prosemble 2.0.0__tar.gz → 2.1.1__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (311) hide show
  1. {prosemble-2.0.0 → prosemble-2.1.1}/.github/workflows/release.yml +1 -1
  2. prosemble-2.1.1/ONNX_COVERAGE.md +168 -0
  3. {prosemble-2.0.0 → prosemble-2.1.1}/PKG-INFO +4 -1
  4. prosemble-2.1.1/examples/large_dataset_training.py +169 -0
  5. {prosemble-2.0.0 → prosemble-2.1.1}/nix/package.nix +4 -14
  6. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/core/__init__.py +26 -0
  7. prosemble-2.1.1/prosemble/core/data.py +161 -0
  8. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/core/distance.py +39 -54
  9. prosemble-2.1.1/prosemble/core/distributed.py +104 -0
  10. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/core/kernel.py +6 -7
  11. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/core/losses.py +16 -10
  12. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/core/manifolds.py +12 -12
  13. prosemble-2.1.1/prosemble/core/onnx_export.py +2383 -0
  14. prosemble-2.1.1/prosemble/core/protocols.py +216 -0
  15. prosemble-2.1.1/prosemble/core/serialization.py +188 -0
  16. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/core/similarities.py +8 -6
  17. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/core/utils.py +1 -1
  18. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/models/__init__.py +14 -0
  19. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/models/afcm.py +68 -44
  20. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/models/base.py +49 -95
  21. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/models/bgpc.py +19 -17
  22. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/models/cbc.py +107 -4
  23. prosemble-2.1.1/prosemble/models/celvq_ng.py +122 -0
  24. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/models/celvq_ng_mixin.py +100 -2
  25. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/models/crossentropy_lvq.py +5 -0
  26. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/models/fcm.py +90 -47
  27. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/models/fpcm.py +64 -35
  28. prosemble-2.1.1/prosemble/models/glvq.py +202 -0
  29. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/models/growing_neural_gas.py +29 -5
  30. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/models/hcm.py +42 -22
  31. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/models/heskes_som.py +41 -8
  32. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/models/image_cbc.py +104 -11
  33. prosemble-2.1.1/prosemble/models/image_lvq.py +794 -0
  34. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/models/ipcm.py +75 -44
  35. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/models/ipcm2.py +73 -44
  36. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/models/kafcm.py +50 -33
  37. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/models/kfcm.py +62 -32
  38. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/models/kfpcm.py +46 -7
  39. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/models/kipcm.py +47 -3
  40. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/models/kipcm2.py +48 -6
  41. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/models/kmeans.py +5 -0
  42. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/models/knn.py +5 -5
  43. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/models/kohonen_som.py +29 -6
  44. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/models/kpcm.py +64 -31
  45. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/models/kpfcm.py +53 -5
  46. prosemble-2.1.1/prosemble/models/lcelvq_ng.py +275 -0
  47. prosemble-2.1.1/prosemble/models/local_matrix_lvq.py +233 -0
  48. prosemble-2.1.1/prosemble/models/lvq1.py +204 -0
  49. prosemble-2.1.1/prosemble/models/lvq21.py +204 -0
  50. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/models/lvqmln.py +100 -4
  51. prosemble-2.1.1/prosemble/models/matrix_lvq.py +251 -0
  52. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/models/matrix_rslvq.py +216 -24
  53. prosemble-2.1.1/prosemble/models/mcelvq_ng.py +285 -0
  54. prosemble-2.1.1/prosemble/models/median_lvq.py +214 -0
  55. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/models/mrslvq_ng.py +221 -27
  56. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/models/neural_gas.py +42 -12
  57. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/models/npc.py +3 -2
  58. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/models/oc_glvq.py +112 -19
  59. prosemble-2.1.1/prosemble/models/oc_glvq_ng.py +124 -0
  60. prosemble-2.1.1/prosemble/models/oc_glvq_ng_mixin.py +255 -0
  61. prosemble-2.1.1/prosemble/models/oc_gmlvq.py +250 -0
  62. prosemble-2.1.1/prosemble/models/oc_gmlvq_ng.py +128 -0
  63. prosemble-2.1.1/prosemble/models/oc_grlvq.py +240 -0
  64. prosemble-2.1.1/prosemble/models/oc_grlvq_ng.py +127 -0
  65. prosemble-2.1.1/prosemble/models/oc_gtlvq.py +252 -0
  66. prosemble-2.1.1/prosemble/models/oc_gtlvq_ng.py +129 -0
  67. prosemble-2.1.1/prosemble/models/oc_lgmlvq.py +239 -0
  68. prosemble-2.1.1/prosemble/models/oc_lgmlvq_ng.py +128 -0
  69. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/models/oc_mrslvq.py +212 -10
  70. prosemble-2.1.1/prosemble/models/oc_mrslvq_ng.py +282 -0
  71. prosemble-2.1.1/prosemble/models/oc_rslvq.py +226 -0
  72. prosemble-2.1.1/prosemble/models/oc_rslvq_ng.py +147 -0
  73. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/models/oc_rslvq_ng_mixin.py +120 -9
  74. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/models/pcm.py +130 -92
  75. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/models/pfcm.py +75 -51
  76. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/models/plvq.py +107 -7
  77. prosemble-2.1.1/prosemble/models/probabilistic_lvq.py +353 -0
  78. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/models/prototype_base.py +175 -187
  79. prosemble-2.1.1/prosemble/models/relevance_lvq.py +213 -0
  80. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/models/riemannian_neural_gas.py +46 -42
