isotree 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/CHANGELOG.md +3 -0
- data/LICENSE.txt +25 -0
- data/README.md +111 -0
- data/ext/isotree/ext.cpp +178 -0
- data/ext/isotree/extconf.rb +21 -0
- data/lib/isotree.rb +9 -0
- data/lib/isotree/isolation_forest.rb +94 -0
- data/lib/isotree/version.rb +3 -0
- data/vendor/isotree/LICENSE +25 -0
- data/vendor/isotree/README.md +167 -0
- data/vendor/isotree/src/Makevars +4 -0
- data/vendor/isotree/src/RcppExports.cpp +267 -0
- data/vendor/isotree/src/Rwrapper.cpp +762 -0
- data/vendor/isotree/src/crit.cpp +912 -0
- data/vendor/isotree/src/dealloc.cpp +66 -0
- data/vendor/isotree/src/dist.cpp +749 -0
- data/vendor/isotree/src/extended.cpp +790 -0
- data/vendor/isotree/src/fit_model.cpp +1068 -0
- data/vendor/isotree/src/helpers_iforest.cpp +309 -0
- data/vendor/isotree/src/impute.cpp +1205 -0
- data/vendor/isotree/src/isoforest.cpp +771 -0
- data/vendor/isotree/src/isotree.hpp +929 -0
- data/vendor/isotree/src/merge_models.cpp +116 -0
- data/vendor/isotree/src/mult.cpp +607 -0
- data/vendor/isotree/src/predict.cpp +849 -0
- data/vendor/isotree/src/serialize.cpp +262 -0
- data/vendor/isotree/src/utils.cpp +1574 -0
- metadata +154 -0
@@ -0,0 +1,66 @@
|
|
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. "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).
|
23
|
+
*
|
24
|
+
* BSD 2-Clause License
|
25
|
+
* Copyright (c) 2019, David Cortes
|
26
|
+
* All rights reserved.
|
27
|
+
* Redistribution and use in source and binary forms, with or without
|
28
|
+
* modification, are permitted provided that the following conditions are met:
|
29
|
+
* * Redistributions of source code must retain the above copyright notice, this
|
30
|
+
* list of conditions and the following disclaimer.
|
31
|
+
* * Redistributions in binary form must reproduce the above copyright notice,
|
32
|
+
* this list of conditions and the following disclaimer in the documentation
|
33
|
+
* and/or other materials provided with the distribution.
|
34
|
+
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
|
35
|
+
* AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
36
|
+
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
|
37
|
+
* DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
|
38
|
+
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
|
39
|
+
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
|
40
|
+
* SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
|
41
|
+
* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
|
42
|
+
* OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
43
|
+
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
44
|
+
*/
|
45
|
+
#include "isotree.hpp"
|
46
|
+
|
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. */
|
52
|
+
|
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
|
+
}
|
@@ -0,0 +1,749 @@
|
|
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. "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).
|
23
|
+
*
|
24
|
+
* BSD 2-Clause License
|
25
|
+
* Copyright (c) 2019, David Cortes
|
26
|
+
* All rights reserved.
|
27
|
+
* Redistribution and use in source and binary forms, with or without
|
28
|
+
* modification, are permitted provided that the following conditions are met:
|
29
|
+
* * Redistributions of source code must retain the above copyright notice, this
|
30
|
+
* list of conditions and the following disclaimer.
|
31
|
+
* * Redistributions in binary form must reproduce the above copyright notice,
|
32
|
+
* this list of conditions and the following disclaimer in the documentation
|
33
|
+
* and/or other materials provided with the distribution.
|
34
|
+
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
|
35
|
+
* AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
36
|
+
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
|
37
|
+
* DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
|
38
|
+
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
|
39
|
+
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
|
40
|
+
* SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
|
41
|
+
* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
|
42
|
+
* OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
43
|
+
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
44
|
+
*/
|
45
|
+
#include "isotree.hpp"
|
46
|
+
|
47
|
+
|
48
|
+
/* Calculate distance or similarity between data points
|
49
|
+
*
|
50
|
+
* Parameters
|
51
|
+
* ==========
|
52
|
+
* - numeric_data[nrows * ncols_numeric]
|
53
|
+
* Pointer to numeric data for which to make calculations. Must be ordered by columns like Fortran,
|
54
|
+
* not ordered by rows like C (i.e. entries 1..n contain column 0, n+1..2n column 1, etc.),
|
55
|
+
* and the column order must be the same as in the data that was used to fit the model.
|
56
|
+
* If making calculations between two sets of observations/rows (see documentation for 'rmat'),
|
57
|
+
* the first group is assumed to be the earlier rows here.
|
58
|
+
* Pass NULL if there are no dense numeric columns.
|
59
|
+
* Can only pass one of 'numeric_data' or 'Xc' + 'Xc_ind' + 'Xc_indptr'.
|
60
|
+
* - categ_data[nrows * ncols_categ]
|
61
|
+
* Pointer to categorical data for which to make calculations. Must be ordered by columns like Fortran,
|
62
|
+
* not ordered by rows like C (i.e. entries 1..n contain column 0, n+1..2n column 1, etc.),
|
63
|
+
* and the column order must be the same as in the data that was used to fit the model.
|
64
|
+
* Pass NULL if there are no categorical columns.
|
65
|
+
* Each category should be represented as an integer, and these integers must start at zero and
|
66
|
+
* be in consecutive order - i.e. if category '3' is present, category '2' must have also been
|
67
|
+
* present when the model was fit (note that they are not treated as being ordinal, this is just
|
68
|
+
* an encoding). Missing values should be encoded as negative numbers such as (-1). The encoding
|
69
|
+
* must be the same as was used in the data to which the model was fit.
