disco 0.2.1 → 0.2.3
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/CHANGELOG.md +10 -0
- data/README.md +3 -3
- data/lib/disco/recommender.rb +39 -3
- data/lib/disco/version.rb +1 -1
- metadata +2 -114
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: e9b8792d465e2bd894ce9aaa5dabf79dd89e93337d838917c709ac7747b85772
|
4
|
+
data.tar.gz: 9d34a5124dc26f8a2ecb7e2ed3cbf524fe586c37c693d885e668974e24dfaf0a
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 658b48b75994a295382eb22908d4a5f1825b01bfc26f52428e993802c42f7ebb435a59e7f1262d17400d65eda886f1a4f38edff82cdeda96c2a0ce280602742f
|
7
|
+
data.tar.gz: c9acce77cae8a575c5814456247600367d5fea4eb85a52309e26cac643d107bc03c42c99ce094c2f9ec46a329fd2dfa97d2f58f0020b337feb88b56346630942
|
data/CHANGELOG.md
CHANGED
@@ -1,3 +1,13 @@
|
|
1
|
+
## 0.2.3 (2020-11-28)
|
2
|
+
|
3
|
+
- Added `predict` method
|
4
|
+
- Fixed bad recommendations and scores with `user_recs` and explicit feedback
|
5
|
+
- Fixed `item_ids` option for `user_recs`
|
6
|
+
|
7
|
+
## 0.2.2 (n/a)
|
8
|
+
|
9
|
+
- Not available (released by previous gem owner)
|
10
|
+
|
1
11
|
## 0.2.1 (2020-10-28)
|
2
12
|
|
3
13
|
- Fixed issue with `user_recs` returning rated items
|
data/README.md
CHANGED
@@ -6,7 +6,7 @@
|
|
6
6
|
- Works with explicit and implicit feedback
|
7
7
|
- Uses high-performance matrix factorization
|
8
8
|
|
9
|
-
[![Build Status](https://
|
9
|
+
[![Build Status](https://github.com/ankane/disco/workflows/build/badge.svg?branch=master)](https://github.com/ankane/disco/actions)
|
10
10
|
|
11
11
|
## Installation
|
12
12
|
|
@@ -64,10 +64,10 @@ Use the `count` option to specify the number of recommendations (default is 5)
|
|
64
64
|
recommender.user_recs(user_id, count: 3)
|
65
65
|
```
|
66
66
|
|
67
|
-
Get predicted ratings for specific items
|
67
|
+
Get predicted ratings for specific users and items
|
68
68
|
|
69
69
|
```ruby
|
70
|
-
recommender.
|
70
|
+
recommender.predict([{user_id: 1, item_id: 2}, {user_id: 2, item_id: 4}])
|
71
71
|
```
|
72
72
|
|
73
73
|
Get similar users
|
data/lib/disco/recommender.rb
CHANGED
@@ -71,12 +71,31 @@ module Disco
|
|
71
71
|
@item_index = nil
|
72
72
|
end
|
73
73
|
|
74
|
+
# generates a prediction even if a user has already rated the item
|
75
|
+
def predict(data)
|
76
|
+
data = to_dataset(data)
|
77
|
+
|
78
|
+
u = data.map { |v| @user_map[v[:user_id]] }
|
79
|
+
i = data.map { |v| @item_map[v[:item_id]] }
|
80
|
+
|
81
|
+
new_index = data.each_index.select { |index| u[index].nil? || i[index].nil? }
|
82
|
+
new_index.each do |j|
|
83
|
+
u[j] = 0
|
84
|
+
i[j] = 0
|
85
|
+
end
|
86
|
+
|
87
|
+
predictions = @user_factors[u, true].inner(@item_factors[i, true])
|
88
|
+
predictions.inplace.clip(@min_rating, @max_rating) if @min_rating