  81. prosemble-2.1.1/prosemble/models/riemannian_slng.py +242 -0
  82. prosemble-2.1.1/prosemble/models/riemannian_smng.py +303 -0
  83. prosemble-2.1.1/prosemble/models/riemannian_srng.py +476 -0
  84. prosemble-2.1.1/prosemble/models/riemannian_stng.py +262 -0
  85. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/models/rslvq_ng.py +108 -11
  86. prosemble-2.1.1/prosemble/models/siamese_lvq.py +813 -0
  87. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/models/slng.py +135 -23
  88. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/models/smng.py +140 -28
  89. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/models/som.py +4 -5
  90. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/models/srng.py +110 -15
  91. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/models/stng.py +132 -20
  92. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/models/svq_occ.py +131 -22
  93. prosemble-2.1.1/prosemble/models/svq_occ_lm.py +329 -0
  94. prosemble-2.1.1/prosemble/models/svq_occ_m.py +341 -0
  95. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/models/svq_occ_r.py +136 -15
  96. prosemble-2.1.1/prosemble/models/svq_occ_t.py +347 -0
  97. prosemble-2.1.1/prosemble/models/tangent_lvq.py +246 -0
  98. prosemble-2.1.1/prosemble/models/tcelvq_ng.py +288 -0
  99. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble.egg-info/PKG-INFO +4 -1
  100. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble.egg-info/SOURCES.txt +19 -0
  101. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble.egg-info/requires.txt +4 -0
  102. {prosemble-2.0.0 → prosemble-2.1.1}/pyproject.toml +5 -1
  103. {prosemble-2.0.0 → prosemble-2.1.1}/sphinx-docs/api/core.rst +37 -0
  104. {prosemble-2.0.0 → prosemble-2.1.1}/sphinx-docs/api/models.rst +27 -4
  105. {prosemble-2.0.0 → prosemble-2.1.1}/sphinx-docs/conf.py +2 -2
  106. prosemble-2.1.1/sphinx-docs/guides/advanced.rst +776 -0
  107. {prosemble-2.0.0 → prosemble-2.1.1}/sphinx-docs/guides/one_class.rst +1 -1
  108. prosemble-2.1.1/sphinx-docs/guides/onnx.rst +246 -0
  109. prosemble-2.1.1/sphinx-docs/guides/riemannian.rst +224 -0
  110. {prosemble-2.0.0 → prosemble-2.1.1}/sphinx-docs/guides/topology.rst +31 -2
  111. {prosemble-2.0.0 → prosemble-2.1.1}/sphinx-docs/index.rst +2 -0
  112. {prosemble-2.0.0 → prosemble-2.1.1}/sphinx-docs/installation.rst +1 -1
  113. prosemble-2.1.1/tests/test_data.py +123 -0
  114. prosemble-2.1.1/tests/test_distributed.py +249 -0
  115. prosemble-2.1.1/tests/test_onnx_export.py +1330 -0
  116. prosemble-2.1.1/tests/test_protocols.py +74 -0
  117. prosemble-2.1.1/tests/test_riemannian_supervised_ng.py +388 -0
  118. prosemble-2.1.1/tests/test_serialization.py +170 -0
  119. {prosemble-2.0.0 → prosemble-2.1.1}/uv.lock +162 -44
  120. prosemble-2.0.0/prosemble/models/celvq_ng.py +0 -57
  121. prosemble-2.0.0/prosemble/models/glvq.py +0 -81
  122. prosemble-2.0.0/prosemble/models/image_lvq.py +0 -482
  123. prosemble-2.0.0/prosemble/models/lcelvq_ng.py +0 -174
  124. prosemble-2.0.0/prosemble/models/local_matrix_lvq.py +0 -138
  125. prosemble-2.0.0/prosemble/models/lvq1.py +0 -116
  126. prosemble-2.0.0/prosemble/models/lvq21.py +0 -111
  127. prosemble-2.0.0/prosemble/models/matrix_lvq.py +0 -152
  128. prosemble-2.0.0/prosemble/models/mcelvq_ng.py +0 -184
  129. prosemble-2.0.0/prosemble/models/median_lvq.py +0 -121
  130. prosemble-2.0.0/prosemble/models/oc_glvq_ng.py +0 -50
  131. prosemble-2.0.0/prosemble/models/oc_glvq_ng_mixin.py +0 -147
  132. prosemble-2.0.0/prosemble/models/oc_gmlvq.py +0 -152
  133. prosemble-2.0.0/prosemble/models/oc_gmlvq_ng.py +0 -54
  134. prosemble-2.0.0/prosemble/models/oc_grlvq.py +0 -142
  135. prosemble-2.0.0/prosemble/models/oc_grlvq_ng.py +0 -53
  136. prosemble-2.0.0/prosemble/models/oc_gtlvq.py +0 -154
  137. prosemble-2.0.0/prosemble/models/oc_gtlvq_ng.py +0 -55
  138. prosemble-2.0.0/prosemble/models/oc_lgmlvq.py +0 -141
  139. prosemble-2.0.0/prosemble/models/oc_lgmlvq_ng.py +0 -54
  140. prosemble-2.0.0/prosemble/models/oc_mrslvq_ng.py +0 -123
  141. prosemble-2.0.0/prosemble/models/oc_rslvq.py +0 -122
  142. prosemble-2.0.0/prosemble/models/oc_rslvq_ng.py +0 -62
  143. prosemble-2.0.0/prosemble/models/probabilistic_lvq.py +0 -155
  144. prosemble-2.0.0/prosemble/models/relevance_lvq.py +0 -118
  145. prosemble-2.0.0/prosemble/models/siamese_lvq.py +0 -492
  146. prosemble-2.0.0/prosemble/models/svq_occ_lm.py +0 -196
  147. prosemble-2.0.0/prosemble/models/svq_occ_m.py +0 -207
  148. prosemble-2.0.0/prosemble/models/svq_occ_t.py +0 -214
  149. prosemble-2.0.0/prosemble/models/tangent_lvq.py +0 -149
  150. prosemble-2.0.0/prosemble/models/tcelvq_ng.py +0 -188
  151. prosemble-2.0.0/sphinx-docs/guides/advanced.rst +0 -180
  152. {prosemble-2.0.0 → prosemble-2.1.1}/.bumpversion.cfg +0 -0
  153. {prosemble-2.0.0 → prosemble-2.1.1}/.editorconfig +0 -0
  154. {prosemble-2.0.0 → prosemble-2.1.1}/.envrc +0 -0
  155. {prosemble-2.0.0 → prosemble-2.1.1}/.github/ISSUE_TEMPLATE/bug_report.md +0 -0
  156. {prosemble-2.0.0 → prosemble-2.1.1}/.github/ISSUE_TEMPLATE/config.yml +0 -0
  157. {prosemble-2.0.0 → prosemble-2.1.1}/.github/ISSUE_TEMPLATE/feature_request.md +0 -0
  158. {prosemble-2.0.0 → prosemble-2.1.1}/.github/workflows/ci.yml +0 -0
  159. {prosemble-2.0.0 → prosemble-2.1.1}/.gitignore +0 -0
  160. {prosemble-2.0.0 → prosemble-2.1.1}/.readthedocs.yaml +0 -0
  161. {prosemble-2.0.0 → prosemble-2.1.1}/CONSTITUTION.md +0 -0
  162. {prosemble-2.0.0 → prosemble-2.1.1}/LICENSE +0 -0
  163. {prosemble-2.0.0 → prosemble-2.1.1}/MANIFEST.in +0 -0
  164. {prosemble-2.0.0 → prosemble-2.1.1}/README.md +0 -0
  165. {prosemble-2.0.0 → prosemble-2.1.1}/TASK.md +0 -0
  166. {prosemble-2.0.0 → prosemble-2.1.1}/benchmarks/benchmark_distance_jax.py +0 -0
  167. {prosemble-2.0.0 → prosemble-2.1.1}/benchmarks/benchmark_fcm_jax.py +0 -0
  168. {prosemble-2.0.0 → prosemble-2.1.1}/benchmarks/benchmark_pcm_jax.py +0 -0
  169. {prosemble-2.0.0 → prosemble-2.1.1}/devenv.lock +0 -0
