isotree 0.2.2 → 0.3.0

Sign up to get free protection for your applications and to get access to all the features.
Files changed (151) hide show
  1. checksums.yaml +4 -4
  2. data/CHANGELOG.md +8 -1
  3. data/LICENSE.txt +2 -2
  4. data/README.md +32 -14
  5. data/ext/isotree/ext.cpp +144 -31
  6. data/ext/isotree/extconf.rb +7 -7
  7. data/lib/isotree/isolation_forest.rb +110 -30
  8. data/lib/isotree/version.rb +1 -1
  9. data/vendor/isotree/LICENSE +1 -1
  10. data/vendor/isotree/README.md +165 -27
  11. data/vendor/isotree/include/isotree.hpp +2111 -0
  12. data/vendor/isotree/include/isotree_oop.hpp +394 -0
  13. data/vendor/isotree/inst/COPYRIGHTS +62 -0
  14. data/vendor/isotree/src/RcppExports.cpp +525 -52
  15. data/vendor/isotree/src/Rwrapper.cpp +1931 -268
  16. data/vendor/isotree/src/c_interface.cpp +953 -0
  17. data/vendor/isotree/src/crit.hpp +4232 -0
  18. data/vendor/isotree/src/dist.hpp +1886 -0
  19. data/vendor/isotree/src/exp_depth_table.hpp +134 -0
  20. data/vendor/isotree/src/extended.hpp +1444 -0
  21. data/vendor/isotree/src/external_facing_generic.hpp +399 -0
  22. data/vendor/isotree/src/fit_model.hpp +2401 -0
  23. data/vendor/isotree/src/{dealloc.cpp → headers_joined.hpp} +38 -22
  24. data/vendor/isotree/src/helpers_iforest.hpp +813 -0
  25. data/vendor/isotree/src/{impute.cpp → impute.hpp} +353 -122
  26. data/vendor/isotree/src/indexer.cpp +515 -0
  27. data/vendor/isotree/src/instantiate_template_headers.cpp +118 -0
  28. data/vendor/isotree/src/instantiate_template_headers.hpp +240 -0
  29. data/vendor/isotree/src/isoforest.hpp +1659 -0
  30. data/vendor/isotree/src/isotree.hpp +1804 -392
  31. data/vendor/isotree/src/isotree_exportable.hpp +99 -0
  32. data/vendor/isotree/src/merge_models.cpp +159 -16
  33. data/vendor/isotree/src/mult.hpp +1321 -0
  34. data/vendor/isotree/src/oop_interface.cpp +842 -0
  35. data/vendor/isotree/src/oop_interface.hpp +278 -0
  36. data/vendor/isotree/src/other_helpers.hpp +219 -0
  37. data/vendor/isotree/src/predict.hpp +1932 -0
  38. data/vendor/isotree/src/python_helpers.hpp +134 -0
  39. data/vendor/isotree/src/ref_indexer.hpp +154 -0
  40. data/vendor/isotree/src/robinmap/LICENSE +21 -0
  41. data/vendor/isotree/src/robinmap/README.md +483 -0
  42. data/vendor/isotree/src/robinmap/include/tsl/robin_growth_policy.h +406 -0
  43. data/vendor/isotree/src/robinmap/include/tsl/robin_hash.h +1620 -0
  44. data/vendor/isotree/src/robinmap/include/tsl/robin_map.h +807 -0
  45. data/vendor/isotree/src/robinmap/include/tsl/robin_set.h +660 -0
  46. data/vendor/isotree/src/serialize.cpp +4300 -139
  47. data/vendor/isotree/src/sql.cpp +141 -59
  48. data/vendor/isotree/src/subset_models.cpp +174 -0
  49. data/vendor/isotree/src/utils.hpp +3808 -0
  50. data/vendor/isotree/src/xoshiro.hpp +467 -0
  51. data/vendor/isotree/src/ziggurat.hpp +405 -0
  52. metadata +38 -104
  53. data/vendor/cereal/LICENSE +0 -24
  54. data/vendor/cereal/README.md +0 -85
  55. data/vendor/cereal/include/cereal/access.hpp +0 -351
  56. data/vendor/cereal/include/cereal/archives/adapters.hpp +0 -163
  57. data/vendor/cereal/include/cereal/archives/binary.hpp +0 -169
  58. data/vendor/cereal/include/cereal/archives/json.hpp +0 -1019
  59. data/vendor/cereal/include/cereal/archives/portable_binary.hpp +0 -334
  60. data/vendor/cereal/include/cereal/archives/xml.hpp +0 -956
  61. data/vendor/cereal/include/cereal/cereal.hpp +0 -1089
