isotree 0.2.0 → 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 +16 -1
- data/LICENSE.txt +2 -2
- data/README.md +41 -23
- data/ext/isotree/ext.cpp +144 -31
- data/ext/isotree/extconf.rb +7 -7
- data/lib/isotree/dataset.rb +0 -1
- data/lib/isotree/isolation_forest.rb +114 -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 +40 -106
- 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
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: a2ed0745b24db6c7d55b86cbf60394de590225509f3be5dbc79934606cd402cb
|
4
|
+
data.tar.gz: d1601d80e3878cc678544a245defd04831e6f11f4f374ecff6d1916e1618af6e
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: b461f501114e56810ed6075fba28ae79a611763838147670f357a8a9645000f139072bf3bb3a2120cc09ad302df429d39f6b67522b1c2bc18862e75a65266eb4
|
7
|
+
data.tar.gz: 57fc3f334fac2a6918ef95fb4827a67543a2aa5c1cdfcd86225c3411a409348593764109bcbc5155ddd6e49217f0764686847265550d145e72007556ae7fd00e
|
data/CHANGELOG.md
CHANGED
@@ -1,3 +1,18 @@
|
|
1
|
+
## 0.3.0 (2022-06-13)
|
2
|
+
|
3
|
+
- Updated IsoTree to 0.5.16
|
4
|
+
- Updated serialization format (exported models must be recreated)
|
5
|
+
- Dropped support for Ruby < 2.7
|
6
|
+
- Dropped support for Windows
|
7
|
+
|
8
|
+
## 0.2.2 (2022-06-12)
|
9
|
+
|
10
|
+
- Fixed segfault when data is smaller than sample size
|
11
|
+
|
12
|
+
## 0.2.1 (2021-05-23)
|
13
|
+
|
14
|
+
- Improved performance
|
15
|
+
|
1
16
|
## 0.2.0 (2021-05-17)
|
2
17
|
|
3
18
|
- Updated to Rice 4
|
@@ -5,7 +20,7 @@
|
|
5
20
|
|
6
21
|
## 0.1.5 (2021-03-14)
|
7
22
|
|
8
|
-
- Updated
|
23
|
+
- Updated IsoTree to 0.1.25
|
9
24
|
- Added support for exporting and importing models
|
10
25
|
|
11
26
|
## 0.1.4 (2020-08-22)
|
data/LICENSE.txt
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
BSD 2-Clause License
|
2
2
|
|
3
|
-
Copyright (c) 2020, David Cortes
|
4
|
-
Copyright (c) 2020-
|
3
|
+
Copyright (c) 2020-2022, David Cortes
|
4
|
+
Copyright (c) 2020-2022, Andrew Kane
|
5
5
|
All rights reserved.
|
6
6
|
|
7
7
|
Redistribution and use in source and binary forms, with or without
|
data/README.md
CHANGED
@@ -1,21 +1,23 @@
|
|
1
|
-
# IsoTree
|
1
|
+
# IsoTree Ruby
|
2
2
|
|
3
3
|
:evergreen_tree: [IsoTree](https://github.com/david-cortes/isotree) - outlier/anomaly detection using Isolation Forest - for Ruby
|
4
4
|
|
5
5
|
Learn how [Isolation Forest](https://www.youtube.com/watch?v=RyFQXQf4w4w) works
|
6
6
|
|
7
|
-
:deciduous_tree: Check out [OutlierTree](https://github.com/ankane/outliertree) for human-readable explanations of outliers
|
7
|
+
:deciduous_tree: Check out [OutlierTree](https://github.com/ankane/outliertree-ruby) for human-readable explanations of outliers
|
8
8
|
|
9
|
-
[![Build Status](https://github.com/ankane/isotree/workflows/build/badge.svg?branch=master)](https://github.com/ankane/isotree/actions)
|
9
|
+
[![Build Status](https://github.com/ankane/isotree-ruby/workflows/build/badge.svg?branch=master)](https://github.com/ankane/isotree-ruby/actions)
|
10
10
|
|
11
11
|
## Installation
|
12
12
|
|
13
13
|
Add this line to your application’s Gemfile:
|
14
14
|
|
15
15
|
```ruby
|
16
|
-
gem
|
16
|
+
gem "isotree"
