isotree 0.2.2 → 0.3.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/CHANGELOG.md +8 -1
- data/LICENSE.txt +2 -2
- data/README.md +32 -14
- data/ext/isotree/ext.cpp +144 -31
- data/ext/isotree/extconf.rb +7 -7
- data/lib/isotree/isolation_forest.rb +110 -30
- data/lib/isotree/version.rb +1 -1
- data/vendor/isotree/LICENSE +1 -1
- data/vendor/isotree/README.md +165 -27
- data/vendor/isotree/include/isotree.hpp +2111 -0
- data/vendor/isotree/include/isotree_oop.hpp +394 -0
- data/vendor/isotree/inst/COPYRIGHTS +62 -0
- data/vendor/isotree/src/RcppExports.cpp +525 -52
- data/vendor/isotree/src/Rwrapper.cpp +1931 -268
- data/vendor/isotree/src/c_interface.cpp +953 -0
- data/vendor/isotree/src/crit.hpp +4232 -0
- data/vendor/isotree/src/dist.hpp +1886 -0
- data/vendor/isotree/src/exp_depth_table.hpp +134 -0
- data/vendor/isotree/src/extended.hpp +1444 -0
- data/vendor/isotree/src/external_facing_generic.hpp +399 -0
- data/vendor/isotree/src/fit_model.hpp +2401 -0
- data/vendor/isotree/src/{dealloc.cpp → headers_joined.hpp} +38 -22
- data/vendor/isotree/src/helpers_iforest.hpp +813 -0
- data/vendor/isotree/src/{impute.cpp → impute.hpp} +353 -122
- data/vendor/isotree/src/indexer.cpp +515 -0
- data/vendor/isotree/src/instantiate_template_headers.cpp +118 -0
- data/vendor/isotree/src/instantiate_template_headers.hpp +240 -0
- data/vendor/isotree/src/isoforest.hpp +1659 -0
- data/vendor/isotree/src/isotree.hpp +1804 -392
- data/vendor/isotree/src/isotree_exportable.hpp +99 -0
- data/vendor/isotree/src/merge_models.cpp +159 -16
- data/vendor/isotree/src/mult.hpp +1321 -0
- data/vendor/isotree/src/oop_interface.cpp +842 -0
- data/vendor/isotree/src/oop_interface.hpp +278 -0
- data/vendor/isotree/src/other_helpers.hpp +219 -0
- data/vendor/isotree/src/predict.hpp +1932 -0
- data/vendor/isotree/src/python_helpers.hpp +134 -0
- data/vendor/isotree/src/ref_indexer.hpp +154 -0
- data/vendor/isotree/src/robinmap/LICENSE +21 -0
- data/vendor/isotree/src/robinmap/README.md +483 -0
- data/vendor/isotree/src/robinmap/include/tsl/robin_growth_policy.h +406 -0
- data/vendor/isotree/src/robinmap/include/tsl/robin_hash.h +1620 -0
- data/vendor/isotree/src/robinmap/include/tsl/robin_map.h +807 -0
- data/vendor/isotree/src/robinmap/include/tsl/robin_set.h +660 -0
- data/vendor/isotree/src/serialize.cpp +4300 -139
- data/vendor/isotree/src/sql.cpp +141 -59
- data/vendor/isotree/src/subset_models.cpp +174 -0
- data/vendor/isotree/src/utils.hpp +3808 -0
- data/vendor/isotree/src/xoshiro.hpp +467 -0
- data/vendor/isotree/src/ziggurat.hpp +405 -0
- metadata +38 -104
- data/vendor/cereal/LICENSE +0 -24
- data/vendor/cereal/README.md +0 -85
- data/vendor/cereal/include/cereal/access.hpp +0 -351
- data/vendor/cereal/include/cereal/archives/adapters.hpp +0 -163
- data/vendor/cereal/include/cereal/archives/binary.hpp +0 -169
- data/vendor/cereal/include/cereal/archives/json.hpp +0 -1019
- data/vendor/cereal/include/cereal/archives/portable_binary.hpp +0 -334
- data/vendor/cereal/include/cereal/archives/xml.hpp +0 -956
- data/vendor/cereal/include/cereal/cereal.hpp +0 -1089
- data/vendor/cereal/include/cereal/details/helpers.hpp +0 -422
- data/vendor/cereal/include/cereal/details/polymorphic_impl.hpp +0 -796
- data/vendor/cereal/include/cereal/details/polymorphic_impl_fwd.hpp +0 -65
- data/vendor/cereal/include/cereal/details/static_object.hpp +0 -127
- data/vendor/cereal/include/cereal/details/traits.hpp +0 -1411
- data/vendor/cereal/include/cereal/details/util.hpp +0 -84
- data/vendor/cereal/include/cereal/external/base64.hpp +0 -134
- data/vendor/cereal/include/cereal/external/rapidjson/allocators.h +0 -284
- data/vendor/cereal/include/cereal/external/rapidjson/cursorstreamwrapper.h +0 -78
