowers_example.html">
+        <a href="https://adapt-python.github.io/adapt/examples/Office_example.html">
             <br>
             <b>Deep Domain Adaptation</b>
             <br>
             <br>
-            <img src="src_docs/_static/images/office_item.png">
+            <img src="https://github.com/adapt-python/adapt/blob/41c13055facc0733faf49c4e3979709e82be10e5/docs/_static/images/office_item.png">
         </a>
     </td>
     <td width="50%">
@@ -85,7 +85,7 @@ Finally import the module in your python scripts with:
 import adapt
 ```
 
-An simple example of usage is given in the [Qick-Start](#Quick-Start) below.
+A simple example of usage is given in the [Qick-Start](#Quick-Start) below.
 
 
 ## ADAPT Guideline
@@ -217,9 +217,9 @@ adapt_model.score(Xt, yt)
 >>> 0.574
 ```
 
-| <img src="src_docs/_static/images/results_qs.png"> | 
+| <img src="https://github.com/adapt-python/adapt/blob/41c13055facc0733faf49c4e3979709e82be10e5/docs/_static/images/results_qs.png"> | 
 |:--:| 
-| **Quick-Start Plotting Results**. *The dotted and dashed lines are respectively the class separation of the "source only" and KMM models. Note that the predicted positive class is on the right of the dotted line for the "source only" model but on the left of the dashed line for KMM. (The code for plotting the Figure is available [here](docs/examples/Quick_start.html))* |
+| **Quick-Start Plotting Results**. *The dotted and dashed lines are respectively the class separation of the "source only" and KMM models. Note that the predicted positive class is on the right of the dotted line for the "source only" model but on the left of the dashed line for KMM. (The code for plotting the Figure is available [here](https://adapt-python.github.io/adapt/examples/Quick_start.html))* |
 
 
 ## Contents
@@ -285,4 +285,4 @@ If you use this library in your research, please cite ADAPT using the following
 
 This work has been funded by Michelin and the Industrial Data Analytics and Machine Learning chair from ENS Paris-Saclay, Borelli center.
 
-[<img src="src_docs/_static/images/michelin.png" width=200px alt="Michelin">](https://www.michelin.com/) <img src="src_docs/_static/images/idaml.jpg" width=200px alt="IDAML"> <img src="src_docs/_static/images/borelli.jpg" alt="Centre Borelli" width=150px>
+[<img src="https://github.com/adapt-python/adapt/blob/41c13055facc0733faf49c4e3979709e82be10e5/docs/_static/images/michelin.png" width=200px alt="Michelin">](https://www.michelin.com/) [<img src="https://github.com/adapt-python/adapt/blob/41c13055facc0733faf49c4e3979709e82be10e5/docs/_static/images/idaml.jpg" width=200px alt="IDAML">](https://centreborelli.ens-paris-saclay.fr/fr/chaire-idaml) [<img src="https://github.com/adapt-python/adapt/blob/41c13055facc0733faf49c4e3979709e82be10e5/docs/_static/images/borelli.jpg" alt="Centre Borelli" width=150px>](https://centreborelli.ens-paris-saclay.fr/fr)