|
70
|
+
* If making calculations between two sets of observations/rows (see documentation for 'rmat'),
|
71
|
+
* the first group is assumed to be the earlier rows here.
|
72
|
+
* - Xc[nnz]
|
73
|
+
* Pointer to numeric data in sparse numeric matrix in CSC format (column-compressed).
|
74
|
+
* Pass NULL if there are no sparse numeric columns.
|
75
|
+
* Can only pass one of 'numeric_data' or 'Xc' + 'Xc_ind' + 'Xc_indptr'.
|
76
|
+
* - Xc_ind[nnz]
|
77
|
+
* Pointer to row indices to which each non-zero entry in 'Xc' corresponds.
|
78
|
+
* Pass NULL if there are no sparse numeric columns in CSC format.
|
79
|
+
* - Xc_indptr[ncols_categ + 1]
|
80
|
+
* Pointer to column index pointers that tell at entry [col] where does column 'col'
|
81
|
+
* start and at entry [col + 1] where does column 'col' end.
|
82
|
+
* Pass NULL if there are no sparse numeric columns in CSC format.
|
83
|
+
* If making calculations between two sets of observations/rows (see documentation for 'rmat'),
|
84
|
+
* the first group is assumed to be the earlier rows here.
|
85
|
+
* - nrows
|
86
|
+
* Number of rows in 'numeric_data', 'Xc', 'Xr, 'categ_data'.
|
87
|
+
* - nthreads
|
88
|
+
* Number of parallel threads to use. Note that, the more threads, the more memory will be
|
89
|
+
* allocated, even if the thread does not end up being used. Ignored when not building with
|
90
|
+
* OpenMP support.
|
91
|
+
* - assume_full_distr
|
92
|
+
* Whether to assume that the fitted model represents a full population distribution (will use a
|
93
|
+
* standardizing criterion assuming infinite sample, and the results of the similarity between two points
|
94
|
+
* at prediction time will not depend on the prescence of any third point that is similar to them, but will
|
95
|
+
* differ more compared to the pairwise distances between points from which the model was fit). If passing
|
96
|
+
* 'false', will calculate pairwise distances as if the new observations at prediction time were added to
|
97
|
+
* the sample to which each tree was fit, which will make the distances between two points potentially vary
|
98
|
+
* according to other newly introduced points.
|
99
|
+
* - standardize_dist
|
100
|
+
* Whether to standardize the resulting average separation depths between rows according
|
101
|
+
* to the expected average separation depth in a similar way as when predicting outlierness,
|
102
|
+
* in order to obtain a standardized distance. If passing 'false', will output the average
|
103
|
+
* separation depth instead.
|
104
|
+
* - model_outputs
|
105
|
+
* Pointer to fitted single-variable model object from function 'fit_iforest'. Pass NULL
|
106
|
+
* if the calculations are to be made from an extended model. Can only pass one of
|
107
|
+
* 'model_outputs' and 'model_outputs_ext'.
|
108
|
+
* - model_outputs_ext
|
109
|
+
* Pointer to fitted extended model object from function 'fit_iforest'. Pass NULL
|
110
|
+
* if the calculations are to be made from a single-variable model. Can only pass one of
|
111
|
+
* 'model_outputs' and 'model_outputs_ext'.
|
112
|
+
* - tmat[nrows * (nrows - 1) / 2] (out)
|
113
|
+
* Pointer to array where the resulting pairwise distances or average separation depths will
|
114
|
+
* be written into. As the output is a symmetric matrix, this function will only fill in the
|
115
|
+
* upper-triangular part, in which entry 0 <= i < j < n will be located at position
|
116
|
+
* p(i,j) = (i * (n - (i+1)/2) + j - i - 1).
|
117
|
+
* Can be converted to a dense square matrix through function 'tmat_to_dense'.
|
118
|
+
* The array must already be initialized to zeros.
|
119
|
+
* If calculating distance/separation from a group of points to another group of points,
|
120
|
+
* pass NULL here and use 'rmat' instead.
|
121
|
+
* - rmat[nrows1 * nrows2] (out)
|
122
|
+
* Pointer to array where to write the distances or separation depths between each row in
|
123
|
+
* one set of observations and each row in a different set of observations. If doing these
|
124
|
+
* calculations for all pairs of observations/rows, pass 'rmat' instead.
|
125
|
+
* Will take the first group of observations as the rows in this matrix, and the second
|
126
|
+
* group as the columns. The groups are assumed to be in the same data arrays, with the
|
127
|
+
* first group corresponding to the earlier rows there.
|
128
|
+
* This matrix will be used in row-major order (i.e. entries 1..n_from contain the first row).
|
129
|
+
* Must be already initialized to zeros.
|
130
|
+
* Ignored when 'tmat' is passed.
|
131
|
+
* - n_from
|
132
|
+
* When calculating distances between two groups of points, this indicates the number of
|
133
|
+
* observations/rows belonging to the first group (the rows in 'rmat'), which will be
|
134
|
+
* assumed to be the first 'n_from' rows.
|
135
|
+
* Ignored when 'tmat' is passed.
