InsurAutoML 0.2.8__tar.gz → 0.2.9__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 (149) hide show
  1. insurautoml-0.2.9/InsurAutoML/VERSION +1 -0
  2. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/__init__.py +5 -83
  3. insurautoml-0.2.9/InsurAutoML/_optional.py +94 -0
  4. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/balancing/mixed_sampling.py +10 -4
  5. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/balancing/over_sampling.py +14 -3
  6. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/balancing/under_sampling.py +79 -29
  7. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/base.py +1 -0
  8. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/datasets/image.py +2 -9
  9. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/datasets/tabular.py +0 -43
  10. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/datasets/text.py +0 -1
  11. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/encoding/encoding.py +22 -14
  12. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/ext/__init__.py +16 -2
  13. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/ext/suppsplit/__init__.py +1 -1
  14. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/ext/suppsplit/suppsplit/__init__.py +1 -1
  15. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/ext/suppsplit/suppsplit/split.py +8 -2
  16. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/ext/suppsplit/suppsplit/utils.py +4 -3
  17. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/ext/suppsplit/suppsplit_cpp/bindings.cpp +10 -7
  18. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/feature_selection/__init__.py +10 -53
  19. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/feature_selection/base.py +3 -3
  20. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/feature_selection/filter.py +15 -2
  21. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/feature_selection/hybrid.py +9 -2
  22. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/feature_selection/sklearn.py +11 -5
  23. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/feature_selection/wrapper.py +5 -4
  24. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/hpo/ML.py +17 -17
  25. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/hpo/base.py +345 -377
  26. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/hpo/informed/ML.py +24 -25
  27. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/hpo/informed/__init__.py +24 -5
  28. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/hpo/informed/base.py +166 -390
  29. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/hpo/informed/fixed.py +37 -33
  30. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/hpo/informed/informed_ensemble.py +47 -22
  31. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/hpo/informed/utils.py +74 -58
  32. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/hpo/utils.py +123 -60
  33. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/hyperparameters/__init__.py +2 -2
  34. insurautoml-0.2.9/InsurAutoML/hyperparameters/ray/balancing_hyperparameter.py +115 -0
  35. insurautoml-0.2.9/InsurAutoML/hyperparameters/ray/classifier_hyperparameter.py +365 -0
  36. insurautoml-0.2.8/InsurAutoML/utils/_c/__init__.py → insurautoml-0.2.9/InsurAutoML/hyperparameters/ray/encoder_hyperparameter.py +31 -16
  37. insurautoml-0.2.9/InsurAutoML/hyperparameters/ray/feature_selection_hyperparameter.py +274 -0
  38. insurautoml-0.2.9/InsurAutoML/hyperparameters/ray/imputer_hyperparameter.py +109 -0
  39. insurautoml-0.2.8/InsurAutoML/ext/twinreduction/twinreduction/__init__.py → insurautoml-0.2.9/InsurAutoML/hyperparameters/ray/prep_hyperparameter.py +32 -6
  40. insurautoml-0.2.9/InsurAutoML/hyperparameters/ray/regressor_hyperparameter.py +387 -0
  41. insurautoml-0.2.9/InsurAutoML/hyperparameters/ray/scaling_hyperparameter.py +80 -0
  42. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/imputation/base.py +1 -1
  43. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/imputation/clustering.py +9 -6
  44. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/imputation/multiple.py +14 -15
