disco 0.2.6 → 0.2.7

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: a7823dbe0e68967c39a59f8cdc2fe577f4366b492e0559487606b74a7de1cc84
-  data.tar.gz: ba40e46b203e424eccb811c6b042c9a283356c42585b7e00123b4bb2f232b1e2
+  metadata.gz: 5f400f07839587b574ddcfa4c88335bfe20fcd876164b943e8094a35c3c1cfef
+  data.tar.gz: e2426b283146837d14be154ff0e67eb2505fd6587958b39212bf2dfe3bfccd80
 SHA512:
-  metadata.gz: ee43326933ac019b0bae631631ba79a7b1e03d1e9669361ef7722aa5a43b7bf2a2f49ccf8b098ab23539392fd09b83224c3cb9d340b80483179fabb45d62ee30
-  data.tar.gz: 9733820cc4e81b22cca51dbf89a02aa87e96cbbc1add753b2799878b5b50b549f2a27886dcfae387ad4cc158ce4bd651354f8bbd2514460ac07a60560ad5c455
+  metadata.gz: 2be9f24184036ec5b093de55640aebb60887ac59c566f37698fcba7a18daa15cf586566708def0060f80fc0747a50447538cf42fdf36024ae19ddac0de8b415c
+  data.tar.gz: 4682a5524a8cad4a247ec53f99c78e317d56ee55433bb2ad7806af4f2a9854bc016fd23564003f009dc69d0fdcf81949dc88c64d3cbe824a8e76fc5cae8abc7d

data/CHANGELOG.md

@@ -1,3 +1,7 @@
+## 0.2.7 (2021-08-06)
+
+- Added warning for `value`
+
 ## 0.2.6 (2021-02-24)
 
 - Improved performance

data/README.md

@@ -35,17 +35,15 @@ recommender.fit([
 
 > IDs can be integers, strings, or any other data type
 
-If users don’t rate items directly (for instance, they’re purchasing items or reading posts), this is known as implicit feedback. Leave out the rating, or use a value like number of purchases, number of page views, or time spent on page:
+If users don’t rate items directly (for instance, they’re purchasing items or reading posts), this is known as implicit feedback. Leave out the rating.
 
 ```ruby
 recommender.fit([
-  {user_id: 1, item_id: 1, value: 1},
-  {user_id: 2, item_id: 1, value: 1}
+  {user_id: 1, item_id: 1},
+  {user_id: 2, item_id: 1}
 ])
 ```
 
-> Use `value` instead of `rating` for implicit feedback
-
 Get user-based recommendations - “users like you also liked”
 
 ```ruby
@@ -106,11 +104,10 @@ views = Ahoy::Event.
   count
 
 data =
-  views.map do |(user_id, post_id), count|
+  views.map do |(user_id, post_id), _|
     {
       user_id: user_id,
-      item_id: post_id,
-      value: count
+      item_id: post_id
     }
   end
 ```
@@ -201,7 +198,7 @@ bin = File.binread("recommender.bin")
 recommender = Marshal.load(bin)
 ```
 
-Alternatively, you can store only the factors and use a library like [Neighbor](https://github.com/ankane/neighbor)
+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).
 
 ## Algorithms
 
@@ -282,22 +279,22 @@ gem 'faiss'
 Speed up the `user_recs` method with:
 
 ```ruby
-model.optimize_user_recs
+recommender.optimize_user_recs
 ```
 
 Speed up the `item_recs` method with:
 
 ```ruby
-model.optimize_item_recs
+recommender.optimize_item_recs
 ```
 
 Speed up the `similar_users` method with:
 