  170. {prosemble-2.0.0 → prosemble-2.1.1}/devenv.nix +0 -0
  171. {prosemble-2.0.0 → prosemble-2.1.1}/devenv.yaml +0 -0
  172. {prosemble-2.0.0 → prosemble-2.1.1}/examples/afcm_iris.py +0 -0
  173. {prosemble-2.0.0 → prosemble-2.1.1}/examples/bgpc_iris.py +0 -0
  174. {prosemble-2.0.0 → prosemble-2.1.1}/examples/cbc_iris.py +0 -0
  175. {prosemble-2.0.0 → prosemble-2.1.1}/examples/celvq_ng_iris.py +0 -0
  176. {prosemble-2.0.0 → prosemble-2.1.1}/examples/fcm_iris.py +0 -0
  177. {prosemble-2.0.0 → prosemble-2.1.1}/examples/fpcm_iris.py +0 -0
  178. {prosemble-2.0.0 → prosemble-2.1.1}/examples/glvq_advanced_iris.py +0 -0
  179. {prosemble-2.0.0 → prosemble-2.1.1}/examples/glvq_iris.py +0 -0
  180. {prosemble-2.0.0 → prosemble-2.1.1}/examples/glvq_unequal_prototypes_iris.py +0 -0
  181. {prosemble-2.0.0 → prosemble-2.1.1}/examples/gmlvq_iris.py +0 -0
  182. {prosemble-2.0.0 → prosemble-2.1.1}/examples/grlvq_iris.py +0 -0
  183. {prosemble-2.0.0 → prosemble-2.1.1}/examples/hcm_iris.py +0 -0
  184. {prosemble-2.0.0 → prosemble-2.1.1}/examples/heskes_som_iris.py +0 -0
  185. {prosemble-2.0.0 → prosemble-2.1.1}/examples/ipcm2_iris.py +0 -0
  186. {prosemble-2.0.0 → prosemble-2.1.1}/examples/ipcm_iris.py +0 -0
  187. {prosemble-2.0.0 → prosemble-2.1.1}/examples/kafcm_iris.py +0 -0
  188. {prosemble-2.0.0 → prosemble-2.1.1}/examples/kfcm_iris.py +0 -0
  189. {prosemble-2.0.0 → prosemble-2.1.1}/examples/kfpcm_iris.py +0 -0
  190. {prosemble-2.0.0 → prosemble-2.1.1}/examples/kipcm2_iris.py +0 -0
  191. {prosemble-2.0.0 → prosemble-2.1.1}/examples/kipcm_iris.py +0 -0
  192. {prosemble-2.0.0 → prosemble-2.1.1}/examples/kmeans_iris.py +0 -0
  193. {prosemble-2.0.0 → prosemble-2.1.1}/examples/knn_iris.py +0 -0
  194. {prosemble-2.0.0 → prosemble-2.1.1}/examples/kohonen_som_iris.py +0 -0
  195. {prosemble-2.0.0 → prosemble-2.1.1}/examples/kpcm_iris.py +0 -0
  196. {prosemble-2.0.0 → prosemble-2.1.1}/examples/kpfcm_iris.py +0 -0
  197. {prosemble-2.0.0 → prosemble-2.1.1}/examples/lcelvq_ng_iris.py +0 -0
  198. {prosemble-2.0.0 → prosemble-2.1.1}/examples/lmrslvq_iris.py +0 -0
  199. {prosemble-2.0.0 → prosemble-2.1.1}/examples/lmrslvq_ng_iris.py +0 -0
  200. {prosemble-2.0.0 → prosemble-2.1.1}/examples/lvq1_iris.py +0 -0
  201. {prosemble-2.0.0 → prosemble-2.1.1}/examples/lvqmln_iris.py +0 -0
  202. {prosemble-2.0.0 → prosemble-2.1.1}/examples/mcelvq_ng_iris.py +0 -0
  203. {prosemble-2.0.0 → prosemble-2.1.1}/examples/mrslvq_iris.py +0 -0
  204. {prosemble-2.0.0 → prosemble-2.1.1}/examples/mrslvq_ng_iris.py +0 -0
  205. {prosemble-2.0.0 → prosemble-2.1.1}/examples/neural_gas_iris.py +0 -0
  206. {prosemble-2.0.0 → prosemble-2.1.1}/examples/npc_iris.py +0 -0
  207. {prosemble-2.0.0 → prosemble-2.1.1}/examples/oc_lmrslvq_iris.py +0 -0
  208. {prosemble-2.0.0 → prosemble-2.1.1}/examples/oc_lmrslvq_ng_iris.py +0 -0
  209. {prosemble-2.0.0 → prosemble-2.1.1}/examples/oc_mrslvq_iris.py +0 -0
  210. {prosemble-2.0.0 → prosemble-2.1.1}/examples/oc_mrslvq_ng_iris.py +0 -0
  211. {prosemble-2.0.0 → prosemble-2.1.1}/examples/oc_rslvq_iris.py +0 -0
  212. {prosemble-2.0.0 → prosemble-2.1.1}/examples/oc_rslvq_ng_iris.py +0 -0
  213. {prosemble-2.0.0 → prosemble-2.1.1}/examples/pcm_iris.py +0 -0
  214. {prosemble-2.0.0 → prosemble-2.1.1}/examples/pfcm_iris.py +0 -0
  215. {prosemble-2.0.0 → prosemble-2.1.1}/examples/plvq_iris.py +0 -0
  216. {prosemble-2.0.0 → prosemble-2.1.1}/examples/rslvq_ng_iris.py +0 -0
  217. {prosemble-2.0.0 → prosemble-2.1.1}/examples/slng_iris.py +0 -0
  218. {prosemble-2.0.0 → prosemble-2.1.1}/examples/smng_iris.py +0 -0
  219. {prosemble-2.0.0 → prosemble-2.1.1}/examples/som_iris.py +0 -0
  220. {prosemble-2.0.0 → prosemble-2.1.1}/examples/srng_iris.py +0 -0
  221. {prosemble-2.0.0 → prosemble-2.1.1}/examples/stng_iris.py +0 -0
  222. {prosemble-2.0.0 → prosemble-2.1.1}/examples/tcelvq_ng_iris.py +0 -0
  223. {prosemble-2.0.0 → prosemble-2.1.1}/examples/vis_fcm_iris.py +0 -0
  224. {prosemble-2.0.0 → prosemble-2.1.1}/examples/vis_glvq_iris.py +0 -0
  225. {prosemble-2.0.0 → prosemble-2.1.1}/examples/vis_neural_gas_iris.py +0 -0
  226. {prosemble-2.0.0 → prosemble-2.1.1}/examples/vis_som_iris.py +0 -0
  227. {prosemble-2.0.0 → prosemble-2.1.1}/flake.nix +0 -0
  228. {prosemble-2.0.0 → prosemble-2.1.1}/mkdocs.yml +0 -0
  229. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/__init__.py +0 -0
  230. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/core/activations.py +0 -0
  231. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/core/callbacks.py +0 -0
  232. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/core/competitions.py +0 -0
  233. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/core/initializers.py +0 -0
  234. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/core/model_selection.py +0 -0
  235. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/core/pipeline.py +0 -0
  236. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/core/pooling.py +0 -0
  237. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/core/quantization.py +0 -0
  238. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/core/vis.py +0 -0
  239. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/core/visualizer.py +0 -0
  240. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/datasets/__init__.py +0 -0
  241. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/datasets/dataset.py +0 -0
  242. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble/py.typed +0 -0
  243. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble.egg-info/dependency_links.txt +0 -0
  244. {prosemble-2.0.0 → prosemble-2.1.1}/prosemble.egg-info/top_level.txt +0 -0
  245. {prosemble-2.0.0 → prosemble-2.1.1}/requirements_docs.txt +0 -0
  246. {prosemble-2.0.0 → prosemble-2.1.1}/setup.cfg +0 -0
  247. {prosemble-2.0.0 → prosemble-2.1.1}/sphinx-docs/Makefile +0 -0
  248. {prosemble-2.0.0 → prosemble-2.1.1}/sphinx-docs/guides/clustering.rst +0 -0
  249. {prosemble-2.0.0 → prosemble-2.1.1}/sphinx-docs/guides/supervised.rst +0 -0
