disco 0.4.2 → 0.5.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: bbc2c36a98486f496c7c5aed996b3250def9f87ce444dc48e4f8c9164db9e630
-  data.tar.gz: a862bf6d66484f5dac154586dea0a89d85a4873644ff00f4420ac3dfc0c9a852
+  metadata.gz: b1d7b56a9c40088874bbd79ff7fa5bf8783a4406a9e5dadf1dddb04303ca7fee
+  data.tar.gz: 0d843da83fc246b5da2aa097eba3534d729b51d9b03c368226b884fe33e61795
 SHA512:
-  metadata.gz: 948d564359a61c1ad356c0806e34c57d6dcae354cc55cf1bff4bce5f40ee94b37edd3c5d8fc35e36cb0aeae59ee467acb561c0074bbb7fb8da929b7e548bcf1f
-  data.tar.gz: f3d98a62dd540957343a29c01624586e853a0f400f8105d2ae67d34e85e408b652befc0d702720e4d7e33852ac738b2a8e276acb6ac143195620386b07e99084
+  metadata.gz: 49341b30e2ffa7348c19af2c0073f8f9e15afe3dcd856922fb5ae3fd3cd6e5ab555731c38bf3678f5f4efb064ecfce994d24b6238aa93fbc62e4621d7de036ab
+  data.tar.gz: 9bb387230927cf55e94c3614c4a68881031206c9ee2dee2d48c06f6053134cdff0af4c4d24eba825acf3429394556368378bd51860f4dfcddf0dd1742309794f

data/CHANGELOG.md

@@ -1,3 +1,13 @@
+## 0.5.1 (2024-12-29)
+
+- Removed dependency on `base64` gem for serialization
+
+## 0.5.0 (2024-10-22)
+
+- Changed dataset directory to match XDG Base Directory Specification
+- Dropped support for marshal serialization
+- Dropped support for Ruby < 3.1 and Rails < 7
+
 ## 0.4.2 (2024-06-24)
 