- data/vendor/cereal/include/cereal/external/rapidjson/document.h +0 -2652
- data/vendor/cereal/include/cereal/external/rapidjson/encodedstream.h +0 -299
- data/vendor/cereal/include/cereal/external/rapidjson/encodings.h +0 -716
- data/vendor/cereal/include/cereal/external/rapidjson/error/en.h +0 -74
- data/vendor/cereal/include/cereal/external/rapidjson/error/error.h +0 -161
- data/vendor/cereal/include/cereal/external/rapidjson/filereadstream.h +0 -99
- data/vendor/cereal/include/cereal/external/rapidjson/filewritestream.h +0 -104
- data/vendor/cereal/include/cereal/external/rapidjson/fwd.h +0 -151
- data/vendor/cereal/include/cereal/external/rapidjson/internal/biginteger.h +0 -290
- data/vendor/cereal/include/cereal/external/rapidjson/internal/diyfp.h +0 -271
- data/vendor/cereal/include/cereal/external/rapidjson/internal/dtoa.h +0 -245
- data/vendor/cereal/include/cereal/external/rapidjson/internal/ieee754.h +0 -78
- data/vendor/cereal/include/cereal/external/rapidjson/internal/itoa.h +0 -308
- data/vendor/cereal/include/cereal/external/rapidjson/internal/meta.h +0 -186
- data/vendor/cereal/include/cereal/external/rapidjson/internal/pow10.h +0 -55
- data/vendor/cereal/include/cereal/external/rapidjson/internal/regex.h +0 -740
- data/vendor/cereal/include/cereal/external/rapidjson/internal/stack.h +0 -232
- data/vendor/cereal/include/cereal/external/rapidjson/internal/strfunc.h +0 -69
- data/vendor/cereal/include/cereal/external/rapidjson/internal/strtod.h +0 -290
- data/vendor/cereal/include/cereal/external/rapidjson/internal/swap.h +0 -46
- data/vendor/cereal/include/cereal/external/rapidjson/istreamwrapper.h +0 -128
- data/vendor/cereal/include/cereal/external/rapidjson/memorybuffer.h +0 -70
- data/vendor/cereal/include/cereal/external/rapidjson/memorystream.h +0 -71
- data/vendor/cereal/include/cereal/external/rapidjson/msinttypes/inttypes.h +0 -316
- data/vendor/cereal/include/cereal/external/rapidjson/msinttypes/stdint.h +0 -300
- data/vendor/cereal/include/cereal/external/rapidjson/ostreamwrapper.h +0 -81
- data/vendor/cereal/include/cereal/external/rapidjson/pointer.h +0 -1414
- data/vendor/cereal/include/cereal/external/rapidjson/prettywriter.h +0 -277
- data/vendor/cereal/include/cereal/external/rapidjson/rapidjson.h +0 -656
- data/vendor/cereal/include/cereal/external/rapidjson/reader.h +0 -2230
- data/vendor/cereal/include/cereal/external/rapidjson/schema.h +0 -2497
- data/vendor/cereal/include/cereal/external/rapidjson/stream.h +0 -223
- data/vendor/cereal/include/cereal/external/rapidjson/stringbuffer.h +0 -121
- data/vendor/cereal/include/cereal/external/rapidjson/writer.h +0 -709
- data/vendor/cereal/include/cereal/external/rapidxml/license.txt +0 -52
- data/vendor/cereal/include/cereal/external/rapidxml/manual.html +0 -406
- data/vendor/cereal/include/cereal/external/rapidxml/rapidxml.hpp +0 -2624
- data/vendor/cereal/include/cereal/external/rapidxml/rapidxml_iterators.hpp +0 -175
- data/vendor/cereal/include/cereal/external/rapidxml/rapidxml_print.hpp +0 -428
- data/vendor/cereal/include/cereal/external/rapidxml/rapidxml_utils.hpp +0 -123
- data/vendor/cereal/include/cereal/macros.hpp +0 -154
- data/vendor/cereal/include/cereal/specialize.hpp +0 -139
- data/vendor/cereal/include/cereal/types/array.hpp +0 -79
- data/vendor/cereal/include/cereal/types/atomic.hpp +0 -55
- data/vendor/cereal/include/cereal/types/base_class.hpp +0 -203
- data/vendor/cereal/include/cereal/types/bitset.hpp +0 -176
- data/vendor/cereal/include/cereal/types/boost_variant.hpp +0 -164
- data/vendor/cereal/include/cereal/types/chrono.hpp +0 -72
- data/vendor/cereal/include/cereal/types/common.hpp +0 -129
- data/vendor/cereal/include/cereal/types/complex.hpp +0 -56
- data/vendor/cereal/include/cereal/types/concepts/pair_associative_container.hpp +0 -73