 ```ruby
-model.optimize_similar_users
+recommender.optimize_similar_users
 ```
 
-This should be called after fitting or loading the model.
+This should be called after fitting or loading the recommender.
 
 ## Reference
 
@@ -336,6 +333,28 @@ Thanks to:
 - [Implicit](https://github.com/benfred/implicit/) for serving as an initial reference for user and item similarity
 - [@dasch](https://github.com/dasch) for the gem name
 
+## Upgrading
+
+### 0.2.7
+
+There’s now a warning when passing `:value` with implicit feedback, as this has no effect on recommendations and can be removed. Earlier versions of the library incorrectly stated this was used.
+
+```ruby
+recommender.fit([
+  {user_id: 1, item_id: 1, value: 1},
+  {user_id: 2, item_id: 1, value: 3}
+])
+```
+
+to:
+
+```ruby
+recommender.fit([
+  {user_id: 1, item_id: 1},
+  {user_id: 2, item_id: 1}
+])
+```
+
 ## History
 
 View the [changelog](https://github.com/ankane/disco/blob/master/CHANGELOG.md)

data/lib/disco/recommender.rb

@@ -22,6 +22,10 @@ module Disco
       # but may be confusing if they are all missing and later ones aren't
       @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."
+      end
+
       # TODO improve performance
       # (catch exception instead of checking ahead of time)
       unless @implicit
@@ -34,7 +38,6 @@ module Disco
 
       @rated = Hash.new { |hash, key| hash[key] = {} }
       input = []
-      value_key = @implicit ? :value : :rating
       train_set.each do |v|
         # update maps and build matrix in single pass
         u = (@user_map[v[:user_id]] ||= @user_map.size)
@@ -42,7 +45,7 @@ module Disco
         @rated[u][i] = true
 
         # explicit will always have a value due to check_ratings
-        input << [u, i, v[value_key] || 1]
+        input << [u, i, @implicit ? 1 : v[:rating]]
       end
       @rated.default = nil
 
@@ -61,7 +64,7 @@ module Disco
         train_set.each do |v|
           i = @item_map[v[:item_id]]
           @item_count[i] += 1
-          @item_sum[i] += (v[value_key] || 1)
+          @item_sum[i] += (@implicit ? 1 : v[:rating])
         end
       end
 
@@ -76,7 +79,7 @@ module Disco
           u ||= -1
           i ||= -1
 
-          eval_set << [u, i, v[value_key] || 1]
+          eval_set << [u, i, @implicit ? 1 : v[:rating]]
         end
       end
 
@@ -138,8 +141,7 @@ module Disco
           predictions, ids = @user_recs_index.search(@user_factors[u, true].expand_dims(0), count + rated.size).map { |v| v[0, true] }
         else
           predictions = @item_factors.inner(@user_factors[u, true])
-          # TODO make sure reverse isn't hurting performance
-          indexes = predictions.sort_index.reverse
+          indexes = predictions.sort_index.reverse # reverse just creates view
           indexes = indexes[0...[count + rated.size, indexes.size].min] if count
           predictions = predictions[indexes]
           ids = indexes
@@ -179,19 +181,32 @@ module Disco
       raise "top_items not computed" unless @top_items
 
       if @implicit
-        scores = @item_count
+        scores = Numo::UInt64.cast(@item_count)
       else
         require "wilson_score"
 
         range = @min_rating..@max_rating
-        scores = @item_sum.zip(@item_count).map { |s, c| WilsonScore.rating_lower_bound(s / c, c, range) }
+        scores = Numo::DFloat.cast(@item_sum.zip(@item_count).map { |s, c| WilsonScore.rating_lower_bound(s / c, c, range) })
+
+        # 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
       end
 
-      scores = scores.map.with_index.sort_by { |s, _| -s }
-      scores = scores.first(count) if count
-      item_ids = item_ids()
-      scores.map do |s, i|
-        {item_id: item_ids[i], score: s}
+      indexes = scores.sort_index.reverse
+      indexes = indexes[0...[count, indexes.size].min] if count
+      scores = scores[indexes]
+
+      keys = @item_map.keys
+      indexes.size.times.map do |i|
+        {item_id: keys[indexes[i]], score: scores[i]}
       end
     end
 
@@ -255,8 +270,9 @@ module Disco
         # inner product is cosine similarity with normalized vectors
         # https://github.com/facebookresearch/faiss/issues/95
         #
-        # TODO use non-exact index
+        # TODO use non-exact index in 0.3.0
         # 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])
 
         # ids are from 0...total

data/lib/disco/version.rb

@@ -1,3 +1,3 @@
 module Disco
-  VERSION = "0.2.6"
+  VERSION = "0.2.7"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: disco
 version: !ruby/object:Gem::Version
-  version: 0.2.6
+  version: 0.2.7
 platform: ruby
 authors:
 - Andrew Kane
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2021-02-24 00:00:00.000000000 Z
+date: 2021-08-06 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: libmf
@@ -76,7 +76,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.2.3
+rubygems_version: 3.2.22
 signing_key:
 specification_version: 4
 summary: Recommendations for Ruby and Rails using collaborative filtering