v1.1.2

gagolews · Sep 17, 2022 · d371c3d · d371c3d
1 parent f215b33
commit d371c3d
Show file tree

Hide file tree

Showing 43 changed files with 123 additions and 116 deletions.
diff --git a/.devel/sphinx/news.md b/.devel/sphinx/news.md
@@ -1,7 +1,7 @@
 # What Is New in *genieclust*
 
 
-## 1.1.1.9001 (under development)
+## 1.1.2 (2022-09-17)
 
 *  [Python and R] `adjusted_asymmetric_accuracy`
    now accepts confusion matrices with fewer columns than rows.
@@ -10,8 +10,6 @@
 *  [Python and R] `pair_sets_index`, and `normalized_accuracy` return
    the same results for nonsymmetric confusion matrices and transposes thereof.
 
-*  ...
-
 
 ## 1.1.1 (2022-09-15)
 

diff --git a/.github/workflows/py.yml b/.github/workflows/py.yml
@@ -47,6 +47,6 @@ jobs:
     - name: Lint with flake8
       run: |
         # stop the build if there are Python syntax errors or undefined names
-        flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics  --exclude=devel,build,docs,.git,R,dist,genieclust.egg-info,man,tutorials
+        flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics  --exclude=.devel,build,docs,.git,R,dist,genieclust.egg-info,man,tutorials
         # exit-zero treats all errors as warnings
-        flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics  --exclude=devel,build,docs,.git,R,dist,genieclust.egg-info,man,tutorials
+        flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics  --exclude=.devel,build,docs,.git,R,dist,genieclust.egg-info,man,tutorials
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -1,7 +1,7 @@
 Package: genieclust
 Type: Package
 Title: Fast and Robust Hierarchical Clustering with Noise Points Detection
-Version: 1.1.1.9001
+Version: 1.1.2
 Date: 2022-09-17
 Authors@R: c(
     person("Marek", "Gagolewski",

diff --git a/NEWS b/NEWS
@@ -1,7 +1,7 @@
 # What Is New in *genieclust*
 
 
-## 1.1.1.9001 (under development)
+## 1.1.2 (2022-09-17)
 
 *  [Python and R] `adjusted_asymmetric_accuracy`
    now accepts confusion matrices with fewer columns than rows.
@@ -10,8 +10,6 @@
 *  [Python and R] `pair_sets_index`, and `normalized_accuracy` return
    the same results for nonsymmetric confusion matrices and transposes thereof.
 
-*  ...
-
 
 ## 1.1.1 (2022-09-15)
 

diff --git a/docs/_static/documentation_options.js b/docs/_static/documentation_options.js
@@ -1,6 +1,6 @@
 var DOCUMENTATION_OPTIONS = {
     URL_ROOT: document.getElementById("documentation_options").getAttribute('data-url_root'),
-    VERSION: '1.1.1',
+    VERSION: '1.1.2',
     LANGUAGE: 'en',
     COLLAPSE_INDEX: false,
     BUILDER: 'html',

diff --git a/docs/genieclust.html b/docs/genieclust.html
@@ -78,7 +78,7 @@
           </a>
 
           <div class="version">
-              Python and R Package<br />    v1.1.1
+              Python and R Package<br />    v1.1.2
           </div>
 
 <!--
@@ -303,7 +303,7 @@ <h1>Python Package <cite>genieclust</cite> Reference<a class="headerlink" href="
     and a customised <a href="https://github.com/rtfd/sphinx_rtd_theme">rtd</a>
     theme.
       <span class="lastupdated">
-        Last updated on 2022-09-15T13:23:22+1000.
+        Last updated on 2022-09-17T17:13:14+1000.
       </span>
 
 

diff --git a/docs/genieclust_cluster_validity.html b/docs/genieclust_cluster_validity.html
@@ -80,7 +80,7 @@
           </a>
 
           <div class="version">
-              Python and R Package<br />    v1.1.1
+              Python and R Package<br />    v1.1.2
           </div>
 
 <!--
@@ -901,7 +901,7 @@
     and a customised <a href="https://github.com/rtfd/sphinx_rtd_theme">rtd</a>
     theme.
       <span class="lastupdated">
-        Last updated on 2022-09-15T13:23:22+1000.
+        Last updated on 2022-09-17T17:13:14+1000.
       </span>
 