|
136
|
+
*/
|
137
|
+
void calc_similarity(double numeric_data[], int categ_data[],
|
138
|
+
double Xc[], sparse_ix Xc_ind[], sparse_ix Xc_indptr[],
|
139
|
+
size_t nrows, int nthreads, bool assume_full_distr, bool standardize_dist,
|
140
|
+
IsoForest *model_outputs, ExtIsoForest *model_outputs_ext,
|
141
|
+
double tmat[], double rmat[], size_t n_from)
|
142
|
+
{
|
143
|
+
PredictionData prediction_data = {numeric_data, categ_data, nrows,
|
144
|
+
Xc, Xc_ind, Xc_indptr,
|
145
|
+
NULL, NULL, NULL};
|
146
|
+
|
147
|
+
size_t ntrees = (model_outputs != NULL)? model_outputs->trees.size() : model_outputs_ext->hplanes.size();
|
148
|
+
|
149
|
+
if (tmat != NULL) n_from = 0;
|
150
|
+
|
151
|
+
if ((size_t)nthreads > ntrees)
|
152
|
+
nthreads = (int)ntrees;
|
153
|
+
#ifdef _OPENMP
|
154
|
+
std::vector<WorkerForSimilarity> worker_memory(nthreads);
|
155
|
+
#else
|
156
|
+
std::vector<WorkerForSimilarity> worker_memory(1);
|
157
|
+
#endif
|
158
|
+
|
159
|
+
if (model_outputs != NULL)
|
160
|
+
{
|
161
|
+
#pragma omp parallel for schedule(dynamic) num_threads(nthreads) shared(ntrees, worker_memory, prediction_data, model_outputs)
|
162
|
+
for (size_t_for tree = 0; tree < ntrees; tree++)
|
163
|
+
{
|
164
|
+
initialize_worker_for_sim(worker_memory[omp_get_thread_num()], prediction_data,
|
165
|
+
model_outputs, NULL, n_from, assume_full_distr);
|
166
|
+
traverse_tree_sim(worker_memory[omp_get_thread_num()],
|
167
|
+
prediction_data,
|
168
|
+
*model_outputs,
|
169
|
+
model_outputs->trees[tree],
|
170
|
+
(size_t)0);
|
171
|
+
}
|
172
|
+
}
|
173
|
+
|
174
|
+
else
|
175
|
+
{
|
176
|
+
#pragma omp parallel for schedule(dynamic) num_threads(nthreads) shared(ntrees, worker_memory, prediction_data, model_outputs_ext)
|
177
|
+
for (size_t_for hplane = 0; hplane < ntrees; hplane++)
|
178
|
+
{
|
179
|
+
initialize_worker_for_sim(worker_memory[omp_get_thread_num()], prediction_data,
|
180
|
+
NULL, model_outputs_ext, n_from, assume_full_distr);
|
181
|
+
traverse_hplane_sim(worker_memory[omp_get_thread_num()],
|
182
|
+
prediction_data,
|
183
|
+
*model_outputs_ext,
|
184
|
+
model_outputs_ext->hplanes[hplane],
|
185
|
+
(size_t)0);
|
186
|
+
}
|
187
|
+
}
|
188
|
+
|
189
|
+
/* gather and transform the results */
|
190
|
+
gather_sim_result(&worker_memory, NULL,
|
191
|
+
&prediction_data, NULL,
|
192
|
+
model_outputs, model_outputs_ext,
|
193
|
+
tmat, rmat, n_from,
|
194
|
+
ntrees, assume_full_distr,
|
195
|
+
standardize_dist, nthreads);
|
196
|
+
}
|
197
|
+
|
198
|
+
void traverse_tree_sim(WorkerForSimilarity &workspace,
|
199
|
+
PredictionData &prediction_data,
|
200
|
+
IsoForest &model_outputs,
|
201
|
+
std::vector<IsoTree> &trees,
|
202
|
+
size_t curr_tree)
|
203
|
+
{
|
204
|
+
if (workspace.st == workspace.end)
|
205
|
+
return;
|
206
|
+
|
207
|
+
if (!workspace.tmat_sep.size())
|
208
|
+
{
|
209
|
+
std::sort(workspace.ix_arr.begin() + workspace.st, workspace.ix_arr.begin() + workspace.end + 1);
|
210
|
+
if (workspace.ix_arr[workspace.st] >= workspace.n_from)
|
211
|
+
return;
|
212
|
+
if (workspace.ix_arr[workspace.end] < workspace.n_from)
|
213
|
+
return;
|
214
|
+
}
|
215
|
+
|
216
|
+
/* Note: the first separation step will not be added here, as it simply consists of adding +1
|
217
|
+
to every combination regardless. It has to be added at the end in 'gather_sim_result' to
|
218
|
+
obtain the average separation depth. */
|
219
|
+
if (trees[curr_tree].score >= 0.)