|
89
|
+
predictions[new_index] = @global_mean
|
90
|
+
predictions.to_a
|
91
|
+
end
|
92
|
+
|
74
93
|
def user_recs(user_id, count: 5, item_ids: nil)
|
94
|
+
check_fit
|
75
95
|
u = @user_map[user_id]
|
76
96
|
|
77
97
|
if u
|
78
|
-
predictions = @
|
79
|
-
predictions.inplace.clip(@min_rating, @max_rating) if @min_rating
|
98
|
+
predictions = @item_factors.inner(@user_factors[u, true])
|
80
99
|
|
81
100
|
predictions =
|
82
101
|
@item_map.keys.zip(predictions).map do |item_id, pred|
|
@@ -85,7 +104,7 @@ module Disco
|
|
85
104
|
|
86
105
|
if item_ids
|
87
106
|
idx = item_ids.map { |i| @item_map[i] }.compact
|
88
|
-
predictions.values_at(*idx)
|
107
|
+
predictions = predictions.values_at(*idx)
|
89
108
|
else
|
90
109
|
@rated[u].keys.sort_by { |v| -v }.each do |i|
|
91
110
|
predictions.delete_at(i)
|
@@ -94,6 +113,15 @@ module Disco
|
|
94
113
|
|
95
114
|
predictions.sort_by! { |pred| -pred[:score] } # already sorted by id
|
96
115
|
predictions = predictions.first(count) if count && !item_ids
|
116
|
+
|
117
|
+
# clamp *after* sorting
|
118
|
+
# also, only needed for returned predictions
|
119
|
+
if @min_rating
|
120
|
+
predictions.each do |pred|
|
121
|
+
pred[:score] = pred[:score].clamp(@min_rating, @max_rating)
|
122
|
+
end
|
123
|
+
end
|
124
|
+
|
97
125
|
predictions
|
98
126
|
else
|
99
127
|
# no items if user is unknown
|
@@ -103,20 +131,24 @@ module Disco
|
|
103
131
|
end
|
104
132
|
|
105
133
|
def optimize_similar_items
|
134
|
+
check_fit
|
106
135
|
@item_index = create_index(@item_factors)
|
107
136
|
end
|
108
137
|
alias_method :optimize_item_recs, :optimize_similar_items
|
109
138
|
|
110
139
|
def optimize_similar_users
|
140
|
+
check_fit
|
111
141
|
@user_index = create_index(@user_factors)
|
112
142
|
end
|
113
143
|
|
114
144
|
def similar_items(item_id, count: 5)
|
145
|
+
check_fit
|
115
146
|
similar(item_id, @item_map, @item_factors, item_norms, count, @item_index)
|
116
147
|
end
|
117
148
|
alias_method :item_recs, :similar_items
|
118
149
|
|
119
150
|
def similar_users(user_id, count: 5)
|
151
|
+
check_fit
|
120
152
|
similar(user_id, @user_map, @user_factors, user_norms, count, @user_index)
|
121
153
|
end
|
122
154
|
|
@@ -203,6 +235,10 @@ module Disco
|
|
203
235
|
raise ArgumentError, "No training data" if train_set.empty?
|
204
236
|
end
|
205
237
|
|
238
|
+
def check_fit
|
239
|
+
raise "Not fit" unless defined?(@implicit)
|
240
|
+
end
|
241
|
+
|
206
242
|
def to_dataset(dataset)
|
207
243
|
if defined?(Rover::DataFrame) && dataset.is_a?(Rover::DataFrame)
|
208
244
|
# convert keys to symbols
|
data/lib/disco/version.rb
CHANGED
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: disco
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.2.
