isotree 0.1.5 → 0.2.2
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/CHANGELOG.md +13 -0
- data/README.md +9 -9
- data/ext/isotree/ext.cpp +86 -64
- data/ext/isotree/extconf.rb +1 -1
- data/lib/isotree/dataset.rb +0 -1
- data/lib/isotree/isolation_forest.rb +4 -0
- data/lib/isotree/version.rb +1 -1
- metadata +7 -7
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 1876c50ef4d9bbd7fc7898c222b9f10b8d287a38cf9d37af53e9841f63494299
|
4
|
+
data.tar.gz: ea7b60ae9683498df1910fb3f4774ce8c94daf9fe2a6e23ffd87a9d488bcc5ce
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 3d0f6d95cac8b7dd457512c0ce41c3ae286cf8f344ccc8a47dee1c00104657b3d2d9c97be1c1211fcb253065ba7fcf3d3b955a89dd9bac8b2b6e5e35516c7b7d
|
7
|
+
data.tar.gz: 476d7c8ffe5c252ba94ecc7a68e59fc3afbbb2a732fd9e3127e032e543a74957fcdef6173b6225dfee7370dbb86625b61b02d16a68cc7257be8f7cbdae87a581
|
data/CHANGELOG.md
CHANGED
@@ -1,3 +1,16 @@
|
|
1
|
+
## 0.2.2 (2022-06-12)
|
2
|
+
|
3
|
+
- Fixed segfault when data is smaller than sample size
|
4
|
+
|
5
|
+
## 0.2.1 (2021-05-23)
|
6
|
+
|
7
|
+
- Improved performance
|
8
|
+
|
9
|
+
## 0.2.0 (2021-05-17)
|
10
|
+
|
11
|
+
- Updated to Rice 4
|
12
|
+
- Dropped support for Ruby < 2.6
|
13
|
+
|
1
14
|
## 0.1.5 (2021-03-14)
|
2
15
|
|
3
16
|
- Updated Isotree to 0.1.25
|
data/README.md
CHANGED
@@ -1,19 +1,19 @@
|
|
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
19
|
## Getting Started
|
@@ -147,22 +147,22 @@ model.predict(data, output: "avg_depth")
|
|
147
147
|
|
148
148
|
## History
|
149
149
|
|
150
|
-
View the [changelog](https://github.com/ankane/isotree/blob/master/CHANGELOG.md)
|
150
|
+
View the [changelog](https://github.com/ankane/isotree-ruby/blob/master/CHANGELOG.md)
|
151
151
|
|
152
152
|
## Contributing
|
153
153
|
|
154
154
|
Everyone is encouraged to help improve this project. Here are a few ways you can help:
|
155
155
|
|
156
|
-
- [Report bugs](https://github.com/ankane/isotree/issues)
|
157
|
-
- Fix bugs and [submit pull requests](https://github.com/ankane/isotree/pulls)
|
156
|
+
- [Report bugs](https://github.com/ankane/isotree-ruby/issues)
|
157
|
+
- Fix bugs and [submit pull requests](https://github.com/ankane/isotree-ruby/pulls)
|
158
158
|
- Write, clarify, or fix documentation
|
159
159
|
- Suggest or add new features
|
160
160
|
|
161
161
|
To get started with development:
|
162
162
|
|
163
163
|
```sh
|
164
|
-
git clone --recursive https://github.com/ankane/isotree.git
|
165
|
-
cd isotree
|
164
|
+
git clone --recursive https://github.com/ankane/isotree-ruby.git
|
165
|
+
cd isotree-ruby
|
166
166
|
bundle install
|
167
167
|
bundle exec rake compile
|
168
168
|
bundle exec rake test
|
data/ext/isotree/ext.cpp
CHANGED
@@ -2,12 +2,7 @@
|
|
2
2
|
#include <isotree.hpp>
|
3
3
|
|
4
4
|
// rice
|
5
|
-
#include <rice/
|
6
|
-
#include <rice/Hash.hpp>
|
7
|
-
#include <rice/Module.hpp>
|
8
|
-
#include <rice/Object.hpp>
|
9
|
-
#include <rice/String.hpp>
|
10
|
-
#include <rice/Symbol.hpp>
|
5
|
+
#include <rice/rice.hpp>
|
11
6
|
|
12
7
|
using Rice::Array;
|
13
8
|
using Rice::Hash;
|
@@ -18,62 +13,89 @@ using Rice::Symbol;
|
|
18
13
|
using Rice::define_class_under;
|
19
14
|
using Rice::define_module;
|
20
15
|
|
21
|
-
|
22
|
-