|
220
|
+
{
|
221
|
+
long double rem = (long double) trees[curr_tree].remainder;
|
222
|
+
if (!workspace.weights_arr.size())
|
223
|
+
{
|
224
|
+
rem += (long double)(workspace.end - workspace.st + 1);
|
225
|
+
if (workspace.tmat_sep.size())
|
226
|
+
increase_comb_counter(workspace.ix_arr.data(), workspace.st, workspace.end,
|
227
|
+
prediction_data.nrows, workspace.tmat_sep.data(),
|
228
|
+
workspace.assume_full_distr? 3. : expected_separation_depth(rem));
|
229
|
+
else
|
230
|
+
increase_comb_counter_in_groups(workspace.ix_arr.data(), workspace.st, workspace.end,
|
231
|
+
workspace.n_from, prediction_data.nrows, workspace.rmat.data(),
|
232
|
+
workspace.assume_full_distr? 3. : expected_separation_depth(rem));
|
233
|
+
}
|
234
|
+
|
235
|
+
else
|
236
|
+
{
|
237
|
+
if (!workspace.assume_full_distr)
|
238
|
+
{
|
239
|
+
rem += std::accumulate(workspace.ix_arr.begin() + workspace.st,
|
240
|
+
workspace.ix_arr.begin() + workspace.end,
|
241
|
+
(long double) 0.,
|
242
|
+
[&workspace](long double curr, size_t ix)
|
243
|
+
{return curr + (long double)workspace.weights_arr[ix];}
|
244
|
+
);
|
245
|
+
}
|
246
|
+
|
247
|
+
if (workspace.tmat_sep.size())
|
248
|
+
increase_comb_counter(workspace.ix_arr.data(), workspace.st, workspace.end,
|
249
|
+
prediction_data.nrows, workspace.tmat_sep.data(),
|
250
|
+
workspace.weights_arr.data(),
|
251
|
+
workspace.assume_full_distr? 3. : expected_separation_depth(rem));
|
252
|
+
else
|
253
|
+
increase_comb_counter_in_groups(workspace.ix_arr.data(), workspace.st, workspace.end,
|
254
|
+
workspace.n_from, prediction_data.nrows,
|
255
|
+
workspace.rmat.data(), workspace.weights_arr.data(),
|
256
|
+
workspace.assume_full_distr? 3. : expected_separation_depth(rem));
|
257
|
+
}
|
258
|
+
return;
|
259
|
+
}
|
260
|
+
|
261
|
+
else if (curr_tree > 0)
|
262
|
+
{
|
263
|
+
if (workspace.tmat_sep.size())
|
264
|
+
if (!workspace.weights_arr.size())
|
265
|
+
increase_comb_counter(workspace.ix_arr.data(), workspace.st, workspace.end,
|
266
|
+
prediction_data.nrows, workspace.tmat_sep.data(), -1.);
|
267
|
+
else
|
268
|
+
increase_comb_counter(workspace.ix_arr.data(), workspace.st, workspace.end,
|
269
|
+
prediction_data.nrows, workspace.tmat_sep.data(),
|
270
|
+
workspace.weights_arr.data(), -1.);
|
271
|
+
else
|
272
|
+
if (!workspace.weights_arr.size())
|
273
|
+
increase_comb_counter_in_groups(workspace.ix_arr.data(), workspace.st, workspace.end,
|
274
|
+
workspace.n_from, prediction_data.nrows, workspace.rmat.data(), -1.);
|
275
|
+
else
|
276
|
+
increase_comb_counter_in_groups(workspace.ix_arr.data(), workspace.st, workspace.end,
|
277
|
+
workspace.n_from, prediction_data.nrows,
|
278
|
+
workspace.rmat.data(), workspace.weights_arr.data(), -1.);
|
279
|
+
}
|
280
|
+
|
281
|
+
|
282
|
+
/* divide according to tree */
|
283
|
+
if (prediction_data.Xc != NULL && !workspace.tmat_sep.size())
|
284
|
+
std::sort(workspace.ix_arr.begin() + workspace.st, workspace.ix_arr.begin() + workspace.end + 1);
|
285
|
+
size_t st_NA, end_NA, split_ix;
|
286
|
+
switch(trees[curr_tree].col_type)
|
287
|
+
{
|
288
|
+
case Numeric:
|
289
|
+
{
|
290
|
+
if (prediction_data.Xc == NULL)
|
291
|
+
divide_subset_split(workspace.ix_arr.data(),
|
292
|
+
prediction_data.numeric_data + prediction_data.nrows * trees[curr_tree].col_num,
|
293
|
+
workspace.st, workspace.end, trees[curr_tree].num_split,
|
294
|
+
model_outputs.missing_action, st_NA, end_NA, split_ix);
|
295
|
+
else
|
296
|
+
divide_subset_split(workspace.ix_arr.data(), workspace.st, workspace.end, trees[curr_tree].col_num,
|
297
|
+
prediction_data.Xc, prediction_data.Xc_ind, prediction_data.Xc_indptr,
|
298
|
+
trees[curr_tree].num_split, model_outputs.missing_action,
|
299
|
+
st_NA, end_NA, split_ix);
|
300
|
+
|
301
|
+
break;
|
302
|
+
}
|
303
|
+
|
304
|
+
case Categorical:
|
305
|
+
{
|
306
|
+
switch(model_outputs.cat_split_type)
|
307
|
+
{
|
308
|
+
case SingleCateg:
|
309
|
+
{
|
310
|
+
divide_subset_split(workspace.ix_arr.data(),
|
311
|
+
prediction_data.categ_data + prediction_data.nrows * trees[curr_tree].col_num,
|
312
|
+
workspace.st, workspace.end, trees[curr_tree].chosen_cat,
|
313
|
+
model_outputs.missing_action, st_NA, end_NA, split_ix);
|
314
|
+
break;
|
315
|
+
}
|
316
|
+
|
317
|
+
case SubSet:
|
318
|
+
{
|
319
|
+
if (!trees[curr_tree].cat_split.size())
|
320
|
+
divide_subset_split(workspace.ix_arr.data(),
