disco 0.2.3 → 0.2.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: e9b8792d465e2bd894ce9aaa5dabf79dd89e93337d838917c709ac7747b85772
-  data.tar.gz: 9d34a5124dc26f8a2ecb7e2ed3cbf524fe586c37c693d885e668974e24dfaf0a
+  metadata.gz: e4a978d2eec39ca280142c49fb4ef4be2e1ad4f35dfa4d977941f46d5d34b466
+  data.tar.gz: 8a29a54bba5ac8b715294e2fce4e34fa1b11442b1800c388807c60b9520ced23
 SHA512:
-  metadata.gz: 658b48b75994a295382eb22908d4a5f1825b01bfc26f52428e993802c42f7ebb435a59e7f1262d17400d65eda886f1a4f38edff82cdeda96c2a0ce280602742f
-  data.tar.gz: c9acce77cae8a575c5814456247600367d5fea4eb85a52309e26cac643d107bc03c42c99ce094c2f9ec46a329fd2dfa97d2f58f0020b337feb88b56346630942
+  metadata.gz: 99376dd48cce340a4fdcb0d76c93b03af494d88167e2caaca0d186fcf5d2303f2524884e0c712c2f8e3d7be79a92b029a8d5fa726bb94826315f283afea0f74b
+  data.tar.gz: eeb8c480098616f93d6c7e39a1bb57e2feefa6af3696c407791ff6f052450eb035f1d1659ded70d7b5fbbbe8cff9f7309118828a454b1d4f9d459321b90035cf

data/CHANGELOG.md

@@ -1,3 +1,9 @@
+## 0.2.4 (2021-02-15)
+
+- Added `user_ids` and `item_ids` methods
+- Added `user_id` argument to `user_factors`
+- Added `item_id` argument to `item_factors`
+
 ## 0.2.3 (2020-11-28)
 
 - Added `predict` method

data/LICENSE.txt

@@ -1,4 +1,4 @@
-Copyright (c) 2019-2020 Andrew Kane
+Copyright (c) 2019-2021 Andrew Kane
 
 MIT License
 

data/README.md

@@ -46,13 +46,13 @@ recommender.fit([
 
 > Use `value` instead of rating for implicit feedback
 
-Get user-based (user-item) recommendations - “users like you also liked”
+Get user-based recommendations - “users like you also liked”
 
 ```ruby
 recommender.user_recs(user_id)
 ```
 
-Get item-based (item-item) recommendations - “users who liked this item also liked”
+Get item-based recommendations - “users who liked this item also liked”
 
 ```ruby
 recommender.item_recs(item_id)
@@ -283,19 +283,33 @@ This should be called after fitting or loading the model.
 
 ## Reference
 
+Get ids
+
+```ruby
+recommender.user_ids
+recommender.item_ids
+```
+
 Get the global mean
 