  62. data/vendor/cereal/include/cereal/details/helpers.hpp +0 -422
  63. data/vendor/cereal/include/cereal/details/polymorphic_impl.hpp +0 -796
  64. data/vendor/cereal/include/cereal/details/polymorphic_impl_fwd.hpp +0 -65
  65. data/vendor/cereal/include/cereal/details/static_object.hpp +0 -127
  66. data/vendor/cereal/include/cereal/details/traits.hpp +0 -1411
  67. data/vendor/cereal/include/cereal/details/util.hpp +0 -84
  68. data/vendor/cereal/include/cereal/external/base64.hpp +0 -134
  69. data/vendor/cereal/include/cereal/external/rapidjson/allocators.h +0 -284
  70. data/vendor/cereal/include/cereal/external/rapidjson/cursorstreamwrapper.h +0 -78
  71. data/vendor/cereal/include/cereal/external/rapidjson/document.h +0 -2652
  72. data/vendor/cereal/include/cereal/external/rapidjson/encodedstream.h +0 -299
  73. data/vendor/cereal/include/cereal/external/rapidjson/encodings.h +0 -716
  74. data/vendor/cereal/include/cereal/external/rapidjson/error/en.h +0 -74
  75. data/vendor/cereal/include/cereal/external/rapidjson/error/error.h +0 -161
  76. data/vendor/cereal/include/cereal/external/rapidjson/filereadstream.h +0 -99
  77. data/vendor/cereal/include/cereal/external/rapidjson/filewritestream.h +0 -104
  78. data/vendor/cereal/include/cereal/external/rapidjson/fwd.h +0 -151
  79. data/vendor/cereal/include/cereal/external/rapidjson/internal/biginteger.h +0 -290
  80. data/vendor/cereal/include/cereal/external/rapidjson/internal/diyfp.h +0 -271
  81. data/vendor/cereal/include/cereal/external/rapidjson/internal/dtoa.h +0 -245
  82. data/vendor/cereal/include/cereal/external/rapidjson/internal/ieee754.h +0 -78
  83. data/vendor/cereal/include/cereal/external/rapidjson/internal/itoa.h +0 -308
  84. data/vendor/cereal/include/cereal/external/rapidjson/internal/meta.h +0 -186
  85. data/vendor/cereal/include/cereal/external/rapidjson/internal/pow10.h +0 -55
  86. data/vendor/cereal/include/cereal/external/rapidjson/internal/regex.h +0 -740
  87. data/vendor/cereal/include/cereal/external/rapidjson/internal/stack.h +0 -232
  88. data/vendor/cereal/include/cereal/external/rapidjson/internal/strfunc.h +0 -69
  89. data/vendor/cereal/include/cereal/external/rapidjson/internal/strtod.h +0 -290
  90. data/vendor/cereal/include/cereal/external/rapidjson/internal/swap.h +0 -46
  91. data/vendor/cereal/include/cereal/external/rapidjson/istreamwrapper.h +0 -128
  92. data/vendor/cereal/include/cereal/external/rapidjson/memorybuffer.h +0 -70
  93. data/vendor/cereal/include/cereal/external/rapidjson/memorystream.h +0 -71
  94. data/vendor/cereal/include/cereal/external/rapidjson/msinttypes/inttypes.h +0 -316
  95. data/vendor/cereal/include/cereal/external/rapidjson/msinttypes/stdint.h +0 -300
  96. data/vendor/cereal/include/cereal/external/rapidjson/ostreamwrapper.h +0 -81
  97. data/vendor/cereal/include/cereal/external/rapidjson/pointer.h +0 -1414
  98. data/vendor/cereal/include/cereal/external/rapidjson/prettywriter.h +0 -277
  99. data/vendor/cereal/include/cereal/external/rapidjson/rapidjson.h +0 -656
  100. data/vendor/cereal/include/cereal/external/rapidjson/reader.h +0 -2230
  101. data/vendor/cereal/include/cereal/external/rapidjson/schema.h +0 -2497
  102. data/vendor/cereal/include/cereal/external/rapidjson/stream.h +0 -223
  103. data/vendor/cereal/include/cereal/external/rapidjson/stringbuffer.h +0 -121
