rumale 0.19.1 → 0.19.2
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/CHANGELOG.md +5 -0
- data/lib/rumale.rb +2 -0
- data/lib/rumale/feature_extraction/tfidf_transformer.rb +113 -0
- data/lib/rumale/preprocessing/l1_normalizer.rb +62 -0
- data/lib/rumale/preprocessing/l2_normalizer.rb +2 -1
- data/lib/rumale/version.rb +1 -1
- metadata +4 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 1bff2e1e6182aa954be00ed107ed1bd81220298f89514b4b31304f8890ff27c4
|
4
|
+
data.tar.gz: '09b185f468baf9dbec6280fa6c06984c95919308f1d2247277bf30348ed392bc'
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 6d8f1fcaffcd6714c6156fc615d87e6b6950e82ab40fc7434cfc5a014d6c08eb0170ee7c45d8fed978c2a52f839b1ce647fd6e088cbab2ea45e517b34c88407a
|
7
|
+
data.tar.gz: b255ae4c24cdc91ebad59f79ee5a58c5d2a5ffa79bda0ac221e3a33bd824d2fd94e5cd83f3a06e54a2dc537a074276cea5a71651deeee2a304d23e963ff92c9d
|
data/CHANGELOG.md
CHANGED
@@ -1,3 +1,8 @@
|
|
1
|
+
# 0.19.2
|
2
|
+
- Fix L2Normalizer to avoid zero divide.
|
3
|
+
- Add preprocssing class for [L1Normalizer](https://yoshoku.github.io/rumale/doc/Rumale/Preprocessing/L1Normalizer.html).
|
4
|
+
- Add transformer class for [TfidfTransformer](https://yoshoku.github.io/rumale/doc/Rumale/FeatureExtraction/TfidfTransformer.html).
|
5
|
+
|
1
6
|
# 0.19.1
|
2
7
|
- Add cluster analysis class for [mini-batch K-Means](https://yoshoku.github.io/rumale/doc/Rumale/Clustering/MiniBatchKMeans.html).
|
3
8
|
- Fix some typos.
|
data/lib/rumale.rb
CHANGED
@@ -93,7 +93,9 @@ require 'rumale/neural_network/mlp_regressor'
|
|
93
93
|
require 'rumale/neural_network/mlp_classifier'
|
94
94
|
require 'rumale/feature_extraction/hash_vectorizer'
|
95
95
|
require 'rumale/feature_extraction/feature_hasher'
|
96
|
+
require 'rumale/feature_extraction/tfidf_transformer'
|
96
97
|
require 'rumale/preprocessing/l2_normalizer'
|
98
|
+
require 'rumale/preprocessing/l1_normalizer'
|
97
99
|
require 'rumale/preprocessing/min_max_scaler'
|
98
100
|
require 'rumale/preprocessing/max_abs_scaler'
|
99
101
|
require 'rumale/preprocessing/standard_scaler'
|
@@ -0,0 +1,113 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require 'rumale/base/base_estimator'
|
4
|
+
require 'rumale/base/transformer'
|
5
|
+
require 'rumale/preprocessing/l1_normalizer'
|
6
|
+
require 'rumale/preprocessing/l2_normalizer'
|
7
|
+
|
8
|
+
module Rumale
|
9
|
+
module FeatureExtraction
|
10
|
+
# Transform sample matrix with term frequecy (tf) to a normalized tf-idf (inverse document frequency) reprensentation.
|
11
|
+
#
|
12
|
+
# @example
|
13
|
+
# encoder = Rumale::FeatureExtraction::HashVectorizer.new
|
14
|
+
# x = encoder.fit_transform([
|
15
|
+
# { foo: 1, bar: 2 },
|
16
|
+
# { foo: 3, baz: 1 }
|
17
|
+
# ])
|
18
|
+
#
|
19
|
+
# # > pp x
|
20
|
+
# # Numo::DFloat#shape=[2,3]
|
21
|
+
# # [[2, 0, 1],
|
22
|
+
# # [0, 1, 3]]
|
23
|
+
#
|
24
|
+
# transformer = Rumale::FeatureExtraction::TfidfTransformer.new
|
25
|
+
# x_tfidf = transformer.fit_transform(x)
|
26
|
+
#
|
27
|
+
# # > pp x_tfidf
|
28
|
+
# # Numo::DFloat#shape=[2,3]
|
29
|
+
# # [[0.959056, 0, 0.283217],
|
30
|
+
# # [0, 0.491506, 0.870874]]
|
31
|
+
#
|
32
|
+
# *Reference*
|
33
|
+
# - Manning, C D., Raghavan, P., and Schutze, H., "Introduction to Information Retrieval," Cambridge University Press., 2008.
