rabbit-slide-kou-rubykaigi-takeout-2021 2021.9.11.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 4e7819063a4ebcbedeb7a6ea8ffad85ca4e15a57ce9aa6dbcecd02f338610d7c
+  data.tar.gz: 6a9734a5a02321f2ce4c1e20676556c0c6efa9aa18649cfa263d1dd3832ce702
+SHA512:
+  metadata.gz: a89c84882adff989423129df414b42cdc4e3f49bc61fb2651bb722105d1a4d06aa5271892cfcb790cc25a54cb6de2d11e1f335977fcf7ba59c436c97d2002eb8
+  data.tar.gz: 8a2d3ea6e38fda7c3972a8f31f5d5dd75c38ac94d852968133f27f1c99e24e0a7aa6a26155f2be330660a1012433310ca0d52bf3fe76395414cfa18b571f269c

data/.rabbit

@@ -0,0 +1 @@
+--size=1920,1080 red-arrow.rab

data/README.rd

@@ -0,0 +1,51 @@
+= Red Arrow - Ruby and Apache Arrow
+
+To use Ruby for data processing widely, Apache Arrow support is important. We can do the followings with Apache Arrow:
+
+  * Super fast large data interchange and processing
+  * Reading/writing data in several famous formats such as CSV and Apache Parquet
+  * Reading/writing partitioned large data on cloud storage such as Amazon S3
+
+This talk describes the followings:
+
+  * What is Apache Arrow
+  * How to use Apache Arrow with Ruby
+  * How to integrate with Ruby 3.0 features such as MemoryView and Ractor
+
+== License
+
+=== Slide
+
+CC BY-SA 4.0
+
+Use the followings for notation of the author:
+
+  * Sutou Kouhei
+
+==== ClearCode Inc. logo
+
+CC BY-SA 4.0
+
+Author: ClearCode Inc.
+
+It is used in page header and some pages in the slide.
+
+== For author
+
+=== Show
+
+  rake
+
+=== Publish
+
+  rake publish
+
+== For viewers
+
+=== Install
+
+  gem install rabbit-slide-kou-rubykaigi-takeout-2021
+
+=== Show
+
+  rabbit rabbit-slide-kou-rubykaigi-takeout-2021.gem

data/Rakefile

@@ -0,0 +1,18 @@
+require "rabbit/task/slide"
+
+# Edit ./config.yaml to customize meta data
+
+spec = nil
+Rabbit::Task::Slide.new do |task|
+  spec = task.spec
+  # spec.files += Dir.glob("doc/**/*.*")
+  spec.files += Dir.glob("images/**/*.*")
+  # spec.files -= Dir.glob("private/**/*.*")
+  spec.add_runtime_dependency("rabbit-theme-clear-code")
+end
+
+desc "Tag #{spec.version}"
+task :tag do
+  sh("git", "tag", "-a", spec.version.to_s, "-m", "Publish #{spec.version}")
+  sh("git", "push", "--tags")
+end

data/config.yaml

@@ -0,0 +1,24 @@
+---
+id: rubykaigi-takeout-2021
+base_name: red-arrow
+tags:
+- rabbit
+- rubykaigi
+- ruby
+- apache_arrow
+presentation_date: 2021-09-11
+version: 2021.9.11.0
+licenses:
+- CC-BY-SA-4.0
+slideshare_id: 
+speaker_deck_id: 
+ustream_id: 
+vimeo_id: 
+youtube_id: 
+author:
+  markup_language: :rd
+  name: Sutou Kouhei
+  email: kou@clear-code.com
+  rubygems_user: kou
+  slideshare_user: kou
+  speaker_deck_user: 