|
17
17
|
```
|
18
18
|
|
19
|
+
Windows is not supported at the moment
|
20
|
+
|
19
21
|
## Getting Started
|
20
22
|
|
21
23
|
Prep your data
|
@@ -24,7 +26,8 @@ Prep your data
|
|
24
26
|
data = [
|
25
27
|
{department: "Books", sale: false, price: 2.50},
|
26
28
|
{department: "Books", sale: true, price: 3.00},
|
27
|
-
{department: "Movies", sale: false, price: 5.00}
|
29
|
+
{department: "Movies", sale: false, price: 5.00},
|
30
|
+
# ...
|
28
31
|
]
|
29
32
|
```
|
30
33
|
|
@@ -61,28 +64,38 @@ Pass parameters - default values below
|
|
61
64
|
|
62
65
|
```ruby
|
63
66
|
IsoTree::IsolationForest.new(
|
64
|
-
sample_size:
|
67
|
+
sample_size: "auto",
|
65
68
|
ntrees: 500,
|
66
69
|
ndim: 3,
|
67
|
-
ntry:
|
68
|
-
|
69
|
-
|
70
|
-
|
71
|
-
|
72
|
-
|
73
|
-
|
74
|
-
|
75
|
-
|
70
|
+
ntry: 1,
|
71
|
+
max_depth: "auto",
|
72
|
+
ncols_per_tree: nil,
|
73
|
+
prob_pick_pooled_gain: 0.0,
|
74
|
+
prob_pick_avg_gain: 0.0,
|
75
|
+
prob_pick_full_gain: 0.0,
|
76
|
+
prob_pick_dens: 0.0,
|
77
|
+
prob_pick_col_by_range: 0.0,
|
78
|
+
prob_pick_col_by_var: 0.0,
|
79
|
+
prob_pick_col_by_kurt: 0.0,
|
80
|
+
min_gain: 0.0,
|
81
|
+
missing_action: "auto",
|
82
|
+
new_categ_action: "auto",
|
83
|
+
categ_split_type: "auto",
|
76
84
|
all_perm: false,
|
77
85
|
coef_by_prop: false,
|
78
86
|
sample_with_replacement: false,
|
79
|
-
penalize_range:
|
87
|
+
penalize_range: false,
|
88
|
+
standardize_data: true,
|
89
|
+
scoring_metric: "depth",
|
90
|
+
fast_bratio: true,
|
80
91
|
weigh_by_kurtosis: false,
|
81
|
-
coefs: "
|
92
|
+
coefs: "uniform",
|
93
|
+
assume_full_distr: true,
|
82
94
|
min_imp_obs: 3,
|
83
95
|
depth_imp: "higher",
|
84
96
|
weigh_imp_rows: "inverse",
|
85
97
|
random_seed: 1,
|
98
|
+
use_long_double: false,
|
86
99
|
nthreads: -1
|
87
100
|
)
|
88
101
|
```
|
@@ -134,7 +147,6 @@ Check out [Trove](https://github.com/ankane/trove) for deploying models.
|
|
134
147
|
|
135
148
|
```sh
|
136
149
|
trove push model.bin
|
137
|
-
trove push model.bin.metadata
|
138
150
|
```
|
139
151
|
|
140
152
|
## Reference
|
@@ -145,24 +157,30 @@ Get the average isolation depth
|
|
145
157
|
model.predict(data, output: "avg_depth")
|
146
158
|
```
|
147
159
|
|
160
|
+
## Upgrading
|
161
|
+
|
162
|
+
### 0.3.0
|
163
|
+
|
164
|
+
This version uses IsoTree’s new serialization format. Exported models must be recreated.
