Documentation figures.

_docs/docs/ot/cm.md

@@ -22,6 +22,7 @@ The description is based on the docummentation of [pymfe](https://pymfe.readthed
 | VDU | Dunn Index — The lowest intercluster distance divided by the highest intracluster distance. |
             
 ### Complexity
+
 | Metafeature name / name abbreviation | Description |
 | --- | --- |
 | C1 | Entropy of Class Proportions. |    

_docs/docs/ot/da.md

@@ -2,6 +2,7 @@
 layout: page
 title:  "Drift Annotation procedure"
 has_children: true
+nav_order: 10
 ---
 
 ## Drift annotation procedure
@@ -17,19 +18,19 @@ It should be emphasized that the processed streams were previously divided into
 Below we present the classification results using scetterplot (top row) and plot (bottom row) for the processed streams. The quality obtained by GNB is marked in blue, the MLP is marked in gold, and in red - ELM. The x-axis shows the identified moments of drift, determined based on changes in classification quality.
 
 ### Electricity
-![electricity](data/real_streams_gt/electricity.png)
+![electricity](/meta-concept-descriptor/fig_stream/electricity.png)
 
 ### Covtype
-![covtype](data/real_streams_gt/covtypeNorm-1-2vsAll-pruned.png)
+![covtype](/meta-concept-descriptor/fig_stream/covtypeNorm-1-2vsAll-pruned.png)
 
 ### Poker
-![poker](data/real_streams_gt/poker-lsn-1-2vsAll-pruned.png)
+![poker](/meta-concept-descriptor/fig_stream/poker-lsn-1-2vsAll-pruned.png)
 
 ### Insect abrupt
-![insect-abrupt](data/real_streams_gt/INSECTS-abrupt_imbalanced_norm.png)
+![insect-abrupt](/meta-concept-descriptor/fig_stream/INSECTS-abrupt_imbalanced_norm.png)
 
 ### Insect gradual
-![insect-grad](data/real_streams_gt/INSECTS-gradual_imbalanced_norm.png)
+![insect-grad](/meta-concept-descriptor/fig_stream/INSECTS-gradual_imbalanced_norm.png)
 
 ### Insect incremental
-![insect-abrupt](data/real_streams_gt/INSECTS-incremental_imbalanced_norm.png)
+![insect-abrupt](/meta-concept-descriptor/fig_stream/INSECTS-incremental_imbalanced_norm.png)