  250. {prosemble-2.0.0 → prosemble-2.1.1}/sphinx-docs/make.bat +0 -0
  251. {prosemble-2.0.0 → prosemble-2.1.1}/sphinx-docs/quickstart.rst +0 -0
  252. {prosemble-2.0.0 → prosemble-2.1.1}/tests/__init__.py +0 -0
  253. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_activations.py +0 -0
  254. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_cbc.py +0 -0
  255. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_celvq_ng.py +0 -0
  256. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_checkpoint.py +0 -0
  257. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_clustering_patience.py +0 -0
  258. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_competitions.py +0 -0
  259. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_core.py +0 -0
  260. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_core_jax.py +0 -0
  261. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_dataset.py +0 -0
  262. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_dataset_jax.py +0 -0
  263. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_distance_jax.py +0 -0
  264. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_examples.sh +0 -0
  265. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_fcm_jax.py +0 -0
  266. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_glvq.py +0 -0
  267. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_gmlvq.py +0 -0
  268. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_heskes_som.py +0 -0
  269. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_image_lvq.py +0 -0
  270. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_initializers.py +0 -0
  271. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_jax_models.py +0 -0
  272. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_jit_inference.py +0 -0
  273. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_kohonen_som.py +0 -0
  274. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_lcelvq_ng.py +0 -0
  275. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_losses.py +0 -0
  276. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_lvq_nongradient.py +0 -0
  277. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_lvqmln_plvq.py +0 -0
  278. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_matrix_rslvq.py +0 -0
  279. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_mcelvq_ng.py +0 -0
  280. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_minibatch.py +0 -0
  281. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_mixed_precision.py +0 -0
  282. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_model_selection.py +0 -0
  283. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_mrslvq_ng.py +0 -0
  284. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_neural_gas.py +0 -0
  285. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_oc_glvq.py +0 -0
  286. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_oc_glvq_ng.py +0 -0
  287. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_oc_glvq_variants.py +0 -0
  288. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_oc_mrslvq.py +0 -0
  289. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_oc_rslvq.py +0 -0
  290. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_oc_rslvq_ng.py +0 -0
  291. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_pcm_jax.py +0 -0
  292. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_pfcm_jax.py +0 -0
  293. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_pipeline.py +0 -0
  294. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_pooling.py +0 -0
  295. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_probabilistic.py +0 -0
  296. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_prototype_base.py +0 -0
  297. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_quantization.py +0 -0
  298. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_riemannian_neural_gas.py +0 -0
  299. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_rslvq_ng.py +0 -0
  300. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_scan_training.py +0 -0
  301. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_siamese_lvq.py +0 -0
  302. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_similarities.py +0 -0
  303. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_slng.py +0 -0
  304. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_smng.py +0 -0
  305. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_srng.py +0 -0
  306. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_stng.py +0 -0
  307. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_svq_occ.py +0 -0
  308. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_svq_occ_r.py +0 -0
  309. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_svq_occ_variants.py +0 -0
  310. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_tcelvq_ng.py +0 -0
  311. {prosemble-2.0.0 → prosemble-2.1.1}/tests/test_vis.py +0 -0
@@ -24,7 +24,7 @@ jobs:
24
24
  python -m pip install --upgrade pip
25
25
  pip install .[all]
26
26
  - name: Run tests
27
- run: pytest tests/ -x -q --ignore=tests/test_oc_glvq.py --ignore=tests/test_oc_glvq_ng.py --ignore=tests/test_oc_glvq_variants.py --ignore=tests/test_svq_occ.py --ignore=tests/test_svq_occ_r.py --ignore=tests/test_svq_occ_variants.py --ignore=tests/test_smng.py --ignore=tests/test_slng.py --ignore=tests/test_stng.py --ignore=tests/test_riemannian_neural_gas.py
27
+ run: pytest tests/ -x -q --ignore=tests/test_oc_glvq.py --ignore=tests/test_oc_glvq_ng.py --ignore=tests/test_oc_glvq_variants.py --ignore=tests/test_svq_occ.py --ignore=tests/test_svq_occ_r.py --ignore=tests/test_svq_occ_variants.py --ignore=tests/test_smng.py --ignore=tests/test_slng.py --ignore=tests/test_stng.py --ignore=tests/test_riemannian_neural_gas.py --ignore=tests/test_riemannian_supervised_ng.py
28
28
 
29
29
  build:
30
30
  needs: test
@@ -0,0 +1,168 @@
1
+ # ONNX Export Coverage
2
+
3
+ Status of ONNX export support across all 87 prosemble models.