- data/vendor/cereal/include/cereal/types/deque.hpp +0 -62
- data/vendor/cereal/include/cereal/types/forward_list.hpp +0 -68
- data/vendor/cereal/include/cereal/types/functional.hpp +0 -43
- data/vendor/cereal/include/cereal/types/list.hpp +0 -62
- data/vendor/cereal/include/cereal/types/map.hpp +0 -36
- data/vendor/cereal/include/cereal/types/memory.hpp +0 -425
- data/vendor/cereal/include/cereal/types/optional.hpp +0 -66
- data/vendor/cereal/include/cereal/types/polymorphic.hpp +0 -483
- data/vendor/cereal/include/cereal/types/queue.hpp +0 -132
- data/vendor/cereal/include/cereal/types/set.hpp +0 -103
- data/vendor/cereal/include/cereal/types/stack.hpp +0 -76
- data/vendor/cereal/include/cereal/types/string.hpp +0 -61
- data/vendor/cereal/include/cereal/types/tuple.hpp +0 -123
- data/vendor/cereal/include/cereal/types/unordered_map.hpp +0 -36
- data/vendor/cereal/include/cereal/types/unordered_set.hpp +0 -99
- data/vendor/cereal/include/cereal/types/utility.hpp +0 -47
- data/vendor/cereal/include/cereal/types/valarray.hpp +0 -89
- data/vendor/cereal/include/cereal/types/variant.hpp +0 -109
- data/vendor/cereal/include/cereal/types/vector.hpp +0 -112
- data/vendor/cereal/include/cereal/version.hpp +0 -52
- data/vendor/isotree/src/Makevars +0 -4
- data/vendor/isotree/src/crit.cpp +0 -912
- data/vendor/isotree/src/dist.cpp +0 -749
- data/vendor/isotree/src/extended.cpp +0 -790
- data/vendor/isotree/src/fit_model.cpp +0 -1090
- data/vendor/isotree/src/helpers_iforest.cpp +0 -324
- data/vendor/isotree/src/isoforest.cpp +0 -771
- data/vendor/isotree/src/mult.cpp +0 -607
- data/vendor/isotree/src/predict.cpp +0 -853
- data/vendor/isotree/src/utils.cpp +0 -1566
@@ -0,0 +1,278 @@
|
|
1
|
+
/* Isolation forests and variations thereof, with adjustments for incorporation
|
2
|
+
* of categorical variables and missing values.
|
3
|
+
* Writen for C++11 standard and aimed at being used in R and Python.
|
4
|
+
*
|
5
|
+
* This library is based on the following works:
|
6
|
+
* [1] Liu, Fei Tony, Kai Ming Ting, and Zhi-Hua Zhou.
|
7
|
+
* "Isolation forest."
|
8
|
+
* 2008 Eighth IEEE International Conference on Data Mining. IEEE, 2008.
|
9
|
+
* [2] Liu, Fei Tony, Kai Ming Ting, and Zhi-Hua Zhou.
|
10
|
+
* "Isolation-based anomaly detection."
|
11
|
+
* ACM Transactions on Knowledge Discovery from Data (TKDD) 6.1 (2012): 3.
|
12
|
+
* [3] Hariri, Sahand, Matias Carrasco Kind, and Robert J. Brunner.
|
13
|
+
* "Extended Isolation Forest."
|
14
|
+
* arXiv preprint arXiv:1811.02141 (2018).
|
15
|
+
* [4] Liu, Fei Tony, Kai Ming Ting, and Zhi-Hua Zhou.
|
16
|
+
* "On detecting clustered anomalies using SCiForest."
|
17
|
+
* Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer, Berlin, Heidelberg, 2010.
|
18
|
+
* [5] https://sourceforge.net/projects/iforest/
|
19
|
+
* [6] https://math.stackexchange.com/questions/3388518/expected-number-of-paths-required-to-separate-elements-in-a-binary-tree
|
20
|
+
* [7] Quinlan, J. Ross. C4. 5: programs for machine learning. Elsevier, 2014.
|
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.
|
41
|
+
*
|
42
|
+
* BSD 2-Clause License
|
43
|
+
* Copyright (c) 2019-2022, David Cortes
|
44
|
+
* All rights reserved.
|
45
|
+
* Redistribution and use in source and binary forms, with or without
|
46
|
+
* modification, are permitted provided that the following conditions are met:
|
47
|
+
* * Redistributions of source code must retain the above copyright notice, this
|
48
|
+
* list of conditions and the following disclaimer.
|
49
|
+
* * Redistributions in binary form must reproduce the above copyright notice,
|
50
|
+
* this list of conditions and the following disclaimer in the documentation
|
51
|
+
* and/or other materials provided with the distribution.
