close #84

.devel/pytest/test_compare_partitions.py

@@ -46,6 +46,8 @@ def test_compare_partitions():
             assert -1e-9<pair_sets_index(x, y)<1.0+1e-9
             assert -1e-9<pair_sets_index(x, y, True)<1.0+1e-9
 
+            assert normalized_clustering_accuracy(x, y) == normalized_clustering_accuracy(confusion_matrix(x, y))
+
             y = x.copy()
             y[:5] = 1
             compare_with_sklearn(x, y)

.devel/pytest/test_disjoint_sets.py

@@ -13,7 +13,7 @@ def test_DisjointSets():
         d = DisjointSets(n)
         assert all([i==d.find(i) for i in range(n)])
 
-        for k in range(int(np.random.randint(0, n-2, 1))):
+        for k in range(int(np.random.randint(0, n-2))):
             i = np.random.randint(0, n)
             j = np.random.randint(0, n)
             if d.find(i) == d.find(j): continue
@@ -31,7 +31,7 @@ def test_GiniDisjointSets():
         d = GiniDisjointSets(n)
         assert all([i==d.find(i) for i in range(n)])
 
-        for k in range(int(np.random.randint(0, n-2, 1))):
+        for k in range(int(np.random.randint(0, n-2))):
             i = np.random.randint(0, n)
             j = np.random.randint(0, n)
             if d.find(i) == d.find(j): continue

.devel/sphinx/news.md

@@ -9,12 +9,17 @@
     `adjusted_asymmetric_accuracy` -> `normalized_clustering_accuracy`,
     `normalized_accuracy` -> `normalized_pivoted_accuracy`.
 
+* [BACKWARD INCOMPATIBILITY] [Python] `compare_partitions2` has been removed,
+    as `compare_partitions` and other partition similarity scores
+    now support both pairs of label vectors `(x, y)` and confusion matrices
+    `(x=C, y=None)`.
+
 * [Python and R] New parameter to `pair_sets_index`: `clipped`.
 
-* [R] In `normalizing_permutation` and external cluster validity measures,
-    the input matrix can now be of the type `double`.
+* In `normalizing_permutation` and external cluster validity measures,
+    the input matrices can now be of the type `double`.
 
-* [BUGFIX] [Python] #80: fixed adjustment for `nmslib_n_neighbors`
+* [BUGFIX] [Python] #80: Fixed adjustment for `nmslib_n_neighbors`
     in small samples.
 
 * [BUGFIX] [Python] #82: `cluster_validity` submodule not imported.

.devel/sphinx/rapi/compare_partitions.md

@@ -40,7 +40,7 @@ normalizing_permutation(x, y = NULL)
 |--------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
 | `x`          | an integer vector of length n (or an object coercible to) representing a K-partition of an n-set (e.g., a reference partition), or a confusion matrix with K rows and L columns (see [`table(x, y)`](https://stat.ethz.ch/R-manual/R-devel/library/base/html/table.html)) |
 | `y`          | an integer vector of length n (or an object coercible to) representing an L-partition of the same set (e.g., the output of a clustering algorithm we wish to compare with `x`), or NULL (if x is an K\*L confusion matrix)                                                |
-| `simplified` | whether to assume E=1 in the definition of the pair sets index index, i.e., use Eq. (20) instead of (18); see (Rezaei, Franti, 2016).                                                                                                                                     |
+| `simplified` | whether to assume E=1 in the definition of the pair sets index index, i.e., use Eq. (20) in (Rezaei, Franti, 2016) instead of Eq. (18)                                                                                                                                    |
 | `clipped`    | whether the result should be clipped to the unit interval, i.e., \[0, 1\]                                                                                                                                                                                                 |
 
 ## Details
@@ -53,7 +53,7 @@ Each index except `mi_score()` (which computes the mutual information score) out
 
 `normalized_pivoted_accuracy()` is defined as $(Accuracy(C_\sigma)-1/max(K,L))/(1-1/max(K,L))$, where $C_\sigma$ is a version of the confusion matrix for given `x` and `y` with columns permuted based on the solution to the maximal linear sum assignment problem. The $Accuracy(C_\sigma)$ part is sometimes referred to as set-matching classification rate or pivoted accuracy.
 