data/red-arrow.rab

@@ -0,0 +1,801 @@
+= Red Arrow
+
+: subtitle
+   ((*Ruby*)) and ((*Apache Arrow*))
+: author
+   Sutou Kouhei
+: institution
+   ClearCode Inc.
+: content-source
+   RubyKaigi Takeout 2021
+: date
+   2021-09-11
+: start-time
+   2021-09-11T13:30:00+09:00
+: end-time
+   2021-09-11T13:55:00+09:00
+: theme
+   .
+
+= Sutou Kouhei\nA president Rubyist
+
+The president of ClearCode Inc.\n
+(('note:クリアコードの社長'))
+
+  # img
+  # src = images/clear-code-rubykaigi-takeout-2021-gold-sponsor.png
+  # relative_height = 100
+  # reflect_ratio = 0.1
+
+= Sutou Kouhei\nAn Apache Arrow contributor
+
+  * A member of PMC of Apache Arrow\n
+    (('note:PMC: Project Management Committee'))\n
+    (('note:Apache Arrowのプロジェクト管理委員会メンバー'))
+  * #2 commits(('note:（コミット数2位）'))
+
+  # img
+  # src = images/apache-arrow-commits-kou.png
+  # relative_height = 120
+  # reflect_ratio = 0.1
+
+= Sutou Kouhei\nThe pioneer in Ruby and Arrow
+
+  * The author of Red Arrow\n
+    (('note:Red Arrowの作者'))
+  * Red Arrow:
+    * The official Apache Arrow library for Ruby\n
+      (('note:公式のRuby用のApache Arrowライブラリー'))
+    * GObject Introspection based bindings\n
+      (('note:GObject Introspectionベースのバインディング'))
+    * Apache Arrow GLib is developed for Red Arrow\n
+      (('note:Red ArrowのためにApache Arrow GLibも開発'))
+
+= GObject Introspection?
+
+(('tag:center'))
+(('tag:margin-bottom * -0.3'))
+A way to implement bindings\n
+(('note:バインディングの実装方法の1つ'))
+
+  # img
+  # src = https://slide.rabbit-shocker.org/authors/kou/rubykaigi-2016/how-to-create-bindings-2016.pdf
+  # relative_height = 90
+
+(('tag:center'))
+(('note:((<URL:https://rubykaigi.org/2016/presentations/ktou.html>))'))
+
+= Why do I work on Red Arrow?\n(('note:なぜRed Arrowの開発をしているか'))
+
+  * To use Ruby for data processing!\n
+    (('note:データ処理でRubyを使いたい！'))
+    * At least a part of data processing\n
+      (('note:データ処理の全部と言わず一部だけでも'))
+  * Results of my 5 years of work:\n
+    (('note:私のここ5年の仕事の成果'))
+    * We can use Ruby for some data processing!\n
+      (('note:いくつかのデータ処理でRubyを使える！'))
+
+= Goal of this talk\n(('note:このトークのゴール'))
+
+  * You want to use Ruby\n
+    for some data processing\n
+    (('note:いくつかのデータ処理でRubyを使いたくなる'))
+  * You join Red Data Tools project\n
+    (('note:Red Data Toolsプロジェクトに参加する'))
+
+= Red Data Tools project?
+
+  # blockquote
+
+  Red Data Tools is a project that provides data processing tools for Ruby
+
+(('note:Red Data ToolsはRuby用のデータ処理ツールを提供するプロジェクト'))
+
+(('note:((<URL:https://red-data-tools.github.io/>))'))
+
+= Data processing?
+
+... how?
+
+= 0. Why do you want?\n(('note:0. データ処理の目的を明らかにする'))
+
+  * What problem do you want to resolve?\n
+    (('note:どんな問題を解決したい？'))
+  * What data is needed for it?\n
+    (('note:そのためにはどんなデータが必要？'))
+  * ...
+
+No Red Arrow support in this area\n
+(('note:このあたりにはRed Arrowを使えない'))
+
+= 1. Collect data\n(('note:1. データ収集'))
+
+  * Where are data?\n
+    (('note:データはどこにある？'))
+  * Where are collected data stored?\n
+    (('note:集めたデータはどこに保存する？'))
+  * ...
+
+Some Red Arrow supports in this area\n
+(('note:このあたりでは少しRed Arrowを使えない'))
+
+= Common dataset\n(('note:よく使われるデータセット'))
+
+  # rouge ruby
+
+  require "datasets"
+  Datasets::Iris.new
+  Datasets::PostalCodeJapan.new
+  Datasets::Wikipedia.new
+
+(('note:((<Red Datasets|URL:https://github.com/red-data-tools/red-datasets>))'))\n
+(('note:((<URL:https://github.com/red-data-tools/red-datasets>))'))
+
+= Output: Local file\n(('note:出力先：ローカルファイル'))
+
+  # rouge ruby
+
+  require "datasets-arrow"
+  dataset = Datasets::PostalCodeJapan.new
+  dataset.to_arrow.save("codes.csv")
+  dataset.to_arrow.save("codes.arrow")
+
+(('note:((<Red Datasets Arrow|URL:https://github.com/red-data-tools/red-datasets-arrow>))'))\n
+(('note:((<URL:https://github.com/red-data-tools/red-datasets-arrow>))'))
+
+= (({#save}))
+
+  * General serialize API for table data\n
+    (('note:テーブルデータ用の汎用シリアライズAPI'))
+    * Serialize as the specified format\n
+      (('note:指定したフォーマットにシリアライズ'))
+    * If you use Red Arrow object for in-memory table data, you can serialize to many formats! Cool!\n
+      (('note:メモリー上のテーブルデータをRed Arrowオブジェクトにするといろんなフォーマットにシリアライズできる！かっこいい！'))
+  * Extensible!\n
+    (('note:拡張可能！'))
+
+= (({#save})): Implementation
+
+  # rouge ruby
+
+  module Arrow