  45. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/imputation/nn.py +34 -23
  46. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/model/FNN.py +1 -1
  47. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/model/RNN.py +9 -6
  48. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/model/__init__.py +0 -87
  49. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/model/catboost.py +9 -1
  50. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/model/gam.py +4 -2
  51. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/model/sklearn_classifiers.py +5 -6
  52. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/model/sklearn_regressors.py +12 -3
  53. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/prep/__init__.py +6 -1
  54. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/prep/pipeline.py +61 -70
  55. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/prep/prep.py +1 -1
  56. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/prep/utils.py +25 -19
  57. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/scaling/scaling.py +6 -8
  58. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/utils/base.py +48 -28
  59. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/utils/data.py +61 -21
  60. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/utils/eda.py +12 -7
  61. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/utils/file.py +11 -3
  62. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/utils/metadata.py +24 -20
  63. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/utils/optimize.py +319 -234
  64. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/utils/stats.py +1 -2
  65. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML.egg-info/PKG-INFO +64 -54
  66. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML.egg-info/SOURCES.txt +52 -12
  67. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML.egg-info/requires.txt +13 -30
  68. insurautoml-0.2.9/InsurAutoML.egg-info/top_level.txt +5 -0
  69. {insurautoml-0.2.8 → insurautoml-0.2.9}/PKG-INFO +64 -54
  70. {insurautoml-0.2.8 → insurautoml-0.2.9}/README.md +291 -259
  71. insurautoml-0.2.9/pyproject.toml +120 -0
  72. insurautoml-0.2.9/setup.py +379 -0
  73. insurautoml-0.2.9/tests/test_balancing/test_balancing.py +72 -0
  74. insurautoml-0.2.9/tests/test_datasets/test_datasets_hf.py +164 -0
  75. insurautoml-0.2.9/tests/test_datasets/test_datasets_tabular.py +343 -0
  76. insurautoml-0.2.9/tests/test_encoder/test_encoder.py +95 -0
  77. insurautoml-0.2.9/tests/test_feature_selection/test_feature_selection.py +261 -0
  78. insurautoml-0.2.9/tests/test_feature_selection/test_feature_selection_more.py +736 -0
  79. insurautoml-0.2.9/tests/test_feature_selection/test_feature_selection_wrapper.py +226 -0
  80. insurautoml-0.2.9/tests/test_hpo/test_hpo.py +434 -0
  81. insurautoml-0.2.9/tests/test_hpo/test_hpo_2.py +435 -0
  82. insurautoml-0.2.9/tests/test_hpo/test_hpo_3.py +531 -0
  83. insurautoml-0.2.9/tests/test_hpo/test_hpo_ensemble.py +212 -0
  84. insurautoml-0.2.9/tests/test_hpo/test_hpo_ensemble_voting.py +237 -0
  85. insurautoml-0.2.9/tests/test_hpo/test_hpo_spaces.py +147 -0
  86. insurautoml-0.2.9/tests/test_hyperparameters/test_hyperparameters.py +109 -0
  87. insurautoml-0.2.9/tests/test_imputer/test_imputer.py +245 -0
  88. insurautoml-0.2.9/tests/test_imputer/test_imputer_clustering.py +381 -0
  89. insurautoml-0.2.9/tests/test_imputer/test_imputer_more.py +424 -0
  90. insurautoml-0.2.9/tests/test_imputer/test_imputer_nn.py +257 -0
  91. insurautoml-0.2.9/tests/test_informed/conftest.py +110 -0
  92. insurautoml-0.2.9/tests/test_informed/test_informed_automl.py +172 -0
  93. insurautoml-0.2.9/tests/test_informed/test_informed_ensemble.py +185 -0
  94. insurautoml-0.2.9/tests/test_informed/test_informed_objective.py +217 -0
  95. insurautoml-0.2.9/tests/test_informed/test_informed_pipeline.py +138 -0
  96. insurautoml-0.2.9/tests/test_informed/test_informed_prep.py +175 -0
  97. insurautoml-0.2.9/tests/test_model/test_model.py +208 -0
  98. insurautoml-0.2.9/tests/test_model/test_model_2.py +350 -0
  99. insurautoml-0.2.9/tests/test_model/test_model_nn.py +343 -0