|
4
|
+
version: 0.2.3
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Andrew Kane
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2020-
|
11
|
+
date: 2020-11-28 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: libmf
|
@@ -38,118 +38,6 @@ dependencies:
|
|
38
38
|
- - ">="
|
39
39
|
- !ruby/object:Gem::Version
|
40
40
|
version: '0'
|
41
|
-
- !ruby/object:Gem::Dependency
|
42
|
-
name: bundler
|
43
|
-
requirement: !ruby/object:Gem::Requirement
|
44
|
-
requirements:
|
45
|
-
- - ">="
|
46
|
-
- !ruby/object:Gem::Version
|
47
|
-
version: '0'
|
48
|
-
type: :development
|
49
|
-
prerelease: false
|
50
|
-
version_requirements: !ruby/object:Gem::Requirement
|
51
|
-
requirements:
|
52
|
-
- - ">="
|
53
|
-
- !ruby/object:Gem::Version
|
54
|
-
version: '0'
|
55
|
-
- !ruby/object:Gem::Dependency
|
56
|
-
name: rake
|
57
|
-
requirement: !ruby/object:Gem::Requirement
|
58
|
-
requirements:
|
59
|
-
- - ">="
|
60
|
-
- !ruby/object:Gem::Version
|
61
|
-
version: '0'
|
62
|
-
type: :development
|
63
|
-
prerelease: false
|
64
|
-
version_requirements: !ruby/object:Gem::Requirement
|
65
|
-
requirements:
|
66
|
-
- - ">="
|
67
|
-
- !ruby/object:Gem::Version
|
68
|
-
version: '0'
|
69
|
-
- !ruby/object:Gem::Dependency
|
70
|
-
name: minitest
|
71
|
-
requirement: !ruby/object:Gem::Requirement
|
72
|
-
requirements:
|
73
|
-
- - ">="
|
74
|
-
- !ruby/object:Gem::Version
|
75
|
-
version: '5'
|
76
|
-
type: :development
|
77
|
-
prerelease: false
|
78
|
-
version_requirements: !ruby/object:Gem::Requirement
|
79
|
-
requirements:
|
80
|
-
- - ">="
|
81
|
-
- !ruby/object:Gem::Version
|
82
|
-
version: '5'
|
83
|
-
- !ruby/object:Gem::Dependency
|
84
|
-
name: activerecord
|
85
|
-
requirement: !ruby/object:Gem::Requirement
|
86
|
-
requirements:
|
87
|
-
- - ">="
|
88
|
-
- !ruby/object:Gem::Version
|
89
|
-
version: '0'
|
90
|
-
type: :development
|
91
|
-
prerelease: false
|
92
|
-
version_requirements: !ruby/object:Gem::Requirement
|
93
|
-
requirements:
|
94
|
-
- - ">="
|
95
|
-
- !ruby/object:Gem::Version
|
96
|
-
version: '0'
|
97
|
-
- !ruby/object:Gem::Dependency
|
98
|
-
name: sqlite3
|
99
|
-
requirement: !ruby/object:Gem::Requirement
|
100
|
-
requirements:
|
101
|
-
- - ">="
|
102
|
-
- !ruby/object:Gem::Version
|
103
|
-
version: '0'
|
104
|
-
type: :development
|
105
|
-
prerelease: false
|
106
|
-
version_requirements: !ruby/object:Gem::Requirement
|
107
|
-
requirements:
|
108
|
-
- - ">="
|
109
|
-
- !ruby/object:Gem::Version
|
110
|
-
version: '0'
|
111
|
-
- !ruby/object:Gem::Dependency
|
112
|
-
name: daru
|
113
|
-
requirement: !ruby/object:Gem::Requirement
|
114
|
-
requirements:
|
115
|
-
- - ">="
|
116
|
-
- !ruby/object:Gem::Version
|
117
|
-
version: '0'
|
118
|
-
type: :development
|
119
|
-
prerelease: false
|
120
|
-
version_requirements: !ruby/object:Gem::Requirement
|
121
|
-
requirements:
|
122
|
-
- - ">="
|
123
|
-
- !ruby/object:Gem::Version
|
124
|
-
version: '0'
|
125
|
-
- !ruby/object:Gem::Dependency
|
126
|
-
name: rover-df
|
127
|
-
requirement: !ruby/object:Gem::Requirement
|
128
|
-
requirements:
|
129
|
-
- - ">="
|
130
|
-
- !ruby/object:Gem::Version
|
131
|
-
version: '0'
|
132
|
-
type: :development
|
133
|
-
prerelease: false
|
134
|
-
version_requirements: !ruby/object:Gem::Requirement
|
135
|
-
requirements:
|
136
|
-
- - ">="
|
137
|
-
- !ruby/object:Gem::Version
|
138
|
-
version: '0'
|
139
|
-
- !ruby/object:Gem::Dependency
|
140
|
-
name: ngt
|
141
|
-
requirement: !ruby/object:Gem::Requirement
|
142
|
-
requirements:
|
143
|
-
- - ">="
|
144
|
-
- !ruby/object:Gem::Version
|
145
|
-
version: 0.3.0
|
146
|
-
type: :development
|
147
|
-
prerelease: false
|
148
|
-
version_requirements: !ruby/object:Gem::Requirement
|
149
|
-
requirements:
|
150
|
-
- - ">="
|
151
|
-
- !ruby/object:Gem::Version
|
152
|
-
version: 0.3.0
|
153
41
|
description:
|
154
42
|
email: andrew@chartkick.com
|
155
43
|
executables: []
|