rumale 0.17.2 → 0.17.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: '09585216da740231269c5675c48a8fa2ee3a8aba3f5c5b7d671429d113aaa4ba'
-  data.tar.gz: 66eb473c718f6a03938db19df06694373c781e098d68e2f2c20162865dc4f9f8
+  metadata.gz: 68b01301c9e7b9aa9d98f0a252e87fc0c5e5e888379e347660a76a63ae7f86a4
+  data.tar.gz: dd464110ff410705a20fa2446c884ed039b9f0ea3febfc4cd12ef8d6b542b736
 SHA512:
-  metadata.gz: d68eaa297116c4b834cbf2745355d07e4e4b0e50b170c631c417f623d7a0e75a515389903b6e2cb6f22355f9cf5eded4968eac5c7f216f5a98698bb5283c2e00
-  data.tar.gz: ddb3be08dc88cc99f5c7086e8bea83496f2644316d382f052a954ce6d1056bc2aabfbd2664ff572a55fdb1017a9bbb0d790d4d83b3788b781d133a97d26bd92e
+  metadata.gz: d95cf5140e5846431b812867a64927f51ede6f6a925ffdc3a43f3ae1add1ce33756ad6481ca7645edeed56084fe0f8d294f5032364ff664cae19e9edcdaac57e
+  data.tar.gz: 620bd2099ddd5ce14ff9525062938740835fe9714f1c42023f7782e963a96b423bba4921e35d134877aada0d05189d5213b90e5556b50799dadfebdeeaf59eba

data/CHANGELOG.md

@@ -1,3 +1,7 @@
+# 0.17.3
+- Add pipeline class for [FeatureUnion](https://yoshoku.github.io/rumale/doc/Rumale/Pipeline/FeatureUnion.html).
+- Fix to use mmh3 gem for generating hash value on [FeatureHasher](https://yoshoku.github.io/rumale/doc/Rumale/FeatureExtraction/FeatureHasher.html).
+
 # 0.17.2
 - Add transformer class for kernel approximation with [Nystroem](https://yoshoku.github.io/rumale/doc/Rumale/KernelApproximation/Nystroem.html) method.
 - Delete array validation on [Pipeline](https://yoshoku.github.io/rumale/doc/Rumale/Pipeline/Pipeline.html) class considering that array of hash is given to HashVectorizer.

data/LICENSE.txt

@@ -1,4 +1,4 @@
-Copyright (c) 2017-2019 Atsushi Tatsuma
+Copyright (c) 2017-2020 Atsushi Tatsuma
 All rights reserved.
 
 Redistribution and use in source and binary forms, with or without

data/lib/rumale.rb

@@ -25,6 +25,7 @@ require 'rumale/optimizer/adam'
 require 'rumale/optimizer/nadam'
 require 'rumale/optimizer/yellow_fin'
 require 'rumale/pipeline/pipeline'
+require 'rumale/pipeline/feature_union'
 require 'rumale/kernel_approximation/rbf'
 require 'rumale/kernel_approximation/nystroem'
 require 'rumale/linear_model/base_linear_model'

data/lib/rumale/feature_extraction/feature_hasher.rb

@@ -1,5 +1,6 @@
 # frozen_string_literal: true
 
+require 'mmh3'
 require 'rumale/base/base_estimator'
 require 'rumale/base/transformer'
 
@@ -72,7 +73,7 @@ module Rumale
             val = v.is_a?(String) ? 1 : v
             next if val.zero?
 
-            h = murmur_hash(k.to_s)
+            h = Mmh3.hash32(k)
             fid = h.abs % n_features
             val *= h >= 0 ? 1 : -1 if alternate_sign?
             z[i, fid] = val
@@ -91,59 +92,6 @@ module Rumale
       def alternate_sign?
         @params[:alternate_sign]
       end
-
-      # MurmurHash3_32
-      # References:
-      # - https://en.wikipedia.org/wiki/MurmurHash
-      # - https://github.com/aappleby/smhasher
-      def murmur_hash(key_str, seed = 0)
-        keyb = key_str.bytes
-        key_len = keyb.size
-        n_blocks = key_len / 4
-
-        h = seed
-        (0...n_blocks * 4).step(4) do |bstart|
-          k = keyb[bstart + 3] << 24 | keyb[bstart + 2] << 16 | keyb[bstart + 1] << 8 | keyb[bstart + 0]
-          h ^= murmur_scramble(k)
-          h = murmur_rotl(h, 13)
-          h = (h * 5 + 0xe6546b64) & 0xFFFFFFFF
-        end
-
-        tail_id = n_blocks * 4
-        tail_sz = key_len & 3
-
-        k = 0
-        k ^= keyb[tail_id + 2] << 16 if tail_sz >= 3
-        k ^= keyb[tail_id + 1] << 8 if tail_sz >= 2
-        k ^= keyb[tail_id + 0] if tail_sz >= 1
-        h ^= murmur_scramble(k) if tail_sz.positive?
-
-        h = murmur_fmix(h ^ key_len)
-
-        if (h & 0x80000000).zero?
-          h
-        else
-          -((h ^ 0xFFFFFFFF) + 1)
-        end
-      end
-
-      def murmur_rotl(x, r)
-        (x << r | x >> (32 - r)) & 0xFFFFFFFF
-      end
-
-      def murmur_scramble(k)
-        k = (k * 0xcc9e2d51) & 0xFFFFFFFF
-        k = murmur_rotl(k, 15)
-        (k * 0x1b873593) & 0xFFFFFFFF
-      end
-
-      def murmur_fmix(h)
-        h ^= h >> 16
-        h = (h * 0x85ebca6b) & 0xFFFFFFFF
-        h ^= h >> 13
-        h = (h * 0xc2b2ae35) & 0xFFFFFFFF
-        h ^ (h >> 16)
-      end
     end
   end
 end