|
321
|
+
prediction_data.categ_data + prediction_data.nrows * trees[curr_tree].col_num,
|
322
|
+
workspace.st, workspace.end,
|
323
|
+
model_outputs.missing_action, model_outputs.new_cat_action,
|
324
|
+
trees[curr_tree].pct_tree_left < .5, st_NA, end_NA, split_ix);
|
325
|
+
else
|
326
|
+
divide_subset_split(workspace.ix_arr.data(),
|
327
|
+
prediction_data.categ_data + prediction_data.nrows * trees[curr_tree].col_num,
|
328
|
+
workspace.st, workspace.end, trees[curr_tree].cat_split.data(),
|
329
|
+
(int) trees[curr_tree].cat_split.size(),
|
330
|
+
model_outputs.missing_action, model_outputs.new_cat_action,
|
331
|
+
(bool)(trees[curr_tree].pct_tree_left < .5), st_NA, end_NA, split_ix);
|
332
|
+
break;
|
333
|
+
}
|
334
|
+
}
|
335
|
+
break;
|
336
|
+
}
|
337
|
+
}
|
338
|
+
|
339
|
+
|
340
|
+
/* continue splitting recursively */
|
341
|
+
size_t orig_end = workspace.end;
|
342
|
+
switch(model_outputs.missing_action)
|
343
|
+
{
|
344
|
+
case Impute:
|
345
|
+
{
|
346
|
+
split_ix = (trees.back().pct_tree_left >= .5)? end_NA : st_NA;
|
347
|
+
}
|
348
|
+
|
349
|
+
case Fail:
|
350
|
+
{
|
351
|
+
if (split_ix > workspace.st)
|
352
|
+
{
|
353
|
+
workspace.end = split_ix - 1;
|
354
|
+
traverse_tree_sim(workspace,
|
355
|
+
prediction_data,
|
356
|
+
model_outputs,
|
357
|
+
trees,
|
358
|
+
trees[curr_tree].tree_left);
|
359
|
+
}
|
360
|
+
|
361
|
+
|
362
|
+
if (split_ix < orig_end)
|
363
|
+
{
|
364
|
+
workspace.st = split_ix;
|
365
|
+
workspace.end = orig_end;
|
366
|
+
traverse_tree_sim(workspace,
|
367
|
+
prediction_data,
|
368
|
+
model_outputs,
|
369
|
+
trees,
|
370
|
+
trees[curr_tree].tree_right);
|
371
|
+
}
|
372
|
+
break;
|
373
|
+
}
|
374
|
+
|
375
|
+
case Divide: /* new_cat_action = 'Weighted' will also fall here */
|
376
|
+
{
|
377
|
+
std::vector<double> weights_arr;
|
378
|
+
std::vector<size_t> ix_arr;
|
379
|
+
if (end_NA > workspace.st)
|
380
|
+
{
|
381
|
+
weights_arr.assign(workspace.weights_arr.begin(),
|
382
|
+
workspace.weights_arr.begin() + end_NA);
|
383
|
+
ix_arr.assign(workspace.ix_arr.begin(),
|
384
|
+
workspace.ix_arr.begin() + end_NA);
|
385
|
+
}
|
386
|
+
|
387
|
+
if (end_NA > workspace.st)
|
388
|
+
{
|
389
|
+
workspace.end = end_NA - 1;
|
390
|
+
for (size_t row = st_NA; row < end_NA; row++)
|
391
|
+
workspace.weights_arr[workspace.ix_arr[row]] *= trees[curr_tree].pct_tree_left;
|
392
|
+
traverse_tree_sim(workspace,
|
393
|
+
prediction_data,
|
394
|
+
model_outputs,
|
395
|
+
trees,
|
396
|
+
trees[curr_tree].tree_left);
|
397
|
+
}
|
398
|
+
|
399
|
+
if (st_NA < orig_end)
|
400
|
+
{
|
401
|
+
workspace.st = st_NA;
|
402
|
+
workspace.end = orig_end;
|
403
|
+
if (weights_arr.size())
|
404
|
+
{
|
405
|
+
std::copy(weights_arr.begin(),
|
406
|
+
weights_arr.end(),
|
407
|
+
workspace.weights_arr.begin());
|
408
|
+
std::copy(ix_arr.begin(),
|
409
|
+
ix_arr.end(),
|
410
|
+
workspace.ix_arr.begin());
|
411
|
+
weights_arr.clear();
|
412
|
+
weights_arr.shrink_to_fit();
|
413
|
+
ix_arr.clear();
|
414
|
+
ix_arr.shrink_to_fit();
|
415
|
+
}
|
416
|
+
|
417
|
+
for (size_t row = st_NA; row < end_NA; row++)
|
418
|
+
workspace.weights_arr[workspace.ix_arr[row]] *= (1 - trees[curr_tree].pct_tree_left);
|
419
|
+
traverse_tree_sim(workspace,
|
420
|
+
prediction_data,
|
421
|
+
model_outputs,
|
422
|
+
trees,
|
423
|
+
trees[curr_tree].tree_right);
|
424
|
+
}
|
425
|
+
break;
|
426
|
+
}
|
427
|
+
}
|
428
|
+
}
|
429
|
+
|
430
|
+
void traverse_hplane_sim(WorkerForSimilarity &workspace,
|
431
|
+
PredictionData &prediction_data,
|
432
|
+
ExtIsoForest &model_outputs,
|
433
|
+
std::vector<IsoHPlane> &hplanes,
|
434
|
+
size_t curr_tree)
|
435
|
+
{
|
436
|
+
if (workspace.st == workspace.end)
|
437
|
+
return;
|
438
|
+
|
439
|
+
if (!workspace.tmat_sep.size())
|
440
|
+
{
|
441
|
+
std::sort(workspace.ix_arr.begin() + workspace.st, workspace.ix_arr.begin() + workspace.end + 1);
|
442
|
+
if (workspace.ix_arr[workspace.st] >= workspace.n_from)
|
443
|
+
return;
|
444
|
+
if (workspace.ix_arr[workspace.end] < workspace.n_from)
|
445
|
+
return;
|
446
|
+
}
|
447
|
+
|
448
|
+
/* Note: the first separation step will not be added here, as it simply consists of adding +1
|
449
|
+
to every combination regardless. It has to be added at the end in 'gather_sim_result' to
|
450
|
+
obtain the average separation depth. */
|
451
|
+
if (hplanes[curr_tree].score >= 0)
