disco 0.1.3 → 0.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 33961b51cd8461f821c4622f5983b2ac6138cc3b70c9be8ef1d3a6e82c37ab9e
-  data.tar.gz: f4e8cdfa4efb354878c459b57b522a81cd3f0c81e4297c53f9dc88517b312ac8
+  metadata.gz: 96836166496bb14ec8f973fb5e3709e0a28b7d5d8678608d074c0d7613076cc2
+  data.tar.gz: c68d12941fddc51a67938ef951be4ee809faef2e131de0f5856908d8ed1f93d9
 SHA512:
-  metadata.gz: 2f4c207486e858a23480e52b4b9a479fd23b26f0259ef12e39b964d9d7f4cc0067f162207d88119f76414269d65e3ee3d7c675c46f5f143c5b016eacab6e888c
-  data.tar.gz: 2734c1dcc87c423566dd2f842ef7fdd1b7e3cbaa1ecac61dbfafdbc1769b43edca81d28ce60712008eee9d381d64c9e2dea71b210c1a10fecaef75696ee2fd05
+  metadata.gz: 8b960dc961ead701713dbc7f9c104852355ac6d61f9f1f6e1cde43d1d4fa257b2c55859ca42896a6780f006d25f5ff613bf0261e601033db7d3c063f2a9f3d3e
+  data.tar.gz: 6c82413ce53a9100fc97f9a3849c6231ebee4945fd26a3e3a1150f8c3abcca915032d35f4373b83217fa786600181097c003d1d071aab9de00612baf4c4eaa99

data/CHANGELOG.md

@@ -1,3 +1,7 @@
+## 0.2.0 (2020-07-31)
+
+- Changed score to always be between -1 and 1 for `item_recs` and `similar_users` (cosine similarity - this makes it easier to understand and consistent with `optimize_item_recs` and `optimize_similar_users`)
+
 ## 0.1.3 (2020-06-28)
 
 - Added support for Rover

data/LICENSE.txt

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

data/README.md

@@ -101,14 +101,14 @@ recommender.item_recs("Star Wars (1977)")
 ```ruby
 views = Ahoy::Event.
   where(name: "Viewed post").
-  group(:user_id, "properties->>'post_id'") # postgres syntax
+  group(:user_id, "properties->>'post_id'"). # postgres syntax
   count
 
 data =
   views.map do |(user_id, post_id), count|
     {
       user_id: user_id,
-      post_id: post_id,
+      item_id: post_id,
       value: count
     }
   end

data/lib/disco/data.rb

@@ -36,8 +36,7 @@ module Disco
 
       return dest if File.exist?(dest)
 
-      temp_dir ||= File.dirname(Tempfile.new("disco"))
-      temp_path = "#{temp_dir}/#{Time.now.to_f}" # TODO better name
+      temp_path = "#{Dir.tmpdir}/disco-#{Time.now.to_f}" # TODO better name
 
       digest = Digest::SHA2.new
 

data/lib/disco/recommender.rb

@@ -139,7 +139,7 @@ module Disco
     end
 
     def norms(factors)
-      norms = Numo::DFloat::Math.sqrt((factors * factors).sum(axis: 1))
+      norms = Numo::SFloat::Math.sqrt((factors * factors).sum(axis: 1))
       norms[norms.eq(0)] = 1e-10 # no zeros
       norms
     end
@@ -171,8 +171,7 @@ module Disco
           predictions = predictions.first(count) if count
           # divide by max score to get cosine similarity
           # only need to do for returned records
-          # could alternatively do cosine distance = 1 - cosine similarity
-          # predictions.each { |pred| pred[:score] /= max_score }
+          predictions.each { |pred| pred[:score] /= max_score }
           predictions
         end
       else

data/lib/disco/version.rb

@@ -1,3 +1,3 @@
 module Disco
-  VERSION = "0.1.3"
+  VERSION = "0.2.0"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: disco
 version: !ruby/object:Gem::Version
-  version: 0.1.3
+  version: 0.2.0
 platform: ruby
 authors:
 - Andrew Kane
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2020-06-29 00:00:00.000000000 Z
+date: 2020-07-31 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: libmf
@@ -142,14 +142,14 @@ dependencies:
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 0.2.3
+        version: 0.3.0
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 0.2.3
+        version: 0.3.0
 description: 
 email: andrew@chartkick.com
 executables: []