docs/_images/deep_da.png

@@ -49,6 +49,7 @@
 <p class="caption" role="heading"><span class="caption-text">Tutorials</span></p>
 <ul>
 <li class="toctree-l1"><a class="reference internal" href="map.html">Choosing the right algorithm</a></li>
+<li class="toctree-l1"><a class="reference internal" href="examples/Quick_start.html">Quick-Start</a></li>
 </ul>
 <p class="caption" role="heading"><span class="caption-text">API Documentation</span></p>
 <ul>
@@ -118,7 +119,7 @@
 </ul>
 </li>
 </ul>
-<p class="caption" role="heading"><span class="caption-text">Examples Gallery</span></p>
+<p class="caption" role="heading"><span class="caption-text">Synthetic Examples</span></p>
 <ul>
 <li class="toctree-l1"><a class="reference internal" href="examples/Classification.html">Classification</a><ul>
 <li class="toctree-l2"><a class="reference internal" href="examples/Classification.html#Experimental-Setup">Experimental Setup</a></li>
@@ -181,13 +182,31 @@
 <li class="toctree-l2"><a class="reference internal" href="examples/Multi_fidelity.html#RegularTransferNN">RegularTransferNN</a></li>
 </ul>
 </li>
+</ul>
+<p class="caption" role="heading"><span class="caption-text">Real Examples</span></p>
+<ul>
+<li class="toctree-l1"><a class="reference internal" href="examples/Sample_bias_example.html">Sample Bias</a><ul>
+<li class="toctree-l2"><a class="reference internal" href="examples/Sample_bias_example.html#Sample-Bias-on-the-diabetes-dataset">Diabetes Dataset</a></li>
+<li class="toctree-l2"><a class="reference internal" href="examples/Sample_bias_example.html#Applying-Transfer-Learning-for-correcting-sample-bias">Sample bias correction</a></li>
+<li class="toctree-l2"><a class="reference internal" href="examples/Sample_bias_example.html#Hidden-bias-and-features-importance-estimation">Features importance</a></li>
+</ul>
+</li>
+<li class="toctree-l1"><a class="reference internal" href="examples/Flowers_example.html">Fine-Tuning</a><ul>
+<li class="toctree-l2"><a class="reference internal" href="examples/Flowers_example.html#Training-a-model-from-scratch">Train from Scratch</a></li>
+<li class="toctree-l2"><a class="reference internal" href="examples/Flowers_example.html#Model-based-Transfer">Model-based Transfer</a></li>
+</ul>
+</li>
+<li class="toctree-l1"><a class="reference internal" href="examples/Office_example.html">Deep Domain Adaptation</a><ul>
+<li class="toctree-l2"><a class="reference internal" href="examples/Office_example.html#Dataset-Preprocessing">Dataset Preprocessing</a></li>
+<li class="toctree-l2"><a class="reference internal" href="examples/Office_example.html#Fit-without-adaptation">Fit without adaptation</a></li>
+<li class="toctree-l2"><a class="reference internal" href="examples/Office_example.html#Fit-with-adaptation">Fit with adaptation</a></li>
+</ul>
+</li>
 <li class="toctree-l1"><a class="reference internal" href="examples/tradaboost_experiments.html">TrAdaBoost Experiments</a><ul>
 <li class="toctree-l2"><a class="reference internal" href="examples/tradaboost_experiments.html#Mushrooms">Mushrooms</a></li>
 <li class="toctree-l2"><a class="reference internal" href="examples/tradaboost_experiments.html#20-NewsGroup">20-NewsGroup</a></li>
 </ul>
 </li>
-    
-    
 </ul>
 