data/lib/rumale/pipeline/feature_union.rb

@@ -0,0 +1,69 @@
+# frozen_string_literal: true
+
+require 'rumale/validation'
+require 'rumale/base/base_estimator'
+
+module Rumale
+  module Pipeline
+    # FeatureUnion is a class that implements the function concatenating the multi-transformer results.
+    #
+    # @example
+    #   fu = Rumale::Pipeline::FeatureUnion.new(
+    #     transformers: {
+    #       'rbf': Rumale::KernelApproximation::RBF.new(gamma: 1.0, n_components: 96, random_seed: 1),
+    #       'pca': Rumale::Decomposition::PCA.new(n_components: 32)
+    #     }
+    #   )
+    #   fu.fit(training_samples, traininig_labels)
+    #   results = fu.predict(testing_samples)
+    #
+    #   # > p results.shape[1]
+    #   # > 128
+    #
+    class FeatureUnion
+      include Base::BaseEstimator
+      include Validation
+
+      # Return the transformers
+      # @return [Hash]
+      attr_reader :transformers
+
+      # Create a new feature union.
+      #
+      # @param transformers [Hash] List of transformers.  The order of transforms follows the insertion order of hash keys.
+      def initialize(transformers:)
+        check_params_type(Hash, transformers: transformers)
+        @params = {}
+        @transformers = transformers
+      end
+
+      # Fit the model with given training data.
+      #
+      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The training data to be used for fitting the transformers.
+      # @param y [Numo::NArray/Nil] (shape: [n_samples, n_outputs]) The target values or labels to be used for fitting the transformers.
+      # @return [FeatureUnion] The learned feature union itself.
+      def fit(x, y = nil)
+        @transformers.each { |_k, t| t.fit(x, y) }
+        self
+      end
+
+      # Fit the model with training data, and then transform them with the learned model.
+      #
+      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The training data to be used for fitting the transformers.
+      # @param y [Numo::NArray/Nil] (shape: [n_samples, n_outputs]) The target values or labels to be used for fitting the transformers.
+      # @return [Numo::DFloat] (shape: [n_samples, sum_n_components]) The transformed and concatenated data.
+      def fit_transform(x, y = nil)
+        fit(x, y).transform(x)
+      end
+
+      # Transform the given data with the learned model.
+      #
+      # @param x [Numo::DFloat] (shape: [n_samples, n_features]) The data to be transformed with the learned transformers.
+      # @return [Numo::DFloat] (shape: [n_samples, sum_n_components]) The transformed and concatenated data.
+      def transform(x)
+        z = @transformers.values.map { |t| t.transform(x) }
+        Numo::NArray.hstack(z)
+      end
+    end
+  end
+end

data/lib/rumale/version.rb

@@ -3,5 +3,5 @@
 # Rumale is a machine learning library in Ruby.
 module Rumale
   # The version of Rumale you are using.
-  VERSION = '0.17.2'
+  VERSION = '0.17.3'
 end

data/rumale.gemspec

@@ -45,6 +45,7 @@ Gem::Specification.new do |spec|
   spec.required_ruby_version = '>= 2.3'
 
   spec.add_runtime_dependency 'numo-narray', '>= 0.9.1'
+  spec.add_runtime_dependency 'mmh3', '~> 0.1'
 
   spec.add_development_dependency 'bundler', '~> 2.0'
   spec.add_development_dependency 'coveralls', '~> 0.8'

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: rumale
 version: !ruby/object:Gem::Version
-  version: 0.17.2
+  version: 0.17.3
 platform: ruby
 authors:
 - yoshoku
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2020-02-01 00:00:00.000000000 Z
+date: 2020-02-16 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: numo-narray
@@ -24,6 +24,20 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: 0.9.1
+- !ruby/object:Gem::Dependency
+  name: mmh3
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.1'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.1'
 - !ruby/object:Gem::Dependency
   name: bundler
   requirement: !ruby/object:Gem::Requirement
@@ -247,6 +261,7 @@ files:
 - lib/rumale/optimizer/sgd.rb
 - lib/rumale/optimizer/yellow_fin.rb
 - lib/rumale/pairwise_metric.rb
+- lib/rumale/pipeline/feature_union.rb
 - lib/rumale/pipeline/pipeline.rb
 - lib/rumale/polynomial_model/base_factorization_machine.rb
 - lib/rumale/polynomial_model/factorization_machine_classifier.rb