-`pair_sets_index()` gives the pair sets index (PSI) (Rezaei, Franti, 2016). 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, i.e., uses Eq. (20) instead of (18).
+`pair_sets_index()` gives the pair sets index (PSI) (Rezaei, Franti, 2016). Pairing is based on the solution to the linear sum assignment problem of a transformed version of the confusion matrix. For non-square matrices, missing rows/columns are assumed to be filled with 0s. The simplified PSI assumes E=1 in the definition of the index, i.e., uses Eq. (20) in the said paper instead of Eq. (18).
 
 `rand_score()` gives the Rand score (the \"probability\" of agreement between the two partitions) and `adjusted_rand_score()` is its version corrected for chance, see (Hubert, Arabie, 1985), its expected value is 0.0 given two independent partitions. Due to the adjustment, the resulting index might also be negative for some inputs.
 

.devel/sphinx/weave/timings_g2mg.py

@@ -133,7 +133,7 @@ def register_result(
         labels_true):
     #########################################################
     partsims = [
-        genieclust.compare_partitions.compare_partitions2(labels_pred, l)
+        genieclust.compare_partitions.compare_partitions(labels_pred, l)
         for l in labels_true
         ]
     partsims = {

DESCRIPTION

@@ -1,8 +1,8 @@
 Package: genieclust
 Type: Package
 Title: Fast and Robust Hierarchical Clustering with Noise Points Detection
-Version: 1.1.4.9003
-Date: 2023-09-19
+Version: 1.1.4.9004
+Date: 2023-09-22
 Authors@R: c(
     person("Marek", "Gagolewski",
         role = c("aut", "cre", "cph"),

NEWS

@@ -9,12 +9,17 @@
     `adjusted_asymmetric_accuracy` -> `normalized_clustering_accuracy`,
     `normalized_accuracy` -> `normalized_pivoted_accuracy`.
 
+* [BACKWARD INCOMPATIBILITY] [Python] `compare_partitions2` has been removed,
+    as `compare_partitions` and other partition similarity scores
+    now support both pairs of label vectors `(x, y)` and confusion matrices
+    `(x=C, y=None)`.
+
 * [Python and R] New parameter to `pair_sets_index`: `clipped`.
 
-* [R] In `normalizing_permutation` and external cluster validity measures,
-    the input matrix can now be of the type `double`.
+* In `normalizing_permutation` and external cluster validity measures,
+    the input matrices can now be of the type `double`.
 
-* [BUGFIX] [Python] #80: fixed adjustment for `nmslib_n_neighbors`
+* [BUGFIX] [Python] #80: Fixed adjustment for `nmslib_n_neighbors`
     in small samples.
 
 * [BUGFIX] [Python] #82: `cluster_validity` submodule not imported.

R/RcppExports.R

@@ -51,8 +51,9 @@
 #' (Rezaei, Franti, 2016).
 #' 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,
-#' i.e., uses Eq. (20) instead of (18).
+#' For non-square matrices, missing rows/columns are assumed to be filled with 0s.
+#' The simplified PSI assumes E=1 in the definition of the index,
+#' i.e., uses Eq. (20) in the said paper instead of Eq. (18).
 #'
 #' \code{rand_score()} gives the Rand score (the "probability" of agreement
 #' between the two partitions) and
@@ -129,7 +130,7 @@
 #' or NULL (if x is an K*L confusion matrix)
 #'
 #' @param simplified whether to assume E=1 in the definition of the pair sets index index,
-#'     i.e., use Eq. (20) instead of (18); see (Rezaei, Franti, 2016).
+#'     i.e., use Eq. (20) in (Rezaei, Franti, 2016) instead of Eq. (18)
 #'
 #' @param clipped whether the result should be clipped to the unit interval, i.e., [0, 1]
 #'

docs/_static/documentation_options.js

@@ -1,5 +1,5 @@
 const DOCUMENTATION_OPTIONS = {
-    VERSION: '1.1.4.9003',
+    VERSION: '1.1.4.9004',
     LANGUAGE: 'en',
     COLLAPSE_INDEX: false,
     BUILDER: 'html',