|
34
|
+
class TfidfTransformer
|
35
|
+
include Base::BaseEstimator
|
36
|
+
include Base::Transformer
|
37
|
+
|
38
|
+
# Return the vector consists of inverse document frequency.
|
39
|
+
# @return [Numo::DFloat] (shape: [n_features])
|
40
|
+
attr_reader :idf
|
41
|
+
|
42
|
+
# Create a new transfomer for converting tf vectors to tf-idf vectors.
|
43
|
+
#
|
44
|
+
# @param norm [String] The normalization method to be used ('l1', 'l2' and 'none').
|
45
|
+
# @param use_idf [Boolean] The flag indicating whether to use inverse document frequency weighting.
|
46
|
+
# @param smooth_idf [Boolean] The flag indicating whether to apply idf smoothing by log((n_samples + 1) / (df + 1)) + 1.
|
47
|
+
# @param sublinear_tf [Boolean] The flag indicating whether to perform subliner tf scaling by 1 + log(tf).
|
48
|
+
def initialize(norm: 'l2', use_idf: true, smooth_idf: false, sublinear_tf: false)
|
49
|
+
check_params_string(norm: norm)
|
50
|
+
check_params_boolean(use_idf: use_idf, smooth_idf: smooth_idf, sublinear_tf: sublinear_tf)
|
51
|
+
@params = {}
|
52
|
+
@params[:norm] = norm
|
53
|
+
@params[:use_idf] = use_idf
|
54
|
+
@params[:smooth_idf] = smooth_idf
|
55
|
+
@params[:sublinear_tf] = sublinear_tf
|
56
|
+
@idf = nil
|
57
|
+
end
|
58
|
+
|
59
|
+
# Calculate the inverse document frequency for weighting.
|
60
|
+
#
|
61
|
+
# @overload fit(x) -> TfidfTransformer
|
62
|
+
#
|
63
|
+
# @param x [Numo::DFloat] (shape: [n_samples, n_features]) The samples to calculate the idf values.
|
64
|
+
# @return [TfidfTransformer]
|
65
|
+
def fit(x, _y = nil)
|
66
|
+
return self unless @params[:use_idf]
|
67
|
+
|
68
|
+
x = check_convert_sample_array(x)
|
69
|
+
|
70
|
+
n_samples = x.shape[0]
|
71
|
+
df = x.class.cast(x.gt(0.0).count(0))
|
72
|
+
|
73
|
+
if @params[:smooth_idf]
|
74
|
+
df += 1
|
75
|
+
n_samples += 1
|
76
|
+
end
|
77
|
+
|
78
|
+
@idf = Numo::NMath.log(n_samples / df) + 1
|
79
|
+
|
80
|
+
self
|
81
|
+
end
|
82
|
+
|
83
|
+
# Calculate the idf values, and then transfrom samples to the tf-idf representation.
|
84
|
+
#
|
85
|
+
# @overload fit_transform(x) -> Numo::DFloat
|
86
|
+
#
|
87
|
+
# @param x [Numo::DFloat] (shape: [n_samples, n_features]) The samples to calculate idf and be transformed to tf-idf representation.
|
88
|
+
# @return [Numo::DFloat] The transformed samples.
|
89
|
+
def fit_transform(x, _y = nil)
|
90
|
+
fit(x).transform(x)
|
91
|
+
end
|
92
|
+
|
93
|
+
# Perform transforming the given samples to the tf-idf representation.
|
94
|
+
#
|
95
|
+
# @param x [Numo::DFloat] (shape: [n_samples, n_features]) The samples to be transformed.
|
96
|
+
# @return [Numo::DFloat] The transformed samples.
|
97
|
+
def transform(x)
|
98
|
+
x = check_convert_sample_array(x)
|
99
|
+
z = x.dup
|
100
|
+
|
101
|
+
z[z.ne(0)] = Numo::NMath.log(z[z.ne(0)]) + 1 if @params[:sublinear_tf]
|
102
|
+
z *= @idf if @params[:use_idf]
|
103
|
+
case @params[:norm]
|
104
|
+
when 'l2'
|
105
|
+
z = Rumale::Preprocessing::L2Normalizer.new.fit_transform(z)
|
106
|
+
when 'l1'
|
107
|
+
z = Rumale::Preprocessing::L1Normalizer.new.fit_transform(z)
|
108
|
+
end
|
109
|
+
z
|
110
|
+
end
|
111
|
+
end
|
112
|
+
end
|
113
|
+
end
|
@@ -0,0 +1,62 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require 'rumale/base/base_estimator'
|
4
|
+
require 'rumale/base/transformer'