docs/docs/ot/cm/index.html

@@ -220,30 +220,105 @@ <h3 id="clustering">Clustering</h3>
 </table></div>
 
 <h3 id="complexity">Complexity</h3>
-<p>| Metafeature name / name abbreviation | Description |
-| — | — |
-| C1 | Entropy of Class Proportions. |  <br />
-| C2 | Imbalance Ratio |  <br />
-| Cls_coef | Generates an epsilon-Nearest Neighbours graph. The edges are selected based on the Gower distance between samples, normalized to the range between 0 and 1. Edges between instances of distinct classes are removed. The neighborhood of each vertex is calculated – the instances directly connected to it. Then, the number of edges between the sample’s neighbors is calculated and divided by the maximum possible number of edges between them. The final measure is calculated based on the neighborhood of each point.|  <br />
-| Density | Generates an epsilon-Nearest Neighbours graph as decribed in Cls_coef. The measure calculates the number of edges in the final graph divided by the total possible number of edges.|  <br />
-| F1 | Maximum Fisher’s discriminant ratio. |  <br />
-| F1v | Directional vector maximum Fisher’s discriminant ratio. |  <br />
-| F2 | Volume of overlapping region. |  <br />
-| F3 | Maximum individual feature efficiency. |  <br />
-| F4 | Collective feature efficiency. |  <br />
-| Hubs | Generates an epsilon-Nearest Neighbours graph as decribed in Cls_coef. The measure scores each sample by the number of connections to neighbors, weighted by the number of connections the neighbors have. |  <br />
-| L1 | Sum of the error distance by linear programming. |  <br />
-| L2 | Error rate of linear classifier. |  <br />
-| L3 | Non linearity of linear classifier. |  <br />
-| LSC | Local set average cardinality. |  <br />
-| N1 | Fraction of borderline points. |
-| N2 | Ratio of intra/extra class NN distance. |  <br />
-| N3 | Error rate of NN classifier. |  <br />
-| N4 | Nonlinearity of NN classifier. |  <br />
-| T1 | Fraction of hyperspheres covering data. |      <br />
-| T2 | Number of features per dimension. |      <br />
-| T3 | Number of PCA dimensions per points. |      <br />
-| T4 | Ration of the PCA dimension to the original dimension. |</p>
+
+<div class="table-wrapper"><table>
+  <thead>
+    <tr>
+      <th>Metafeature name / name abbreviation</th>
+      <th>Description</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <td>C1</td>
+      <td>Entropy of Class Proportions.</td>
+    </tr>
+    <tr>
+      <td>C2</td>
+      <td>Imbalance Ratio</td>
+    </tr>
+    <tr>
+      <td>Cls_coef</td>
+      <td>Generates an epsilon-Nearest Neighbours graph. The edges are selected based on the Gower distance between samples, normalized to the range between 0 and 1. Edges between instances of distinct classes are removed. The neighborhood of each vertex is calculated – the instances directly connected to it. Then, the number of edges between the sample’s neighbors is calculated and divided by the maximum possible number of edges between them. The final measure is calculated based on the neighborhood of each point.</td>
+    </tr>
+    <tr>
+      <td>Density</td>
+      <td>Generates an epsilon-Nearest Neighbours graph as decribed in Cls_coef. The measure calculates the number of edges in the final graph divided by the total possible number of edges.</td>
+    </tr>
+    <tr>
+      <td>F1</td>
+      <td>Maximum Fisher’s discriminant ratio.</td>
+    </tr>
+    <tr>
+      <td>F1v</td>
+      <td>Directional vector maximum Fisher’s discriminant ratio.</td>
+    </tr>
+    <tr>
+      <td>F2</td>
+      <td>Volume of overlapping region.</td>
+    </tr>
+    <tr>
+      <td>F3</td>
+      <td>Maximum individual feature efficiency.</td>
+    </tr>
+    <tr>
+      <td>F4</td>
+      <td>Collective feature efficiency.</td>
+    </tr>
+    <tr>
+      <td>Hubs</td>
+      <td>Generates an epsilon-Nearest Neighbours graph as decribed in Cls_coef. The measure scores each sample by the number of connections to neighbors, weighted by the number of connections the neighbors have.</td>
+    </tr>
+    <tr>
+      <td>L1</td>
+      <td>Sum of the error distance by linear programming.</td>
+    </tr>
+    <tr>
+      <td>L2</td>
+      <td>Error rate of linear classifier.</td>
+    </tr>
+    <tr>
+      <td>L3</td>
+      <td>Non linearity of linear classifier.</td>
+    </tr>
+    <tr>
+      <td>LSC</td>
+      <td>Local set average cardinality.</td>
+    </tr>
+    <tr>
+      <td>N1</td>
+      <td>Fraction of borderline points.</td>
+    </tr>
+    <tr>
+      <td>N2</td>
+      <td>Ratio of intra/extra class NN distance.</td>
+    </tr>
+    <tr>
+      <td>N3</td>
+      <td>Error rate of NN classifier.</td>
+    </tr>
+    <tr>
+      <td>N4</td>
+      <td>Nonlinearity of NN classifier.</td>
+    </tr>
+    <tr>
+      <td>T1</td>
+      <td>Fraction of hyperspheres covering data.</td>
+    </tr>
+    <tr>
+      <td>T2</td>
+      <td>Number of features per dimension.</td>
+    </tr>
+    <tr>
+      <td>T3</td>
+      <td>Number of PCA dimensions per points.</td>
+    </tr>
+    <tr>
+      <td>T4</td>
+      <td>Ration of the PCA dimension to the original dimension.</td>
+    </tr>
+  </tbody>
+</table></div>
 