4
+
5
+ ## Currently Supported (73 models)
6
+
7
+ ### Supervised LVQ — squared euclidean (9)
8
+
9
+ GLVQ, GLVQ1, GLVQ21, LVQ1, LVQ21, MedianLVQ, CELVQ, SLVQ, RSLVQ
10
+
11
+ ### Supervised LVQ — global omega (2)
12
+
13
+ GMLVQ, MRSLVQ
14
+
15
+ ### Supervised LVQ — local omega (2)
16
+
17
+ LGMLVQ, LMRSLVQ
18
+
19
+ ### Supervised LVQ — relevance-weighted (1)
20
+
21
+ GRLVQ
22
+
23
+ ### Supervised LVQ — tangent (1)
24
+
25
+ GTLVQ
26
+
27
+ ### Supervised NG — squared euclidean (3)
28
+
29
+ SRNG, CELVQ_NG, RSLVQ_NG
30
+
31
+ ### Supervised NG — global omega (3)
32
+
33
+ SMNG, MCELVQ_NG, MRSLVQ_NG
34
+
35
+ ### Supervised NG — local omega (3)
36
+
37
+ SLNG, LCELVQ_NG, LMRSLVQ_NG
38
+
39
+ ### Supervised NG — tangent (2)
40
+
41
+ STNG, TCELVQ_NG
42
+
43
+ ### Unsupervised — squared euclidean (4)
44
+
45
+ NeuralGas, GrowingNeuralGas, KohonenSOM, HeskesSOM
46
+
47
+ ### Fuzzy clustering — squared euclidean (8)
48
+
49
+ FCM, PCM, FPCM, PFCM, AFCM, HCM, IPCM, IPCM2
50
+
51
+ For FCM and variants with fuzzifier m > 1, membership u_ij is monotonically decreasing in distance d_ij, so `argmax(membership) = argmin(distance)`. The ONNX graph uses `argmin(distance)` which produces identical predictions.
52
+
53
+ ### One-class — hard nearest decision (10)
54
+
55
+ OCGLVQ, OCGLVQ_NG, OCGRLVQ, OCGRLVQ_NG, OCGMLVQ, OCGMLVQ_NG, OCLGMLVQ, OCLGMLVQ_NG, OCGTLVQ, OCGTLVQ_NG
56
+
57
+ Decision: `argmin(d) → gather(d, theta) → mu = (d-theta)/(d+theta) → 1 - sigmoid(beta*mu) → threshold 0.5`. Distance varies per model (squared euclidean, relevance-weighted, global omega, local omega, tangent).
58
+
59
+ ### One-class — Gaussian soft decision (3)
60
+
61
+ OCRSLVQ, OCMRSLVQ, OCLMRSLVQ
62
+
63
+ Decision: softmax Gaussian weights over all prototypes, weighted mu aggregation, sigmoid threshold.
64
+
65
+ ### One-class — Gaussian+NG soft decision (3)
66
+
67
+ OCRSLVQ_NG, OCMRSLVQ_NG, OCLMRSLVQ_NG
68
+
69
+ Decision: combined Gaussian × NG rank weights (using converged gamma), weighted mu aggregation. NG ranks computed via TopK + ScatterElements.
70
+
71
+ ### SVQ-OCC — response model (5)
72
+
73
+ SVQOCC, SVQOCC_R, SVQOCC_M, SVQOCC_LM, SVQOCC_T
74
+
75
+ Decision: response probability (Gaussian softmax, Student-t, or uniform) × differentiable Heaviside sigmoid → summed responsibility → threshold 0.5.
76
+
77
+ ### Encoder — MLP backbone + WTAC (4)
78
+
79
+ SiameseGLVQ, SiameseGMLVQ, SiameseGTLVQ, LVQMLN
80
+
81
+ Input encoded through MLP layers (MatMul → Add → Activation per layer). Prototypes pre-computed in latent space at export time (Siamese: re-encoded; LVQMLN: already latent). Distance varies per model (squared euclidean, global omega, tangent).
82
+
83
+ ### Encoder — CNN backbone + WTAC (3)
84
+
85
+ ImageGLVQ, ImageGMLVQ, ImageGTLVQ
86
+
87
+ Input reshaped to NHWC, transposed to NCHW, then Conv layers (SAME padding) → GlobalAveragePool → Linear head. Prototypes pre-computed in latent space at export time. Distance varies per model (squared euclidean, global omega, tangent).
88
+
89
+ ### Encoder — PLVQ Gaussian mixture (1)
90
+
91
+ PLVQ
92
+
93
+ MLP encoder → squared Euclidean distance → Softmax soft assignment → class aggregation via MatMul with binary class mask → ArgMax.
94
+
95
+ ### CBC — reasoning matrices (2)
96
+
97
+ CBC, ImageCBC
98
+
99
+ Squared Euclidean distance → Gaussian similarity `exp(-d²/(2σ²))` → CBCC reasoning: `probs = (detections @ (pk - nk) + sum(nk)) / (sum(pk + nk) + eps)` → ArgMax. ImageCBC adds a CNN encoder before distance computation, with components pre-computed in latent space.
100
+
101
+ ### Riemannian — SO(n) chordal distance (1)
102
+
103
+ RiemannianSRNG (with SO(n) manifold)
104
+
105
+ Chordal distance: `d²(R,S) = ||R - S||²_F`. Pure Frobenius norm on flattened rotation matrices.
106
+
107
+ ### Riemannian — SO(n) tangent-space metric (3)
108
+
109
+ RiemannianSMNG, RiemannianSLNG, RiemannianSTNG (with SO(n) manifold)
110
+
111
+ Log map: `Log_R(S) = R @ skew(R^T S)` where `skew(A) = (A - A^T)/2`. Then metric adaptation (global omega, local omega, or tangent subspace) applied to flattened tangent vectors. All ops are MatMul/Sub/Transpose.
112
+
113
+ ### Riemannian — Grassmannian tangent-space metric (same 3 models, alternate manifold)
114
+
115
+ RiemannianSMNG, RiemannianSLNG, RiemannianSTNG (with Grassmannian(n,k) manifold)
116
+
117
+ Log map: `Log_{Q1}(Q2) = Q2 - Q1(Q1^T Q2)`. Then metric adaptation applied to flattened tangent vectors. All ops are MatMul/Sub.
118
+
119
+ ---
120
+
121
+ ## Not Supported (14 models)
122
+
123
+ ### Kernel fuzzy clustering (7) — kernel distance not exportable
124
+
125
+ KFCM, KPCM, KFPCM, KPFCM, KAFCM, KIPCM, KIPCM2
126
+
127
+ **Blocker:** Predict uses Gaussian kernel distance (1 - K) computed via `batch_gaussian_kernel()`. Kernel evaluation requires the `sigma` parameter and a different distance computation that has no standard ONNX equivalent.
128
+
129
+ ### Riemannian models — non-exportable (1)
130
+
131
+ - **RiemannianNeuralGas** — uses `jsl.funm` (matrix logarithm via Schur decomposition, no ONNX op)
132
+
133
+ Note: The 4 supervised Riemannian models (RiemannianSRNG/SMNG/SLNG/STNG) are exportable on SO(n) and Grassmannian manifolds. SPD(n) manifold is not exportable (eigendecomposition required) but is a runtime configuration choice, not a separate model. RiemannianSRNG on Grassmannian is also not exportable (SVD required) but again is the same model with a different manifold choice.
134
+
135
+ ### Other (2)
136
+
137
+ - **KNN** — k-nearest-neighbor logic, not prototype-based
138
+ - **NPC** — nearest prototype classifier with different predict pattern
139
+
140
+ ### Utility models not applicable (4)
141
+
142
+ KMeansPlusPlus, Kmeans, SOM, BGPC — don't inherit from prototype model base classes.