  104. data/vendor/cereal/include/cereal/external/rapidjson/writer.h +0 -709
  105. data/vendor/cereal/include/cereal/external/rapidxml/license.txt +0 -52
  106. data/vendor/cereal/include/cereal/external/rapidxml/manual.html +0 -406
  107. data/vendor/cereal/include/cereal/external/rapidxml/rapidxml.hpp +0 -2624
  108. data/vendor/cereal/include/cereal/external/rapidxml/rapidxml_iterators.hpp +0 -175
  109. data/vendor/cereal/include/cereal/external/rapidxml/rapidxml_print.hpp +0 -428
  110. data/vendor/cereal/include/cereal/external/rapidxml/rapidxml_utils.hpp +0 -123
  111. data/vendor/cereal/include/cereal/macros.hpp +0 -154
  112. data/vendor/cereal/include/cereal/specialize.hpp +0 -139
  113. data/vendor/cereal/include/cereal/types/array.hpp +0 -79
  114. data/vendor/cereal/include/cereal/types/atomic.hpp +0 -55
  115. data/vendor/cereal/include/cereal/types/base_class.hpp +0 -203
  116. data/vendor/cereal/include/cereal/types/bitset.hpp +0 -176
  117. data/vendor/cereal/include/cereal/types/boost_variant.hpp +0 -164
  118. data/vendor/cereal/include/cereal/types/chrono.hpp +0 -72
  119. data/vendor/cereal/include/cereal/types/common.hpp +0 -129
  120. data/vendor/cereal/include/cereal/types/complex.hpp +0 -56
  121. data/vendor/cereal/include/cereal/types/concepts/pair_associative_container.hpp +0 -73
  122. data/vendor/cereal/include/cereal/types/deque.hpp +0 -62
  123. data/vendor/cereal/include/cereal/types/forward_list.hpp +0 -68
  124. data/vendor/cereal/include/cereal/types/functional.hpp +0 -43
  125. data/vendor/cereal/include/cereal/types/list.hpp +0 -62
  126. data/vendor/cereal/include/cereal/types/map.hpp +0 -36
  127. data/vendor/cereal/include/cereal/types/memory.hpp +0 -425
  128. data/vendor/cereal/include/cereal/types/optional.hpp +0 -66
  129. data/vendor/cereal/include/cereal/types/polymorphic.hpp +0 -483
  130. data/vendor/cereal/include/cereal/types/queue.hpp +0 -132
  131. data/vendor/cereal/include/cereal/types/set.hpp +0 -103
  132. data/vendor/cereal/include/cereal/types/stack.hpp +0 -76
  133. data/vendor/cereal/include/cereal/types/string.hpp +0 -61
  134. data/vendor/cereal/include/cereal/types/tuple.hpp +0 -123
  135. data/vendor/cereal/include/cereal/types/unordered_map.hpp +0 -36
  136. data/vendor/cereal/include/cereal/types/unordered_set.hpp +0 -99
  137. data/vendor/cereal/include/cereal/types/utility.hpp +0 -47
  138. data/vendor/cereal/include/cereal/types/valarray.hpp +0 -89
  139. data/vendor/cereal/include/cereal/types/variant.hpp +0 -109
  140. data/vendor/cereal/include/cereal/types/vector.hpp +0 -112
  141. data/vendor/cereal/include/cereal/version.hpp +0 -52
  142. data/vendor/isotree/src/Makevars +0 -4
  143. data/vendor/isotree/src/crit.cpp +0 -912
  144. data/vendor/isotree/src/dist.cpp +0 -749
  145. data/vendor/isotree/src/extended.cpp +0 -790
  146. data/vendor/isotree/src/fit_model.cpp +0 -1090
  147. data/vendor/isotree/src/helpers_iforest.cpp +0 -324
  148. data/vendor/isotree/src/isoforest.cpp +0 -771
  149. data/vendor/isotree/src/mult.cpp +0 -607
  150. data/vendor/isotree/src/predict.cpp +0 -853
  151. data/vendor/isotree/src/utils.cpp +0 -1566
@@ -18,11 +18,29 @@
18
18
  * [5] https://sourceforge.net/projects/iforest/
19
19
  * [6] https://math.stackexchange.com/questions/3388518/expected-number-of-paths-required-to-separate-elements-in-a-binary-tree
20
20
  * [7] Quinlan, J. Ross. C4. 5: programs for machine learning. Elsevier, 2014.