|
452
|
+
{
|
453
|
+
if (workspace.tmat_sep.size())
|
454
|
+
increase_comb_counter(workspace.ix_arr.data(), workspace.st, workspace.end,
|
455
|
+
prediction_data.nrows, workspace.tmat_sep.data(),
|
456
|
+
workspace.assume_full_distr? 3. :
|
457
|
+
expected_separation_depth((long double) hplanes[curr_tree].remainder
|
458
|
+
+ (long double)(workspace.end - workspace.st + 1))
|
459
|
+
);
|
460
|
+
else
|
461
|
+
increase_comb_counter_in_groups(workspace.ix_arr.data(), workspace.st, workspace.end, workspace.n_from,
|
462
|
+
prediction_data.nrows, workspace.rmat.data(),
|
463
|
+
workspace.assume_full_distr? 3. :
|
464
|
+
expected_separation_depth((long double) hplanes[curr_tree].remainder
|
465
|
+
+ (long double)(workspace.end - workspace.st + 1))
|
466
|
+
);
|
467
|
+
return;
|
468
|
+
}
|
469
|
+
|
470
|
+
else if (curr_tree > 0)
|
471
|
+
{
|
472
|
+
if (workspace.tmat_sep.size())
|
473
|
+
increase_comb_counter(workspace.ix_arr.data(), workspace.st, workspace.end,
|
474
|
+
prediction_data.nrows, workspace.tmat_sep.data(), -1.);
|
475
|
+
else
|
476
|
+
increase_comb_counter_in_groups(workspace.ix_arr.data(), workspace.st, workspace.end, workspace.n_from,
|
477
|
+
prediction_data.nrows, workspace.rmat.data(), -1.);
|
478
|
+
}
|
479
|
+
|
480
|
+
if (prediction_data.Xc != NULL && !workspace.tmat_sep.size())
|
481
|
+
std::sort(workspace.ix_arr.begin() + workspace.st, workspace.ix_arr.begin() + workspace.end + 1);
|
482
|
+
|
483
|
+
/* reconstruct linear combination */
|
484
|
+
size_t ncols_numeric = 0;
|
485
|
+
size_t ncols_categ = 0;
|
486
|
+
std::fill(workspace.comb_val.begin(), workspace.comb_val.begin() + (workspace.end - workspace.st + 1), 0);
|
487
|
+
if (prediction_data.categ_data != NULL || prediction_data.Xc != NULL)
|
488
|
+
{
|
489
|
+
for (size_t col = 0; col < hplanes[curr_tree].col_num.size(); col++)
|
490
|
+
{
|
491
|
+
switch(hplanes[curr_tree].col_type[col])
|
492
|
+
{
|
493
|
+
case Numeric:
|
494
|
+
{
|
495
|
+
if (prediction_data.Xc == NULL)
|
496
|
+
add_linear_comb(workspace.ix_arr.data(), workspace.st, workspace.end, workspace.comb_val.data(),
|
497
|
+
prediction_data.numeric_data + prediction_data.nrows * hplanes[curr_tree].col_num[col],
|
498
|
+
hplanes[curr_tree].coef[ncols_numeric], (double)0, hplanes[curr_tree].mean[ncols_numeric],
|
499
|
+
(model_outputs.missing_action == Fail)? workspace.comb_val[0] : hplanes[curr_tree].fill_val[col],
|
500
|
+
model_outputs.missing_action, NULL, NULL, false);
|
501
|
+
else
|
502
|
+
add_linear_comb(workspace.ix_arr.data(), workspace.st, workspace.end,
|
503
|
+
hplanes[curr_tree].col_num[col], workspace.comb_val.data(),
|
504
|
+
prediction_data.Xc, prediction_data.Xc_ind, prediction_data.Xc_indptr,
|
505
|
+
hplanes[curr_tree].coef[ncols_numeric], (double)0, hplanes[curr_tree].mean[ncols_numeric],
|
506
|
+
(model_outputs.missing_action == Fail)? workspace.comb_val[0] : hplanes[curr_tree].fill_val[col],
|
507
|
+
model_outputs.missing_action, NULL, NULL, false);
|
508
|
+
ncols_numeric++;
|
509
|
+
break;
|
510
|
+
}
|
511
|
+
|
512
|
+
case Categorical:
|
513
|
+
{
|
514
|
+
switch(model_outputs.cat_split_type)
|
515
|
+
{
|
516
|
+
case SingleCateg:
|
517
|
+
{
|
518
|
+
add_linear_comb(workspace.ix_arr.data(), workspace.st, workspace.end, workspace.comb_val.data(),
|
519
|
+
prediction_data.categ_data + prediction_data.nrows * hplanes[curr_tree].col_num[col],
|
520
|
+
(int)0, NULL, hplanes[curr_tree].fill_new[ncols_categ],
|
521
|
+
hplanes[curr_tree].chosen_cat[ncols_categ],
|
522
|
+
(model_outputs.missing_action == Fail)? workspace.comb_val[0] : hplanes[curr_tree].fill_val[col],
|
523
|
+
workspace.comb_val[0], NULL, NULL, model_outputs.new_cat_action,
|
524
|
+
model_outputs.missing_action, SingleCateg, false);
|
525
|
+
break;
|
526
|
+
}
|
527
|
+
|
528
|
+
case SubSet:
|
529
|
+
{
|
530
|
+
add_linear_comb(workspace.ix_arr.data(), workspace.st, workspace.end, workspace.comb_val.data(),
|
531
|
+
prediction_data.categ_data + prediction_data.nrows * hplanes[curr_tree].col_num[col],
|
532
|
+
(int) hplanes[curr_tree].cat_coef[ncols_categ].size(),
|
533
|
+
hplanes[curr_tree].cat_coef[ncols_categ].data(), (double) 0, (int) 0,
|
534
|
+
(model_outputs.missing_action == Fail)? workspace.comb_val[0] : hplanes[curr_tree].fill_val[col],
|
535
|
+
hplanes[curr_tree].fill_new[ncols_categ], NULL, NULL,
|
536
|
+