NewCategAction from_ruby<NewCategAction>(Object x)
|
16
|
+
namespace Rice::detail
|
23
17
|
{
|
24
|
-
|
25
|
-
|
26
|
-
|
27
|
-
|
28
|
-
|
29
|
-
|
18
|
+
template<>
|
19
|
+
class From_Ruby<NewCategAction>
|
20
|
+
{
|
21
|
+
public:
|
22
|
+
NewCategAction convert(VALUE x)
|
23
|
+
{
|
24
|
+
auto value = Object(x).to_s().str();
|
25
|
+
if (value == "weighted") return Weighted;
|
26
|
+
if (value == "smallest") return Smallest;
|
27
|
+
if (value == "random") return Random;
|
28
|
+
throw std::runtime_error("Unknown new categ action: " + value);
|
29
|
+
}
|
30
|
+
};
|
30
31
|
|
31
|
-
template<>
|
32
|
-
|
33
|
-
{
|
34
|
-
|
35
|
-
|
36
|
-
|
37
|
-
|
38
|
-
|
39
|
-
|
32
|
+
template<>
|
33
|
+
class From_Ruby<MissingAction>
|
34
|
+
{
|
35
|
+
public:
|
36
|
+
MissingAction convert(VALUE x)
|
37
|
+
{
|
38
|
+
auto value = Object(x).to_s().str();
|
39
|
+
if (value == "divide") return Divide;
|
40
|
+
if (value == "impute") return Impute;
|
41
|
+
if (value == "fail") return Fail;
|
42
|
+
throw std::runtime_error("Unknown missing action: " + value);
|
43
|
+
}
|
44
|
+
};
|
40
45
|
|
41
|
-
template<>
|
42
|
-
|
43
|
-
{
|
44
|
-
|
45
|
-
|
46
|
-
|
47
|
-
|
48
|
-
|
46
|
+
template<>
|
47
|
+
class From_Ruby<CategSplit>
|
48
|
+
{
|
49
|
+
public:
|
50
|
+
CategSplit convert(VALUE x)
|
51
|
+
{
|
52
|
+
auto value = Object(x).to_s().str();
|
53
|
+
if (value == "subset") return SubSet;
|
54
|
+
if (value == "single_categ") return SingleCateg;
|
55
|
+
throw std::runtime_error("Unknown categ split: " + value);
|
56
|
+
}
|
57
|
+
};
|
49
58
|
|
50
|
-
template<>
|
51
|
-
|
52
|
-
{
|
53
|
-
|
54
|
-
|
55
|
-
|
56
|
-
|
57
|
-
|
59
|
+
template<>
|
60
|
+
class From_Ruby<CoefType>
|
61
|
+
{
|
62
|
+
public:
|
63
|
+
CoefType convert(VALUE x)
|
64
|
+
{
|
65
|
+
auto value = Object(x).to_s().str();
|
66
|
+
if (value == "uniform") return Uniform;
|
67
|
+
if (value == "normal") return Normal;
|
68
|
+
throw std::runtime_error("Unknown coef type: " + value);
|
69
|
+
}
|
70
|
+
};
|
58
71
|
|
59
|
-
template<>
|
60
|
-
|
61
|
-
{
|
62
|
-
|
63
|
-
|
64
|
-
|
65
|
-
|
66
|
-
|
67
|
-
|
72
|
+
template<>
|
73
|
+
class From_Ruby<UseDepthImp>
|
74
|
+
{
|
75
|
+
public:
|
76
|
+
UseDepthImp convert(VALUE x)
|
77
|
+
{
|
78
|
+
auto value = Object(x).to_s().str();
|
79
|
+
if (value == "lower") return Lower;
|
80
|
+
if (value == "higher") return Higher;
|
81
|
+
if (value == "same") return Same;
|
82
|
+
throw std::runtime_error("Unknown depth imp: " + value);
|
83
|
+
}
|
84
|
+
};
|
68
85
|
|
69
|
-
template<>
|
70
|
-
|
71
|
-
{
|
72
|
-
|
73
|
-
|
74
|
-
|
75
|
-
|
76
|
-
|
86
|
+
template<>
|
87
|
+
class From_Ruby<WeighImpRows>
|
88
|
+
{
|
89
|
+
public:
|
90
|
+
WeighImpRows convert(VALUE x)
|
91
|
+
{
|
92
|
+
auto value = Object(x).to_s().str();
|
93
|
+
if (value == "inverse") return Inverse;
|
94
|
+
if (value == "prop") return Prop;
|
95
|
+
if (value == "flat") return Flat;
|
96
|
+
throw std::runtime_error("Unknown weight imp rows: " + value);
|
97
|
+
}
|
98
|
+
};
|
77
99
|
}
|
78
100
|
|
79
101
|
extern "C"
|
@@ -85,9 +107,9 @@ void Init_ext()
|
|
85
107
|
define_class_under<ExtIsoForest>(rb_mExt, "ExtIsoForest");
|
86
108
|
|
87
109
|
rb_mExt
|
88
|
-
.