|
52
|
+
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
|
53
|
+
* AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
54
|
+
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
|
55
|
+
* DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
|
56
|
+
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
|
57
|
+
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
|
58
|
+
* SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
|
59
|
+
* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
|
60
|
+
* OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
61
|
+
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
62
|
+
*/
|
63
|
+
|
64
|
+
|
65
|
+
/***********************************************************************************
|
66
|
+
---------------------
|
67
|
+
IsoTree OOP interface
|
68
|
+
---------------------
|
69
|
+
|
70
|
+
This is provided as an alternative easier-to-use interface for this library
|
71
|
+
which follows scikit-learn-style methods with a single C++ class. It is a
|
72
|
+
wrapper over the non-OOP header 'isotree.hpp', providing the same functionality
|
73
|
+
in a perhaps more comprehensible structure, while still offering direct access
|
74
|
+
to the underlying objects so as to allow using the functions from 'isotree.hpp'.
|
75
|
+
|
76
|
+
It is a more limited interface as it does not implement all the functionality
|
77
|
+
for serialization, distance prediction, oproducing predictions in the same call
|
78
|
+
as the model is fit, or fitting/predicting on data with types other than
|
79
|
+
'double' and 'int'.
|
80
|
+
|
81
|
+
The descriptions here do not contain the full documentation, but rather only
|
82
|
+
some hints so as to make them more comprehensible, aiming at producing function
|
83
|
+
signatures that are self-descriptive instead (if you are familiar with the
|
84
|
+
scikit-learn library for Python).
|
85
|
+
|
86
|
+
For detailed documentation see the same or similar-looking methods in the
|
87
|
+
'isotree.hpp' header instead.
|
88
|
+
|
89
|
+
***********************************************************************************/
|
90
|
+
|
91
|
+
#if !defined(_FOR_R) && !defined(_FOR_PYTHON)
|
92
|
+
|
93
|
+
#include "isotree.hpp"
|
94
|
+
|
95
|
+
namespace isotree {
|
96
|
+
|
97
|
+
class ISOTREE_EXPORTED IsolationForest
|
98
|
+
{
|
99
|
+
public:
|
100
|
+
int nthreads = -1;
|
101
|
+
|
102
|
+
uint64_t random_seed = 1;
|
103
|
+
|
104
|
+
size_t ndim = 3;
|
105
|
+
size_t ntry = 1;
|
106
|
+
CoefType coef_type = Uniform;
|
107
|
+
bool with_replacement = false;
|
108
|
+
bool weight_as_sample = true;
|
109
|
+
size_t sample_size = 0;
|
110
|
+
size_t ntrees = 500;
|
111
|
+
size_t max_depth = 0;
|
112
|
+
size_t ncols_per_tree = 0;
|
113
|
+
bool limit_depth = true;
|
114
|
+
bool penalize_range = false;
|
115
|
+
bool standardize_data = true;
|
116
|
+
ScoringMetric scoring_metric = Depth;
|
117
|
+
bool fast_bratio = true;
|
118
|
+
bool weigh_by_kurt = false;
|
119
|
+
double prob_pick_by_gain_pl = 0.;
|
120
|
+
double prob_pick_by_gain_avg = 0.;
|
121
|
+
double prob_pick_by_full_gain = 0.;
|
122
|
+
double prob_pick_by_dens = 0.;
|
123
|
+
double prob_pick_col_by_range = 0.;
|
124
|
+
double prob_pick_col_by_var = 0.;
|
125
|
+
double prob_pick_col_by_kurt = 0.;
|
126
|
+
double min_gain = 0.;
|
127
|
+
MissingAction missing_action = Impute;
|
128
|
+
|
129
|
+
CategSplit cat_split_type = SubSet;
|
130
|
+
NewCategAction new_cat_action = Weighted;
|
131
|
+
bool coef_by_prop = false;
|
132
|
+
bool all_perm = false;
|
133
|
+
|
134
|
+
bool build_imputer = false;
|
135
|
+
size_t min_imp_obs = 3;
|
136
|
+
UseDepthImp depth_imp = Higher;
|
137
|
+
WeighImpRows weigh_imp_rows = Inverse;
|
138
|
+
|
139
|
+
IsoForest model;
|
140
|
+
ExtIsoForest model_ext;
|
141
|
+
Imputer imputer;
|
142
|
+