model_outputs.new_cat_action, model_outputs.missing_action, SubSet, false);
|
537
|
+
break;
|
538
|
+
}
|
539
|
+
}
|
540
|
+
ncols_categ++;
|
541
|
+
break;
|
542
|
+
}
|
543
|
+
}
|
544
|
+
}
|
545
|
+
}
|
546
|
+
|
547
|
+
|
548
|
+
else /* faster version for numerical-only */
|
549
|
+
{
|
550
|
+
for (size_t col = 0; col < hplanes[curr_tree].col_num.size(); col++)
|
551
|
+
add_linear_comb(workspace.ix_arr.data(), workspace.st, workspace.end, workspace.comb_val.data(),
|
552
|
+
prediction_data.numeric_data + prediction_data.nrows * hplanes[curr_tree].col_num[col],
|
553
|
+
hplanes[curr_tree].coef[col], (double)0, hplanes[curr_tree].mean[col],
|
554
|
+
(model_outputs.missing_action == Fail)? workspace.comb_val[0] : hplanes[curr_tree].fill_val[col],
|
555
|
+
model_outputs.missing_action, NULL, NULL, false);
|
556
|
+
}
|
557
|
+
|
558
|
+
/* divide data */
|
559
|
+
size_t split_ix = divide_subset_split(workspace.ix_arr.data(), workspace.comb_val.data(),
|
560
|
+
workspace.st, workspace.end, hplanes[curr_tree].split_point);
|
561
|
+
|
562
|
+
/* continue splitting recursively */
|
563
|
+
size_t orig_end = workspace.end;
|
564
|
+
if (split_ix > workspace.st)
|
565
|
+
{
|
566
|
+
workspace.end = split_ix - 1;
|
567
|
+
traverse_hplane_sim(workspace,
|
568
|
+
prediction_data,
|
569
|
+
model_outputs,
|
570
|
+
hplanes,
|
571
|
+
hplanes[curr_tree].hplane_left);
|
572
|
+
}
|
573
|
+
|
574
|
+
if (split_ix < orig_end)
|
575
|
+
{
|
576
|
+
workspace.st = split_ix;
|
577
|
+
workspace.end = orig_end;
|
578
|
+
traverse_hplane_sim(workspace,
|
579
|
+
prediction_data,
|
580
|
+
model_outputs,
|
581
|
+
hplanes,
|
582
|
+
hplanes[curr_tree].hplane_right);
|
583
|
+
}
|
584
|
+
|
585
|
+
}
|
586
|
+
|
587
|
+
void gather_sim_result(std::vector<WorkerForSimilarity> *worker_memory,
|
588
|
+
std::vector<WorkerMemory> *worker_memory_m,
|
589
|
+
PredictionData *prediction_data, InputData *input_data,
|
590
|
+
IsoForest *model_outputs, ExtIsoForest *model_outputs_ext,
|
591
|
+
double *restrict tmat, double *restrict rmat, size_t n_from,
|
592
|
+
size_t ntrees, bool assume_full_distr,
|
593
|
+
bool standardize_dist, int nthreads)
|
594
|
+
{
|
595
|
+
size_t ncomb = (prediction_data != NULL)?
|
596
|
+
(prediction_data->nrows * (prediction_data->nrows - 1)) / 2
|
597
|
+
:
|
598
|
+
(input_data->nrows * (input_data->nrows - 1)) / 2;
|
599
|
+
size_t n_to = (prediction_data != NULL)? (prediction_data->nrows - n_from) : 0;
|
600
|
+
|
601
|
+
#ifdef _OPENMP
|
602
|
+
if (nthreads > 1)
|
603
|
+
{
|
604
|
+
if (worker_memory != NULL)
|
605
|
+
{
|
606
|
+
for (WorkerForSimilarity &w : *worker_memory)
|
607
|
+
{
|
608
|
+
if (w.tmat_sep.size())
|
609
|
+
{
|
610
|
+
#pragma omp parallel for schedule(static) num_threads(nthreads) shared(ncomb, tmat, w, worker_memory)
|
611
|
+
for (size_t_for ix = 0; ix < ncomb; ix++)
|
612
|
+
tmat[ix] += w.tmat_sep[ix];
|
613
|
+
}
|
614
|
+
else if (w.rmat.size())
|
615
|
+
{
|
616
|
+
#pragma omp parallel for schedule(static) num_threads(nthreads) shared(rmat, w, worker_memory)
|
617
|
+
for (size_t_for ix = 0; ix < w.rmat.size(); ix++)
|
618
|
+
rmat[ix] += w.rmat[ix];
|
619
|
+
}
|
620
|
+
}
|
621
|
+
}
|
622
|
+
|
623
|
+
else
|
624
|
+
{
|
625
|
+
for (WorkerMemory &w : *worker_memory_m)
|
626
|
+
{
|
627
|
+
if (w.tmat_sep.size())
|
628
|
+
{
|
629
|
+
#pragma omp parallel for schedule(static) num_threads(nthreads) shared(ncomb, tmat, w, worker_memory_m)
|
630
|
+
for (size_t_for ix = 0; ix < ncomb; ix++)
|
631
|
+
tmat[ix] += w.tmat_sep[ix];
|
632
|
+
}
|
633
|
+
}
|
634
|
+
}
|
635
|
+
}
|
636
|
+
|
637
|
+
else
|
638
|
+
#endif
|
639
|
+
{
|
640
|
+
if (worker_memory != NULL)
|
641
|
+
{
|
642
|
+
if ((*worker_memory)[0].tmat_sep.size())
|
643
|
+
std::copy((*worker_memory)[0].tmat_sep.begin(), (*worker_memory)[0].tmat_sep.end(), tmat);
|
644
|
+
else
|
645
|
+
std::copy((*worker_memory)[0].rmat.begin(), (*worker_memory)[0].rmat.end(), rmat);
|
646
|
+
}
|
647
|
+
|
648
|
+
else
|
649
|
+
{
|
650
|
+
std::copy((*worker_memory_m)[0].tmat_sep.begin(), (*worker_memory_m)[0].tmat_sep.end(), tmat);
|
651
|
+
}
|
652
|
+
}
|
653
|
+
|
654
|
+
double ntrees_dbl = (double) ntrees;
|
655
|
+
if (standardize_dist)
|
656
|
+
{
|
657
|
+
/* Note: the separation distances up this point are missing the first hop, which is always
|
658
|
+
a +1 to every combination. Thus, it needs to be added back for the average separation depth.