  100. insurautoml-0.2.9/tests/test_scaling/test_scaling.py +148 -0
  101. insurautoml-0.2.8/InsurAutoML/utils/_c/_stat.pyx → insurautoml-0.2.9/tests/test_utils/test_metadata.py +36 -4
  102. insurautoml-0.2.9/tests/test_utils/test_optional.py +151 -0
  103. insurautoml-0.2.9/tests/test_utils/test_utils.py +126 -0
  104. insurautoml-0.2.9/tests/test_utils/test_utils_base.py +223 -0
  105. insurautoml-0.2.9/tests/test_utils/test_utils_data.py +218 -0
  106. insurautoml-0.2.9/tests/test_utils/test_utils_data_extra.py +398 -0
  107. insurautoml-0.2.9/tests/test_utils/test_utils_metadata_extra.py +290 -0
  108. insurautoml-0.2.9/tests/test_utils/test_utils_optimize.py +222 -0
  109. insurautoml-0.2.9/tests/test_utils/test_utils_optimize_more.py +272 -0
  110. insurautoml-0.2.9/tests/test_utils/test_utils_stat.py +189 -0
  111. insurautoml-0.2.9/tests/test_utils/test_utils_stats_extra.py +288 -0
  112. insurautoml-0.2.9/tests/test_utils/test_utils_tensor.py +143 -0
  113. insurautoml-0.2.8/InsurAutoML/ext/twinreduction/__init__.py +0 -41
  114. insurautoml-0.2.8/InsurAutoML/ext/twinreduction/twinning_cpp/bindings.cpp +0 -101
  115. insurautoml-0.2.8/InsurAutoML/ext/twinreduction/twinning_cpp/twinning.cpp +0 -163
  116. insurautoml-0.2.8/InsurAutoML/ext/twinreduction/twinreduction/twinreduction.py +0 -131
  117. insurautoml-0.2.8/InsurAutoML/feature_selection/autosklearn.py +0 -644
  118. insurautoml-0.2.8/InsurAutoML/model/autosklearn.py +0 -1552
  119. insurautoml-0.2.8/InsurAutoML/utils/_c/_base.pyx +0 -154
  120. insurautoml-0.2.8/InsurAutoML.egg-info/not-zip-safe +0 -1
  121. insurautoml-0.2.8/InsurAutoML.egg-info/top_level.txt +0 -1
  122. insurautoml-0.2.8/setup.py +0 -603
  123. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/balancing/__init__.py +0 -0
  124. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/balancing/base.py +0 -0
  125. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/constant.py +0 -0
  126. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/datasets/__init__.py +0 -0
  127. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/encoding/__init__.py +0 -0
  128. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/encoding/base.py +0 -0
  129. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/ext/suppsplit/suppsplit_cpp/sPlit.cpp +0 -0
  130. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/ext/suppsplit/suppsplit_cpp/sp.cpp +0 -0
  131. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/feature_selection/embed.py +0 -0
  132. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/hpo/DL.py +0 -0
  133. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/hpo/__init__.py +0 -0
  134. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/hpo/ensemble.py +0 -0
  135. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/imputation/__init__.py +0 -0
  136. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/model/ML.py +0 -0
  137. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/model/base.py +0 -0
  138. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/model/clustering.py +0 -0
  139. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/model/lightgbm.py +0 -0
  140. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/model/xgboost.py +0 -0
  141. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/scaling/__init__.py +0 -0
  142. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/scaling/base.py +0 -0
  143. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/utils/__init__.py +0 -0
  144. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/utils/tensor.py +0 -0
  145. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML/version.py +0 -0
  146. {insurautoml-0.2.8 → insurautoml-0.2.9}/InsurAutoML.egg-info/dependency_links.txt +0 -0
  147. {insurautoml-0.2.8 → insurautoml-0.2.9}/LICENSE +0 -0
  148. {insurautoml-0.2.8 → insurautoml-0.2.9}/setup.cfg +0 -0
  149. {insurautoml-0.2.8 → insurautoml-0.2.9}/tests/test_base.py +0 -0
@@ -0,0 +1 @@
1
+ 0.2.9
@@ -171,97 +171,19 @@ __version__ = _get_version()
171
171
  # "AutoNextWordPrediction": AutoNextWordPrediction,
172
172
  # }
173
173
 