TreesIndexer indexer;
|
143
|
+
|
144
|
+
IsolationForest() = default;
|
145
|
+
|
146
|
+
~IsolationForest() = default;
|
147
|
+
|
148
|
+
IsolationForest
|
149
|
+
(
|
150
|
+
size_t ndim, size_t ntry, CoefType coef_type, bool coef_by_prop,
|
151
|
+
bool with_replacement, bool weight_as_sample,
|
152
|
+
size_t sample_size, size_t ntrees,
|
153
|
+
size_t max_depth, size_t ncols_per_tree, bool limit_depth,
|
154
|
+
bool penalize_range, bool standardize_datam,
|
155
|
+
ScoringMetric scoring_metric, bool fast_bratio, bool weigh_by_kurt,
|
156
|
+
double prob_pick_by_gain_pl, double prob_pick_by_gain_avg,
|
157
|
+
double prob_pick_by_full_gain, double prob_pick_by_dens,
|
158
|
+
double prob_pick_col_by_range, double prob_pick_col_by_var,
|
159
|
+
double prob_pick_col_by_kurt,
|
160
|
+
double min_gain, MissingAction missing_action,
|
161
|
+
CategSplit cat_split_type, NewCategAction new_cat_action,
|
162
|
+
bool all_perm, bool build_imputer, size_t min_imp_obs,
|
163
|
+
UseDepthImp depth_imp, WeighImpRows weigh_imp_rows,
|
164
|
+
uint64_t random_seed, int nthreads
|
165
|
+
);
|
166
|
+
|
167
|
+
void fit(double X[], size_t nrows, size_t ncols);
|
168
|
+
|
169
|
+
void fit(double numeric_data[], size_t ncols_numeric, size_t nrows,
|
170
|
+
int categ_data[], size_t ncols_categ, int ncat[],
|
171
|
+
double sample_weights[], double col_weights[]);
|
172
|
+
|
173
|
+
void fit(double Xc[], int Xc_ind[], int Xc_indptr[],
|
174
|
+
size_t ncols_numeric, size_t nrows,
|
175
|
+
int categ_data[], size_t ncols_categ, int ncat[],
|
176
|
+
double sample_weights[], double col_weights[]);
|
177
|
+
|
178
|
+
std::vector<double> predict(double X[], size_t nrows, bool standardize);
|
179
|
+
|
180
|
+
void predict(double numeric_data[], int categ_data[], bool is_col_major,
|
181
|
+
size_t nrows, size_t ld_numeric, size_t ld_categ, bool standardize,
|
182
|
+
double output_depths[], int tree_num[], double per_tree_depths[]);
|
183
|
+
|
184
|
+
void predict(double X_sparse[], int X_ind[], int X_indptr[], bool is_csc,
|
185
|
+
int categ_data[], bool is_col_major, size_t ld_categ, size_t nrows, bool standardize,
|
186
|
+
double output_depths[], int tree_num[], double per_tree_depths[]);
|
187
|
+
|
188
|
+
std::vector<double> predict_distance(double X[], size_t nrows,
|
189
|
+
bool as_kernel,
|
190
|
+
bool assume_full_distr, bool standardize,
|
191
|
+
bool triangular);
|
192
|
+
|
193
|
+
void predict_distance(double numeric_data[], int categ_data[],
|
194
|
+
size_t nrows,
|
195
|
+
bool as_kernel,
|
196
|
+
bool assume_full_distr, bool standardize,
|
197
|
+
bool triangular,
|
198
|
+
double dist_matrix[]);
|
199
|
+
|
200
|
+
void predict_distance(double Xc[], int Xc_ind[], int Xc_indptr[], int categ_data[],
|
201
|
+
size_t nrows,
|
202
|
+
bool as_kernel,
|
203
|
+
bool assume_full_distr, bool standardize,
|
204
|
+
bool triangular,
|
205
|
+
double dist_matrix[]);
|
206
|
+
|
207
|
+
void impute(double X[], size_t nrows);
|
208
|
+
|
209
|
+
void impute(double numeric_data[], int categ_data[], bool is_col_major, size_t nrows);
|
210
|
+
|
211
|
+
void impute(double Xr[], int Xr_ind[], int Xr_indptr[],
|
212
|
+
int categ_data[], bool is_col_major, size_t nrows);
|
213
|
+
|
214
|
+
void build_indexer(const bool with_distances);
|
215
|
+
|
216
|
+
void set_as_reference_points(double numeric_data[], int categ_data[], bool is_col_major,
|
217
|
+
size_t nrows, size_t ld_numeric, size_t ld_categ,
|
218
|
+
const bool with_distances);
|
219
|
+
|
220
|
+
void set_as_reference_points(double Xc[], int Xc_ind[], int Xc_indptr[], int categ_data[],
|
221
|
+
size_t nrows, const bool with_distances);
|
222
|
+
|
223
|
+
size_t get_num_reference_points() const noexcept;
|
224
|
+
|
225
|
+
void predict_distance_to_ref_points(double numeric_data[], int categ_data[],
|
226
|
+