21
- * [8] Cortes, David. "Distance approximation using Isolation Forests." arXiv preprint arXiv:1910.12362 (2019).
22
- * [9] Cortes, David. "Imputing missing values with unsupervised random trees." arXiv preprint arXiv:1911.06646 (2019).
21
+ * [8] Cortes, David.
22
+ * "Distance approximation using Isolation Forests."
23
+ * arXiv preprint arXiv:1910.12362 (2019).
24
+ * [9] Cortes, David.
25
+ * "Imputing missing values with unsupervised random trees."
26
+ * arXiv preprint arXiv:1911.06646 (2019).
27
+ * [10] https://math.stackexchange.com/questions/3333220/expected-average-depth-in-random-binary-tree-constructed-top-to-bottom
28
+ * [11] Cortes, David.
29
+ * "Revisiting randomized choices in isolation forests."
30
+ * arXiv preprint arXiv:2110.13402 (2021).
31
+ * [12] Guha, Sudipto, et al.
32
+ * "Robust random cut forest based anomaly detection on streams."
33
+ * International conference on machine learning. PMLR, 2016.
34
+ * [13] Cortes, David.
35
+ * "Isolation forests: looking beyond tree depth."
36
+ * arXiv preprint arXiv:2111.11639 (2021).
37
+ * [14] Ting, Kai Ming, Yue Zhu, and Zhi-Hua Zhou.
38
+ * "Isolation kernel and its effect on SVM"
39
+ * Proceedings of the 24th ACM SIGKDD
40
+ * International Conference on Knowledge Discovery & Data Mining. 2018.
23
41
  *
24
42
  * BSD 2-Clause License
25
- * Copyright (c) 2020, David Cortes
43
+ * Copyright (c) 2019-2022, David Cortes
26
44
  * All rights reserved.
27
45
  * Redistribution and use in source and binary forms, with or without
28
46
  * modification, are permitted provided that the following conditions are met:
@@ -44,23 +62,21 @@
44
62
  */
45
63
  #include "isotree.hpp"
46
64
 
47
- /* Reason behind this file: Cython (as of v0.29) will not auto-deallocate
48
- structs which are part of a cdef'd class, which produces a memory leak
49
- but can be force-destructed. Unfortunately, Cython itself doesn't even
50
- allow calling destructors for structs, so it has to be done externally.
51
- These functions should otherwise have no reason to be. */
65
+ #include "crit.hpp"
66
+ #include "dist.hpp"
67
+ #include "extended.hpp"
68
+ #include "fit_model.hpp"
69
+ #include "helpers_iforest.hpp"
70
+ #include "impute.hpp"
71
+ #include "isoforest.hpp"
72
+ #include "mult.hpp"
73
+ #include "predict.hpp"
74
+ #include "ref_indexer.hpp"
75
+ #include "utils.hpp"
52
76
 
53
- void dealloc_IsoForest(IsoForest &model_outputs)
54
- {
55
- model_outputs.~IsoForest();
56
- }
57
-
58
- void dealloc_IsoExtForest(ExtIsoForest &model_outputs_ext)
59
- {
60
- model_outputs_ext.~ExtIsoForest();
61
- }
62
-
63
- void dealloc_Imputer(Imputer &imputer)
64
- {
65
- imputer.~Imputer();
66
- }
77
+ /* Note: Cython also defines these in its auto-generated code, and leads to
78
+ conflicts if they are not undefined and then included again. */
79
+ #ifdef _FOR_PYTHON
80
+ #undef likely
81
+ #undef unlikely
82
+ #endif