disco 0.1.2 → 0.1.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 04d278a7daf8187ac8a5eadaa279c98a0a51a8cf0ad596e793198dcc9141233a
-  data.tar.gz: '0916f7cfb91d5bf48ce1186502f15647c102eba54e07bdc33eb042b75e1fb0c6'
+  metadata.gz: 33961b51cd8461f821c4622f5983b2ac6138cc3b70c9be8ef1d3a6e82c37ab9e
+  data.tar.gz: f4e8cdfa4efb354878c459b57b522a81cd3f0c81e4297c53f9dc88517b312ac8
 SHA512:
-  metadata.gz: a8e977bcf2988e8e4cb85b13959446d068e3a41feeca26f3789ff7aa0a454258340bc81fb3adb470e0143cc6027cd803ef034900cc29db4648b01f855f6cb011
-  data.tar.gz: defc71dd93461a114338f0737cfa3eccae47605e2922aaf12d960a0cb6309131dbba497f7c7d125e962edd055ff7df898cd406544971ed75906cb8c1db6004cf
+  metadata.gz: 2f4c207486e858a23480e52b4b9a479fd23b26f0259ef12e39b964d9d7f4cc0067f162207d88119f76414269d65e3ee3d7c675c46f5f143c5b016eacab6e888c
+  data.tar.gz: 2734c1dcc87c423566dd2f842ef7fdd1b7e3cbaa1ecac61dbfafdbc1769b43edca81d28ce60712008eee9d381d64c9e2dea71b210c1a10fecaef75696ee2fd05

data/CHANGELOG.md

@@ -1,3 +1,10 @@
+## 0.1.3 (2020-06-28)
+
+- Added support for Rover
+- Raise error when missing user or item ids
+- Fixed string keys for Daru data frames
+- `optimize_item_recs` and `optimize_similar_users` methods are no longer experimental
+
 ## 0.1.2 (2020-03-26)
 
 - Added experimental `optimize_item_recs` and `optimize_similar_users` methods

data/README.md

@@ -244,20 +244,26 @@ Data can be an array of hashes
 [{user_id: 1, item_id: 1, rating: 5}, {user_id: 2, item_id: 1, rating: 3}]
 ```
 
+Or a Rover data frame
+
+```ruby
+Rover.read_csv("ratings.csv")
+```
+
 Or a Daru data frame
 
 ```ruby
 Daru::DataFrame.from_csv("ratings.csv")
 ```
 
-## Faster Similarity [experimental]
+## Faster Similarity
 
 If you have a large number of users/items, you can use an approximate nearest neighbors library like [NGT](https://github.com/ankane/ngt) to speed up item-based recommendations and similar users.
 
 Add this line to your application’s Gemfile:
 
 ```ruby
-gem 'ngt', '>= 0.2.3'
+gem 'ngt', '>= 0.3.0'
 ```
 
 Speed up item-based recommendations with:

data/lib/disco/recommender.rb

@@ -9,14 +9,8 @@ module Disco
     end
 
     def fit(train_set, validation_set: nil)
-      if defined?(Daru)
-        if train_set.is_a?(Daru::DataFrame)
-          train_set = train_set.to_a[0]
-        end
-        if validation_set.is_a?(Daru::DataFrame)
-          validation_set = validation_set.to_a[0]
-        end
-      end
+      train_set = to_dataset(train_set)
+      validation_set = to_dataset(validation_set) if validation_set
 
       @implicit = !train_set.any? { |v| v[:rating] }
 
@@ -190,6 +184,9 @@ module Disco
       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?)
+
       @user_map = user_ids.zip(user_ids.size.times).to_h
       @item_map = item_ids.zip(item_ids.size.times).to_h
     end
@@ -207,6 +204,25 @@ module Disco
       raise ArgumentError, "No training data" if train_set.empty?
     end
 
+    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
+      elsif defined?(Daru::DataFrame) && dataset.is_a?(Daru::DataFrame)
+        # convert keys to symbols
+        dataset = dataset.dup
+        new_names = dataset.vectors.to_a.map { |k| [k, k.to_sym] }.to_h
+        dataset.rename_vectors!(new_names)
+        dataset.to_a[0]
+      else
+        dataset
+      end
+    end
+
     def marshal_dump
       obj = {
         implicit: @implicit,

data/lib/disco/version.rb

@@ -1,3 +1,3 @@
 module Disco
-  VERSION = "0.1.2"
+  VERSION = "0.1.3"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: disco
 version: !ruby/object:Gem::Version
-  version: 0.1.2
+  version: 0.1.3
 platform: ruby
 authors:
 - Andrew Kane
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2020-03-26 00:00:00.000000000 Z
+date: 2020-06-29 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: libmf
@@ -122,6 +122,20 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: rover-df
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: ngt
   requirement: !ruby/object:Gem::Requirement