 

diff --git a/docs/genieclust_compare_partitions.html b/docs/genieclust_compare_partitions.html
@@ -80,7 +80,7 @@
           </a>
 
           <div class="version">
-              Python and R Package<br />    v1.1.1
+              Python and R Package<br />    v1.1.2
           </div>
 
 <!--
@@ -283,13 +283,14 @@
 </div>
 <p class="rubric">Notes</p>
 <p>Let <span class="math notranslate nohighlight">\(C\)</span> be a confusion matrix with <span class="math notranslate nohighlight">\(K\)</span> rows
-and <span class="math notranslate nohighlight">\(K\)</span> columns.
+and <span class="math notranslate nohighlight">\(L\)</span> columns.
 AAA is an external cluster validity measure.
 It is a corrected-for-chance summary of the proportion of correctly
 classified points in each cluster (with cluster matching based on the
 solution to the maximal linear sum assignment problem; see
 <a class="reference internal" href="#genieclust.compare_partitions.normalize_confusion_matrix" title="genieclust.compare_partitions.normalize_confusion_matrix"><code class="xref py py-func docutils literal notranslate"><span class="pre">normalize_confusion_matrix()</span></code></a>), given by:
-<span class="math notranslate nohighlight">\((\max_\sigma \sum_{i=1}^K (c_{i, \sigma(i)}/(c_{i, 1}+...+c_{i, K})) - 1)/(K - 1)\)</span>.</p>
+<span class="math notranslate nohighlight">\((\max_\sigma \sum_{i=1}^K (c_{i, \sigma(i)}/(c_{i, 1}+...+c_{i, K})) - 1)/(K - 1)\)</span>.
+Missing columns are treated as if they were filled with 0s.</p>
 <p>Note that this measure is not symmetric, i.e., <code class="docutils literal notranslate"><span class="pre">index(x,</span> <span class="pre">y)</span></code> does not
 have to be equal to <code class="docutils literal notranslate"><span class="pre">index(y,</span> <span class="pre">x)</span></code>.</p>
 <p>See <a class="reference internal" href="#r4f44c4f81b3c-1" id="id2">[1]</a> for more details and <a class="reference internal" href="#genieclust.compare_partitions.compare_partitions" title="genieclust.compare_partitions.compare_partitions"><code class="xref py py-func docutils literal notranslate"><span class="pre">compare_partitions()</span></code></a> for more functions.</p>
@@ -407,7 +408,7 @@
 <dt class="field-odd">Parameters</dt>
 <dd class="field-odd"><dl class="simple">
 <dt><strong>C</strong><span class="classifier">ndarray</span></dt><dd><p>A <code class="docutils literal notranslate"><span class="pre">c_contiguous</span></code> confusion matrix (contingency table)
-with <span class="math notranslate nohighlight">\(K\)</span> rows and <span class="math notranslate nohighlight">\(L\)</span> columns, where <span class="math notranslate nohighlight">\(K \le L\)</span>.</p>
+with <span class="math notranslate nohighlight">\(K\)</span> rows and <span class="math notranslate nohighlight">\(L\)</span> columns.</p>
 </dd>
 </dl>
 </dd>
@@ -435,7 +436,7 @@
 </dd>
 <dt><code class="docutils literal notranslate"><span class="pre">'spsi'</span></code></dt><dd><p>Simplified pair sets index</p>
 </dd>
-<dt><code class="docutils literal notranslate"><span class="pre">'aaa'</span></code></dt><dd><p>Adjusted asymmetric accuracy (or <code class="docutils literal notranslate"><span class="pre">nan</span></code> if <span class="math notranslate nohighlight">\(K \neq L\)</span>);
+<dt><code class="docutils literal notranslate"><span class="pre">'aaa'</span></code></dt><dd><p>Adjusted asymmetric accuracy;
 it is assumed that rows in <cite>C</cite> represent the ground-truth
 partition</p>
 </dd>
@@ -471,8 +472,8 @@
 nonempty and pairwise disjoint subsets.