 ```ruby
 recommender.global_mean
 ```
 
-Get the factors
+Get factors
 
 ```ruby
 recommender.user_factors
 recommender.item_factors
 ```
 
+Get factors for specific users and items
+
+```ruby
+recommender.user_factors(user_id)
+recommender.item_factors(item_id)
+```
+
 ## Credits
 
 Thanks to:

data/lib/disco/recommender.rb

@@ -1,32 +1,32 @@
 module Disco
   class Recommender
-    attr_reader :global_mean, :item_factors, :user_factors
+    attr_reader :global_mean
 
     def initialize(factors: 8, epochs: 20, verbose: nil)
       @factors = factors
       @epochs = epochs
       @verbose = verbose
+      @user_map = {}
+      @item_map = {}
     end
 
     def fit(train_set, validation_set: nil)
       train_set = to_dataset(train_set)
       validation_set = to_dataset(validation_set) if validation_set
 
-      @implicit = !train_set.any? { |v| v[:rating] }
+      check_training_set(train_set)
 
+      @implicit = !train_set.any? { |v| v[:rating] }
       unless @implicit
-        ratings = train_set.map { |o| o[:rating] }
-        check_ratings(ratings)
-        @min_rating = ratings.min
-        @max_rating = ratings.max
+        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.map { |o| o[:rating] })
+          check_ratings(validation_set)
         end
       end
 
-      check_training_set(train_set)
-      create_maps(train_set)
+      update_maps(train_set)
 
       @rated = Hash.new { |hash, key| hash[key] = {} }
       input = []
@@ -143,13 +143,39 @@ module Disco
 
     def similar_items(item_id, count: 5)
       check_fit
-      similar(item_id, @item_map, @item_factors, item_norms, count, @item_index)
+      similar(item_id, @item_map, @item_factors, @item_index ? nil : item_norms, count, @item_index)
     end
     alias_method :item_recs, :similar_items
 
     def similar_users(user_id, count: 5)
       check_fit
-      similar(user_id, @user_map, @user_factors, user_norms, count, @user_index)
+      similar(user_id, @user_map, @user_factors, @user_index ? nil : user_norms, count, @user_index)
+    end
+
+    def user_ids
+      @user_map.keys
+    end
+
+    def item_ids
+      @item_map.keys
+    end
+
+    def user_factors(user_id = nil)
+      if user_id
+        u = @user_map[user_id]
+        @user_factors[u, true] if u
+      else
+        @user_factors
+      end
+    end
+
+    def item_factors(item_id = nil)
+      if item_id
+        i = @item_map[item_id]
+        @item_factors[i, true] if i
+      else
+        @item_factors
+      end
     end
 
     private
@@ -157,8 +183,11 @@ module Disco
     def create_index(factors)
       require "ngt"
 
+      # could speed up search with normalized cosine
+      # https://github.com/yahoojapan/NGT/issues/36
       index = Ngt::Index.new(factors.shape[1], distance_type: "Cosine")
-      index.batch_insert(factors)
+      ids = index.batch_insert(factors)
+      raise "Unexpected ids. Please report a bug." if ids.first != 1 || ids.last != factors.shape[0]
       index
     end
 
@@ -191,19 +220,21 @@ module Disco
             }
           end
         else
-          predictions = factors.dot(factors[i, true]) / norms
+          # cosine similarity without norms[i]
+          # otherwise, denominator would be (norms[i] * norms)
+          predictions = factors.inner(factors[i, true]) / norms
 
           predictions =
             map.keys.zip(predictions).map do |item_id, pred|
               {item_id: item_id, score: pred}
             end
 
-          max_score = predictions.delete_at(i)[:score]
+          predictions.delete_at(i)
           predictions.sort_by! { |pred| -pred[:score] } # already sorted by id
           predictions = predictions.first(count) if count
-          # divide by max score to get cosine similarity
+          # divide by norms[i] to get cosine similarity
           # only need to do for returned records
-          predictions.each { |pred| pred[:score] /= max_score }
+          predictions.each { |pred| pred[:score] /= norms[i] }
           predictions
         end
       else
@@ -211,22 +242,21 @@ module Disco
       end
     end
 
-    def create_maps(train_set)
-      user_ids = train_set.map { |v| v[:user_id] }.uniq.sort
-      item_ids = train_set.map { |v| v[:item_id] }.uniq.sort
-
-      raise ArgumentError, "Missing user_id" if user_ids.any?(&:nil?)
-      raise ArgumentError, "Missing item_id" if item_ids.any?(&:nil?)
+    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? }
 
-      @user_map = user_ids.zip(user_ids.size.times).to_h
-      @item_map = item_ids.zip(item_ids.size.times).to_h
+      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.nil? }
+      unless ratings.all? { |r| !r[:rating].nil? }
         raise ArgumentError, "Missing ratings"
       end
-      unless ratings.all? { |r| r.is_a?(Numeric) }
+      unless ratings.all? { |r| r[:rating].is_a?(Numeric) }
         raise ArgumentError, "Ratings must be numeric"
       end
     end

data/lib/disco/version.rb

@@ -1,3 +1,3 @@
 module Disco
-  VERSION = "0.2.3"
+  VERSION = "0.2.4"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: disco
 version: !ruby/object:Gem::Version
-  version: 0.2.3
+  version: 0.2.4
 platform: ruby
 authors:
 - Andrew Kane
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2020-11-28 00:00:00.000000000 Z
+date: 2021-02-16 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: libmf
@@ -39,7 +39,7 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '0'
 description:
-email: andrew@chartkick.com
+email: andrew@ankane.org
 executables: []
 extensions: []
 extra_rdoc_files: []
@@ -75,7 +75,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.1.4
+rubygems_version: 3.2.3
 signing_key:
 specification_version: 4
 summary: Recommendations for Ruby and Rails using collaborative filtering