 <h3 id="concept">Concept</h3>
 

docs/docs/ot/da/index.html

@@ -183,22 +183,22 @@ <h2 id="drift-annotation-procedure">Drift annotation procedure</h2>
 <p>Below we present the classification results using scetterplot (top row) and plot (bottom row) for the processed streams. The quality obtained by GNB is marked in blue, the MLP is marked in gold, and in red - ELM. The x-axis shows the identified moments of drift, determined based on changes in classification quality.</p>
 
 <h3 id="electricity">Electricity</h3>
-<p><img src="data/real_streams_gt/electricity.png" alt="electricity" /></p>
+<p><img src="/meta-concept-descriptor/fig_streams/electricity.png" alt="electricity" /></p>
 
 <h3 id="covtype">Covtype</h3>
-<p><img src="data/real_streams_gt/covtypeNorm-1-2vsAll-pruned.png" alt="covtype" /></p>
+<p><img src="/meta-concept-descriptor/data/real_streams_gt/covtypeNorm-1-2vsAll-pruned.png" alt="covtype" /></p>
 
 <h3 id="poker">Poker</h3>
-<p><img src="data/real_streams_gt/poker-lsn-1-2vsAll-pruned.png" alt="poker" /></p>
+<p><img src="/meta-concept-descriptor/data/real_streams_gt/poker-lsn-1-2vsAll-pruned.png" alt="poker" /></p>
 
 <h3 id="insect-abrupt">Insect abrupt</h3>
-<p><img src="data/real_streams_gt/INSECTS-abrupt_imbalanced_norm.png" alt="insect-abrupt" /></p>
+<p><img src="/meta-concept-descriptor/data/real_streams_gt/INSECTS-abrupt_imbalanced_norm.png" alt="insect-abrupt" /></p>
 
 <h3 id="insect-gradual">Insect gradual</h3>
-<p><img src="data/real_streams_gt/INSECTS-gradual_imbalanced_norm.png" alt="insect-grad" /></p>
+<p><img src="/meta-concept-descriptor/data/real_streams_gt/INSECTS-gradual_imbalanced_norm.png" alt="insect-grad" /></p>
 
 <h3 id="insect-incremental">Insect incremental</h3>
-<p><img src="data/real_streams_gt/INSECTS-incremental_imbalanced_norm.png" alt="insect-abrupt" /></p>
+<p><img src="/meta-concept-descriptor/data/real_streams_gt/INSECTS-incremental_imbalanced_norm.png" alt="insect-abrupt" /></p>
 
 
 

docs/feed.xml

@@ -1 +1 @@
-<?xml version="1.0" encoding="utf-8"?><feed xmlns="http://www.w3.org/2005/Atom" ><generator uri="https://jekyllrb.com/" version="4.3.2">Jekyll</generator><link href="/meta-concept-descriptor/feed.xml" rel="self" type="application/atom+xml" /><link href="/meta-concept-descriptor/" rel="alternate" type="text/html" /><updated>2023-10-25T14:40:16+02:00</updated><id>/meta-concept-descriptor/feed.xml</id><title type="html">Supplementary materials</title><subtitle>On metaattribute ability of implicit concept identification</subtitle></feed>
+<?xml version="1.0" encoding="utf-8"?><feed xmlns="http://www.w3.org/2005/Atom" ><generator uri="https://jekyllrb.com/" version="4.3.2">Jekyll</generator><link href="/meta-concept-descriptor/feed.xml" rel="self" type="application/atom+xml" /><link href="/meta-concept-descriptor/" rel="alternate" type="text/html" /><updated>2023-10-25T14:46:37+02:00</updated><id>/meta-concept-descriptor/feed.xml</id><title type="html">Supplementary materials</title><subtitle>On metaattribute ability of implicit concept identification</subtitle></feed>