Recent Releases of genieclust
genieclust - genieclust_1.2.0
1.2.0 (2025-07-24)
[Python and R] Using the new implementation of Euclidean and mutual reachability minimum spanning trees (quite fast in low dimensional spaces) from the
quitefastmstpackage.[Python and R] [BACKWARD INCOMPATIBILITY]
mlpackis not used anymore.[Python] [BACKWARD INCOMPATIBILITY] Seeking approximate near-neighbours with
nmslibis no longer supported directly (the package has not been updated for a while).[Python]
MSTClusterMixin(BaseEstimator, ClusterMixin): A base class for Genie, GIc, and other MST-based clustering algorithms.[Python] [BACKWARD INCOMPATIBILITY]
GenieandGIc:affinitywas renamedmatrix.
- C++
Published by gagolews 10 months ago
genieclust - genieclust_1.1.6
1.1.6 (2024-08-22)
- [PYTHON] The package now works with numpy 2.0.
- C++
Published by gagolews almost 2 years ago
genieclust - genieclust_1.1.5
1.1.5 (2023-10-18)
[BACKWARD INCOMPATIBILITY] [Python and R] Inequality measures are no longer referred to as inequity measures.
[BACKWARD INCOMPATIBILITY] [Python and R] Some external cluster validity measures were renamed (as per the major revision of https://doi.org/10.48550/arXiv.2209.02935):
adjusted_asymmetric_accuracy->normalized_clustering_accuracy,normalized_accuracy->normalized_pivoted_accuracy.[BACKWARD INCOMPATIBILITY] [Python]
compare_partitions2has been removed, ascompare_partitionsand 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.In
normalizing_permutationand external cluster validity measures, the input matrices can now be of the typedouble.[BUGFIX] [Python] #80: Fixed adjustment for
nmslib_n_neighborsin small samples.[BUGFIX] [Python] #82:
cluster_validitysubmodule not imported.[BUGFIX] Some external cluster validity measures now handle NaNs better and are slightly less prone to round-off errors.
- C++
Published by gagolews over 2 years ago
genieclust - genieclust_1.1.3
1.1.3 (2023-01-17)
[R]
mst.defaultnow throws an error if any element in the input matrix is missing/infinite.[Python] Fixed call to
mlpack.emstthat no longer worked with the new version ofmlpack.
- C++
Published by gagolews over 3 years ago
genieclust - genieclust_1.1.2
1.1.2 (2022-09-17)
[Python and R]
adjusted_asymmetric_accuracynow accepts confusion matrices with fewer columns than rows. Such "missing" columns are now treated as if they were filled with 0s.[Python and R]
pair_sets_index, andnormalized_accuracyreturn the same results for non-symmetric confusion matrices and transposes thereof.
- C++
Published by gagolews over 3 years ago
genieclust - genieclust_1.1.1
1.1.1 (2022-09-15)
[Python] #75:
nmslibis now optional.[BUILD TIME]: The use of
ssize_twas not portable.
- C++
Published by gagolews over 3 years ago
genieclust - genieclust_1.1.0
1.1.0 (2022-09-05)
[GENERAL] The cluster validity measures are discussed in more detail at https://clustering-benchmarks.gagolewski.com.
[Python and R] New function:
compare_partitions.adjusted_asymmetric_accuracy.[Python and R] Implementations of the so-called internal cluster validity measures discussed in DOI: 10.1016/j.ins.2021.10.004; see our (GitHub-only) CVI package for R. In particular, the generalised Dunn indices are based on the code originally authored by Maciej Bartoszuk. Thanks.
Functions added (to the cluster_validity module in the Python version):
calinski_harabasz_index,
dunnowa_index,
generalised_dunn_index,
negated_ball_hall_index,
negated_davies_bouldin_index,
negated_wcss_index,
silhouette_index,
silhouette_w_index,
wcnn_index.
[BACKWARD INCOMPATIBILITY]
compare_partitions.normalized_confusion_matrixnow solves the maximal assignment problem instead of applying a primitive partial pivoting.[Python and R] New function:
compare_partitions.normalizing_permutation[R] New function:
normalized_confusion_matrix.[Python and R] New parameter to
compare_partitions.pair_sets_index:simplified.[Python] New parameters to
plots.plot_scatter:axis,title,xlabel,ylabel,xlim,ylim.
- C++
Published by gagolews over 3 years ago
genieclust - genieclust_1.0.1
genieclust 1.0.1 (2022-08-08)
[GENERAL] A paper on the
genieclustpackage has appeared in SoftwareX, see https://doi.org/10.1016/j.softx.2021.100722.[Python]
plot_scatternow uses a more accessible default palette (from R 4.0.0).[Python] New function:
inequity.devergottini_index.[R] New function:
devergottini_index.
- C++
Published by gagolews almost 4 years ago
genieclust - genieclust_0.9.8 (R only)
Fixed build errors on Solaris: _X is a reserved identifier.
- C++
Published by gagolews over 5 years ago
genieclust - genieclust_0.9.7 (R only)
- Fixed missing LinkingTo: BH
- C++
Published by gagolews over 5 years ago
genieclust - genieclust_0.9.6 (R only)
[Python] Python >= 3.7 is now required (implied by
numpy).[R] Use
RcppMLPACKdirectly instead of via a wrapper,emstreeR.
- C++
Published by gagolews over 5 years ago
genieclust - genieclust_0.9.5 (R only)
genieclust 0.9.5 (2020-12-26)
[Python]
nmslibis now required.[R] switched to
tinytestfor unit testing.[R] fixed the examples that relied on a now-changed API of
emstreeR.
- C++
Published by gagolews over 5 years ago
genieclust - genieclust_0.9.4
genieclust 0.9.4 (2020-07-31)
- [BUGFIX] [R] Fix build on Solaris.
- C++
Published by gagolews almost 6 years ago
genieclust - genieclust_0.9.3
genieclust 0.9.3 (2020-07-25)
[BUGFIX] [PYTHON] Code coverage CI added. Fixed some minor inconsistencies. Automated the bdist build chain.
[R] Updated DESCRIPTION to meet the CRAN policies.
- C++
Published by gagolews almost 6 years ago
genieclust - genieclust_0.9.2
genieclust 0.9.2 (2020-07-22)
- [BUGFIX] [PYTHON] Fixed broken build script for OS X with no OpenMP.
- C++
Published by gagolews almost 6 years ago
genieclust - genieclust_0.9.1
genieclust 0.9.1 (2020-07-18)
[GENERAL] The package has been completely rewritten. The core functionality is now implemented in C++ (with OpenMP).
[GENERAL] Clustering with respect to HDBSCAN*-like mutual reachability distances is supported.
[GENERAL] The parallelised Jarnik-Prim algorithm now supports on-the-fly distance computations. Euclidean minimum spanning tree can be determined with
mlpack, which is much faster in low-dimensional spaces.[R] R version is now available.
[PYTHON] [EXPERIMENTAL] The GIc algorithm proposed by Anna Cena in her 2018 PhD thesis was added.
[PYTHON] Approximate version based on nearest neighbour graphs produced by
nmslibwas added.
- C++
Published by gagolews almost 6 years ago