[bug#57099] [PATCH] Add python-hdbscan

[Kiran Shila <me@kiranshila.com>]

---
 gnu/packages/python-science.scm | 41 +++++++++++++++++++++++++++++++++
 1 file changed, 41 insertions(+)

diff --git a/gnu/packages/python-science.scm b/gnu/packages/python-science.scm
index 95f60aae7b..758079c8b6 100644
--- a/gnu/packages/python-science.scm
+++ b/gnu/packages/python-science.scm
@@ -20,6 +20,7 @@
 ;;; Copyright © 2022 Paul A. Patience <paul@apatience.com>
 ;;; Copyright © 2022 Wiktor Żelazny <wzelazny@vurv.cz>
 ;;; Copyright © 2022 Eric Bavier <bavier@posteo.net>
+;;; Copyright © 2022 Kiran Shila <me@kiranshila.com>
 ;;;
 ;;; This file is part of GNU Guix.
 ;;;
@@ -1478,3 +1479,43 @@ (define-public python-opt-einsum
 well as potentially any library which conforms to a standard API. See the
 documentation for more information.")
     (license license:expat)))
+
+(define-public python-hdbscan
+  (package
+    (name "python-hdbscan")
+    (version "0.8.28")
+    (source (origin
+              (method url-fetch)
+              (uri (pypi-uri "hdbscan" version))
+              (sha256
+               (base32
+                "0nn0xm9ji74pkil1lbkrskmyak25jx4av8cdqg2dzgiv5wgzgnpf"))))
+    (build-system python-build-system)
+    (arguments
+     `(#:modules ((ice-9 ftw)
+                  (srfi srfi-1)
+                  (guix build utils)
+                  (guix build python-build-system))
+       #:phases (modify-phases
+                    %standard-phases
+                  (replace 'check
+                    (lambda* (#:key tests? #:allow-other-keys)
+                      (when tests?
+                        (let ((outdir (string-append
+                                       (getcwd) "/build/"
+                                       (car (filter (lambda (s) (string-contains s "lib"))
+                                                    (scandir "build"))))))
+                          (invoke "pytest" "-vv" outdir))))))))
+    (propagated-inputs (list python-cython python-joblib python-numpy
+                             python-scikit-learn python-scipy))
+    (native-inputs (list python-nose python-pytest python-pandas python-networkx))
+    (home-page "http://github.com/scikit-learn-contrib/hdbscan")
+    (synopsis "Clustering based on density with variable density clusters")
+    (description "HDBSCAN - Hierarchical Density-Based Spatial Clustering of
+Applications with Noise. Performs DBSCAN over varying epsilon values and
+integrates the result to find a clustering that gives the best stability over
+epsilon. This allows HDBSCAN to find clusters of varying densities (unlike
+DBSCAN), and be more robust to parameter selection. HDBSCAN is ideal for
+exploratory data analysis; it's a fast and robust algorithm that you can trust
+to return meaningful clusters (if there are any).")
+    (license license:bsd-3)))
-- 
2.37.1