cmfrec 0.1.5 → 0.1.6

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 7a200b99780aeee83c5a0190e593c3806c4140aa4c096b0ef2c112fd21a858b7
-  data.tar.gz: 27b354dd491ca1d7a728d4ef2318c72c56d76c691286bc267c74d3b8dafd7c5b
+  metadata.gz: 34e8dc08914cbc418470cd7eb3adf3d33013b786319f4510212c80bf3629f3ca
+  data.tar.gz: c1b91a1f77b4b51a5ca4491376f8a02230ea54873f8c1b2b06f4761d6ddd0686
 SHA512:
-  metadata.gz: 0c1ceefeac9131a804d94b6da78c7a6614f50c15d144841277829e5279ce2583872a681e972e336e21cb82d49466dee9f5f1de6a482fe8a99ab7aa5176ab0e5c
-  data.tar.gz: 930b20b017b92555071699b38d903230da3ca1fc7b8b91b9e2f96ae3ae4dda9c8c289a47117beaa1e2539e5c9d622fe958d431f5106e8ab7c4809ea17e9fb6e8
+  metadata.gz: a3c57734379199196a4e3f51d9ec02b19ef1abac13d57a10ca3c20e9b76c9ee5db4b17d790330d41a9576c2ba28a9eeccafeb5760b54cfdf80a7431368895068
+  data.tar.gz: 5a24a77a6665854abb38916a22e8141a6cae637a51f98e3df3762566f2e73cb60b9bd9a25303df0411ea53dec3211bf7534711dc55c510311620341cbe4e4ac3

data/CHANGELOG.md

@@ -1,3 +1,13 @@
+## 0.1.6 (2021-08-12)
+
+- Added `user_ids` and `item_ids` methods
+- Added `user_id` argument to `user_factors`
+- Added `item_id` argument to `item_factors`
+- Added `user_id` argument to `user_bias`
+- Added `item_id` argument to `item_bias`
+- Added `item_ids` argument to `new_user_recs`
+- Fixed order for `user_recs`
+
 ## 0.1.5 (2021-08-10)
 
 - Fixed issue with `user_recs` and `new_user_recs` returning rated items

data/README.md

@@ -232,6 +232,13 @@ recommender = Marshal.load(bin)
 