double Xc[], int Xc_ind[], int Xc_indptr[],
|
227
|
+
size_t nrows, bool is_col_major, size_t ld_numeric, size_t ld_categ,
|
228
|
+
bool as_kernel, bool standardize,
|
229
|
+
double dist_matrix[]);
|
230
|
+
|
231
|
+
void serialize(FILE *out) const;
|
232
|
+
|
233
|
+
void serialize(std::ostream &out) const;
|
234
|
+
|
235
|
+
static IsolationForest deserialize(FILE *inp, int nthreads);
|
236
|
+
|
237
|
+
static IsolationForest deserialize(std::istream &inp, int nthreads);
|
238
|
+
|
239
|
+
friend std::ostream& operator<<(std::ostream &ost, const IsolationForest &model);
|
240
|
+
|
241
|
+
friend std::istream& operator>>(std::istream &ist, IsolationForest &model);
|
242
|
+
|
243
|
+
IsoForest& get_model();
|
244
|
+
|
245
|
+
ExtIsoForest& get_model_ext();
|
246
|
+
|
247
|
+
Imputer& get_imputer();
|
248
|
+
|
249
|
+
TreesIndexer& get_indexer();
|
250
|
+
|
251
|
+
void check_nthreads();
|
252
|
+
|
253
|
+
size_t get_ntrees() const;
|
254
|
+
|
255
|
+
bool check_can_predict_per_tree() const;
|
256
|
+
|
257
|
+
private:
|
258
|
+
bool is_fitted = false;
|
259
|
+
|
260
|
+
void override_previous_fit();
|
261
|
+
void check_params();
|
262
|
+
void check_is_fitted() const;
|
263
|
+
IsolationForest(int nthreads, size_t ndim, size_t ntrees, bool build_imputer);
|
264
|
+
template <class otype>
|
265
|
+
void serialize_template(otype &out) const;
|
266
|
+
template <class itype>
|
267
|
+
static IsolationForest deserialize_template(itype &inp, int nthreads);
|
268
|
+
|
269
|
+
};
|
270
|
+
|
271
|
+
ISOTREE_EXPORTED
|
272
|
+
std::ostream& operator<<(std::ostream &ost, const IsolationForest &model);
|
273
|
+
ISOTREE_EXPORTED
|
274
|
+
std::istream& operator>>(std::istream &ist, IsolationForest &model);
|
275
|
+
|
276
|
+
}
|
277
|
+
#endif
|
278
|
+
|
@@ -0,0 +1,219 @@
|
|
1
|
+
/* Isolation forests and variations thereof, with adjustments for incorporation
|
2
|
+
* of categorical variables and missing values.
|
3
|
+
* Writen for C++11 standard and aimed at being used in R and Python.
|
4
|
+
*
|
5
|
+
* This library is based on the following works:
|
6
|
+
* [1] Liu, Fei Tony, Kai Ming Ting, and Zhi-Hua Zhou.
|
7
|
+
* "Isolation forest."
|
8
|
+
* 2008 Eighth IEEE International Conference on Data Mining. IEEE, 2008.
|
9
|
+
* [2] Liu, Fei Tony, Kai Ming Ting, and Zhi-Hua Zhou.
|
10
|
+
* "Isolation-based anomaly detection."
|
11
|
+
* ACM Transactions on Knowledge Discovery from Data (TKDD) 6.1 (2012): 3.
|
12
|
+
* [3] Hariri, Sahand, Matias Carrasco Kind, and Robert J. Brunner.
|
13
|
+
* "Extended Isolation Forest."
|
14
|
+
* arXiv preprint arXiv:1811.02141 (2018).
|
15
|
+
* [4] Liu, Fei Tony, Kai Ming Ting, and Zhi-Hua Zhou.
|
16
|
+
* "On detecting clustered anomalies using SCiForest."
|
17
|
+
* Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer, Berlin, Heidelberg, 2010.
|
18
|
+
* [5] https://sourceforge.net/projects/iforest/
|
19
|
+
* [6] https://math.stackexchange.com/questions/3388518/expected-number-of-paths-required-to-separate-elements-in-a-binary-tree
|
20
|
+
* [7] Quinlan, J. Ross. C4. 5: programs for machine learning. Elsevier, 2014.
|
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.
|
41
|
+
*
|
42
|
+
* BSD 2-Clause License
|
43
|
+
* Copyright (c) 2019-2022, David Cortes
|
44
|
+
* All rights reserved.
|
45
|
+
* Redistribution and use in source and binary forms, with or without
|
46
|
+
* modification, are permitted provided that the following conditions are met:
|
47
|
+
* * Redistributions of source code must retain the above copyright notice, this
|
48
|
+
* list of conditions and the following disclaimer.
|
49
|
+
* * Redistributions in binary form must reproduce the above copyright notice,
|
50
|
+
* this list of conditions and the following disclaimer in the documentation
|
51
|
+
* and/or other materials provided with the distribution.