174
+ # public names of the package (the submodules export the individual components,
175
+ # e.g. InsurAutoML.encoding, InsurAutoML.imputation, InsurAutoML.model)
174
176
  __all__ = [
175
177
  "load_data", # _base
176
178
  "no_processing",
177
- "random_guess", # _utils
178
- "random_index",
179
- "random_list",
180
- "is_date",
181
- "feature_rounding",
182
- "train_test_split",
183
- "minloc",
184
- "maxloc",
185
- "True_index",
186
- "nan_cov",
187
- "class_means",
188
- "empirical_covariance",
189
- "class_cov",
190
- "Pearson_Corr",
191
- "MI",
192
- "t_score",
193
- "ANOVA",
194
- "as_dataframe",
179
+ "set_seed",
180
+ "train_test_split", # _utils
195
181
  "type_of_task",
196
- "formatting",
197
- "Timer",
198
- "unify_nan",
199
- "remove_index_columns",
200
- "get_missing_matrix",
201
- "SimpleImputer", # _missing
202
- "DummyImputer",
203
- "JointImputer",
204
- "ExpectationMaximization",
205
- "KNNImputer",
206
- "MissForestImputer",
207
- "MICE",
208
- "GAIN",
209
- "AAI_kNN",
210
- "KMI",
211
- "CMI",
212
- "k_Prototype_NN",
213
- "DataEncoding", # _encoding
214
- "MinMaxScale", # _scaling
215
- "Standardize",
216
- "Normalize",
217
- "RobustScale",
218
- "PowerTransformer",
219
- "QuantileTransformer",
220
- "Winsorization",
221
- "Feature_Manipulation",
222
- "Feature_Truncation",
223
- "SimpleRandomOverSampling", # _imbalance
224
- "SimpleRandomUnderSampling",
225
- "TomekLink",
226
- "EditedNearestNeighbor",
227
- "CondensedNearestNeighbor",
228
- "OneSidedSelection",
229
- "CNN_TomekLink",
230
- "Smote",
231
- "Smote_TomekLink",
232
- "Smote_ENN",
233
- "LDASelection", # _feature_selection
234
- "PCA_FeatureSelection",
235
- "RBFSampler",
236
- "FeatureFilter",
237
- "ASFFS",
238
- "GeneticAlgorithm",
239
- "densifier", # from sklearn
240
- "extra_trees_preproc_for_classification",
241
- "extra_trees_preproc_for_regression",
242
- "fast_ica",
243
- "feature_agglomeration",
244
- "kernel_pca",
245
- "kitchen_sinks",
246
- "liblinear_svc_preprocessor",
247
- "nystroem_sampler",
248
- "pca",
249
- "polynomial",
250
- "random_trees_embedding",
251
- # 'select_percentile',
252
- "select_percentile_classification",
253
- "select_percentile_regression",
254
- "select_rates_classification",
255
- "select_rates_regression",
256
- "truncatedSVD",
257
- "classifiers", # _model
258
- "regressors",
182
+ "EDA",
259
183
  "AutoTabular", # _model_selection
260
184
  "AutoTabularClassifier",
261
185
  "AutoTabularRegressor",
262
186
  "InformedAutoTabular",
263
187
  "InformedAutoTabularRegressor",
264
188
  "InformedAutoTabularClassifier",
265
- "AutoTextClassifier",
266
- "AutoNextWordPrediction",
267
189
  ]
@@ -0,0 +1,94 @@
1
+ """
2
+ File: _optional.py
3
+ Author: Panyi Dong
4
+ GitHub: https://github.com/PanyiDong/
5
+ Mathematics Department, University of Illinois at Urbana-Champaign (UIUC)
6
+
7
+ Project: InsurAutoML
8
+ Relative Path: /InsurAutoML/_optional.py
9
+
10
+ Availability of the optional "informed" installation.
11
+
12
+ The informed pipelines (InformedAutoTabular*, InsurAutoML.prep) need the compiled
13
+ C++ extension in InsurAutoML.ext (SPlit) and the extra Python
14
+ dependencies (missforest, ...). They are only built/installed with
15
+
16
+ INFORMEDAUTOML=1 pip install "InsurAutoML[informed]"
17
+
18
+ The checks below do not import anything, so a default installation can import
19
+ InsurAutoML without the optional components.