|
165
|
+
|
148
166
|
## History
|
149
167
|
|
150
|
-
View the [changelog](https://github.com/ankane/isotree/blob/master/CHANGELOG.md)
|
168
|
+
View the [changelog](https://github.com/ankane/isotree-ruby/blob/master/CHANGELOG.md)
|
151
169
|
|
152
170
|
## Contributing
|
153
171
|
|
154
172
|
Everyone is encouraged to help improve this project. Here are a few ways you can help:
|
155
173
|
|
156
|
-
- [Report bugs](https://github.com/ankane/isotree/issues)
|
157
|
-
- Fix bugs and [submit pull requests](https://github.com/ankane/isotree/pulls)
|
174
|
+
- [Report bugs](https://github.com/ankane/isotree-ruby/issues)
|
175
|
+
- Fix bugs and [submit pull requests](https://github.com/ankane/isotree-ruby/pulls)
|
158
176
|
- Write, clarify, or fix documentation
|
159
177
|
- Suggest or add new features
|
160
178
|
|
161
179
|
To get started with development:
|
162
180
|
|
163
181
|
```sh
|
164
|
-
git clone --recursive https://github.com/ankane/isotree.git
|
165
|
-
cd isotree
|
182
|
+
git clone --recursive https://github.com/ankane/isotree-ruby.git
|
183
|
+
cd isotree-ruby
|
166
184
|
bundle install
|
167
185
|
bundle exec rake compile
|
168
186
|
bundle exec rake test
|
data/ext/isotree/ext.cpp
CHANGED
@@ -1,3 +1,8 @@
|
|
1
|
+
// stdlib
|
2
|
+
#include <cmath>
|
3
|
+
#include <fstream>
|
4
|
+
#include <iostream>
|
5
|
+
|
1
6
|
// isotree
|
2
7
|
#include <isotree.hpp>
|
3
8
|
|
@@ -22,7 +27,7 @@ namespace Rice::detail
|
|
22
27
|
NewCategAction convert(VALUE x)
|
23
28
|
{
|
24
29
|
auto value = Object(x).to_s().str();
|
25
|
-
if (value == "weighted") return Weighted;
|
30
|
+
if (value == "weighted" || value == "impute") return Weighted;
|
26
31
|
if (value == "smallest") return Smallest;
|
27
32
|
if (value == "random") return Random;
|
28
33
|
throw std::runtime_error("Unknown new categ action: " + value);
|
@@ -96,6 +101,24 @@ namespace Rice::detail
|
|
96
101
|
throw std::runtime_error("Unknown weight imp rows: " + value);
|
97
102
|
}
|
98
103
|
};
|
104
|
+
|
105
|
+
template<>
|
106
|
+
class From_Ruby<ScoringMetric>
|
107
|
+
{
|
108
|
+
public:
|
109
|
+
ScoringMetric convert(VALUE x)
|
110
|
+
{
|
111
|
+
auto value = Object(x).to_s().str();
|
112
|
+
if (value == "depth") return Depth;
|
113
|
+
if (value == "adj_depth") return AdjDepth;
|
114
|
+
if (value == "density") return Density;
|
115
|
+
if (value == "adj_density") return AdjDensity;
|
116
|
+
if (value == "boxed_density") return BoxedDensity;
|
117
|
+
if (value == "boxed_density2") return BoxedDensity2;
|
118
|
+
if (value == "boxed_ratio") return BoxedRatio;
|
119
|
+
throw std::runtime_error("Unknown scoring metric: " + value);
|
120
|
+
}
|
121
|
+
};
|
99
122
|
}
|
100
123
|
|
101
124
|
extern "C"
|
@@ -118,20 +141,20 @@ void Init_ext()
|
|
118
141
|