 For instance, these can be two clusterings of a dataset with <span class="math notranslate nohighlight">\(n\)</span>
 observations specified as vectors of labels. Moreover, let <cite>C</cite> be the
-confusion matrix (with <span class="math notranslate nohighlight">\(K\)</span> rows and <span class="math notranslate nohighlight">\(L\)</span> columns,
-<span class="math notranslate nohighlight">\(K \leq L\)</span>) corresponding to <cite>x</cite> and <cite>y</cite>; see also
+confusion matrix with <span class="math notranslate nohighlight">\(K\)</span> rows and <span class="math notranslate nohighlight">\(L\)</span> columns,
+corresponding to <cite>x</cite> and <cite>y</cite>; see also
 <a class="reference internal" href="#genieclust.compare_partitions.confusion_matrix" title="genieclust.compare_partitions.confusion_matrix"><code class="xref py py-func docutils literal notranslate"><span class="pre">confusion_matrix()</span></code></a>.</p>
 <p>This function implements a few scores that aim to quantify
 the similarity between <cite>x</cite> and <cite>y</cite>.</p>
@@ -487,8 +488,7 @@
 Note that partitions are always defined up to a bijection of the set of
 possible labels, e.g., (1, 1, 2, 1) and (4, 4, 2, 4)
 represent the same 2-partition.</p>
-<p><cite>adjusted_asymmetric_accuracy</cite> <a class="reference internal" href="#rb28289ab3e3a-2" id="id5">[2]</a>
-only accepts <span class="math notranslate nohighlight">\(K = L\)</span>. It is an external cluster validity measure
+<p><cite>adjusted_asymmetric_accuracy</cite> <a class="reference internal" href="#rb28289ab3e3a-2" id="id5">[2]</a> is an external cluster validity measure
 which assumes that the label vector <cite>x</cite> (or rows in the confusion
 matrix) represents the reference (ground truth) partition.
 It is a corrected-for-chance summary of the proportion of correctly
@@ -498,15 +498,15 @@
 <span class="math notranslate nohighlight">\((\max_\sigma \sum_{i=1}^K (c_{i, \sigma(i)}/(c_{i, 1}+...+c_{i, K})) - 1)/(K - 1)\)</span>,
 where <span class="math notranslate nohighlight">\(C\)</span> is the confusion matrix.</p>
 <p><cite>normalized_accuracy</cite> is a measure defined as
-<span class="math notranslate nohighlight">\((\mathrm{Accuracy}(C_\sigma)-1/L)/(1-1/L)\)</span>,
+<span class="math notranslate nohighlight">\((\mathrm{Accuracy}(C_\sigma)-1/\max(K,L))/(1-1/\max(K,L))\)</span>,
 where <span class="math notranslate nohighlight">\(C_\sigma\)</span> is a version of the confusion matrix
-for given <cite>x</cite> and <cite>y</cite>, <span class="math notranslate nohighlight">\(K \leq L\)</span>, with columns permuted
+for given <cite>x</cite> and <cite>y</cite> with columns permuted
 based on the solution to the maximal linear sum assignment problem.
 Note that the <span class="math notranslate nohighlight">\(\mathrm{Accuracy}(C_\sigma)\)</span> part
 is sometimes referred to as set-matching classification
 rate or pivoted accuracy.</p>
 <p><cite>pair_sets_index</cite> gives the Pair Sets Index (PSI)
-adjusted for chance <a class="reference internal" href="#rb28289ab3e3a-3" id="id6">[3]</a>, <span class="math notranslate nohighlight">\(K \leq L\)</span>.
+adjusted for chance <a class="reference internal" href="#rb28289ab3e3a-3" id="id6">[3]</a>.
 Pairing is based on the solution to the linear sum assignment problem
 of a transformed version of the confusion matrix.
 Its simplified version assumes E=1 in the definition of the index,
@@ -1026,7 +1026,7 @@
     and a customised <a href="https://github.com/rtfd/sphinx_rtd_theme">rtd</a>
     theme.
       <span class="lastupdated">
-        Last updated on 2022-09-15T13:23:22+1000.
+        Last updated on 2022-09-17T17:13:14+1000.
       </span>
 
