disco 0.3.0 → 0.3.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 815bc7de802959be7093d9e0478d83a0cf49a522e72a2df928de86223799d83d
-  data.tar.gz: cbfacf86f1e0507abe4df07b45f20bc3d06d682617c482419a05935186a61c15
+  metadata.gz: 645a5f169c78e36ee6394a71ba61ac611cb333176adff84812c8a25549e2ea28
+  data.tar.gz: 68caa44554bff09a39a68522ad5c8008164840186c08e0fdbad8f9e465855c89
 SHA512:
-  metadata.gz: d0f3285b53cb8fe7e7d5ef30a970c632c52112c6b0503b8c81155f6cdb37583f036107b052c37019671355d0838512f904a61aeff5b69b7f6f8a2c1f4fabe785
-  data.tar.gz: f1b9c5759d77c1f497a0ac09ccf455beda29417024c4cd8ba6c0f8fcbac3347ab233c9e8c558a75382ef3b41495b5b693495ab0533c3a084a416c1f75a38313b
+  metadata.gz: 104a016c693c0256cae13d4545df4112538a1f7a66c8790c38a1b434f144c8d2fb173d2428bbc9168e2581e0e9399d761083500fca69919c07f86b2f1e6582ee
+  data.tar.gz: 3d06f45fdcf63ea26fa48c18ec5304d22f3306da5bb3fa0a2bcd107455002dbfda56e0df22f61270c12374cb693ad6da2d747bd363c0ec001048f23690b3efe1

data/CHANGELOG.md

@@ -1,3 +1,11 @@
+## 0.3.2 (2022-09-26)
+
+- Fixed issue when `fit` is called multiple times
+
+## 0.3.1 (2022-07-10)
+
+- Added support for JSON serialization
+
 ## 0.3.0 (2022-03-22)
 
 - Changed `item_id` to `user_id` for `similar_users`

data/README.md

@@ -183,17 +183,17 @@ For Rails < 6, speed up inserts by adding [activerecord-import](https://github.c
 If you’d prefer to perform recommendations on-the-fly, store the recommender
 
 ```ruby
-bin = Marshal.dump(recommender)
-File.binwrite("recommender.bin", bin)
+json = recommender.to_json
+File.write("recommender.json", json)
 ```
 
-> You can save it to a file, database, or any other storage system
+The serialized recommender includes user activity from the training data (to avoid recommending previously rated items), so be sure to protect it. You can save it to a file, database, or any other storage system, or use a tool like [Trove](https://github.com/ankane/trove). Also, user and item IDs should be integers or strings for this.
 
 Load a recommender
 
 ```ruby
-bin = File.binread("recommender.bin")
-recommender = Marshal.load(bin)
+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).
@@ -223,7 +223,7 @@ recommender.fit(data, validation_set: validation_set)
 
 ## Cold Start
 
-Collaborative filtering suffers from the [cold start problem](https://www.yuspify.com/blog/cold-start-problem-recommender-systems/). It’s unable to make good recommendations without data on a user or item, which is problematic for new users and items.
+Collaborative filtering suffers from the [cold start problem](https://en.wikipedia.org/wiki/Cold_start_(recommender_systems)). It’s unable to make good recommendations without data on a user or item, which is problematic for new users and items.
 
 ```ruby
 recommender.user_recs(new_user_id) # returns empty array

data/lib/disco/recommender.rb

@@ -36,6 +36,8 @@ module Disco
         end
       end
 
+      @user_map = {}
+      @item_map = {}
       @rated = Hash.new { |hash, key| hash[key] = {} }
       input = []
       train_set.each do |v|
@@ -56,6 +58,9 @@ module Disco
       # TODO improve performance
       unless @implicit
         @min_rating, @max_rating = train_set.minmax_by { |o| o[:rating] }.map { |o| o[:rating] }
+      else
+        @min_rating = nil
+        @max_rating = nil
       end
 
       if @top_items
@@ -255,6 +260,46 @@ module Disco
       to_s # for now
     end
 
+    def to_json
+      require "base64"
+      require "json"
+
+      obj = {
+        implicit: @implicit,
+        user_ids: @user_map.keys,
+        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),
+        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
+
+      JSON.generate(obj)
+    end
+
+    def self.load_json(json)
+      require "json"
+
+      obj = JSON.parse(json)
+
+      recommender = new
+      recommender.send(:json_load, obj)
+      recommender
+    end
+
     private
 
     # factors should already be normalized for similar users/items
@@ -434,5 +479,31 @@ module Disco
         @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])
+      @epochs = obj["epochs"].to_i
+      @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
   end
 end

data/lib/disco/version.rb

@@ -1,3 +1,3 @@
 module Disco
-  VERSION = "0.3.0"
+  VERSION = "0.3.2"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: disco
 version: !ruby/object:Gem::Version
-  version: 0.3.0
+  version: 0.3.2
 platform: ruby
 authors:
 - Andrew Kane
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2022-03-22 00:00:00.000000000 Z
+date: 2022-09-27 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: libmf