|
52
|
+
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
|
53
|
+
* AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
54
|
+
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
|
55
|
+
* DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
|
56
|
+
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
|
57
|
+
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
|
58
|
+
* SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
|
59
|
+
* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
|
60
|
+
* OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
61
|
+
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
62
|
+
*/
|
63
|
+
#include "isotree.hpp"
|
64
|
+
|
65
|
+
template <class sparse_ix__>
|
66
|
+
bool check_indices_are_sorted(sparse_ix__ indices[], size_t n)
|
67
|
+
{
|
68
|
+
if (n <= 1)
|
69
|
+
return true;
|
70
|
+
if (indices[n-1] < indices[0])
|
71
|
+
return false;
|
72
|
+
for (size_t ix = 1; ix < n; ix++)
|
73
|
+
if (indices[ix] < indices[ix-1])
|
74
|
+
return false;
|
75
|
+
return true;
|
76
|
+
}
|
77
|
+
|
78
|
+
template <class real_t__, class sparse_ix__>
|
79
|
+
void sort_csc_indices(real_t__ *restrict Xc, sparse_ix__ *restrict Xc_ind, sparse_ix__ *restrict Xc_indptr, size_t ncols_numeric)
|
80
|
+
{
|
81
|
+
std::vector<double> buffer_sorted_vals;
|
82
|
+
std::vector<sparse_ix__> buffer_sorted_ix;
|
83
|
+
std::vector<size_t> argsorted;
|
84
|
+
size_t n_this;
|
85
|
+
size_t ix1, ix2;
|
86
|
+
for (size_t col = 0; col < ncols_numeric; col++)
|
87
|
+
{
|
88
|
+
ix1 = Xc_indptr[col];
|
89
|
+
ix2 = Xc_indptr[col+1];
|
90
|
+
n_this = ix2 - ix1;
|
91
|
+
if (n_this && !check_indices_are_sorted(Xc_ind + ix1, n_this))
|
92
|
+
{
|
93
|
+
if (buffer_sorted_vals.size() < n_this)
|
94
|
+
{
|
95
|
+
buffer_sorted_vals.resize(n_this);
|
96
|
+
buffer_sorted_ix.resize(n_this);
|
97
|
+
argsorted.resize(n_this);
|
98
|
+
}
|
99
|
+
std::iota(argsorted.begin(), argsorted.begin() + n_this, ix1);
|
100
|
+
std::sort(argsorted.begin(), argsorted.begin() + n_this,
|
101
|
+
[&Xc_ind](const size_t a, const size_t b){return Xc_ind[a] < Xc_ind[b];});
|
102
|
+
for (size_t ix = 0; ix < n_this; ix++)
|
103
|
+
buffer_sorted_ix[ix] = Xc_ind[argsorted[ix]];
|
104
|
+
std::copy(buffer_sorted_ix.begin(), buffer_sorted_ix.begin() + n_this, Xc_ind + ix1);
|
105
|
+
for (size_t ix = 0; ix < n_this; ix++)
|
106
|
+
buffer_sorted_vals[ix] = Xc[argsorted[ix]];
|
107
|
+
std::copy(buffer_sorted_vals.begin(), buffer_sorted_vals.begin() + n_this, Xc + ix1);
|
108
|
+
}
|
109
|
+
}
|
110
|
+
}
|
111
|
+
|
112
|
+
|
113
|
+
template <class real_t__, class sparse_ix__>
|
114
|
+
void reconstruct_csr_sliced
|
115
|
+
(
|
116
|
+
real_t__ *restrict orig_Xr, sparse_ix__ *restrict orig_Xr_indptr,
|
117
|
+
real_t__ *restrict rec_Xr, sparse_ix__ *restrict rec_Xr_indptr,
|
118
|
+
size_t nrows
|
119
|
+
)
|
120
|
+
{
|
121
|
+
for (size_t row = 0; row < nrows; row++)
|
122
|
+
std::copy(rec_Xr + rec_Xr_indptr[row],
|
123
|
+
rec_Xr + rec_Xr_indptr[row+(size_t)1],
|
124
|
+
orig_Xr + orig_Xr_indptr[row]);
|
125
|
+
}
|
126
|
+
|
127
|
+
#define is_in_set(vv, ss) ((ss).find((vv)) != (ss).end())
|
128
|
+
|
129
|
+
template <class real_t__, class sparse_ix__, class size_t_>
|
130
|
+
void reconstruct_csr_with_categ
|
131
|
+
(
|