143
+
144
+ ---
145
+
146
+ ## Distance Functions Supported
147
+
148
+ | Distance | ONNX Implementation | Models |
149
+ |----------|-------------------|--------|
150
+ | Squared Euclidean | expansion trick | GLVQ family, NG, NeuralGas, FCM, OCGLVQ, OCRSLVQ, SVQOCC, Siamese/Image/LVQMLN/PLVQ, CBC |
151
+ | Euclidean | sqrt of above | (available) |
152
+ | Manhattan | broadcast + abs + sum | (available) |
153
+ | Global Omega | project then sq. euclidean | GMLVQ, MRSLVQ, SMNG, OCGMLVQ, OCMRSLVQ, SVQOCC_M, SiameseGMLVQ, ImageGMLVQ |
154
+ | Relevance-weighted | element-wise weighted sq. diff | GRLVQ, OCGRLVQ, SVQOCC_R |
155
+ | Local Omega | batched MatMul | LGMLVQ, SLNG, LCELVQ_NG, LMRSLVQ, OCLGMLVQ, SVQOCC_LM |
156
+ | Tangent | batched MatMul project-reconstruct | GTLVQ, STNG, TCELVQ_NG, OCGTLVQ, SVQOCC_T, SiameseGTLVQ, ImageGTLVQ |
157
+ | SO(n) Chordal | broadcast subtract + Frobenius | RiemannianSRNG |
158
+ | SO(n) Tangent | skew-symmetric log map + metric | RiemannianSMNG/SLNG/STNG (SO) |
159
+ | Grassmannian Tangent | projection log map + metric | RiemannianSMNG/SLNG/STNG (Gr) |
160
+
161
+ ## Encoder Support
162
+
163
+ | Encoder | ONNX Implementation | Models |
164
+ |---------|-------------------|--------|
165
+ | MLP | MatMul → Add → Activation per layer | SiameseGLVQ, SiameseGMLVQ, SiameseGTLVQ, LVQMLN, PLVQ |
166
+ | CNN | Reshape → Transpose → Conv(SAME) → GlobalAveragePool → Linear | ImageGLVQ, ImageGMLVQ, ImageGTLVQ, ImageCBC |
167
+
168
+ Activations supported: Sigmoid, Relu, Tanh, LeakyRelu, Selu.
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: prosemble
3
- Version: 2.0.0
3
+ Version: 2.1.1
4
4
  Summary: A python project for prototype-based machine learning models
5
5
  Author-email: Nana Abeka Otoo <nanaabekaotoo@gmail.com>
6
6
  License: MIT
@@ -82,6 +82,9 @@ Requires-Dist: chex>=0.1.85; extra == "all"
82
82
  Requires-Dist: optax>=0.2.0; extra == "all"
83
83
  Provides-Extra: export
84
84
  Requires-Dist: flatbuffers>=25.12.19; extra == "export"
85
+ Provides-Extra: onnx
86
+ Requires-Dist: onnx>=1.21.0; extra == "onnx"
87
+ Requires-Dist: onnxruntime>=1.26.0; extra == "onnx"
85
88
  Dynamic: license-file
86
89
 
87
90
  # Prosemble
@@ -0,0 +1,169 @@
1
+ """
2
+ Large dataset training patterns for prosemble.
3
+
4
+ When datasets are too large to fit in memory, use external data loaders
5
+ (tf.data, grain, webdataset) and feed batches into prosemble via
6
+ partial_fit(). This example demonstrates three patterns:
7
+
8
+ 1. partial_fit() with simulated streaming data
9
+ 2. batched_iterator() for epoch-based training
10
+ 3. padded_batches() for lax.scan-compatible static batching
11
+
12
+ For datasets that DO fit in memory, prefer fit(batch_size=32) instead —
13
+ it handles mini-batch training, shuffling, and early stopping internally.
14
+ """
15
+
16
+ import jax
17
+ import jax.numpy as jnp
18
+ import numpy as np
19
+
20
+ from prosemble.models import GLVQ
21
+ from prosemble.core.data import batched_iterator, padded_batches, shuffle_arrays
22
+
23
+ # ---------------------------------------------------------------------------
24
+ # Generate synthetic data (stand-in for your real dataset)
25
+ # ---------------------------------------------------------------------------
26
+
27
+ np.random.seed(42)
28
+ n_samples, n_features, n_classes = 501, 10, 3
29
+ X_all = jnp.array(np.random.randn(n_samples, n_features).astype(np.float32))
30
+ y_all = jnp.array(np.tile(np.arange(n_classes), n_samples // n_classes))
31
+
32
+ # Split into initial fit set and streaming set
33
+ # (y_all is interleaved [0,1,2,0,1,2,...] so every split has all classes)
34
+ X_init, y_init = X_all[:60], y_all[:60]
35
+ X_stream, y_stream = X_all[60:], y_all[60:]
36
+
37
+ # ===================================================================
38
+ # Pattern 1: partial_fit() with simulated streaming data
39
+ # ===================================================================
40
+ # Use this when data arrives in batches from an external source
41
+ # (database, file system, network stream, tf.data pipeline, etc.)
42
+
43
+ print("=" * 60)
44
+ print("Pattern 1: partial_fit() with streaming batches")
45
+ print("=" * 60)
46
+
47
+ model = GLVQ(
48
+ n_prototypes_per_class=2,
49
+ max_iter=10,
50
+ lr=0.01,
51
+ random_seed=42,
52
+ )
53
+
54
+ # Initial fit to initialize prototypes and optimizer
55
+ model.fit(X_init, y_init)
56
+ print(f"After initial fit: {model.n_iter_} iterations, loss={model.loss_:.4f}")
57
+
58
+ # Simulate streaming batches
59
+ # In practice, replace this loop with your data loader:
60
+ # for batch in tf_dataset:
61
+ # for batch in grain.DataLoader(...):
62
+ # for batch in webdataset.WebLoader(...):
63
+ batch_size = 32
64
+ n_stream = len(X_stream)
65
+ losses = []
66
+
67
+ for start in range(0, n_stream, batch_size):
68
+ end = min(start + batch_size, n_stream)
69
+ X_batch = X_stream[start:end]
70
+ y_batch = y_stream[start:end]
71
+
72
+ model.partial_fit(X_batch, y_batch)
73
+ losses.append(float(model.loss_))
74
+
75
+ print(f"After {len(losses)} streaming batches: loss={losses[-1]:.4f}")
76
+
77
+ preds = model.predict(X_all)
78
+ acc = float(jnp.mean(preds == y_all))
79
+ print(f"Accuracy: {acc:.2%}")
80
+
81
+ # ===================================================================
82
+ # Pattern 2: batched_iterator() for epoch-based training
83
+ # ===================================================================
84
+ # Use this when all data fits in memory but you want explicit
85
+ # epoch/batch control with partial_fit().