20
+ """
21
+
22
+ from __future__ import annotations
23
+
24
+ import importlib.util
25
+ import os
26
+ from importlib.machinery import EXTENSION_SUFFIXES
27
+ from typing import List
28
+
29
+ INFORMED_INSTALL_CMD = 'INFORMEDAUTOML=1 pip install "InsurAutoML[informed]"'
30
+ # an existing (normal) installation is kept by pip as "already satisfied", reinstall
31
+ # InsurAutoML itself to build the C++ extension
32
+ INFORMED_REINSTALL_CMD = (
33
+ "INFORMEDAUTOML=1 pip install --force-reinstall --no-deps --no-cache-dir "
34
+ "InsurAutoML"
35
+ )
36
+
37
+ # Python packages only needed by the informed pipelines
38
+ INFORMED_PACKAGES = ["missforest"]
39
+
40
+ # compiled extensions: (sub-package of InsurAutoML.ext, extension module name)
41
+ INFORMED_EXTENSIONS = [
42
+ ("suppsplit", "suppsplit_cpp"),
43
+ ]
44
+
45
+ _EXT_DIR = os.path.join(os.path.dirname(os.path.abspath(__file__)), "ext")
46
+
47
+
48
+ class InformedNotInstalledError(ImportError):
49
+ """The optional informed installation is missing."""
50
+
51
+
52
+ def missing_informed_components() -> List[str]:
53
+ """Names of the missing informed components (empty if all are available)."""
54
+ missing = [
55
+ package
56
+ for package in INFORMED_PACKAGES
57
+ if importlib.util.find_spec(package) is None
58
+ ]
59
+ for subpackage, module in INFORMED_EXTENSIONS:
60
+ # look for the compiled extension file (e.g. suppsplit_cpp.cpython-312-*.so)
61
+ # without importing; the C++ source folder has the same name as the module
62
+ folder = os.path.join(_EXT_DIR, subpackage)
63
+ if not any(
64
+ os.path.isfile(os.path.join(folder, module + suffix))
65
+ for suffix in EXTENSION_SUFFIXES
66
+ ):
67
+ missing.append("InsurAutoML.ext.{}.{}".format(subpackage, module))
68
+
69
+ return missing
70
+
71
+
72
+ def informed_available() -> bool:
73
+ """Whether the informed pipelines can be used."""
74
+ return len(missing_informed_components()) == 0
75
+
76
+
77
+ def informed_not_installed_error(feature: str = "InformedAutoTabular") -> ImportError:
78
+ """Error asking the user to install the informed version."""
79
+ return InformedNotInstalledError(
80
+ "{} is not available, the InformedAutoML version is not installed "
81
+ "(missing: {}).\nInstall it with:\n {}\nIf InsurAutoML is already installed, "
82
+ "also rebuild it with the C++ extension:\n {}".format(
83
+ feature,
84
+ ", ".join(missing_informed_components()),
85
+ INFORMED_INSTALL_CMD,
86
+ INFORMED_REINSTALL_CMD,
87
+ )
88
+ )
89
+
90
+
91
+ def require_informed(feature: str = "InformedAutoTabular") -> None:
92
+ """Raise InformedNotInstalledError if the informed installation is missing."""
93
+ if not informed_available():
94
+ raise informed_not_installed_error(feature)
@@ -109,8 +109,10 @@ class Smote_TomekLink(Smote, TomekLink):
109
109
  if not is_imbalance(_data, self.imbalance_threshold):
110
110
  warnings.warn("The dataset is balanced, no change.")
111
111
  else:
112
+ # keep the user threshold, __init__ below overwrites it
113
+ _threshold = self.imbalance_threshold
112
114
  super().__init__(
113
- imbalance_threshold=(1.0 + self.imbalance_threshold) / 2,
115
+ imbalance_threshold=(1.0 + _threshold) / 2,
114
116
  norm=self.norm,
115
117
  all=self.all,
116
118
  max_iter=self.max_iter,
@@ -121,13 +123,14 @@ class Smote_TomekLink(Smote, TomekLink):
121
123
  _data = super().fit_transform(_data)
122
124
 
