disco 0.2.9 → 0.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: d677e14bfb504669dd4f36cc00997128bbb0f7282c428ec29f88bf072587d82f
-  data.tar.gz: c797b4f1eb39aff5596b5e10b346260f6701df43e1c84559fb2395b23ed2c8f3
+  metadata.gz: 815bc7de802959be7093d9e0478d83a0cf49a522e72a2df928de86223799d83d
+  data.tar.gz: cbfacf86f1e0507abe4df07b45f20bc3d06d682617c482419a05935186a61c15
 SHA512:
-  metadata.gz: b2f0d889ac2c3dbed66642a15460c87e04eb81731f3a729b111522220159e7c52927aed5238413e323b83901fc490e1dce2cd12d6005b196f91eca69c9023277
-  data.tar.gz: a57abc84399c0cbc57f2997f341d8fe192e2835887df63fc75c13bc6a5d2aed5808aaf555b48c25902a65375df5cfd11990f1e987dfef77a7eef98d63f19914e
+  metadata.gz: d0f3285b53cb8fe7e7d5ef30a970c632c52112c6b0503b8c81155f6cdb37583f036107b052c37019671355d0838512f904a61aeff5b69b7f6f8a2c1f4fabe785
+  data.tar.gz: f1b9c5759d77c1f497a0ac09ccf455beda29417024c4cd8ba6c0f8fcbac3347ab233c9e8c558a75382ef3b41495b5b693495ab0533c3a084a416c1f75a38313b

data/CHANGELOG.md

@@ -1,3 +1,11 @@
+## 0.3.0 (2022-03-22)
+
+- Changed `item_id` to `user_id` for `similar_users`
+- Changed warning to an error when `value` passed to `fit`
+- Changed to use Faiss over NGT for `optimize_item_recs` and `optimize_similar_users` when both are installed
+- Removed dependency on `wilson_score` gem for `top_items`
+- Dropped support for Ruby < 2.6
+
 ## 0.2.9 (2022-03-22)
 
 - Fixed error with `load_movielens`

data/LICENSE.txt

@@ -1,4 +1,4 @@
-Copyright (c) 2019-2021 Andrew Kane
+Copyright (c) 2019-2022 Andrew Kane
 
 MIT License
 

data/README.md

@@ -242,7 +242,7 @@ 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) to 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 and item frequency for implicit feedback.
 
 ## Data
 

data/lib/disco/model.rb

@@ -10,10 +10,9 @@ module Disco
 
         has_many :"recommended_#{name}", -> { where("disco_recommendations.context = ?", name).order("disco_recommendations.score DESC") }, through: :recommendations, source: :item, source_type: class_name
 
-        # TODO use fetch for item_id and score in 0.3.0
         define_method("update_recommended_#{name}") do |items|
           now = Time.now
-          items = items.map { |item| {subject_type: model_name.name, subject_id: id, item_type: class_name, item_id: item[:item_id], context: name, score: item[:score], created_at: now, updated_at: now} }
+          items = items.map { |item| {subject_type: model_name.name, subject_id: id, item_type: class_name, item_id: item.fetch(:item_id), context: name, score: item.fetch(:score), created_at: now, updated_at: now} }
 
           self.class.transaction do
             recommendations.where(context: name).delete_all

data/lib/disco/recommender.rb

@@ -23,7 +23,7 @@ module Disco
       @implicit = !train_set.any? { |v| v[:rating] }
 
       if @implicit && train_set.any? { |v| v[:value] }
-        warn "[disco] WARNING: Passing `:value` with implicit feedback has no effect on recommendations and can be removed. Earlier versions of the library incorrectly stated this was used."
+        raise ArgumentError, "Passing `:value` with implicit feedback has no effect on recommendations and should be removed. Earlier versions of the library incorrectly stated this was used."
       end
 
