cmfrec 0.1.4 → 0.1.5

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: bb7b07ae46500a545f1a130dfc5648aa3f925f9b5766a6c70a1652c7b5732182
-  data.tar.gz: e89a6d1900cda651dc6b0aac2899050e28680cddfb6b39b6b5eacfe467b59aad
+  metadata.gz: 7a200b99780aeee83c5a0190e593c3806c4140aa4c096b0ef2c112fd21a858b7
+  data.tar.gz: 27b354dd491ca1d7a728d4ef2318c72c56d76c691286bc267c74d3b8dafd7c5b
 SHA512:
-  metadata.gz: 117aa6952fe0ab8ddebfaece6655cf479a7adbab7d6f634e7d3428c72824a410812c037ae006366180a9691a6d160d8065b777a9c10a33a5ccfefedb28c99ec6
-  data.tar.gz: 57985a055705b820226a2aa1451453383ee3509e43225f8fdb09e713c4530754b0b608f7d1b4814973b43e3d625f824f9f87939687d015b352cc8905f7b4f118
+  metadata.gz: 0c1ceefeac9131a804d94b6da78c7a6614f50c15d144841277829e5279ce2583872a681e972e336e21cb82d49466dee9f5f1de6a482fe8a99ab7aa5176ab0e5c
+  data.tar.gz: 930b20b017b92555071699b38d903230da3ca1fc7b8b91b9e2f96ae3ae4dda9c8c289a47117beaa1e2539e5c9d622fe958d431f5106e8ab7c4809ea17e9fb6e8

data/CHANGELOG.md

@@ -1,3 +1,8 @@
+## 0.1.5 (2021-08-10)
+
+- Fixed issue with `user_recs` and `new_user_recs` returning rated items
+- Fixed error with `new_user_recs`
+
 ## 0.1.4 (2021-02-04)
 
 - Added support for saving and loading recommenders

data/lib/cmfrec/recommender.rb

@@ -67,6 +67,7 @@ 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] }
@@ -80,7 +81,8 @@ module Cmfrec
         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
-          top_n(a_vec: a_vec, a_bias: a_bias, count: count)
+          # @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
       else
         # no items if user is unknown
@@ -93,8 +95,8 @@ module Cmfrec
     def new_user_recs(data, count: 5, user_info: nil)
       check_fit
 
-      a_vec, a_bias = factors_warm(data, user_info: user_info)
-      top_n(a_vec: a_vec, a_bias: a_bias, count: count)
+      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)
     end
 
     def user_factors
@@ -191,11 +193,17 @@ module Cmfrec
       x_col = []
       x_val = []
       value_key = @implicit ? :value : :rating
+      @rated = Hash.new { |hash, key| hash[key] = {} }
       train_set.each do |v|
-        x_row << @user_map[v[:user_id]]
-        x_col << @item_map[v[:item_id]]
+        u = @user_map[v[:user_id]]
+        i = @item_map[v[:item_id]]
+        @rated[u][i] = true
+
+        x_row << u
+        x_col << i
         x_val << (v[value_key] || 1)
       end
+      @rated.default = nil
 
       @m = @user_map.size
       @n = @item_map.size
@@ -450,11 +458,22 @@ module Cmfrec
       real_array(ptr)
     end
 
-    def top_n(a_vec:, a_bias:, count:)
+    def top_n(a_vec:, a_bias:, count:, rated: nil)
       include_ix = nil
       n_include = 0
-      exclude_ix = nil
-      n_exclude = 0
+
+      if rated
+        # assumes rated is unique and all items are known
+        # calling code is responsible for this
+        exclude_ix = int_ptr(rated)
+        n_exclude = rated.size
+        remaining = @item_map.size - n_exclude
+        return [] if remaining == 0
+        count = remaining if remaining < count
+      else
+        exclude_ix = nil
+        n_exclude = 0
+      end
 
       outp_ix = Fiddle::Pointer.malloc(count * Fiddle::SIZEOF_INT)
       outp_score = Fiddle::Pointer.malloc(count * Fiddle::SIZEOF_DOUBLE)
@@ -484,6 +503,16 @@ module Cmfrec
       data = to_dataset(data)
       user_info = to_dataset(user_info) if user_info
 
+      # remove unknown items
+      data, unknown_data = data.partition { |d| @item_map[d[:item_id]] }
+
+      if unknown_data.any?
+        # TODO warn for unknown items?
+        # warn "[cmfrec] Unknown items: #{unknown_data.map { |d| d[:item_id] }.join(", ")}"
+      end
+
+      item_ids = data.map { |d| @item_map[d[:item_id]] }
+
       nnz = data.size
       a_vec = Fiddle::Pointer.malloc((@k_user + @k + @k_main) * Fiddle::SIZEOF_DOUBLE)
       bias_a = Fiddle::Pointer.malloc(Fiddle::SIZEOF_DOUBLE)
@@ -524,7 +553,7 @@ module Cmfrec
           check_ratings(ratings)
         end
         xa = real_ptr(ratings)
-        x_col = int_ptr(data.map { |d| d[:item_id] })
+        x_col = int_ptr(item_ids)
       else
         xa = nil
         x_col = nil
@@ -587,7 +616,7 @@ module Cmfrec
         check_status FFI.factors_collective_explicit_single(*fiddle_args(args))
       end
 
-      [a_vec, real_array(bias_a).first]
+      [a_vec, real_array(bias_a).first, item_ids.uniq]
     end
 
     # convert boolean to int
@@ -679,6 +708,7 @@ module Cmfrec
       # factors
       obj[:user_map] = @user_map
       obj[:item_map] = @item_map
+      obj[:rated] = @rated
       obj[:user_factors] = dump_ptr(@a)
       obj[:item_factors] = dump_ptr(@b)
 
@@ -726,6 +756,7 @@ module Cmfrec
       # factors
       @user_map = obj[:user_map]
       @item_map = obj[:item_map]
+      @rated = obj[:rated] || {}
       @a = load_ptr(obj[:user_factors])
       @b = load_ptr(obj[:item_factors])
 

data/lib/cmfrec/version.rb

@@ -1,3 +1,3 @@
 module Cmfrec
-  VERSION = "0.1.4"
+  VERSION = "0.1.5"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: cmfrec
 version: !ruby/object:Gem::Version
-  version: 0.1.4
+  version: 0.1.5
 platform: ruby
 authors:
 - Andrew Kane
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2021-02-05 00:00:00.000000000 Z
+date: 2021-08-11 00:00:00.000000000 Z
 dependencies: []
 description:
 email: andrew@ankane.org
@@ -47,7 +47,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.2.3
+rubygems_version: 3.2.22
 signing_key:
 specification_version: 4
 summary: Recommendations for Ruby using collective matrix factorization