size_t ncols_numeric = options.get<size_t, Symbol>("ncols_numeric");
|
119
142
|
size_t ncols_categ = options.get<size_t, Symbol>("ncols_categ");
|
120
143
|
|
121
|
-
|
144
|
+
real_t* numeric_data = NULL;
|
122
145
|
if (ncols_numeric > 0) {
|
123
146
|
numeric_data = (double*) options.get<String, Symbol>("numeric_data").c_str();
|
124
147
|
}
|
125
148
|
|
126
|
-
int
|
127
|
-
int
|
149
|
+
int* categorical_data = NULL;
|
150
|
+
int* ncat = NULL;
|
128
151
|
if (ncols_categ > 0) {
|
129
152
|
categorical_data = (int*) options.get<String, Symbol>("categorical_data").c_str();
|
130
153
|
ncat = (int*) options.get<String, Symbol>("ncat").c_str();
|
131
154
|
}
|
132
155
|
|
133
156
|
// not used (sparse matrices)
|
134
|
-
|
157
|
+
real_t* Xc = NULL;
|
135
158
|
sparse_ix* Xc_ind = NULL;
|
136
159
|
sparse_ix* Xc_indptr = NULL;
|
137
160
|
|
@@ -142,9 +165,7 @@ void Init_ext()
|
|
142
165
|
size_t ntrees = options.get<size_t, Symbol>("ntrees");
|
143
166
|
size_t ntry = options.get<size_t, Symbol>("ntry");
|
144
167
|
double prob_pick_by_gain_avg = options.get<double, Symbol>("prob_pick_avg_gain");
|
145
|
-
double prob_split_by_gain_avg = options.get<double, Symbol>("prob_split_avg_gain");
|
146
168
|
double prob_pick_by_gain_pl = options.get<double, Symbol>("prob_pick_pooled_gain");
|
147
|
-
double prob_split_by_gain_pl = options.get<double, Symbol>("prob_split_pooled_gain");
|
148
169
|
double min_gain = options.get<double, Symbol>("min_gain");
|
149
170
|
MissingAction missing_action = options.get<MissingAction, Symbol>("missing_action");
|
150
171
|
CategSplit cat_split_type = options.get<CategSplit, Symbol>("categ_split_type");
|
@@ -159,21 +180,31 @@ void Init_ext()
|
|
159
180
|
UseDepthImp depth_imp = options.get<UseDepthImp, Symbol>("depth_imp");
|
160
181
|
WeighImpRows weigh_imp_rows = options.get<WeighImpRows, Symbol>("weigh_imp_rows");
|
161
182
|
uint64_t random_seed = options.get<uint64_t, Symbol>("random_seed");
|
183
|
+
bool use_long_double = options.get<bool, Symbol>("use_long_double");
|
162
184
|
int nthreads = options.get<int, Symbol>("nthreads");
|
163
185
|
|
164
186
|
// TODO options
|
165
187
|
double* sample_weights = NULL;
|
166
|
-
bool weight_as_sample =
|
167
|
-
size_t max_depth =
|
168
|
-
bool limit_depth =
|
188
|
+
bool weight_as_sample = options.get<bool, Symbol>("weights_as_sample_prob");
|
189
|
+
size_t max_depth = options.get<size_t, Symbol>("max_depth");
|
190
|
+
bool limit_depth = options.get<bool, Symbol>("limit_depth");
|
169
191
|
bool standardize_dist = false;
|
170
192
|
double* tmat = NULL;
|
171
193
|
double* output_depths = NULL;
|
172
194
|
bool standardize_depth = false;
|
173
|
-
|
174
|
-
Imputer
|
195
|
+
real_t* col_weights = NULL;
|
196
|
+
Imputer* imputer = NULL;
|
175
197
|