       # TODO improve performance
@@ -167,13 +167,13 @@ module Disco
 
     def similar_items(item_id, count: 5)
       check_fit
-      similar(item_id, @item_map, normalized_item_factors, count, @similar_items_index)
+      similar(item_id, :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, normalized_user_factors, count, @similar_users_index)
+      similar(user_id, :user_id, @user_map, normalized_user_factors, count, @similar_users_index)
     end
 
     def top_items(count: 5)
@@ -183,27 +183,20 @@ module Disco
       if @implicit
         scores = Numo::UInt64.cast(@item_count)
       else
-        require "wilson_score"
+        min_rating = @min_rating
 
-        range =
-          if @min_rating == @max_rating
-            # TODO remove temp fix
-            (@min_rating - 1)..@max_rating
-          else
-            @min_rating..@max_rating
-          end
-        scores = Numo::DFloat.cast(@item_sum.zip(@item_count).map { |s, c| WilsonScore.rating_lower_bound(s / c, c, range) })
+        # TODO remove temp fix
+        min_rating -= 1 if @min_rating == @max_rating
 
-        # TODO uncomment in 0.3.0
         # wilson score with continuity correction
         # https://en.wikipedia.org/wiki/Binomial_proportion_confidence_interval#Wilson_score_interval_with_continuity_correction
-        # z = 1.96 # 95% confidence
-        # range = @max_rating - @min_rating
-        # n = Numo::DFloat.cast(@item_count)
-        # phat = (Numo::DFloat.cast(@item_sum) - (@min_rating * n)) / range / n
-        # phat = (phat - (1 / (2 * n))).clip(0, nil) # continuity correction
-        # scores = (phat + z**2 / (2 * n) - z * Numo::DFloat::Math.sqrt((phat * (1 - phat) + z**2 / (4 * n)) / n)) / (1 + z**2 / n)
-        # scores = scores * range + @min_rating
+        z = 1.96 # 95% confidence
+        range = @max_rating - @min_rating
+        n = Numo::DFloat.cast(@item_count)
+        phat = (Numo::DFloat.cast(@item_sum) - (min_rating * n)) / range / n
+        phat = (phat - (1 / (2 * n))).clip(0, nil) # continuity correction
+        scores = (phat + z**2 / (2 * n) - z * Numo::DFloat::Math.sqrt((phat * (1 - phat) + z**2 / (4 * n)) / n)) / (1 + z**2 / n)
+        scores = scores * range + min_rating
       end
 
       indexes = scores.sort_index.reverse
@@ -266,8 +259,7 @@ module Disco
 
     # factors should already be normalized for similar users/items
     def create_index(factors, library:)
-      # TODO make Faiss the default in 0.3.0
-      library ||= defined?(Faiss) && !defined?(Ngt) ? "faiss" : "ngt"
+      library ||= defined?(Ngt) && !defined?(Faiss) ? "ngt" : "faiss"
 
       case library
       when "faiss"
@@ -276,7 +268,7 @@ module Disco
         # inner product is cosine similarity with normalized vectors
         # https://github.com/facebookresearch/faiss/issues/95
         #
-        # TODO use non-exact index in 0.3.0
+        # TODO add option for index type
         # https://github.com/facebookresearch/faiss/wiki/Faiss-indexes
         # index = Faiss::IndexHNSWFlat.new(factors.shape[1], 32, :inner_product)
         index = Faiss::IndexFlatIP.new(factors.shape[1])
@@ -318,7 +310,7 @@ module Disco
       factors / norms.expand_dims(1)
     end
 
-    def similar(id, map, norm_factors, count, index)
+    def similar(id, key, map, norm_factors, count, index)
       i = map[id]
 
       if i && norm_factors.shape[0] > 1
@@ -342,9 +334,6 @@ module Disco
 
         keys = map.keys
 
-        # TODO use user_id for similar_users in 0.3.0
-        key = :item_id
-
         result = []
         # items can have the same score
         # so original item may not be at index 0

data/lib/disco/version.rb

@@ -1,3 +1,3 @@
 module Disco
-  VERSION = "0.2.9"
+  VERSION = "0.3.0"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: disco
 version: !ruby/object:Gem::Version
-  version: 0.2.9
+  version: 0.3.0
 platform: ruby
 authors:
 - Andrew Kane
@@ -69,7 +69,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '2.4'
+      version: '2.6'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="