         </div>
@@ -353,7 +372,7 @@ <h1>ADAPT<a class="headerlink" href="#adapt" title="Permalink to this headline">
 <td><p>Two Stage Transfer AdaBoost for Regression</p></td>
 </tr>
 <tr class="row-even"><td><p><a class="reference internal" href="generated/adapt.instance_based.WANN.html#adapt.instance_based.WANN" title="adapt.instance_based.WANN"><code class="xref py py-obj docutils literal notranslate"><span class="pre">instance_based.WANN</span></code></a>([task, weighter, Xt, ...])</p></td>
-<td><p>WANN: Weighting Adversarial Neural Network is an instance-based domain adaptation method suited for regression tasks.</p></td>
+<td><p>WANN : Weighting Adversarial Neural Network is an instance-based domain adaptation method suited for regression tasks.</p></td>
 </tr>
 </tbody>
 </table>
@@ -490,10 +509,22 @@ <h1>ADAPT<a class="headerlink" href="#adapt" title="Permalink to this headline">
 </table>
 </section>
 </section>
-<section id="examples-gallery">
-<span id="gallery"></span><h1>Examples Gallery<a class="headerlink" href="#examples-gallery" title="Permalink to this headline"></a></h1>
+<section id="synthetic-examples">
+<span id="gallery"></span><h1>Synthetic Examples<a class="headerlink" href="#synthetic-examples" title="Permalink to this headline"></a></h1>
 <div class="toctree-wrapper compound">
 </div>
+<div class="sphx-glr-thumbcontainer">
+  <div class="figure align-center">
+    <img alt="thumbnail" src="./_static/no_image.png" />
+    <p class="caption">
+      <span class="caption-text">
+        <a class="reference internal" href="examples/Quick_start.html">
+          <span class="std std-ref">Quick-Start</span>
+        </a>
+      </span>
+    </p>
+  </div>
+</div>
 <div class="sphx-glr-thumbcontainer">
   <div class="figure align-center">
     <img alt="thumbnail" src="./_images/examples_Classification_9_0.png" />
@@ -578,6 +609,47 @@ <h1>ADAPT<a class="headerlink" href="#adapt" title="Permalink to this headline">
     </p>
   </div>
 </div>
+<div class="sphx-glr-clear"></div></section>
+<section id="real-examples">
+<h1>Real Examples<a class="headerlink" href="#real-examples" title="Permalink to this headline"></a></h1>
+<div class="toctree-wrapper compound">
+</div>
+<div class="sphx-glr-thumbcontainer">
+  <div class="figure align-center">
+    <img alt="thumbnail" src="./_static/images/sample_bias_corr_img.png" />
+    <p class="caption">
+      <span class="caption-text">
+        <a class="reference internal" href="examples/Sample_bias_example.html">
+          <span class="std std-ref">Correcting Sample Bias with Transfer Leanring</span>
+        </a>
+      </span>
+    </p>
+  </div>
+</div>
+<div class="sphx-glr-thumbcontainer">
+  <div class="figure align-center">
+    <img alt="thumbnail" src="./_static/images/finetuned.png" />
+    <p class="caption">
+      <span class="caption-text">
+        <a class="reference internal" href="examples/Flowers_example.html">
+          <span class="std std-ref">Model-Based Transfer Learning</span>
+        </a>
+      </span>
+    </p>
+  </div>
+</div>
+<div class="sphx-glr-thumbcontainer">
+  <div class="figure align-center">
+    <img alt="thumbnail" src="./_static/images/office_item.png" />
+    <p class="caption">
+      <span class="caption-text">
+        <a class="reference internal" href="examples/Office_example.html">
+          <span class="std std-ref">Deep Domain Adaptation: Transfer one domain to another</span>
+        </a>
+      </span>
+    </p>
+  </div>
+</div>
 <div class="sphx-glr-thumbcontainer">
   <div class="figure align-center">
     <img alt="thumbnail" src="./_static/no_image.png" />