123
125
  super(Smote, self).__init__(
124
- imbalance_threshold=self.imbalance_threshold,
126
+ imbalance_threshold=_threshold,
125
127
  norm=self.norm,
126
128
  all=self.all,
127
129
  max_iter=self.max_iter,
128
130
  seed=self.seed,
129
131
  )
130
132
  _data = super(Smote, self).fit_transform(_data)
133
+ self.imbalance_threshold = _threshold
131
134
 
132
135
  self._fitted = True
133
136
 
@@ -187,8 +190,10 @@ class Smote_ENN(Smote, EditedNearestNeighbor):
187
190
  if not is_imbalance(_data, self.imbalance_threshold):
188
191
  warnings.warn("The dataset is balanced, no change.")
189
192
  else:
193
+ # keep the user threshold, __init__ below overwrites it
194
+ _threshold = self.imbalance_threshold
190
195
  super().__init__(
191
- imbalance_threshold=(1.0 + self.imbalance_threshold) / 2,
196
+ imbalance_threshold=(1.0 + _threshold) / 2,
192
197
  norm=self.norm,
193
198
  all=self.all,
194
199
  max_iter=self.max_iter,
@@ -199,13 +204,14 @@ class Smote_ENN(Smote, EditedNearestNeighbor):
199
204
  _data = super().fit_transform(_data)
200
205
 
201
206
  super(Smote, self).__init__(
202
- imbalance_threshold=self.imbalance_threshold,
207
+ imbalance_threshold=_threshold,
203
208
  all=self.all,
204
209
  max_iter=self.max_iter,
205
210
  seed=self.seed,
206
211
  k=self.k,
207
212
  )
208
213
  _data = super(Smote, self).fit_transform(_data)
214
+ self.imbalance_threshold = _threshold
209
215
 
210
216
  self._fitted = True
211
217
 
@@ -233,10 +233,21 @@ class Smote(BaseBalancing):
233
233
  warnings.warn("The dataset is balanced, no change.")
234
234
  else:
235
235
  if self.all:
236
- while is_imbalance(_data, self.imbalance_threshold):
237
- _data = self._fit_transform(_data)
236
+ # stop when a pass does not change the data (can not balance further)
237
+ _iter = 0
238
+ while (
239
+ is_imbalance(_data, self.imbalance_threshold)
240
+ and _iter < self.max_iter
241
+ ):
242
+ _new_data = Smote._fit_transform(self, _data)
243
+ if len(_new_data) == len(_data):
244
+ warnings.warn("Smote can not reduce the imbalance further.")
245
+ _data = _new_data
246
+ break
247
+ _data = _new_data
248
+ _iter += 1
238
249
  else:
239
- _data = self._fit_transform(_data)
250
+ _data = Smote._fit_transform(self, _data)
240
251
 
241
252
  self._fitted = True
242
253
 
@@ -221,10 +221,21 @@ class TomekLink(BaseBalancing):
221
221
  warnings.warn("The dataset is balanced, no change.")
222
222
  else:
223
223
  if self.all:
224
- while is_imbalance(_data, self.imbalance_threshold):
225
- _data = self._fit_transform(_data)
224
+ # stop when a pass does not change the data (can not balance further)
225
+ _iter = 0
226
+ while (
227
+ is_imbalance(_data, self.imbalance_threshold)
228
+ and _iter < self.max_iter
229
+ ):
230
+ _new_data = TomekLink._fit_transform(self, _data)
231
+ if len(_new_data) == len(_data):
232
+ warnings.warn("TomekLink can not reduce the imbalance further.")
233
+ _data = _new_data
234
+ break
235
+ _data = _new_data
236
+ _iter += 1
226
237
  else:
227
- _data = self._fit_transform(_data)
238
+ _data = TomekLink._fit_transform(self, _data)
228
239
 
229
240
  self._fitted = True
230
241
 
@@ -341,10 +352,23 @@ class EditedNearestNeighbor(BaseBalancing):
341
352
  warnings.warn("The dataset is balanced, no change.")
342
353
  else:
343
354
  if self.all:
344
- while is_imbalance(_data, self.imbalance_threshold):
345
- _data = self._fit_transform(_data)
355
+ # stop when a pass does not change the data (can not balance further)
356
+ _iter = 0
357
+ while (
358
+ is_imbalance(_data, self.imbalance_threshold)
359
+ and _iter < self.max_iter
360
+ ):
361
+ _new_data = EditedNearestNeighbor._fit_transform(self, _data)
362
+ if len(_new_data) == len(_data):
363
+ warnings.warn(
364
+ "EditedNearestNeighbor can not reduce the imbalance further."
365
+ )
366
+ _data = _new_data
367
+ break
368
+ _data = _new_data
369
+ _iter += 1
346
370
  else:
347
- _data = self._fit_transform(_data)
371
+ _data = EditedNearestNeighbor._fit_transform(self, _data)
348
372
 