86
+
87
+ print()
88
+ print("=" * 60)
89
+ print("Pattern 2: batched_iterator() with epoch loop")
90
+ print("=" * 60)
91
+
92
+ model2 = GLVQ(
93
+ n_prototypes_per_class=2,
94
+ max_iter=5,
95
+ lr=0.01,
96
+ random_seed=42,
97
+ )
98
+
99
+ # Initial fit
100
+ model2.fit(X_init, y_init)
101
+
102
+ key = jax.random.PRNGKey(0)
103
+ n_epochs = 5
104
+
105
+ for epoch in range(n_epochs):
106
+ key, subkey = jax.random.split(key)
107
+ epoch_losses = []
108
+
109
+ for X_batch, y_batch in batched_iterator(
110
+ X_all, y_all, batch_size=64, key=subkey
111
+ ):
112
+ model2.partial_fit(X_batch, y_batch)
113
+ epoch_losses.append(float(model2.loss_))
114
+
115
+ mean_loss = sum(epoch_losses) / len(epoch_losses)
116
+ print(f"Epoch {epoch + 1}/{n_epochs}: mean_loss={mean_loss:.4f}")
117
+
118
+ preds2 = model2.predict(X_all)
119
+ acc2 = float(jnp.mean(preds2 == y_all))
120
+ print(f"Accuracy: {acc2:.2%}")
121
+
122
+ # ===================================================================
123
+ # Pattern 3: padded_batches() for lax.scan compatibility
124
+ # ===================================================================
125
+ # Use this when building custom JIT-compiled training loops
126
+ # with jax.lax.scan. The output has static shapes required by XLA.
127
+
128
+ print()
129
+ print("=" * 60)
130
+ print("Pattern 3: padded_batches() for static-shaped batching")
131
+ print("=" * 60)
132
+
133
+ key = jax.random.PRNGKey(42)
134
+ X_batches, y_batches = padded_batches(X_all, y_all, batch_size=64, key=key)
135
+
136
+ print(f"Input: X={X_all.shape}, y={y_all.shape}")
137
+ print(f"Output: X_batches={X_batches.shape}, y_batches={y_batches.shape}")
138
+ print(f" {X_batches.shape[0]} batches of {X_batches.shape[1]} samples")
139
+ print(f" (padded from {n_samples} to {X_batches.shape[0] * X_batches.shape[1]})")
140
+ print()
141
+ print("These static-shaped arrays can be passed directly to jax.lax.scan")
142
+ print("for fully JIT-compiled training loops.")
143
+
144
+ # ===================================================================
145
+ # Notes
146
+ # ===================================================================
147
+
148
+ print()
149
+ print("=" * 60)
150
+ print("When to use each pattern")
151
+ print("=" * 60)
152
+ print("""
153
+ fit(batch_size=32) Data fits in memory. Handles shuffling, early
154
+ stopping, and optimizer state internally.
155
+
156
+ partial_fit() Data too large for memory, or arrives as a
157
+ stream. Feed batches from any external loader:
158
+ tf.data, grain, webdataset, torch DataLoader.
159
+ Requires an initial fit() call to set up
160
+ prototypes and optimizer.
161
+
162
+ batched_iterator() Data fits in memory but you want explicit
163
+ epoch/batch control. Yields dynamic-sized
164
+ batches for Python loops.
165
+
166
+ padded_batches() Static-shaped output for jax.lax.scan.
167
+ Advanced: use when building custom JIT-compiled
168
+ training loops.
169
+ """)
@@ -5,8 +5,8 @@
5
5
  # 2. Add to pkgs/top-level/python-packages.nix:
6
6
  # prosemble = callPackage ../development/python-modules/prosemble { };
7
7
  # 3. Update the hash after publishing to PyPI:
8
- # nix-prefetch-url --unpack https://github.com/naotoo1/prosemble/archive/refs/tags/v1.0.0.tar.gz
9
- # 4. PR title: python3Packages.prosemble: init at 1.0.0
8
+ # nix-prefetch-url --unpack https://github.com/naotoo1/prosemble/archive/refs/tags/v2.0.0.tar.gz
9
+ # 4. PR title: python3Packages.prosemble: init at 2.0.0
10
10
  {
11
11
  lib,
12
12
  buildPythonPackage,
@@ -29,14 +29,14 @@
29
29
 
30
30
  buildPythonPackage (finalAttrs: {
31
31
  pname = "prosemble";
32
- version = "1.0.0";
32
+ version = "2.0.0";
33
33
  pyproject = true;
34
34
 
35
35
  src = fetchFromGitHub {
36
36
  owner = "naotoo1";
37
37
  repo = "prosemble";
38
38
  rev = "refs/tags/v${finalAttrs.version}";
39
- hash = "sha256-AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA=";
39
+ hash = "sha256-6Oa7V7tFle74oYBNEaJ1ZCrrku8cav92YkzpnCxsH5c=";
40
40
  };
41
41
 
42
42
  build-system = [
@@ -68,16 +68,6 @@ buildPythonPackage (finalAttrs: {
68
68
  ];
69
69
 
70
70
  disabledTestPaths = [
71
- # Deferred to v1.1
72
- "tests/test_oc_glvq.py"
73
- "tests/test_oc_glvq_ng.py"
74
- "tests/test_oc_glvq_variants.py"
75
- "tests/test_svq_occ.py"
76
- "tests/test_svq_occ_r.py"
77
- "tests/test_svq_occ_variants.py"
78
- "tests/test_smng.py"
79
- "tests/test_slng.py"
80
- "tests/test_stng.py"
81
71
  "tests/test_riemannian_neural_gas.py"
82
72
  ];
83
73
 
@@ -33,6 +33,14 @@ from .losses import (
33
33
  )
34
34
  from .pipeline import Pipeline, StandardScaler, MinMaxScaler, PCA, TransformerMixin
35
35
  from .model_selection import GridSearchCV, cross_val_score, clone
36
+ from .protocols import (
37
+ Manifold, CallbackLike,
38
+ DistanceMatrixFn, DistancePairwiseFn,
39
+ SupervisedInitFn, UnsupervisedInitFn,
40
+ )
41
+ from .serialization import SerializationMixin
42
+ from .data import shuffle_arrays, padded_batches, batched_iterator
43
+ from .distributed import create_mesh, shard_data, replicate_params
36
44
 
37
45
  try:
38
46
  import jax
@@ -75,4 +83,22 @@ __all__ = _distance_all + [
75
83
  'Pipeline', 'StandardScaler', 'MinMaxScaler', 'PCA', 'TransformerMixin',
76
84
  # Model Selection
77
85
  'GridSearchCV', 'cross_val_score', 'clone',
86
+ # Protocols & type aliases
87
+ 'Manifold', 'CallbackLike',
88
+ 'DistanceMatrixFn', 'DistancePairwiseFn',
89
+ 'SupervisedInitFn', 'UnsupervisedInitFn',
90
+ # Serialization
91
+ 'SerializationMixin',
92
+ # Data loading utilities
93
+ 'shuffle_arrays', 'padded_batches', 'batched_iterator',
94
+ # Distributed training
95
+ 'create_mesh', 'shard_data', 'replicate_params',
96
+ # ONNX export (optional)
97
+ 'export_onnx',
78
98
  ]
99
+
100
+ # Conditional ONNX export
101
+ try:
102
+ from .onnx_export import export_onnx
103
+ except ImportError:
104
+ pass
@@ -0,0 +1,161 @@
1
+ """
2
+ Data loading and batching utilities for prosemble.