bool impute_at_fit = false;
|
176
|
-
|
198
|
+
|
199
|
+
int ncols_per_tree = options.get<int, Symbol>("ncols_per_tree");
|
200
|
+
bool standardize_data = options.get<bool, Symbol>("standardize_data");
|
201
|
+
ScoringMetric scoring_metric = options.get<ScoringMetric, Symbol>("scoring_metric");
|
202
|
+
bool fast_bratio = options.get<bool, Symbol>("fast_bratio");
|
203
|
+
double prob_pick_by_full_gain = options.get<double, Symbol>("prob_pick_full_gain");
|
204
|
+
double prob_pick_by_dens = options.get<double, Symbol>("prob_pick_dens");
|
205
|
+
double prob_pick_col_by_range = options.get<double, Symbol>("prob_pick_col_by_range");
|
206
|
+
double prob_pick_col_by_var = options.get<double, Symbol>("prob_pick_col_by_var");
|
207
|
+
double prob_pick_col_by_kurt = options.get<double, Symbol>("prob_pick_col_by_kurt");
|
177
208
|
|
178
209
|
fit_iforest(
|
179
210
|
NULL,
|
@@ -197,18 +228,25 @@ void Init_ext()
|
|
197
228
|
sample_size,
|
198
229
|
ntrees,
|
199
230
|
max_depth,
|
231
|
+
ncols_per_tree,
|
200
232
|
limit_depth,
|
201
233
|
penalize_range,
|
234
|
+
standardize_data,
|
235
|
+
scoring_metric,
|
236
|
+
fast_bratio,
|
202
237
|
standardize_dist,
|
203
238
|
tmat,
|
204
239
|
output_depths,
|
205
240
|
standardize_depth,
|
206
241
|
col_weights,
|
207
242
|
weigh_by_kurt,
|
208
|
-
prob_pick_by_gain_avg,
|
209
|
-
prob_split_by_gain_avg,
|
210
243
|
prob_pick_by_gain_pl,
|
211
|
-
|
244
|
+
prob_pick_by_gain_avg,
|
245
|
+
prob_pick_by_full_gain,
|
246
|
+
prob_pick_by_dens,
|
247
|
+
prob_pick_col_by_range,
|
248
|
+
prob_pick_col_by_var,
|
249
|
+
prob_pick_col_by_kurt,
|
212
250
|
min_gain,
|
213
251
|
missing_action,
|
214
252
|
cat_split_type,
|
@@ -220,7 +258,7 @@ void Init_ext()
|
|
220
258
|
weigh_imp_rows,
|
221
259
|
impute_at_fit,
|
222
260
|
random_seed,
|
223
|
-
|
261
|
+
use_long_double,
|
224
262
|
nthreads
|
225
263
|
);
|
226
264
|
|
@@ -234,21 +272,21 @@ void Init_ext()
|
|
234
272
|
size_t ncols_numeric = options.get<size_t, Symbol>("ncols_numeric");
|
235
273
|
size_t ncols_categ = options.get<size_t, Symbol>("ncols_categ");
|
236
274
|
|
237
|
-
|
275
|
+
real_t* numeric_data = NULL;
|
238
276
|
if (ncols_numeric > 0) {
|
239
277
|
numeric_data = (double*) options.get<String, Symbol>("numeric_data").c_str();
|
240
278
|
}
|
241
279
|
|
242
|
-
int
|
280
|
+
int* categorical_data = NULL;
|
243
281
|
if (ncols_categ > 0) {
|
244
282
|
categorical_data = (int*) options.get<String, Symbol>("categorical_data").c_str();
|
245
283
|
}
|
246
284
|
|
247
285
|
// not used (sparse matrices)
|
248
|
-
|
286
|
+
real_t* Xc = NULL;
|
249
287
|
sparse_ix* Xc_ind = NULL;
|
250
288
|
sparse_ix* Xc_indptr = NULL;
|
251
|
-
|
289
|
+
real_t* Xr = NULL;
|
252
290
|
sparse_ix* Xr_ind = NULL;
|
253
291
|
sparse_ix* Xr_indptr = NULL;