|
110
|
+
.define_singleton_function(
|
89
111
|
"fit_iforest",
|
90
|
-
|
112
|
+
[](Hash options) {
|
91
113
|
// model
|
92
114
|
ExtIsoForest iso;
|
93
115
|
|
@@ -204,9 +226,9 @@ void Init_ext()
|
|
204
226
|
|
205
227
|
return iso;
|
206
228
|
})
|
207
|
-
.
|
229
|
+
.define_singleton_function(
|
208
230
|
"predict_iforest",
|
209
|
-
|
231
|
+
[](ExtIsoForest& iso, Hash options) {
|
210
232
|
// data
|
211
233
|
size_t nrows = options.get<size_t, Symbol>("nrows");
|
212
234
|
size_t ncols_numeric = options.get<size_t, Symbol>("ncols_numeric");
|
@@ -260,9 +282,9 @@ void Init_ext()
|
|
260
282
|
}
|
261
283
|
return ret;
|
262
284
|
})
|
263
|
-
.
|
285
|
+
.define_singleton_function(
|
264
286
|
"serialize_ext_isoforest",
|
265
|
-
|
287
|
+
[](ExtIsoForest& iso, String path) {
|
266
288
|
#ifdef _MSC_VER
|
267
289
|
// TODO convert to wchar_t
|
268
290
|
throw std::runtime_error("Not supported on Windows yet");
|
@@ -270,9 +292,9 @@ void Init_ext()
|
|
270
292
|
serialize_ext_isoforest(iso, path.c_str());
|
271
293
|
#endif
|
272
294
|
})
|
273
|
-
.
|
295
|
+
.define_singleton_function(
|
274
296
|
"deserialize_ext_isoforest",
|
275
|
-
|
297
|
+
[](String path) {
|
276
298
|
ExtIsoForest iso;
|
277
299
|
|
278
300
|
#ifdef _MSC_VER
|
data/ext/isotree/extconf.rb
CHANGED
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"
|
@@ -44,6 +44,10 @@ module IsoTree
|
|
44
44
|
prep_fit(x)
|
45
45
|
options = data_options(x).merge(fit_options)
|
46
46
|
options[:sample_size] ||= options[:nrows]
|
47
|
+
|
48
|
+
# prevent segfault
|
49
|
+
options[:sample_size] = options[:nrows] if options[:sample_size] > options[:nrows]
|
50
|
+
|
47
51
|
@ext_iso_forest = Ext.fit_iforest(options)
|
48
52
|
end
|
49
53
|
|
data/lib/isotree/version.rb
CHANGED
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: isotree
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.2.2
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Andrew Kane
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date:
|
11
|
+
date: 2022-06-13 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: rice
|
@@ -16,14 +16,14 @@ dependencies:
|
|
16
16
|
requirements:
|
17
17
|
- - ">="
|
18
18
|
- !ruby/object:Gem::Version
|
19
|
-
version:
|
19
|
+
version: 4.0.2
|
20
20
|
type: :runtime
|
21
21
|
prerelease: false
|
22
22
|
version_requirements: !ruby/object:Gem::Requirement
|
23
23
|
requirements:
|
24
24
|
- - ">="
|
25
25
|
- !ruby/object:Gem::Version
|
26
|
-
version:
|
26
|
+
version: 4.0.2
|
27
27
|
description:
|
28
28
|
email: andrew@ankane.org
|
29
29
|
executables: []
|
@@ -149,7 +149,7 @@ files:
|
|
149
149
|
- vendor/isotree/src/serialize.cpp
|
150
150
|
- vendor/isotree/src/sql.cpp
|
151
151
|
- vendor/isotree/src/utils.cpp
|
152
|
-
homepage: https://github.com/ankane/isotree
|
152
|
+
homepage: https://github.com/ankane/isotree-ruby
|
153
153
|
licenses:
|
154
154
|
- BSD-2-Clause
|
155
155
|
metadata: {}
|
@@ -161,14 +161,14 @@ required_ruby_version: !ruby/object:Gem::Requirement
|
|
161
161
|
requirements:
|
162
162
|
- - ">="
|
163
163
|
- !ruby/object:Gem::Version
|
164
|
-
version: '2.
|
164
|
+
version: '2.6'
|
165
165
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
166
166
|
requirements:
|
167
167
|
- - ">="
|
168
168
|
- !ruby/object:Gem::Version
|
169
169
|
version: '0'
|
170
170
|
requirements: []
|
171
|
-
rubygems_version: 3.
|
171
|
+
rubygems_version: 3.3.7
|
172
172
|
signing_key:
|
173
173
|
specification_version: 4
|
174
174
|
summary: Outlier/anomaly detection for Ruby using Isolation Forest
|