349
373
  self._fitted = True
350
374
 
@@ -462,10 +486,24 @@ class CondensedNearestNeighbor(BaseBalancing):
462
486
  warnings.warn("The dataset is balanced, no change.")
463
487
  else:
464
488
  if self.all:
465
- while is_imbalance(_data, self.imbalance_threshold):
466
- _data = self._fit_transform(_data)
489
+ # CNN only removes samples, stop when a pass removes none
490
+ # (the remaining imbalance can not be reduced by CNN)
491
+ _iter = 0
492
+ while (
493
+ is_imbalance(_data, self.imbalance_threshold)
494
+ and _iter < self.max_iter
495
+ ):
496
+ _new_data = CondensedNearestNeighbor._fit_transform(self, _data)
497
+ if len(_new_data) == len(_data):
498
+ warnings.warn(
499
+ "CondensedNearestNeighbor can not reduce the imbalance further."
500
+ )
501
+ _data = _new_data
502
+ break
503
+ _data = _new_data
504
+ _iter += 1
467
505
  else:
468
- _data = self._fit_transform(_data)
506
+ _data = CondensedNearestNeighbor._fit_transform(self, _data)
469
507
 
470
508
  self._fitted = True
471
509
 
@@ -497,6 +535,9 @@ class CondensedNearestNeighbor(BaseBalancing):
497
535
  X, self.imbalance_threshold, value=True
498
536
  )
499
537
  ini_neigh = self._get_initial_neigh(X[_imbalanced_feature])
538
+ # unique index, rows are tracked by index labels below
539
+ X = X.reset_index(drop=True)
540
+ _features = X.columns != _imbalanced_feature
500
541
 
501
542
  _seed = self.seed
502
543
  _iter = 0
@@ -507,26 +548,29 @@ class CondensedNearestNeighbor(BaseBalancing):
507
548
  ):
508
549
  _minority_class = X.loc[X[_imbalanced_feature] != _majority]
509
550
  _majority_class = X.loc[X[_imbalanced_feature] == _majority]
510
- _subset = pd.concat(
511
- [_minority_class, _majority_class.sample(n=1, random_state=_seed)]
512
- ).reset_index(drop=True)
551
+ # subset: all minority samples + one random majority sample
552
+ _sample = _majority_class.sample(n=1, random_state=_seed)
553
+ _subset = pd.concat([_minority_class, _sample])
554
+ # majority samples not in the subset, to be checked by 1-NN
555
+ _rest = _majority_class.drop(index=_sample.index)
556
+ if _rest.empty:
557
+ X = _subset.reset_index(drop=True)
558
+ break
559
+
513
560
  neigh = ini_neigh(n_neighbors=1)
514
561
  neigh.fit(
515
- _subset.loc[:, _subset.columns != _imbalanced_feature],
562
+ _subset.loc[:, _features],
516
563
  _subset[_imbalanced_feature],
517
564
  )
518
- y_predict = neigh.predict(
519
- X.loc[
520
- ~X.index.isin(list(_subset.index)), X.columns != _imbalanced_feature
521
- ]
522
- )
523
- y_true = X.loc[
524
- ~X.index.isin(list(_subset.index)), X.columns == _imbalanced_feature
525
- ].values.T[0]
526
- _not_matching_index = np.where((np.array(y_predict) != np.array(y_true)))[0]
527
- X = pd.concat([_subset, X.iloc[_not_matching_index, :]]).reset_index(
528
- drop=True
529
- )
565
+ y_predict = neigh.predict(_rest.loc[:, _features])
566
+ # keep the misclassified samples (by labels, not positions)
567
+ _misclassified = _rest.loc[
568
+ np.asarray(y_predict) != _rest[_imbalanced_feature].values
569
+ ]
570
+ # no sample removed, condensed set reached
571
+ if len(_subset) + len(_misclassified) == len(X):
572
+ break
573
+ X = pd.concat([_subset, _misclassified]).reset_index(drop=True)
530
574
  _seed += 1
531
575
  _iter += 1
532
576
 