|
254
292
|
|
@@ -257,10 +295,17 @@ void Init_ext()
|
|
257
295
|
bool standardize = options.get<bool, Symbol>("standardize");
|
258
296
|
std::vector<double> outlier_scores(nrows);
|
259
297
|
sparse_ix* tree_num = NULL;
|
298
|
+
bool is_col_major = true;
|
299
|
+
size_t ld_numeric = 0;
|
300
|
+
size_t ld_categ = 0;
|
301
|
+
double* per_tree_depths = NULL;
|
260
302
|
|
261
303
|
predict_iforest(
|
262
304
|
numeric_data,
|
263
305
|
categorical_data,
|
306
|
+
is_col_major,
|
307
|
+
ld_numeric,
|
308
|
+
ld_categ,
|
264
309
|
Xc,
|
265
310
|
Xc_ind,
|
266
311
|
Xc_indptr,
|
@@ -273,7 +318,9 @@ void Init_ext()
|
|
273
318
|
NULL,
|
274
319
|
&iso,
|
275
320
|
outlier_scores.data(),
|
276
|
-
tree_num
|
321
|
+
tree_num,
|
322
|
+
per_tree_depths,
|
323
|
+
NULL
|
277
324
|
);
|
278
325
|
|
279
326
|
Array ret;
|
@@ -283,27 +330,93 @@ void Init_ext()
|
|
283
330
|
return ret;
|
284
331
|
})
|
285
332
|
.define_singleton_function(
|
286
|
-
"
|
287
|
-
[](ExtIsoForest& iso, String path) {
|
333
|
+
"serialize_combined",
|
334
|
+
[](ExtIsoForest& iso, String path, String metadata) {
|
288
335
|
#ifdef _MSC_VER
|
289
336
|
// TODO convert to wchar_t
|
290
337
|
throw std::runtime_error("Not supported on Windows yet");
|
291
338
|
#else
|
292
|
-
|
339
|
+
std::ofstream file;
|
340
|
+
file.open(path.c_str());
|
341
|
+
serialize_combined(
|
342
|
+
NULL,
|
343
|
+
&iso,
|
344
|
+
NULL,
|
345
|
+
NULL,
|
346
|
+
metadata.c_str(),
|
347
|
+
// returns bytesize (RSTRING_LEN)
|
348
|
+
metadata.length(),
|
349
|
+
file
|
350
|
+
);
|
351
|
+
file.close();
|
293
352
|
#endif
|
294
353
|
})
|
295
354
|
.define_singleton_function(
|
296
|
-
"
|
355
|
+
"deserialize_combined",
|
297
356
|
[](String path) {
|
298
|
-
ExtIsoForest iso;
|
299
|
-
|
300
357
|
#ifdef _MSC_VER
|
301
358
|
// TODO convert to wchar_t
|
302
359
|
throw std::runtime_error("Not supported on Windows yet");
|
303
360
|
#else
|
304
|
-
|
305
|
-
#endif
|
361
|
+
Array ret;
|
306
362
|
|
307
|
-
|
363
|
+
std::ifstream file;
|
364
|
+
file.open(path.c_str(), std::ios_base::in | std::ios_base::binary);
|
365
|
+
if (!file) {
|
366
|
+
throw std::runtime_error("Cannot open file");
|
367
|
+
}
|
368
|
+
|
369
|
+
bool is_isotree_model = false;
|
370
|
+
bool is_compatible = false;
|
371
|
+
bool has_combined_objects = false;
|
372
|
+
bool has_IsoForest = false;
|
373
|
+
bool has_ExtIsoForest = false;
|
374
|
+
bool has_Imputer = false;
|
375
|
+
bool has_Indexer = false;
|
376
|
+
bool has_metadata = false;
|
377
|
+
size_t size_metadata = 0;
|
378
|
+
|
379
|
+
inspect_serialized_object(
|
380
|
+
file,
|
381
|
+
is_isotree_model,
|
382
|
+
is_compatible,
|
383
|
+
has_combined_objects,
|
384
|
+
has_IsoForest,
|
385
|
+
has_ExtIsoForest,
|
386
|
+
has_Imputer,
|
387