|
659
|
+
For the standardized metric, it takes the expected divisor as 2(=3-1) instead of 3, given
|
660
|
+
that every combination will always get a +1 at the beginning. Since what's obtained here
|
661
|
+
is a sum across all trees, adding this +1 means adding the number of trees. */
|
662
|
+
double div_trees = ntrees_dbl;
|
663
|
+
if (assume_full_distr)
|
664
|
+
{
|
665
|
+
div_trees *= 2;
|
666
|
+
}
|
667
|
+
|
668
|
+
else if (input_data != NULL)
|
669
|
+
{
|
670
|
+
div_trees *= (expected_separation_depth(input_data->nrows) - 1);
|
671
|
+
}
|
672
|
+
|
673
|
+
else
|
674
|
+
{
|
675
|
+
div_trees *= ((
|
676
|
+
(model_outputs != NULL)?
|
677
|
+
expected_separation_depth_hotstart(model_outputs->exp_avg_sep,
|
678
|
+
model_outputs->orig_sample_size,
|
679
|
+
model_outputs->orig_sample_size + prediction_data->nrows)
|
680
|
+
:
|
681
|
+
expected_separation_depth_hotstart(model_outputs_ext->exp_avg_sep,
|
682
|
+
model_outputs_ext->orig_sample_size,
|
683
|
+
model_outputs_ext->orig_sample_size + prediction_data->nrows)
|
684
|
+
) - 1);
|
685
|
+
}
|
686
|
+
|
687
|
+
|
688
|
+
if (tmat != NULL)
|
689
|
+
#pragma omp parallel for schedule(static) num_threads(nthreads) shared(ncomb, tmat, ntrees_dbl, div_trees)
|
690
|
+
for (size_t_for ix = 0; ix < ncomb; ix++)
|
691
|
+
tmat[ix] = exp2( - tmat[ix] / div_trees);
|
692
|
+
else
|
693
|
+
#pragma omp parallel for schedule(static) num_threads(nthreads) shared(ncomb, rmat, ntrees_dbl, div_trees)
|
694
|
+
for (size_t_for ix = 0; ix < n_from * n_to; ix++)
|
695
|
+
rmat[ix] = exp2( - rmat[ix] / div_trees);
|
696
|
+
}
|
697
|
+
|
698
|
+
else
|
699
|
+
{
|
700
|
+
if (tmat != NULL)
|
701
|
+
#pragma omp parallel for schedule(static) num_threads(nthreads) shared(ncomb, tmat, ntrees_dbl)
|
702
|
+
for (size_t_for ix = 0; ix < ncomb; ix++)
|
703
|
+
tmat[ix] = (tmat[ix] + ntrees) / ntrees_dbl;
|
704
|
+
else
|
705
|
+
#pragma omp parallel for schedule(static) num_threads(nthreads) shared(n_from, rmat, ntrees_dbl)
|
706
|
+
for (size_t_for ix = 0; ix < n_from * n_to; ix++)
|
707
|
+
rmat[ix] = (rmat[ix] + ntrees) / ntrees_dbl;
|
708
|
+
}
|
709
|
+
}
|
710
|
+
|
711
|
+
void initialize_worker_for_sim(WorkerForSimilarity &workspace,
|
712
|
+
PredictionData &prediction_data,
|
713
|
+
IsoForest *model_outputs,
|
714
|
+
ExtIsoForest *model_outputs_ext,
|
715
|
+
size_t n_from,
|
716
|
+
bool assume_full_distr)
|
717
|
+
{
|
718
|
+
workspace.st = 0;
|
719
|
+
workspace.end = prediction_data.nrows - 1;
|
720
|
+
workspace.n_from = n_from;
|
721
|
+
workspace.assume_full_distr = assume_full_distr; /* doesn't need to have one copy per worker */
|
722
|
+
|
723
|
+
if (!workspace.ix_arr.size())
|
724
|
+
{
|
725
|
+
workspace.ix_arr.resize(prediction_data.nrows);
|
726
|
+
std::iota(workspace.ix_arr.begin(), workspace.ix_arr.end(), (size_t)0);
|
727
|
+
if (!n_from)
|
728
|
+
workspace.tmat_sep.resize((prediction_data.nrows * (prediction_data.nrows - 1)) / 2, 0);
|
729
|
+
else
|
730
|
+
workspace.rmat.resize(prediction_data.nrows * n_from, 0);
|
731
|
+
}
|
732
|
+
|
733
|
+
if (model_outputs != NULL && (model_outputs->missing_action == Divide || model_outputs->new_cat_action == Weighted))
|
734
|
+
{
|
735
|
+
if (!workspace.weights_arr.size())
|
736
|
+
workspace.weights_arr.resize(prediction_data.nrows, 1);
|
737
|
+
else
|
738
|
+
std::fill(workspace.weights_arr.begin(), workspace.weights_arr.end(), 1);
|
739
|
+
}
|
740
|
+
|
741
|
+
if (model_outputs_ext != NULL)
|
742
|
+
{
|
743
|
+
if (!workspace.comb_val.size())
|
744
|
+
workspace.comb_val.resize(prediction_data.nrows, 0);
|
745
|
+
else
|
746
|
+
std::fill(workspace.comb_val.begin(), workspace.comb_val.end(), 0);
|
747
|
+
}
|
748
|
+
}
|
749
|
+
|