disco 0.5.1 → 0.5.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: b1d7b56a9c40088874bbd79ff7fa5bf8783a4406a9e5dadf1dddb04303ca7fee
-  data.tar.gz: 0d843da83fc246b5da2aa097eba3534d729b51d9b03c368226b884fe33e61795
+  metadata.gz: 8ca6da20099f6ec36c5f07547c61bb368066f2f480fba03c775287f48407a1f8
+  data.tar.gz: 3fbd73bb42398534d31a7b574d5d8dd6e40a1fe867e7cf4fe0ede4bdad5cd0c9
 SHA512:
-  metadata.gz: 49341b30e2ffa7348c19af2c0073f8f9e15afe3dcd856922fb5ae3fd3cd6e5ab555731c38bf3678f5f4efb064ecfce994d24b6238aa93fbc62e4621d7de036ab
-  data.tar.gz: 9bb387230927cf55e94c3614c4a68881031206c9ee2dee2d48c06f6053134cdff0af4c4d24eba825acf3429394556368378bd51860f4dfcddf0dd1742309794f
+  metadata.gz: 570275aaf7887c98318040efde2440f5b6e8e04be25faa7a78b73453e05dec845963067f0808eff09e28621dbd7b3277e98da83521e067b6170a585f717462f5
+  data.tar.gz: 57b86344de0656aa8e4bb0f130d0f3bcd928d05365b7f39479e4c6a69cd49d3a2f2a10082abedaa351d5febb212681236548520a01c9b321132e6f798e74a690

data/CHANGELOG.md

@@ -1,3 +1,8 @@
+## 0.5.2 (2025-09-12)
+
+- Fixed recommendations when numo-narray compiled with GCC 13+
+- Fixed error with Rover 0.5+
+
 ## 0.5.1 (2024-12-29)
 
 - Removed dependency on `base64` gem for serialization

data/lib/disco/recommender.rb

@@ -138,17 +138,13 @@ module Disco
           return [] if ids.size == 0
 
           predictions = @item_factors[ids, true].inner(@user_factors[u, true])
-          indexes = predictions.sort_index.reverse
-          indexes = indexes[0...[count + rated.size, indexes.size].min] if count
-          predictions = predictions[indexes]
+          predictions, indexes = top_k(predictions, count ? count + rated.size : nil)
           ids = ids[indexes]
         elsif @user_recs_index && count
           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])
-          indexes = predictions.sort_index.reverse # reverse just creates view
-          indexes = indexes[0...[count + rated.size, indexes.size].min] if count
-          predictions = predictions[indexes]
+          predictions, indexes = top_k(predictions, count ? count + rated.size : nil)
           ids = indexes
         end
 
@@ -196,7 +192,7 @@ module Disco
         # 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
+        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
@@ -204,9 +200,7 @@ module Disco
         scores = scores * range + min_rating
       end
 
-      indexes = scores.sort_index.reverse
-      indexes = indexes[0...[count, indexes.size].min] if count
-      scores = scores[indexes]
+      scores, indexes = top_k(scores, count)
 
       keys = @item_map.keys
       indexes.size.times.map do |i|
@@ -371,9 +365,7 @@ module Disco
           end
         else
           predictions = factors.inner(factors[i, true]) / (norms * norms[i])
-          indexes = predictions.sort_index.reverse
-          indexes = indexes[0...[count + 1, indexes.size].min] if count
-          predictions = predictions[indexes]
+          predictions, indexes = top_k(predictions, count ? count + 1 : nil)
           ids = indexes
         end
 
@@ -394,6 +386,27 @@ module Disco
       end
     end
 
+    def top_k(values, count)
+      if self.class.sort_index?
+        indexes = values.sort_index.reverse
+        indexes = indexes[0...[count, indexes.size].min] if count
+      else
+        indexes = values.to_a.each_with_index.sort_by { |v, _| -v }
+        indexes = indexes.first(count) if count
+        indexes = indexes.map(&:last)
+      end
+      [values[indexes], indexes]
+    end
+
+    # https://github.com/ruby-numo/numo-narray/issues/243
+    def self.sort_index?
+      unless defined?(@sort_index)
+        arr = Numo::SFloat.new(100).rand
+        @sort_index = arr[arr.sort_index].to_a == arr.to_a.sort
+      end
+      @sort_index
+    end
+
     def check_ratings(ratings)
       unless ratings.all? { |r| !r[:rating].nil? }
         raise ArgumentError, "Missing rating"
@@ -414,11 +427,7 @@ module Disco
     def to_dataset(dataset)
       if defined?(Rover::DataFrame) && dataset.is_a?(Rover::DataFrame)
         # convert keys to symbols
-        dataset = dataset.dup
-        dataset.keys.each do |k, v|
-          dataset[k.to_sym] ||= dataset.delete(k)
-        end
-        dataset.to_a
+        dataset.each_row.map { |v| v.transform_keys(&:to_sym) }
       elsif defined?(Daru::DataFrame) && dataset.is_a?(Daru::DataFrame)
         # convert keys to symbols
         dataset = dataset.dup

data/lib/disco/version.rb

@@ -1,3 +1,3 @@
 module Disco
-  VERSION = "0.5.1"
+  VERSION = "0.5.2"
 end

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification
 name: disco
 version: !ruby/object:Gem::Version
-  version: 0.5.1
+  version: 0.5.2
 platform: ruby
 authors:
 - Andrew Kane
 bindir: bin
 cert_chain: []
-date: 2024-12-30 00:00:00.000000000 Z
+date: 1980-01-02 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: libmf
@@ -73,7 +73,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.6.2
+rubygems_version: 3.6.9
 specification_version: 4
 summary: Recommendations for Ruby and Rails using collaborative filtering
 test_files: []