@@ -594,8 +638,10 @@ class OneSidedSelection(TomekLink, CondensedNearestNeighbor):
594
638
  if not is_imbalance(_data, self.imbalance_threshold):
595
639
  warnings.warn("The dataset is balanced, no change.")
596
640
  else:
641
+ # keep the user threshold, __init__ below overwrites it
642
+ _threshold = self.imbalance_threshold
597
643
  super().__init__(
598
- imbalance_threshold=(1.0 + self.imbalance_threshold) / 2,
644
+ imbalance_threshold=(1.0 + _threshold) / 2,
599
645
  norm=self.norm,
600
646
  all=self.all,
601
647
  max_iter=self.max_iter,
@@ -604,12 +650,13 @@ class OneSidedSelection(TomekLink, CondensedNearestNeighbor):
604
650
  _data = super().fit_transform(_data)
605
651
 
606
652
  super(TomekLink, self).__init__(
607
- imbalance_threshold=self.imbalance_threshold,
653
+ imbalance_threshold=_threshold,
608
654
  all=self.all,
609
655
  max_iter=self.max_iter,
610
656
  seed=self.seed,
611
657
  )
612
658
  _data = super(TomekLink, self).fit_transform(_data)
659
+ self.imbalance_threshold = _threshold
613
660
 
614
661
  self._fitted = True
615
662
 
@@ -680,8 +727,10 @@ class CNN_TomekLink(CondensedNearestNeighbor, TomekLink):
680
727
  if not is_imbalance(_data, self.imbalance_threshold):
681
728
  warnings.warn("The dataset is balanced, no change.")
682
729
  else:
730
+ # keep the user threshold, __init__ below overwrites it
731
+ _threshold = self.imbalance_threshold
683
732
  super().__init__(
684
- imbalance_threshold=(1.0 + self.imbalance_threshold) / 2,
733
+ imbalance_threshold=(1.0 + _threshold) / 2,
685
734
  all=self.all,
686
735
  max_iter=self.max_iter,
687
736
  seed=self.seed,
@@ -689,13 +738,14 @@ class CNN_TomekLink(CondensedNearestNeighbor, TomekLink):
689
738
  _data = super().fit_transform(_data)
690
739
 
691
740
  super(CondensedNearestNeighbor, self).__init__(
692
- imbalance_threshold=self.imbalance_threshold,
741
+ imbalance_threshold=_threshold,
693
742
  norm=self.norm,
694
743
  all=self.all,
695
744
  max_iter=self.max_iter,
696
745
  seed=self.seed,
697
746
  )
698
747
  _data = super(CondensedNearestNeighbor, self).fit_transform(_data)
748
+ self.imbalance_threshold = _threshold
699
749
 
700
750
  self._fitted = True
701
751
 
@@ -49,6 +49,7 @@ import warnings
49
49
  # check if rpy2 available
50
50
  # if not, can not read R type data
51
51
  import importlib
52
+
52
53
  # NOTE: Remove rda/rdata loading as rpy2 sometimes causes installation issues
53
54
  # Uncomment the following lines if R data loading is needed
54
55
  # rpy2_spec = importlib.util.find_spec("rpy2")
@@ -46,7 +46,6 @@ from datasets import load_dataset
46
46
 
47
47
 
48
48
  def CIFAR(train=True, test=False, version=10):
49
-
50
49
  if version == 10:
51
50
  dataname = "cifar10"
52
51
  elif version == 100:
@@ -79,15 +78,9 @@ def MNIST(train=True, test=False):
79
78
 
80
79
  def IMAGENET(train=True, test=False):
81
80
  if train and not test:
82
- dataset = load_dataset(
83
- "imagenet-1k",
84
- use_auth_token=True,
85
- split="train")
81
+ dataset = load_dataset("imagenet-1k", use_auth_token=True, split="train")
86
82
  elif test and not train:
87
- dataset = load_dataset(
88
- "imagenet-1k",
89
- use_auth_token=True,
90
- split="test")
83
+ dataset = load_dataset("imagenet-1k", use_auth_token=True, split="test")
91
84
  elif train and test:
92
85
  dataset = load_dataset("imagenet-1k", use_auth_token=True)
93
86
  else: