disco 0.2.5 → 0.2.6

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 8fbecb858b316ed39a9cb726263e182561cba6df498e6253d88c79ebec5cab05
-  data.tar.gz: 42eb38a6e4e0b3fc5a9452deae5a48676ae9a53e78eeb6197718a0c94bd02b6b
+  metadata.gz: a7823dbe0e68967c39a59f8cdc2fe577f4366b492e0559487606b74a7de1cc84
+  data.tar.gz: ba40e46b203e424eccb811c6b042c9a283356c42585b7e00123b4bb2f232b1e2
 SHA512:
-  metadata.gz: d0250346d75fba75064a29578f6bfd39f09ecf712ba2e505b97a4952b5ff8b31af307eb1b912e9b25cc3dc28dee0d096bea44b47bb2ef268859bb4171f0ef8b2
-  data.tar.gz: 7b341328c12885efd0ffece4201036bb9457caee80a48a99ba110af9a81bcf832bbc1e8f8f5f14e7fddffef2dd3f4643837e0d569c997ab0c2d9ae85e12422f7
+  metadata.gz: ee43326933ac019b0bae631631ba79a7b1e03d1e9669361ef7722aa5a43b7bf2a2f49ccf8b098ab23539392fd09b83224c3cb9d340b80483179fabb45d62ee30
+  data.tar.gz: 9733820cc4e81b22cca51dbf89a02aa87e96cbbc1add753b2799878b5b50b549f2a27886dcfae387ad4cc158ce4bd651354f8bbd2514460ac07a60560ad5c455

data/CHANGELOG.md

@@ -1,3 +1,10 @@
+## 0.2.6 (2021-02-24)
+
+- Improved performance
+- Improved `inspect` method
+- Fixed issue with `similar_users` and `item_recs` returning the original user/item
+- Fixed error with `fit` after loading
+
 ## 0.2.5 (2021-02-20)
 
 - Added `top_items` method

data/README.md

@@ -44,7 +44,7 @@ recommender.fit([
 ])
 ```
 
-> Use `value` instead of rating for implicit feedback
+> Use `value` instead of `rating` for implicit feedback
 
 Get user-based recommendations - “users like you also liked”
 
@@ -247,7 +247,7 @@ recommender.fit(data)
 recommender.top_items
 ```
 
-This uses [Wilson score](https://www.evanmiller.org/how-not-to-sort-by-average-rating.html) for explicit feedback (add [wilson_score](https://github.com/instacart/wilson_score) your application’s Gemfile) and item frequency for implicit feedback.
+This uses [Wilson score](https://www.evanmiller.org/how-not-to-sort-by-average-rating.html) for explicit feedback (add [wilson_score](https://github.com/instacart/wilson_score) to your application’s Gemfile) and item frequency for implicit feedback.
 
 ## Data
 
@@ -269,7 +269,7 @@ Or a Daru data frame
 Daru::DataFrame.from_csv("ratings.csv")
 ```
 
-## Performance [master]
+## Performance
 
 If you have a large number of users or items, you can use an approximate nearest neighbors library like [Faiss](https://github.com/ankane/faiss) to improve the performance of certain methods.
 

data/lib/disco/recommender.rb

@@ -17,24 +17,28 @@ module Disco
 
       check_training_set(train_set)
 
+      # TODO option to set in initializer to avoid pass
+      # could also just check first few values
+      # but may be confusing if they are all missing and later ones aren't
       @implicit = !train_set.any? { |v| v[:rating] }
+
+      # TODO improve performance
+      # (catch exception instead of checking ahead of time)
       unless @implicit
         check_ratings(train_set)
-        @min_rating, @max_rating = train_set.minmax_by { |o| o[:rating] }.map { |o| o[:rating] }
 
         if validation_set
           check_ratings(validation_set)
         end
       end
 
-      update_maps(train_set)
-
       @rated = Hash.new { |hash, key| hash[key] = {} }
       input = []
       value_key = @implicit ? :value : :rating
       train_set.each do |v|
-        u = @user_map[v[:user_id]]
-        i = @item_map[v[:item_id]]
+        # update maps and build matrix in single pass
+        u = (@user_map[v[:user_id]] ||= @user_map.size)
+        i = (@item_map[v[:item_id]] ||= @item_map.size)
         @rated[u][i] = true
 
         # explicit will always have a value due to check_ratings
@@ -42,6 +46,15 @@ module Disco
       end
       @rated.default = nil
 
+      # much more efficient than checking every value in another pass
+      raise ArgumentError, "Missing user_id" if @user_map.key?(nil)
+      raise ArgumentError, "Missing item_id" if @item_map.key?(nil)
+
+      # TODO improve performance
+      unless @implicit
+        @min_rating, @max_rating = train_set.minmax_by { |o| o[:rating] }.map { |o| o[:rating] }
+      end
+
       if @top_items
         @item_count = [0] * @item_map.size
         @item_sum = [0.0] * @item_map.size
@@ -78,6 +91,9 @@ module Disco
       @user_factors = model.p_factors(format: :numo)
       @item_factors = model.q_factors(format: :numo)
 
+      @normalized_user_factors = nil
+      @normalized_item_factors = nil
+
       @user_recs_index = nil
       @similar_users_index = nil
       @similar_items_index = nil
@@ -149,13 +165,13 @@ module Disco
 
     def similar_items(item_id, count: 5)
       check_fit
-      similar(item_id, @item_map, item_norms, count, @similar_items_index)
+      similar(item_id, @item_map, normalized_item_factors, count, @similar_items_index)
     end
     alias_method :item_recs, :similar_items
 
     def similar_users(user_id, count: 5)
       check_fit
-      similar(user_id, @user_map, user_norms, count, @similar_users_index)
+      similar(user_id, @user_map, normalized_user_factors, count, @similar_users_index)
     end
 
     def top_items(count: 5)
@@ -212,13 +228,17 @@ module Disco
 
     def optimize_similar_items(library: nil)
       check_fit
-      @similar_items_index = create_index(item_norms, library: library)
+      @similar_items_index = create_index(normalized_item_factors, library: library)
     end
     alias_method :optimize_item_recs, :optimize_similar_items
 
     def optimize_similar_users(library: nil)
       check_fit
-      @similar_users_index = create_index(user_norms, library: library)
+      @similar_users_index = create_index(normalized_user_factors, library: library)
+    end
+
+    def inspect
+      to_s # for now
     end
 
     private
@@ -251,7 +271,7 @@ module Disco
         # https://github.com/yahoojapan/NGT/issues/36
         index = Ngt::Index.new(factors.shape[1], distance_type: "Cosine")
 
-        # NGT normalizes so could call create_index with factors instead of norms
+        # NGT normalizes so could call create_index without normalized factors
         # but keep code simple for now
         ids = index.batch_insert(factors)
         raise "Unexpected ids. Please report a bug." if ids.first != 1 || ids.last != factors.shape[0]
@@ -262,15 +282,15 @@ module Disco
       end
     end
 
-    def user_norms
-      @user_norms ||= norms(@user_factors)
+    def normalized_user_factors
+      @normalized_user_factors ||= normalize(@user_factors)
     end
 
-    def item_norms
-      @item_norms ||= norms(@item_factors)
+    def normalized_item_factors
+      @normalized_item_factors ||= normalize(@item_factors)
     end
 
-    def norms(factors)
+    def normalize(factors)
       norms = Numo::SFloat::Math.sqrt((factors * factors).sum(axis: 1))
       norms[norms.eq(0)] = 1e-10 # no zeros
       factors / norms.expand_dims(1)
@@ -303,30 +323,26 @@ module Disco
         # TODO use user_id for similar_users in 0.3.0
         key = :item_id
 
-        (1...ids.size).map do |i|
-          {key => keys[ids[i]], score: predictions[i]}
+        result = []
+        # items can have the same score
+        # so original item may not be at index 0
+        ids.each_with_index do |id, j|
+          next if id == i
+
+          result << {key => keys[id], score: predictions[j]}
         end
+        result
       else
         []
       end
     end
 
-    def update_maps(train_set)
-      raise ArgumentError, "Missing user_id" if train_set.any? { |v| v[:user_id].nil? }
-      raise ArgumentError, "Missing item_id" if train_set.any? { |v| v[:item_id].nil? }
-
-      train_set.each do |v|
-        @user_map[v[:user_id]] ||= @user_map.size
-        @item_map[v[:item_id]] ||= @item_map.size
-      end
-    end
-
     def check_ratings(ratings)
       unless ratings.all? { |r| !r[:rating].nil? }
-        raise ArgumentError, "Missing ratings"
+        raise ArgumentError, "Missing rating"
       end
       unless ratings.all? { |r| r[:rating].is_a?(Numeric) }
-        raise ArgumentError, "Ratings must be numeric"
+        raise ArgumentError, "Rating must be numeric"
       end
     end
 
@@ -365,7 +381,10 @@ module Disco
         rated: @rated,
         global_mean: @global_mean,
         user_factors: @user_factors,
-        item_factors: @item_factors
+        item_factors: @item_factors,
+        factors: @factors,
+        epochs: @epochs,
+        verbose: @verbose
       }
 
       unless @implicit
@@ -389,6 +408,9 @@ module Disco
       @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]

data/lib/disco/version.rb

@@ -1,3 +1,3 @@
 module Disco
-  VERSION = "0.2.5"
+  VERSION = "0.2.6"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: disco
 version: !ruby/object:Gem::Version
-  version: 0.2.5
+  version: 0.2.6
 platform: ruby
 authors:
 - Andrew Kane
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2021-02-20 00:00:00.000000000 Z
+date: 2021-02-24 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: libmf