more

.devel/sphinx/conf.py

@@ -6,6 +6,9 @@
 
 import genieclust
 
+
+
+
 pkg_name = "genieclust"
 pkg_title = "genieclust"
 pkg_version = genieclust.__version__
@@ -36,6 +39,20 @@
 highlight_language = "python"
 html_last_updated_fmt = today_fmt
 
+plot_include_source = True
+plot_html_show_source_link = False
+plot_pre_code = """
+import numpy as np
+import genieclust
+import matplotlib.pyplot as plt
+np.random.seed(123)
+"""
+doctest_global_setup = plot_pre_code
+numpydoc_use_plots = True
+# https://www.sphinx-doc.org/en/master/usage/extensions/autosummary.html
+autosummary_imported_members = True
+autosummary_generate = True
+
 extensions = [
     'myst_parser',
     'sphinx.ext.mathjax',
@@ -78,25 +95,7 @@
     'code-block': 'Listing %s',
     'section': 'Section %s'
 }
-numfig_secnum_depth = 1
-
-plot_include_source = True
-plot_html_show_source_link = False
-plot_pre_code = """
-import numpy as np
-import genieclust
-import matplotlib.pyplot as plt
-np.random.seed(123)
-"""
-
-doctest_global_setup = plot_pre_code
-
-numpydoc_use_plots = True
-
-# https://www.sphinx-doc.org/en/master/usage/extensions/autosummary.html
-autosummary_imported_members = True
-autosummary_generate = True
-
+numfig_secnum_depth = 0
 
 html_theme = 'furo'
 

.devel/sphinx/fix-html.sh

@@ -0,0 +1,18 @@
+#!/bin/bash
+
+# Copyright (C) 2020-2023, Marek Gagolewski <https://www.gagolewski.com/>
+
+set -e
+
+if [ ! -d "${1}" ]; then
+    echo "The input directory does not exist or was not provided."
+    exit 1
+fi
+
+
+cd "${1}"
+
+for f in *.html; do
+    # merge input and output chunks:
+    sed -rz --in-place 's/<\/pre><\/div>\n<\/div>\n<div class="highlight-(r|python) notranslate"><div class="highlight"><pre>//g' "${f}"
+done

.devel/sphinx/news.md

@@ -86,7 +86,7 @@
    `wcnn_index`.
 
    These cluster validity measures are discussed
-   in more detail at <https://clustering-benchmarks.gagolewski.com>.
+   in more detail at <https://clustering-benchmarks.gagolewski.com/>.
 
 *  [BACKWARD INCOMPATIBILITY] `normalized_confusion_matrix`
    now solves the maximal assignment problem instead of applying

.devel/sphinx/rapi/cluster_validity.md

@@ -87,7 +87,16 @@ X <- as.matrix(iris[,1:4])
 X[,] <- jitter(X)  # otherwise we get a non-unique solution
 y <- as.integer(iris[[5]])
 calinski_harabasz_index(X, y)  # good
+```
+
+```
 ## [1] 486.6681
+```
+
+```r
 calinski_harabasz_index(X, sample(1:3, nrow(X), replace=TRUE))  # bad
+```
+
+```
 ## [1] 2.836713
 ```

.devel/sphinx/rapi/compare_partitions.md

@@ -108,32 +108,107 @@ Gagolewski M., <span class="pkg">genieclust</span>: Fast and robust hierarchical
 y_true <- iris[[5]]
 y_pred <- kmeans(as.matrix(iris[1:4]), 3)$cluster
 normalized_clustering_accuracy(y_true, y_pred)
+```
+
+```
 ## [1] 0.84
+```
+
+```r
 normalized_pivoted_accuracy(y_true, y_pred)
+```
+
+```
 ## [1] 0.84
+```
+
+```r
 pair_sets_index(y_true, y_pred)
+```
+
+```
 ## [1] 0.7568238
+```
+
+```r
 pair_sets_index(y_true, y_pred, simplified=TRUE)
+```
+
+```
 ## [1] 0.7470968
+```
+
+```r
 adjusted_rand_score(y_true, y_pred)
+```
+
+```
 ## [1] 0.7302383
+```
+
+```r
 rand_score(table(y_true, y_pred)) # the same
+```
+
+```
 ## [1] 0.8797315
+```
+
+```r
 adjusted_fm_score(y_true, y_pred)
+```
+
+```
 ## [1] 0.7304411
+```
+
+```r
 fm_score(y_true, y_pred)
+```
+
+```
 ## [1] 0.8208081
+```
+
+```r
 mi_score(y_true, y_pred)
+```
+
+```
 ## [1] 0.8255911
+```
+
+```r
 normalized_mi_score(y_true, y_pred)
+```
+
+```
 ## [1] 0.7581757
+```
+
+```r
 adjusted_mi_score(y_true, y_pred)
+```
+
+```
 ## [1] 0.7551192
+```
+
+```r
 normalized_confusion_matrix(y_true, y_pred)
+```
+
+```
 ##      [,1] [,2] [,3]
 ## [1,]   50    0    0
 ## [2,]    0   48    2
 ## [3,]    0   14   36
+```
+
+```r
 normalizing_permutation(y_true, y_pred)
+```
+
+```
 ## [1] 1 2 3
 ```