docs/_images/examples_Flowers_example_14_0.png

@@ -49,6 +49,7 @@
 <p class="caption" role="heading"><span class="caption-text">Tutorials</span></p>
 <ul>
 <li class="toctree-l1"><a class="reference internal" href="../map.html">Choosing the right algorithm</a></li>
+<li class="toctree-l1"><a class="reference internal" href="Quick_start.html">Quick-Start</a></li>
 </ul>
 <p class="caption" role="heading"><span class="caption-text">API Documentation</span></p>
 <ul>
@@ -118,7 +119,7 @@
 </ul>
 </li>
 </ul>
-<p class="caption" role="heading"><span class="caption-text">Examples Gallery</span></p>
+<p class="caption" role="heading"><span class="caption-text">Synthetic Examples</span></p>
 <ul>
 <li class="toctree-l1"><a class="reference internal" href="#">Classification</a><ul>
 <li class="toctree-l2"><a class="reference internal" href="#Experimental-Setup">Experimental Setup</a></li>
@@ -181,13 +182,31 @@
 <li class="toctree-l2"><a class="reference internal" href="Multi_fidelity.html#RegularTransferNN">RegularTransferNN</a></li>
 </ul>
 </li>
+</ul>
+<p class="caption" role="heading"><span class="caption-text">Real Examples</span></p>
+<ul>
+<li class="toctree-l1"><a class="reference internal" href="Sample_bias_example.html">Sample Bias</a><ul>
+<li class="toctree-l2"><a class="reference internal" href="Sample_bias_example.html#Sample-Bias-on-the-diabetes-dataset">Diabetes Dataset</a></li>
+<li class="toctree-l2"><a class="reference internal" href="Sample_bias_example.html#Applying-Transfer-Learning-for-correcting-sample-bias">Sample bias correction</a></li>
+<li class="toctree-l2"><a class="reference internal" href="Sample_bias_example.html#Hidden-bias-and-features-importance-estimation">Features importance</a></li>
+</ul>
+</li>
+<li class="toctree-l1"><a class="reference internal" href="Flowers_example.html">Fine-Tuning</a><ul>
+<li class="toctree-l2"><a class="reference internal" href="Flowers_example.html#Training-a-model-from-scratch">Train from Scratch</a></li>
+<li class="toctree-l2"><a class="reference internal" href="Flowers_example.html#Model-based-Transfer">Model-based Transfer</a></li>
+</ul>
+</li>
+<li class="toctree-l1"><a class="reference internal" href="Office_example.html">Deep Domain Adaptation</a><ul>
+<li class="toctree-l2"><a class="reference internal" href="Office_example.html#Dataset-Preprocessing">Dataset Preprocessing</a></li>
+<li class="toctree-l2"><a class="reference internal" href="Office_example.html#Fit-without-adaptation">Fit without adaptation</a></li>
+<li class="toctree-l2"><a class="reference internal" href="Office_example.html#Fit-with-adaptation">Fit with adaptation</a></li>
+</ul>
+</li>
 <li class="toctree-l1"><a class="reference internal" href="tradaboost_experiments.html">TrAdaBoost Experiments</a><ul>
 <li class="toctree-l2"><a class="reference internal" href="tradaboost_experiments.html#Mushrooms">Mushrooms</a></li>
 <li class="toctree-l2"><a class="reference internal" href="tradaboost_experiments.html#20-NewsGroup">20-NewsGroup</a></li>
 </ul>
 </li>
-    
-    
 </ul>
 
         </div>
@@ -485,8 +504,8 @@
 </style>
 <section id="Classification">
 <h1>Classification<a class="headerlink" href="#Classification" title="Permalink to this headline"></a></h1>
-<div class="btn btn-notebook" role="button"><p><img alt="475376cff1634f1d89b22c3f2e3f6411" src="../_images/colab_logo_32px.png" /> <a class="reference external" href="https://colab.research.google.com/drive/1ANQUix9Y6V4RXu-vAaCFGmU979d5m4bO?usp=sharing">Run in Google Colab</a></p>
-</div><div class="btn btn-notebook" role="button"><p><img alt="209d341613514b4dad564fdb33156135" src="../_images/github_logo_32px.png" /> <a class="reference external" href="https://github.com/adapt-python/notebooks/blob/d0364973c642ea4880756cef4e9f2ee8bb5e8495/Classification.ipynb">View on GitHub</a></p>
+<div class="btn btn-notebook" role="button"><p><img alt="dda7d7dd3db14ac69e4918e30af9deca" src="../_images/colab_logo_32px.png" /> <a class="reference external" href="https://colab.research.google.com/drive/1ANQUix9Y6V4RXu-vAaCFGmU979d5m4bO?usp=sharing">Run in Google Colab</a></p>
+</div><div class="btn btn-notebook" role="button"><p><img alt="2f3cd66b341b4a609e2fc4334bdc16d6" src="../_images/github_logo_32px.png" /> <a class="reference external" href="https://github.com/adapt-python/notebooks/blob/d0364973c642ea4880756cef4e9f2ee8bb5e8495/Classification.ipynb">View on GitHub</a></p>
 </div><p>You will find here the application of DA methods from the ADAPT package on a simple two dimensional DA classification problem.</p>
 <p>First we import packages needed in the following. We will use <code class="docutils literal notranslate"><span class="pre">matplotlib</span> <span class="pre">Animation</span></code> tools in order to get a visual understanding of the mselected methods:</p>
 <div class="nbinput nblast docutils container">