132
|
+
real_t__ *restrict orig_Xr, sparse_ix__ *restrict orig_Xr_ind, sparse_ix__ *restrict orig_Xr_indptr,
|
133
|
+
real_t__ *restrict rec_Xr, sparse_ix__ *restrict rec_Xr_ind, sparse_ix__ *restrict rec_Xr_indptr,
|
134
|
+
int *restrict rec_X_cat, bool is_col_major,
|
135
|
+
size_t_ *restrict cols_numeric, size_t_ *restrict cols_categ,
|
136
|
+
size_t nrows, size_t ncols, size_t ncols_numeric, size_t ncols_categ
|
137
|
+
)
|
138
|
+
{
|
139
|
+
/* Check if the numeric columns go first and in the original order */
|
140
|
+
bool num_is_seq = false;
|
141
|
+
if (ncols_numeric > 0 && check_indices_are_sorted(cols_numeric, ncols_numeric)) {
|
142
|
+
if (cols_numeric[0] == 0 && cols_numeric[ncols_numeric-1] == (size_t_)ncols_numeric-1)
|
143
|
+
num_is_seq = true;
|
144
|
+
}
|
145
|
+
|
146
|
+
hashed_set<size_t> cols_numeric_set;
|
147
|
+
hashed_set<size_t> cols_categ_set(cols_categ, cols_categ + ncols_categ);
|
148
|
+
hashed_map<size_t, sparse_ix__> orig_to_rec_num;
|
149
|
+
hashed_map<size_t, size_t> orig_to_rec_cat;
|
150
|
+
|
151
|
+
sparse_ix__ col_orig;
|
152
|
+
sparse_ix__ *restrict col_ptr;
|
153
|
+
|
154
|
+
if (num_is_seq)
|
155
|
+
{
|
156
|
+
reconstruct_csr_sliced(
|
157
|
+
orig_Xr, orig_Xr_indptr,
|
158
|
+
rec_Xr, rec_Xr_indptr,
|
159
|
+
nrows
|
160
|
+
);
|
161
|
+
}
|
162
|
+
|
163
|
+
else
|
164
|
+
{
|
165
|
+
if (ncols_numeric)
|
166
|
+
cols_numeric_set = hashed_set<size_t>(cols_numeric, cols_numeric + ncols_numeric);
|
167
|
+
for (size_t col = 0; col < ncols_numeric; col++)
|
168
|
+
orig_to_rec_num[cols_numeric[col]] = col;
|
169
|
+
}
|
170
|
+
|
171
|
+
for (size_t col = 0; col < ncols_categ; col++)
|
172
|
+
orig_to_rec_cat[cols_categ[col]] = col;
|
173
|
+
|
174
|
+
|
175
|
+
for (size_t row = 0; row < nrows; row++)
|
176
|
+
{
|
177
|
+
for (auto col = orig_Xr_indptr[row]; col < orig_Xr_indptr[row+1]; col++)
|
178
|
+
{
|
179
|
+
if (std::isnan(orig_Xr[col]))
|
180
|
+
{
|
181
|
+
col_orig = orig_Xr_ind[col];
|
182
|
+
if (is_in_set(col_orig, cols_numeric_set)) {
|
183
|
+
col_ptr = std::lower_bound(rec_Xr_ind + rec_Xr_indptr[row],
|
184
|
+
rec_Xr_ind + rec_Xr_indptr[row+1],
|
185
|
+
col_orig);
|
186
|
+
orig_Xr[col] = rec_Xr[std::distance(rec_Xr_ind, col_ptr)];
|
187
|
+
}
|
188
|
+
|
189
|
+
else if (is_in_set((size_t)col_orig, cols_categ_set)) {
|
190
|
+
orig_Xr[col] = rec_X_cat[is_col_major?
|
191
|
+
(row + nrows*orig_to_rec_cat[col_orig])
|
192
|
+
:
|
193
|
+
(orig_to_rec_cat[col_orig] + row*ncols_categ)];
|
194
|
+
#ifndef _FOR_R
|
195
|
+
orig_Xr[col] = (orig_Xr[col] < 0)? NAN : orig_Xr[col];
|
196
|
+
#else
|
197
|
+
orig_Xr[col] = (orig_Xr[col] < 0)? NA_REAL : orig_Xr[col];
|
198
|
+
#endif
|
199
|
+
}
|
200
|
+
}
|
201
|
+
|
202
|
+
else if (orig_Xr[col] < 0)
|
203
|
+
{
|
204
|
+
col_orig = orig_Xr_ind[col];
|
205
|
+
if (is_in_set((size_t)col_orig, cols_categ_set)) {
|
206
|
+
orig_Xr[col] = rec_X_cat[is_col_major?
|
207
|
+
(row + nrows*orig_to_rec_cat[col_orig])
|
208
|
+
:
|
209
|
+
(orig_to_rec_cat[col_orig] + row*ncols_categ)];
|
210
|
+
#ifndef _FOR_R
|
211
|
+
orig_Xr[col] = (orig_Xr[col] < 0)? NAN : orig_Xr[col];
|
212
|
+
#else
|
213
|
+
orig_Xr[col] = (orig_Xr[col] < 0)? NA_REAL : orig_Xr[col];
|
214
|
+
#endif
|
215
|
+
}
|
216
|
+
}
|
217
|
+
}
|
218
|
+
}
|
219
|
+
}
|