.devel/sphinx/rapi/gclust.md

@@ -142,9 +142,21 @@ plot(iris[,2], iris[,3], col=y_pred,
 
 ```r
 adjusted_rand_score(y_test, y_pred)
+```
+
+```
 ## [1] 0.8857921
+```
+
+```r
 pair_sets_index(y_test, y_pred)
+```
+
+```
 ## [1] 0.9049708
+```
+
+```r
 # Fast for low-dimensional Euclidean spaces:
 # h <- gclust(emst_mlpack(X))
 ```

.devel/sphinx/rapi/inequality.md

@@ -87,27 +87,96 @@ Gagolewski M., <span class="pkg">genieclust</span>: Fast and robust hierarchical
 
 ```r
 gini_index(c(2, 2, 2, 2, 2))   # no inequality
+```
+
+```
 ## [1] 0
+```
+
+```r
 gini_index(c(0, 0, 10, 0, 0))  # one has it all
+```
+
+```
 ## [1] 1
+```
+
+```r
 gini_index(c(7, 0, 3, 0, 0))   # give to the poor, take away from the rich
+```
+
+```
 ## [1] 0.85
+```
+
+```r
 gini_index(c(6, 0, 3, 1, 0))   # (a.k.a. Pigou-Dalton principle)
+```
+
+```
 ## [1] 0.75
+```
+
+```r
 bonferroni_index(c(2, 2, 2, 2, 2))
+```
+
+```
 ## [1] 0
+```
+
+```r
 bonferroni_index(c(0, 0, 10, 0, 0))
+```
+
+```
 ## [1] 1
+```
+
+```r
 bonferroni_index(c(7, 0, 3, 0, 0))
+```
+
+```
 ## [1] 0.90625
+```
+
+```r
 bonferroni_index(c(6, 0, 3, 1, 0))
+```
+
+```
 ## [1] 0.8333333
+```
+
+```r
 devergottini_index(c(2, 2, 2, 2, 2))
+```
+
+```
 ## [1] 0
+```
+
+```r
 devergottini_index(c(0, 0, 10, 0, 0))
+```
+
+```
 ## [1] 1
+```
+
+```r
 devergottini_index(c(7, 0, 3, 0, 0))
+```
+
+```
 ## [1] 0.7662338
+```
+
+```r
 devergottini_index(c(6, 0, 3, 1, 0))
+```
+
+```
 ## [1] 0.6493506
 ```

DESCRIPTION

@@ -2,7 +2,7 @@ Package: genieclust
 Type: Package
 Title: Fast and Robust Hierarchical Clustering with Noise Points Detection
 Version: 1.1.5-2
-Date: 2023-10-26
+Date: 2023-10-29
 Authors@R: c(
     person("Marek", "Gagolewski",
         role = c("aut", "cre", "cph"),

LICENSE

@@ -1,5 +1,5 @@
 genieclust package for R and Python
-Copyleft (C) 2018-2023, Marek Gagolewski <https://www.gagolewski.com>
+Copyleft (C) 2018-2023, Marek Gagolewski <https://www.gagolewski.com/>
 
 This program is free software: you can redistribute it and/or modify
 it under the terms of the GNU Affero General Public License