docs/genieclust.html

@@ -165,7 +165,7 @@
 <a class="sidebar-brand" href="index.html">genieclust</a>
 </span>
 <div class="sidebar-brand">
-1.1.4.9003
+1.1.4.9004
 </div>
 <form class="sidebar-search-container" method="get" action="search.html" role="search">
   <input class="sidebar-search" placeholder="Search" name="q" aria-label="Search">
@@ -328,7 +328,6 @@ <h1>Python Package <cite>genieclust</cite> Reference<a class="headerlink" href="
 <li class="toctree-l2"><a class="reference internal" href="genieclust_compare_partitions.html#genieclust.compare_partitions.adjusted_mi_score"><code class="docutils literal notranslate"><span class="pre">adjusted_mi_score()</span></code></a></li>
 <li class="toctree-l2"><a class="reference internal" href="genieclust_compare_partitions.html#genieclust.compare_partitions.adjusted_rand_score"><code class="docutils literal notranslate"><span class="pre">adjusted_rand_score()</span></code></a></li>
 <li class="toctree-l2"><a class="reference internal" href="genieclust_compare_partitions.html#genieclust.compare_partitions.compare_partitions"><code class="docutils literal notranslate"><span class="pre">compare_partitions()</span></code></a></li>
-<li class="toctree-l2"><a class="reference internal" href="genieclust_compare_partitions.html#genieclust.compare_partitions.compare_partitions2"><code class="docutils literal notranslate"><span class="pre">compare_partitions2()</span></code></a></li>
 <li class="toctree-l2"><a class="reference internal" href="genieclust_compare_partitions.html#genieclust.compare_partitions.confusion_matrix"><code class="docutils literal notranslate"><span class="pre">confusion_matrix()</span></code></a></li>
 <li class="toctree-l2"><a class="reference internal" href="genieclust_compare_partitions.html#genieclust.compare_partitions.fm_score"><code class="docutils literal notranslate"><span class="pre">fm_score()</span></code></a></li>
 <li class="toctree-l2"><a class="reference internal" href="genieclust_compare_partitions.html#genieclust.compare_partitions.mi_score"><code class="docutils literal notranslate"><span class="pre">mi_score()</span></code></a></li>
@@ -403,7 +402,7 @@ <h1>Python Package <cite>genieclust</cite> Reference<a class="headerlink" href="
               Some rights reserved. Licensed under <a href='https://creativecommons.org/licenses/by-nc-nd/4.0/'>CC BY-NC-ND 4.0</a>.
               Built with <a href="https://sphinx-doc.org/">Sphinx</a>
               and a customised <a href="https://github.com/pradyunsg/furo">Furo</a> theme.
-              Last updated on 2023-09-19T17:30:17+1000.
+              Last updated on 2023-09-22T11:29:44+1000.
               This site will never display any ads: it is a non-profit project.
               It does not collect any data.
             </div>
@@ -418,7 +417,7 @@ <h1>Python Package <cite>genieclust</cite> Reference<a class="headerlink" href="
 
     </aside>
   </div>
-</div><script src="_static/documentation_options.js?v=b3339ebc"></script>
+</div><script src="_static/documentation_options.js?v=78ba0e71"></script>
     <script src="_static/doctools.js?v=888ff710"></script>
     <script src="_static/sphinx_highlight.js?v=dc90522c"></script>
     <script src="_static/scripts/furo.js?v=32e29ea5"></script>

docs/genieclust_cluster_validity.html

@@ -165,7 +165,7 @@
 <a class="sidebar-brand" href="index.html">genieclust</a>
 </span>
 <div class="sidebar-brand">
-1.1.4.9003
+1.1.4.9004
 </div>
 <form class="sidebar-search-container" method="get" action="search.html" role="search">
   <input class="sidebar-search" placeholder="Search" name="q" aria-label="Search">
@@ -968,7 +968,7 @@
               Some rights reserved. Licensed under <a href='https://creativecommons.org/licenses/by-nc-nd/4.0/'>CC BY-NC-ND 4.0</a>.
               Built with <a href="https://sphinx-doc.org/">Sphinx</a>
               and a customised <a href="https://github.com/pradyunsg/furo">Furo</a> theme.
-              Last updated on 2023-09-19T17:30:17+1000.
+              Last updated on 2023-09-22T11:29:44+1000.
               This site will never display any ads: it is a non-profit project.
               It does not collect any data.
             </div>
@@ -1010,7 +1010,7 @@
 
     </aside>
   </div>
-</div><script src="_static/documentation_options.js?v=b3339ebc"></script>
+</div><script src="_static/documentation_options.js?v=78ba0e71"></script>
     <script src="_static/doctools.js?v=888ff710"></script>
     <script src="_static/sphinx_highlight.js?v=dc90522c"></script>
     <script src="_static/scripts/furo.js?v=32e29ea5"></script>