disco 0.2.7 → 0.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 5f400f07839587b574ddcfa4c88335bfe20fcd876164b943e8094a35c3c1cfef
-  data.tar.gz: e2426b283146837d14be154ff0e67eb2505fd6587958b39212bf2dfe3bfccd80
+  metadata.gz: 815bc7de802959be7093d9e0478d83a0cf49a522e72a2df928de86223799d83d
+  data.tar.gz: cbfacf86f1e0507abe4df07b45f20bc3d06d682617c482419a05935186a61c15
 SHA512:
-  metadata.gz: 2be9f24184036ec5b093de55640aebb60887ac59c566f37698fcba7a18daa15cf586566708def0060f80fc0747a50447538cf42fdf36024ae19ddac0de8b415c
-  data.tar.gz: 4682a5524a8cad4a247ec53f99c78e317d56ee55433bb2ad7806af4f2a9854bc016fd23564003f009dc69d0fdcf81949dc88c64d3cbe824a8e76fc5cae8abc7d
+  metadata.gz: d0f3285b53cb8fe7e7d5ef30a970c632c52112c6b0503b8c81155f6cdb37583f036107b052c37019671355d0838512f904a61aeff5b69b7f6f8a2c1f4fabe785
+  data.tar.gz: f1b9c5759d77c1f497a0ac09ccf455beda29417024c4cd8ba6c0f8fcbac3347ab233c9e8c558a75382ef3b41495b5b693495ab0533c3a084a416c1f75a38313b

data/CHANGELOG.md

@@ -1,3 +1,19 @@
+## 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`
+
+## 0.2.8 (2022-03-13)
+
+- Fixed error with `top_items` with all same rating
+
 ## 0.2.7 (2021-08-06)
 
 - Added warning for `value`

data/LICENSE.txt

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

data/README.md

@@ -13,7 +13,7 @@
 Add this line to your application’s Gemfile:
 
 ```ruby
-gem 'disco'
+gem "disco"
 ```
 
 ## Getting Started
@@ -44,6 +44,8 @@ recommender.fit([
 ])
 ```
 
+> Each `user_id`/`item_id` combination should only appear once
+
 Get user-based recommendations - “users like you also liked”
 
 ```ruby
@@ -97,11 +99,7 @@ recommender.item_recs("Star Wars (1977)")
 [Ahoy](https://github.com/ankane/ahoy) is a great source for implicit feedback
 
 ```ruby
-views = Ahoy::Event.
-  where(name: "Viewed post").
-  group(:user_id).
-  group("properties->>'post_id'"). # postgres syntax
-  count
+views = Ahoy::Event.where(name: "Viewed post").group(:user_id).group_prop(:post_id).count
 
 data =
   views.map do |(user_id, post_id), _|
@@ -244,7 +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
 
@@ -273,7 +271,7 @@ If you have a large number of users or items, you can use an approximate nearest
 Add this line to your application’s Gemfile:
 
 ```ruby
-gem 'faiss'
+gem "faiss"
 ```
 
 Speed up the `user_recs` method with:

data/lib/disco/data.rb

@@ -1,9 +1,11 @@
 module Disco
   module Data
     def load_movielens
-      item_path = download_file("ml-100k/u.item", "http://files.grouplens.org/datasets/movielens/ml-100k/u.item",
+      require "csv"
+
+      item_path = download_file("ml-100k/u.item", "https://files.grouplens.org/datasets/movielens/ml-100k/u.item",
         file_hash: "553841ebc7de3a0fd0d6b62a204ea30c1e651aacfb2814c7a6584ac52f2c5701")
-      data_path = download_file("ml-100k/u.data", "http://files.grouplens.org/datasets/movielens/ml-100k/u.data",
+      data_path = download_file("ml-100k/u.data", "https://files.grouplens.org/datasets/movielens/ml-100k/u.data",
         file_hash: "06416e597f82b7342361e41163890c81036900f418ad91315590814211dca490")
 
       # convert u.item to utf-8
@@ -29,6 +31,11 @@ module Disco
     private
 
     def download_file(fname, origin, file_hash:)
+      require "digest"
+      require "fileutils"
+      require "net/http"
+      require "tmpdir"
+
       # TODO handle this better
       raise "No HOME" unless ENV["HOME"]
       dest = "#{ENV["HOME"]}/.disco/#{fname}"

data/lib/disco/model.rb

@@ -12,7 +12,7 @@ module Disco
 
         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)
@@ -183,21 +183,20 @@ module Disco
       if @implicit
         scores = Numo::UInt64.cast(@item_count)
       else
-        require "wilson_score"
+        min_rating = @min_rating
 
-        range = @min_rating..@max_rating
-        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, 100) # 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
@@ -260,8 +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"
@@ -270,7 +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])
@@ -312,7 +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
@@ -336,9 +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 = "0.2.7"
+  VERSION = "0.3.0"
 end

data/lib/disco.rb

@@ -2,11 +2,6 @@
 require "libmf"
 require "numo/narray"
 
-# stdlib
-require "csv"
-require "fileutils"
-require "net/http"
-
 # modules
 require "disco/data"
 require "disco/metrics"

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: disco
 version: !ruby/object:Gem::Version
-  version: 0.2.7
+  version: 0.3.0
 platform: ruby
 authors:
 - Andrew Kane
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2021-08-06 00:00:00.000000000 Z
+date: 2022-03-22 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: libmf
@@ -69,14 +69,14 @@ 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:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.2.22
+rubygems_version: 3.3.7
 signing_key:
 specification_version: 4
 summary: Recommendations for Ruby and Rails using collaborative filtering