|
5
|
+
|
6
|
+
module Rumale
|
7
|
+
module Preprocessing
|
8
|
+
# Normalize samples to unit L1-norm.
|
9
|
+
#
|
10
|
+
# @example
|
11
|
+
# normalizer = Rumale::Preprocessing::L1Normalizer.new
|
12
|
+
# new_samples = normalizer.fit_transform(samples)
|
13
|
+
class L1Normalizer
|
14
|
+
include Base::BaseEstimator
|
15
|
+
include Base::Transformer
|
16
|
+
|
17
|
+
# Return the vector consists of L1-norm for each sample.
|
18
|
+
# @return [Numo::DFloat] (shape: [n_samples])
|
19
|
+
attr_reader :norm_vec # :nodoc:
|
20
|
+
|
21
|
+
# Create a new normalizer for normaliing to L1-norm.
|
22
|
+
def initialize
|
23
|
+
@params = {}
|
24
|
+
@norm_vec = nil
|
25
|
+
end
|
26
|
+
|
27
|
+
# Calculate L1-norms of each sample.
|
28
|
+
#
|
29
|
+
# @overload fit(x) -> L1Normalizer
|
30
|
+
#
|
31
|
+
# @param x [Numo::DFloat] (shape: [n_samples, n_features]) The samples to calculate L1-norms.
|
32
|
+
# @return [L1Normalizer]
|
33
|
+
def fit(x, _y = nil)
|
34
|
+
x = check_convert_sample_array(x)
|
35
|
+
@norm_vec = x.abs.sum(1)
|
36
|
+
@norm_vec[@norm_vec.eq(0)] = 1
|
37
|
+
self
|
38
|
+
end
|
39
|
+
|
40
|
+
# Calculate L1-norms of each sample, and then normalize samples to L1-norm.
|
41
|
+
#
|
42
|
+
# @overload fit_transform(x) -> Numo::DFloat
|
43
|
+
#
|
44
|
+
# @param x [Numo::DFloat] (shape: [n_samples, n_features]) The samples to calculate L1-norms.
|
45
|
+
# @return [Numo::DFloat] The normalized samples.
|
46
|
+
def fit_transform(x, _y = nil)
|
47
|
+
x = check_convert_sample_array(x)
|
48
|
+
fit(x)
|
49
|
+
x / @norm_vec.expand_dims(1)
|
50
|
+
end
|
51
|
+
|
52
|
+
# Calculate L1-norms of each sample, and then normalize samples to L1-norm.
|
53
|
+
# This method calls the fit_transform method. This method exists for the Pipeline class.
|
54
|
+
#
|
55
|
+
# @param x [Numo::DFloat] (shape: [n_samples, n_features]) The samples to calculate L1-norms.
|
56
|
+
# @return [Numo::DFloat] The normalized samples.
|
57
|
+
def transform(x)
|
58
|
+
fit_transform(x)
|
59
|
+
end
|
60
|
+
end
|
61
|
+
end
|
62
|
+
end
|
@@ -34,6 +34,7 @@ module Rumale
|
|
34
34
|
def fit(x, _y = nil)
|
35
35
|
x = check_convert_sample_array(x)
|
36
36
|
@norm_vec = Numo::NMath.sqrt((x**2).sum(1))
|
37
|
+
@norm_vec[@norm_vec.eq(0)] = 1
|
37
38
|
self
|
38
39
|
end
|
39
40
|
|
@@ -46,7 +47,7 @@ module Rumale
|
|
46
47
|
def fit_transform(x, _y = nil)
|
47
48
|
x = check_convert_sample_array(x)
|
48
49
|
fit(x)
|
49
|
-
x / @norm_vec.
|
50
|
+
x / @norm_vec.expand_dims(1)
|
50
51
|
end
|
51
52
|
|
52
53
|
# Calculate L2-norms of each sample, and then normalize samples to unit L2-norm.
|
data/lib/rumale/version.rb
CHANGED
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: rumale
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.19.
|
4
|
+
version: 0.19.2
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- yoshoku
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date: 2020-06-
|
11
|
+
date: 2020-06-20 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: numo-narray
|
@@ -113,6 +113,7 @@ files:
|
|
113
113
|
- lib/rumale/evaluation_measure/silhouette_score.rb
|
114
114
|
- lib/rumale/feature_extraction/feature_hasher.rb
|
115
115
|
- lib/rumale/feature_extraction/hash_vectorizer.rb
|
116
|
+
- lib/rumale/feature_extraction/tfidf_transformer.rb
|
116
117
|
- lib/rumale/kernel_approximation/nystroem.rb
|
117
118
|
- lib/rumale/kernel_approximation/rbf.rb
|
118
119
|
- lib/rumale/kernel_machine/kernel_fda.rb
|
@@ -166,6 +167,7 @@ files:
|
|
166
167
|
- lib/rumale/polynomial_model/factorization_machine_classifier.rb
|
167
168
|
- lib/rumale/polynomial_model/factorization_machine_regressor.rb
|
168
169
|
- lib/rumale/preprocessing/bin_discretizer.rb
|
170
|
+
- lib/rumale/preprocessing/l1_normalizer.rb
|
169
171
|
- lib/rumale/preprocessing/l2_normalizer.rb
|
170
172
|
- lib/rumale/preprocessing/label_binarizer.rb
|
171
173
|
- lib/rumale/preprocessing/label_encoder.rb
|