disco 0.4.1 → 0.4.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: eb58ae5c2579ef03fc0089f9f9e0421cd38bd8996472bf04ef9383b601759e5a
-  data.tar.gz: 9bb8c5aa186ab1e6364d0ed446dc61e69a0f0ee730cee4c8367586dac69b666a
+  metadata.gz: bbc2c36a98486f496c7c5aed996b3250def9f87ce444dc48e4f8c9164db9e630
+  data.tar.gz: a862bf6d66484f5dac154586dea0a89d85a4873644ff00f4420ac3dfc0c9a852
 SHA512:
-  metadata.gz: ecee89ddb2db25a9ba697ec637f16a2408079b8b3d7d287df0cfdb30d9b7c0a996d6cb38075766d7e3fecf529be6ad90187a1ec95d2d141076ecfe3e2236209a
-  data.tar.gz: 31d7259ac86779530b468392b611f0920b24682f8017e3b50f9a3ca41d30ad08454219881e26eae67d1add7a47d645f7a8b77d253ada4a3d0b5db0f5dbf5e33d
+  metadata.gz: 948d564359a61c1ad356c0806e34c57d6dcae354cc55cf1bff4bce5f40ee94b37edd3c5d8fc35e36cb0aeae59ee467acb561c0074bbb7fb8da929b7e548bcf1f
+  data.tar.gz: f3d98a62dd540957343a29c01624586e853a0f400f8105d2ae67d34e85e408b652befc0d702720e4d7e33852ac738b2a8e276acb6ac143195620386b07e99084

data/CHANGELOG.md

@@ -1,3 +1,7 @@
+## 0.4.2 (2024-06-24)
+
+- Removed dependency on `csv` gem for `load_movielens`
+
 ## 0.4.1 (2024-05-23)
 
 - Reduced memory for `item_recs` and `similar_users`

data/LICENSE.txt

@@ -1,4 +1,4 @@
-Copyright (c) 2019-2022 Andrew Kane
+Copyright (c) 2019-2024 Andrew Kane
 
 MIT License
 

data/lib/disco/data.rb

@@ -1,23 +1,20 @@
 module Disco
   module Data
     def load_movielens
-      require "csv"
-
       item_path = download_file("ml-100k/u.item", "https://files.grouplens.org/datasets/movielens/ml-100k/u.item",
         file_hash: "553841ebc7de3a0fd0d6b62a204ea30c1e651aacfb2814c7a6584ac52f2c5701")
       data_path = download_file("ml-100k/u.data", "https://files.grouplens.org/datasets/movielens/ml-100k/u.data",
         file_hash: "06416e597f82b7342361e41163890c81036900f418ad91315590814211dca490")
 
-      # convert u.item to utf-8
-      movies_str = File.read(item_path).encode("UTF-8", "ISO-8859-1")
-
       movies = {}
-      CSV.parse(movies_str, col_sep: "|") do |row|
+      File.foreach(item_path) do |line|
+        row = line.encode("UTF-8", "ISO-8859-1").split("|")
         movies[row[0]] = row[1]
       end
 
       data = []
-      CSV.foreach(data_path, col_sep: "\t") do |row|
+      File.foreach(data_path) do |line|
+        row = line.split("\t")
         data << {
           user_id: row[0].to_i,
           item_id: movies[row[1]],

data/lib/disco/version.rb

@@ -1,3 +1,3 @@
 module Disco
-  VERSION = "0.4.1"
+  VERSION = "0.4.2"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: disco
 version: !ruby/object:Gem::Version
-  version: 0.4.1
+  version: 0.4.2
 platform: ruby
 authors:
 - Andrew Kane
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2024-05-23 00:00:00.000000000 Z
+date: 2024-06-24 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: libmf
@@ -76,7 +76,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.5.9
+rubygems_version: 3.5.11
 signing_key:
 specification_version: 4
 summary: Recommendations for Ruby and Rails using collaborative filtering