 

diff --git a/docs/genieclust_genie.html b/docs/genieclust_genie.html
@@ -80,7 +80,7 @@
           </a>
 
           <div class="version">
-              Python and R Package<br />    v1.1.1
+              Python and R Package<br />    v1.1.2
           </div>
 
 <!--
@@ -651,7 +651,7 @@ <h1>genieclust.Genie<a class="headerlink" href="#genieclust-genie" title="Permal
     and a customised <a href="https://github.com/rtfd/sphinx_rtd_theme">rtd</a>
     theme.
       <span class="lastupdated">
-        Last updated on 2022-09-15T13:23:22+1000.
+        Last updated on 2022-09-17T17:13:14+1000.
       </span>
 
 

diff --git a/docs/genieclust_inequity.html b/docs/genieclust_inequity.html
@@ -80,7 +80,7 @@
           </a>
 
           <div class="version">
-              Python and R Package<br />    v1.1.1
+              Python and R Package<br />    v1.1.2
           </div>
 
 <!--
@@ -486,7 +486,7 @@
     and a customised <a href="https://github.com/rtfd/sphinx_rtd_theme">rtd</a>
     theme.
       <span class="lastupdated">
-        Last updated on 2022-09-15T13:23:22+1000.
+        Last updated on 2022-09-17T17:13:14+1000.
       </span>
 
 

diff --git a/docs/genieclust_internal.html b/docs/genieclust_internal.html
@@ -80,7 +80,7 @@
           </a>
 
           <div class="version">
-              Python and R Package<br />    v1.1.1
+              Python and R Package<br />    v1.1.2
           </div>
 
 <!--
@@ -580,7 +580,7 @@
     and a customised <a href="https://github.com/rtfd/sphinx_rtd_theme">rtd</a>
     theme.
       <span class="lastupdated">
-        Last updated on 2022-09-15T13:23:22+1000.
+        Last updated on 2022-09-17T17:13:14+1000.
       </span>
 
 

diff --git a/docs/genieclust_plots-1.pdf b/docs/genieclust_plots-1.pdf
diff --git a/docs/genieclust_plots-2.pdf b/docs/genieclust_plots-2.pdf
diff --git a/docs/genieclust_plots-3.pdf b/docs/genieclust_plots-3.pdf
diff --git a/docs/genieclust_plots-4.pdf b/docs/genieclust_plots-4.pdf
diff --git a/docs/genieclust_plots.html b/docs/genieclust_plots.html
@@ -78,7 +78,7 @@
           </a>
 
           <div class="version">
-              Python and R Package<br />    v1.1.1
+              Python and R Package<br />    v1.1.2
           </div>
 
 <!--
@@ -397,7 +397,7 @@
     and a customised <a href="https://github.com/rtfd/sphinx_rtd_theme">rtd</a>
     theme.
       <span class="lastupdated">
-        Last updated on 2022-09-15T13:23:22+1000.
+        Last updated on 2022-09-17T17:13:14+1000.
       </span>
 
 

diff --git a/docs/genieclust_tools.html b/docs/genieclust_tools.html
@@ -80,7 +80,7 @@
           </a>
 
           <div class="version">
-              Python and R Package<br />    v1.1.1
+              Python and R Package<br />    v1.1.2
           </div>
 
 <!--
@@ -424,7 +424,7 @@
     and a customised <a href="https://github.com/rtfd/sphinx_rtd_theme">rtd</a>
     theme.
       <span class="lastupdated">
-        Last updated on 2022-09-15T13:23:22+1000.
+        Last updated on 2022-09-17T17:13:14+1000.
       </span>
 
 

diff --git a/docs/genindex.html b/docs/genindex.html
@@ -75,7 +75,7 @@
           </a>
 
           <div class="version">
-              Python and R Package<br />    v1.1.1
+              Python and R Package<br />    v1.1.2
           </div>
 
 <!--
@@ -539,7 +539,7 @@ <h2 id="W">W</h2>
     and a customised <a href="https://github.com/rtfd/sphinx_rtd_theme">rtd</a>
     theme.
       <span class="lastupdated">
-        Last updated on 2022-09-15T13:23:22+1000.
+        Last updated on 2022-09-17T17:13:14+1000.
       </span>
 
 

diff --git a/docs/index.html b/docs/index.html
@@ -77,7 +77,7 @@
           </a>
 
           <div class="version">
-              Python and R Package<br />    v1.1.1
+              Python and R Package<br />    v1.1.2
           </div>
 
 <!--
@@ -440,7 +440,7 @@ <h2>Contributing<a class="headerlink" href="#contributing" title="Permalink to t
     and a customised <a href="https://github.com/rtfd/sphinx_rtd_theme">rtd</a>
     theme.
       <span class="lastupdated">
-        Last updated on 2022-09-15T13:23:22+1000.
+        Last updated on 2022-09-17T17:13:14+1000.
       </span>