|
+
has_Indexer,
|
388
|
+
has_metadata,
|
389
|
+
size_metadata
|
390
|
+
);
|
391
|
+
|
392
|
+
if (!is_isotree_model || !has_combined_objects) {
|
393
|
+
throw std::runtime_error("Input file is not a serialized isotree model");
|
394
|
+
}
|
395
|
+
if (!is_compatible) {
|
396
|
+
throw std::runtime_error("Model file format is incompatible");
|
397
|
+
}
|
398
|
+
if (size_metadata == 0) {
|
399
|
+
throw std::runtime_error("Input file does not contain metadata");
|
400
|
+
}
|
401
|
+
|
402
|
+
IsoForest model = IsoForest();
|
403
|
+
ExtIsoForest model_ext = ExtIsoForest();
|
404
|
+
Imputer imputer = Imputer();
|
405
|
+
TreesIndexer indexer = TreesIndexer();
|
406
|
+
char *optional_metadata = (char*) calloc(size_metadata, sizeof(char));
|
407
|
+
if (optional_metadata == NULL) {
|
408
|
+
throw std::runtime_error("Cannot allocate memory");
|
409
|
+
}
|
410
|
+
|
411
|
+
deserialize_combined(file, &model, &model_ext, &imputer, &indexer, optional_metadata);
|
412
|
+
file.close();
|
413
|
+
|
414
|
+
ret.push(Object(Rice::detail::To_Ruby<ExtIsoForest>().convert(model_ext)));
|
415
|
+
ret.push(String(std::string(optional_metadata, size_metadata)));
|
416
|
+
|
417
|
+
free(optional_metadata);
|
418
|
+
|
419
|
+
return ret;
|
420
|
+
#endif
|
308
421
|
});
|
309
422
|
}
|
data/ext/isotree/extconf.rb
CHANGED
@@ -1,6 +1,6 @@
|
|
1
1
|
require "mkmf-rice"
|
2
2
|
|
3
|
-
$CXXFLAGS += " -std=c++17 -
|
3
|
+
$CXXFLAGS += " -std=c++17 $(optflags) -D_USE_XOSHIRO -DSUPPORTS_RESTRICT=1 -D_USE_ROBIN_MAP -DDONT_THROW_ON_INTERRUPT"
|
4
4
|
|
5
5
|
apple_clang = RbConfig::CONFIG["CC_VERSION_MESSAGE"] =~ /apple clang/i
|
6
6
|
|
@@ -11,12 +11,12 @@ if have_library("omp") || have_library("gomp")
|
|
11
11
|
end
|
12
12
|
|
13
13
|
ext = File.expand_path(".", __dir__)
|
14
|
-
|
15
|
-
|
14
|
+
isotree_src = File.expand_path("../../vendor/isotree/src", __dir__)
|
15
|
+
isotree_inc = File.expand_path("../../vendor/isotree/include", __dir__)
|
16
16
|
|
17
|
-
exclude = %w(Rwrapper.cpp RcppExports.cpp)
|
18
|
-
$srcs = Dir["{#{ext},#{
|
19
|
-
$INCFLAGS << " -I#{
|
20
|
-
$VPATH <<
|
17
|
+
exclude = %w(c_interface.cpp Rwrapper.cpp RcppExports.cpp)
|
18
|
+
$srcs = Dir["{#{ext},#{isotree_src}}/*.{cc,cpp}"].reject { |f| exclude.include?(File.basename(f)) }
|
19
|
+
$INCFLAGS << " -I#{isotree_inc}"
|
20
|
+
$VPATH << isotree_src
|
21
21
|
|
22
22
|
create_makefile("isotree/ext")
|
data/lib/isotree/dataset.rb
CHANGED
@@ -32,7 +32,6 @@ module IsoTree
|
|
32
32
|
raise ArgumentError, "Array elements must be all hashes or arrays"
|
33
33
|
end
|
34
34
|
|
35
|
-
nrows = data.size
|
36
35
|
ncols = data.first ? data.first.size : 0
|
37
36
|
if data.any? { |r| r.size != ncols }
|
38
37
|
raise ArgumentError, "All rows must have the same number of columns"
|