 ## Reference
 
+Get ids
+
+```ruby
+recommender.user_ids
+recommender.item_ids
+```
+
 Get the global mean
 
 ```ruby

data/lib/cmfrec/recommender.rb

@@ -67,23 +67,10 @@ module Cmfrec
       user = @user_map[user_id]
 
       if user
-        # TODO use top_n for item_ids as well
-        if item_ids
-          # remove missing ids
-          item_ids = item_ids.select { |v| @item_map[v] }
-
-          data = item_ids.map { |v| {user_id: user_id, item_id: v} }
-          scores = predict(data)
-
-          item_ids.zip(scores).map do |item_id, score|
-            {item_id: item_id, score: score}
-          end
-        else
-          a_vec = @a[user * @k * Fiddle::SIZEOF_DOUBLE, @k * Fiddle::SIZEOF_DOUBLE]
-          a_bias = @bias_a ? @bias_a[user * Fiddle::SIZEOF_DOUBLE, Fiddle::SIZEOF_DOUBLE].unpack1("d") : 0
-          # @rated[user] will be nil for recommenders saved before 0.1.5
-          top_n(a_vec: a_vec, a_bias: a_bias, count: count, rated: (@rated[user] || {}).keys)
-        end
+        a_vec = @a[user * @k * Fiddle::SIZEOF_DOUBLE, @k * Fiddle::SIZEOF_DOUBLE]
+        a_bias = @bias_a ? @bias_a[user * Fiddle::SIZEOF_DOUBLE, Fiddle::SIZEOF_DOUBLE].unpack1("d") : 0
+        # @rated[user] will be nil for recommenders saved before 0.1.5
+        top_n(a_vec: a_vec, a_bias: a_bias, count: count, rated: (@rated[user] || {}).keys, item_ids: item_ids)
       else
         # no items if user is unknown
         # TODO maybe most popular items
@@ -91,28 +78,35 @@ module Cmfrec
       end
     end
 
-    # TODO add item_ids
-    def new_user_recs(data, count: 5, user_info: nil)
+    def new_user_recs(data, count: 5, user_info: nil, item_ids: nil)
       check_fit
 
       a_vec, a_bias, rated = factors_warm(data, user_info: user_info)
-      top_n(a_vec: a_vec, a_bias: a_bias, count: count, rated: rated)
+      top_n(a_vec: a_vec, a_bias: a_bias, count: count, rated: rated, item_ids: item_ids)
+    end
+
+    def user_ids
+      @user_map.keys
+    end
+
+    def item_ids
+      @item_map.keys
     end
 
-    def user_factors
-      read_factors(@a, [@m, @m_u].max, @k_user + @k + @k_main)
+    def user_factors(user_id = nil)
+      read_factors(@a, [@m, @m_u].max, @k_user + @k + @k_main, user_id, @user_map)
     end
 
-    def item_factors
-      read_factors(@b, [@n, @n_i].max, @k_item + @k + @k_main)
+    def item_factors(item_id = nil)
+      read_factors(@b, [@n, @n_i].max, @k_item + @k + @k_main, item_id, @item_map)
     end
 
-    def user_bias
-      read_bias(@bias_a) if @bias_a
+    def user_bias(user_id = nil)
+      read_bias(@bias_a, user_id, @user_map) if @bias_a
     end
 
-    def item_bias
-      read_bias(@bias_b) if @bias_b
+    def item_bias(item_id = nil)
+      read_bias(@bias_b, item_id, @item_map) if @bias_b
     end
 
     def similar_items(item_id, count: 5)
@@ -443,26 +437,48 @@ module Cmfrec
       end
     end
 
-    def read_factors(ptr, d1, d2)
-      arr = []
-      offset = 0
+    def read_factors(ptr, d1, d2, id, map)
       width = d2 * Fiddle::SIZEOF_DOUBLE
-      d1.times do |i|
-        arr << ptr[offset, width].unpack("d*")
-        offset += width
+      if id
+        i = map[id]
+        ptr[i * width, width].unpack("d*") if i
+      else
+        arr = []
+        offset = 0
+        d1.times do |i|
+          arr << ptr[offset, width].unpack("d*")
+          offset += width
+        end
+        arr
       end
-      arr
     end
 
-    def read_bias(ptr)
-      real_array(ptr)
+    def read_bias(ptr, id, map)
+      if id
+        i = map[id]
+        ptr[i * Fiddle::SIZEOF_DOUBLE, Fiddle::SIZEOF_DOUBLE].unpack1("d") if i
+      else
+        real_array(ptr)
+      end
     end
 
-    def top_n(a_vec:, a_bias:, count:, rated: nil)
-      include_ix = nil
-      n_include = 0
+    def top_n(a_vec:, a_bias:, count:, rated: nil, item_ids: nil)
+      if item_ids
+        # remove missing ids
+        item_ids = item_ids.map { |v| @item_map[v] }.compact
+        return [] if item_ids.empty?
+
+        include_ix = int_ptr(item_ids)
+        n_include = item_ids.size
+
+        # TODO uncomment in 0.2.0
+        count = n_include # if n_include < count
+      else
+        include_ix = nil
+        n_include = 0
+      end
 
-      if rated
+      if rated && !item_ids
         # assumes rated is unique and all items are known
         # calling code is responsible for this
         exclude_ix = int_ptr(rated)

data/lib/cmfrec/version.rb

@@ -1,3 +1,3 @@
 module Cmfrec
-  VERSION = "0.1.5"
+  VERSION = "0.1.6"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: cmfrec
 version: !ruby/object:Gem::Version
-  version: 0.1.5
+  version: 0.1.6
 platform: ruby
 authors:
 - Andrew Kane
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2021-08-11 00:00:00.000000000 Z
+date: 2021-08-12 00:00:00.000000000 Z
 dependencies: []
 description:
 email: andrew@ankane.org