3
+
4
+ Provides composable primitives for mini-batch iteration, suitable for
5
+ custom training loops. The built-in ``fit()`` methods already handle
6
+ batching internally — these utilities are for advanced users who need
7
+ explicit control over data iteration.
8
+ """
9
+
10
+ from __future__ import annotations
11
+
12
+ import jax
13
+ import jax.numpy as jnp
14
+
15
+
16
+ def shuffle_arrays(key: jax.Array, *arrays: jnp.ndarray) -> tuple[jnp.ndarray, ...]:
17
+ """Shuffle multiple arrays with the same random permutation.
18
+
19
+ Parameters
20
+ ----------
21
+ key : JAX PRNG key
22
+ Random key for generating the permutation.
23
+ *arrays : jnp.ndarray
24
+ Arrays to shuffle. All must have the same length along axis 0.
25
+
26
+ Returns
27
+ -------
28
+ tuple of jnp.ndarray
29
+ Shuffled arrays in the same order as the inputs.
30
+
31
+ Examples
32
+ --------
33
+ >>> key = jax.random.PRNGKey(0)
34
+ >>> X = jnp.arange(12).reshape(4, 3)
35
+ >>> y = jnp.array([0, 1, 0, 1])
36
+ >>> X_s, y_s = shuffle_arrays(key, X, y)
37
+ """
38
+ if len(arrays) == 0:
39
+ return ()
40
+ n = arrays[0].shape[0]
41
+ perm = jax.random.permutation(key, n)
42
+ return tuple(a[perm] for a in arrays)
43
+
44
+
45
+ def padded_batches(
46
+ X: jnp.ndarray,
47
+ y: jnp.ndarray | None = None,
48
+ batch_size: int = 32,
49
+ key: jax.Array | None = None,
50
+ ) -> tuple[jnp.ndarray, jnp.ndarray | None]:
51
+ """Split data into static-shaped batches, padding the last batch.
52
+
53
+ Returns arrays of shape ``(n_batches, batch_size, ...)`` suitable for
54
+ ``jax.lax.scan``. If the data length is not divisible by
55
+ ``batch_size``, the last batch is padded by repeating initial samples.
56
+
57
+ Parameters
58
+ ----------
59
+ X : jnp.ndarray of shape (n_samples, ...)
60
+ Feature array.
61
+ y : jnp.ndarray of shape (n_samples,), optional
62
+ Label array.
63
+ batch_size : int
64
+ Number of samples per batch.
65
+ key : JAX PRNG key, optional
66
+ If provided, data is shuffled before batching.
67
+
68
+ Returns
69
+ -------
70
+ X_batches : jnp.ndarray of shape (n_batches, batch_size, ...)
71
+ y_batches : jnp.ndarray of shape (n_batches, batch_size) or None
72
+
73
+ Examples
74
+ --------
75
+ >>> X = jnp.ones((10, 3))
76
+ >>> y = jnp.arange(10)
77
+ >>> X_b, y_b = padded_batches(X, y, batch_size=4)
78
+ >>> X_b.shape # (3, 4, 3) — 10 samples padded to 12
79
+ (3, 4, 3)
80
+ """
81
+ n_samples = X.shape[0]
82
+
83
+ if key is not None:
84
+ if y is not None:
85
+ X, y = shuffle_arrays(key, X, y)
86
+ else:
87
+ X, = shuffle_arrays(key, X)
88
+
89
+ n_batches = (n_samples + batch_size - 1) // batch_size
90
+ padded_size = n_batches * batch_size
91
+
92
+ if padded_size > n_samples:
93
+ pad_n = padded_size - n_samples
94
+ X = jnp.concatenate([X, X[:pad_n]], axis=0)
95
+ if y is not None:
96
+ y = jnp.concatenate([y, y[:pad_n]], axis=0)
97
+
98
+ X_batches = X.reshape(n_batches, batch_size, *X.shape[1:])
99
+ y_batches = y.reshape(n_batches, batch_size) if y is not None else None
100
+ return X_batches, y_batches
101
+
102
+
103
+ def batched_iterator(
104
+ X: jnp.ndarray,
105
+ y: jnp.ndarray | None = None,
106
+ batch_size: int = 32,
107
+ shuffle: bool = True,
108
+ key: jax.Array | None = None,
109
+ drop_last: bool = False,
110
+ ):
111
+ """Yield mini-batches from data arrays.
112
+
113
+ For use in custom Python training loops.
114
+
115
+ Parameters
116
+ ----------
117
+ X : jnp.ndarray of shape (n_samples, ...)
118
+ Feature array.
119
+ y : jnp.ndarray of shape (n_samples,), optional
120
+ Label array.
121
+ batch_size : int
122
+ Number of samples per batch.
123
+ shuffle : bool
124
+ If True and *key* is provided, shuffle before iterating.
125
+ key : JAX PRNG key, optional
126
+ Required if ``shuffle=True``.
127
+ drop_last : bool
128
+ If True, drop the last batch when it is smaller than
129
+ ``batch_size``. If False (default), the last batch may be
130
+ smaller.
131
+
132
+ Yields
133
+ ------
134
+ X_batch : jnp.ndarray of shape (batch_size, ...) or smaller
135
+ y_batch : jnp.ndarray of shape (batch_size,) or None
136
+
137
+ Examples
138
+ --------
139
+ >>> key = jax.random.PRNGKey(0)
140
+ >>> X = jnp.ones((10, 3))
141
+ >>> for X_b, y_b in batched_iterator(X, batch_size=4, key=key):
142
+ ... print(X_b.shape)
143
+ (4, 3)
144
+ (4, 3)
145
+ (2, 3)
146
+ """
147
+ n_samples = X.shape[0]
148
+
149
+ if shuffle and key is not None:
150
+ if y is not None:
151
+ X, y = shuffle_arrays(key, X, y)
152
+ else:
153
+ X, = shuffle_arrays(key, X)
154
+
155
+ for start in range(0, n_samples, batch_size):
156
+ end = min(start + batch_size, n_samples)
157
+ if drop_last and (end - start) < batch_size:
158
+ break
159
+ X_batch = X[start:end]
160
+ y_batch = y[start:end] if y is not None else None
161
+ yield X_batch, y_batch