 - Removed dependency on `csv` gem for `load_movielens`

data/README.md

@@ -194,7 +194,7 @@ json = File.read("recommender.json")
 recommender = Disco::Recommender.load_json(json)
 ```
 
-Alternatively, you can store only the factors and use a library like [Neighbor](https://github.com/ankane/neighbor). See the [examples](https://github.com/ankane/neighbor/tree/master/examples).
+Alternatively, you can store only the factors and use a library like [Neighbor](https://github.com/ankane/neighbor). See the [examples](https://github.com/ankane/neighbor/tree/master/examples/disco).
 
 ## Algorithms
 

data/lib/disco/data.rb

@@ -33,9 +33,8 @@ module Disco
       require "net/http"
       require "tmpdir"
 
-      # TODO handle this better
-      raise "No HOME" unless ENV["HOME"]
-      dest = "#{ENV["HOME"]}/.disco/#{fname}"
+      cache_home = ENV["XDG_CACHE_HOME"] || "#{ENV.fetch("HOME")}/.cache"
+      dest = "#{cache_home}/disco/#{fname}"
       FileUtils.mkdir_p(File.dirname(dest))
 
       return dest if File.exist?(dest)

data/lib/disco/model.rb

@@ -1,8 +1,8 @@
 module Disco
   module Model
     def has_recommended(name, class_name: nil)
-      if ActiveRecord::VERSION::MAJOR < 6
-        raise Disco::Error, "Requires Active Record 6+"
+      if ActiveRecord::VERSION::MAJOR < 7
+        raise Disco::Error, "Requires Active Record 7+"
       end
 
       class_name ||= name.to_s.singularize.camelize

data/lib/disco/recommender.rb

@@ -64,8 +64,8 @@ module Disco
       end
 
       if @top_items
-        @item_count = [0] * @item_map.size
-        @item_sum = [0.0] * @item_map.size
+        @item_count = Array.new(@item_map.size, 0)
+        @item_sum = Array.new(@item_map.size, 0.0)
         train_set.each do |v|
           i = @item_map[v[:item_id]]
           @item_count[i] += 1
@@ -261,7 +261,6 @@ module Disco
     end
 
     def to_json
-      require "base64"
       require "json"
 
       obj = {
@@ -270,8 +269,8 @@ module Disco
         item_ids: @item_map.keys,
         rated: @user_map.map { |_, u| (@rated[u] || {}).keys },
         global_mean: @global_mean,
-        user_factors: Base64.strict_encode64(@user_factors.to_binary),
-        item_factors: Base64.strict_encode64(@item_factors.to_binary),
+        user_factors: [@user_factors.to_binary].pack("m0"),
+        item_factors: [@item_factors.to_binary].pack("m0"),
         factors: @factors,
         epochs: @epochs,
         verbose: @verbose
@@ -431,72 +430,15 @@ module Disco
       end
     end
 
-    def marshal_dump
-      warn "[disco] Marshal serialization is deprecated - use JSON instead"
-
-      obj = {
-        implicit: @implicit,
-        user_map: @user_map,
-        item_map: @item_map,
-        rated: @rated,
-        global_mean: @global_mean,
-        user_factors: @user_factors,
-        item_factors: @item_factors,
-        factors: @factors,
-        epochs: @epochs,
-        verbose: @verbose
-      }
-
-      unless @implicit
-        obj[:min_rating] = @min_rating
-        obj[:max_rating] = @max_rating
-      end
-
-      if @top_items
-        obj[:item_count] = @item_count
-        obj[:item_sum] = @item_sum
-      end
-
-      obj
-    end
-
-    def marshal_load(obj)
-      warn "[disco] Marshal serialization is deprecated - use JSON instead"
-
-      @implicit = obj[:implicit]
-      @user_map = obj[:user_map]
-      @item_map = obj[:item_map]
-      @rated = obj[:rated]
-      @global_mean = obj[:global_mean]
-      @user_factors = obj[:user_factors]
-      @item_factors = obj[:item_factors]
-      @factors = obj[:factors]
-      @epochs = obj[:epochs]
-      @verbose = obj[:verbose]
-
-      unless @implicit
-        @min_rating = obj[:min_rating]
-        @max_rating = obj[:max_rating]
-      end
-
-      @top_items = obj.key?(:item_count)
-      if @top_items
-        @item_count = obj[:item_count]
-        @item_sum = obj[:item_sum]
-      end
-    end
-
     def json_load(obj)
-      require "base64"
-
       @implicit = obj["implicit"]
       @user_map = obj["user_ids"].map.with_index.to_h
       @item_map = obj["item_ids"].map.with_index.to_h
       @rated = obj["rated"].map.with_index.to_h { |r, i| [i, r.to_h { |v| [v, true] }] }
       @global_mean = obj["global_mean"].to_f
       @factors = obj["factors"].to_i
-      @user_factors = Numo::SFloat.from_binary(Base64.strict_decode64(obj["user_factors"]), [@user_map.size, @factors])
-      @item_factors = Numo::SFloat.from_binary(Base64.strict_decode64(obj["item_factors"]), [@item_map.size, @factors])
+      @user_factors = Numo::SFloat.from_binary(obj["user_factors"].unpack1("m0"), [@user_map.size, @factors])
+      @item_factors = Numo::SFloat.from_binary(obj["item_factors"].unpack1("m0"), [@item_map.size, @factors])
       @epochs = obj["epochs"].to_i
       @verbose = obj["verbose"]
 

data/lib/disco/version.rb

@@ -1,3 +1,3 @@
 module Disco
-  VERSION = "0.4.2"
+  VERSION = "0.5.1"
 end

metadata

@@ -1,14 +1,13 @@
 --- !ruby/object:Gem::Specification
 name: disco
 version: !ruby/object:Gem::Version
-  version: 0.4.2
+  version: 0.5.1
 platform: ruby
 authors:
 - Andrew Kane
-autorequire:
 bindir: bin
 cert_chain: []
-date: 2024-06-24 00:00:00.000000000 Z
+date: 2024-12-30 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: libmf
@@ -16,29 +15,28 @@ dependencies:
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: '0.2'
+        version: '0.4'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: '0.2'
+        version: '0.4'
 - !ruby/object:Gem::Dependency
   name: numo-narray
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: '0'
+        version: 0.9.2
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: '0'
-description:
+        version: 0.9.2
 email: andrew@ankane.org
 executables: []
 extensions: []
@@ -61,7 +59,6 @@ homepage: https://github.com/ankane/disco
 licenses:
 - MIT
 metadata: {}
-post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -69,15 +66,14 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '2.7'
+      version: '3.1'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.5.11
-signing_key:
+rubygems_version: 3.6.2
 specification_version: 4
 summary: Recommendations for Ruby and Rails using collaborative filtering
 test_files: []