+    class Table
+      def save(output)
+        saver = TableSaver.new(self, output)
+        saver.save
+      end
+    end
+  end
+
+= (({#save})): Implementation
+
+  # rouge ruby
+
+  class Arrow::TableSaver
+    def save
+      format = detect_format(@output)
+      __send__("save_as_#{format}")
+    end
+    def save_as_csv
+    end
+  end
+
+= (({#save})): Extend by Red Parquet
+
+  # rouge ruby
+
+  module Parquet::ArrowTableSavable
+    def save_as_parquet
+    end
+    Arrow::TableSaver.include(self)
+  end
+
+(('note:Red Parquet is a subproject of Red Arrow'))\n
+(('note:Red ParquetはRed Arrowのサブプロジェクト'))
+
+= (({#save})): Extended
+
+  # rouge ruby
+
+  require "datasets-arrow"
+  require "parquet"
+  dataset = Datasets::PostalCodeJapan.new
+  dataset.to_arrow.save("codes.parquet")
+
+= Output: Online storage: Fluentd\n(('note:出力先：オンラインストレージ：Fluentd'))
+
+  * fluent-plugin-s3-arrow:
+    * Collect data by Fluentd\n
+      (('note:Fluentdでデータ収集'))
+    * Format data as Apache Parquet by ((*Red Arrow*))\n
+      (('note:((*Red Arrow*))でApache Parquet形式にデータを変換'))
+    * Store data to Amazon S3 by fluent-plugin-s3\n
+      (('note:fluent-plugin-s3でAmazon S3にデータを保存'))
+    * By @kanga33 at Speee/Red Data Tools\n
+      (('note:Speee/Red Data Toolsの香川さんが開発'))
+
+(('note:((<URL:https://github.com/red-data-tools/fluent-plugin-s3-arrow/>))'))
+
+= Output: Online storage: Red Arrow\n(('note:出力先：オンラインストレージ：Red Arrow'))
+
+  # rouge ruby
+
+  require "datasets-arrow"
+  require "arrow-dataset"
+  dataset = Datasets::PostalCodeJapan.new
+  url = URL("s3://mybucket/codes.parquet")
+  dataset.to_arrow.save(url)
+
+(('Implementing...'))\n
+(('note:実装中。。。'))
+
+= (({#save})): Implementing...
+
+  # rouge ruby
+
+  class Arrow::TableSaver
+    def save
+      if @output.is_a?(URI)
+        __send__("save_to_uri")
+      else
+        __send__("save_to_file")
+      end
+    end
+  end
+
+= Collect data w/ Red Arrow: Wrap up\n(('note:Red Arrowでデータ収集：まとめ'))
+
+  * Usable as serializer for common formats\n
+    (('note:よくあるフォーマットにシリアライズするツールとして使える'))
+  * Usable as writer to common locations\n
+    (('note:in the near future...'))\n
+    (('note:近いうちによくある出力先に書き出すツールとして使える'))
+
+= 2. Read data\n(('note:2. データ読み込み'))
+
+  * What format is used?\n
+    (('note:どんなフォーマットで保存されている？'))
+  * Where are collected data?\n
+    (('note:収集したデータはどこ？'))
+  * How large is collected data?\n
+    (('note:データはどれかで大きい？'))
+
+= Format\n(('note:フォーマット'))
+
+  # rouge ruby
+
+  require "arrow"
+  table = Arrow::Table.load("data.csv")
+  table = Arrow::Table.load("data.json")
+  table = Arrow::Table.load("data.arrow")
+  table = Arrow::Table.load("data.orc")
+
+= (({.load}))
+
+  * General deserialize API for table data\n
+    (('note:テーブルデータ用の汎用デシリアライズAPI'))
+    * Deserialize common formats\n
+      (('note:よく使われているフォーマットからデシリアライズ'))
+  * Extensible!\n
+    (('note:拡張可能！'))
+
+= (({.load})): Implementation
+
+  # rouge ruby
+
+  module Arrow
+    def Table.load(input)
+      loader = TableLoader.new(self, input)
+      loader.load
+    end
+  end
+
+= (({.load})): Implementation
+
+  # rouge ruby
+
+  class Arrow::TableLoader
+    def load
+      format = detect_format(@output)
+      __send__("load_as_#{format}")
+    end
+    def load_as_csv
+    end
+  end
+
+= (({.load})): Extend by Red Parquet
+
+  # rouge ruby
+
+  module Parquet::ArrowTableLoadable
+    def load_as_parquet
+    end
+    Arrow::TableLoader.include(self)
+  end
+
+(('note:Red Parquet is a subproject of Red Arrow'))\n
+(('note:Red ParquetはRed Arrowのサブプロジェクト'))
+
+= (({.load})): Extended
+
+  # rouge ruby
+
+  require "parquet"
+  table = Arrow::Table.load("data.parquet")
+
+= (({.load})): More extensible
+
+  # rouge ruby
+
+  class Arrow::TableLoader
+    def load
+      if @output.is_a?(URI)
+        __send__("load_from_uri")
+      else
+        __send__("load_from_file")
+      end
+    end
+  end
+
+= (({.load})): Extend by Red Arrow Dataset
+
+  # rouge ruby
+
+  module ArrowDataset::ArrowTableLoadable
+    def load_from_uri
+    end
+    Arrow::TableLoader.include(self)
+  end
+
+(('note:Red Arrow Dataset is a subproject of Red Arrow'))\n
+(('note:Red Arrow DatasetはRed Arrowのサブプロジェクト'))
+
+= Location: Online storage\n(('note:場所：オンラインストレージ'))
+
+  # rouge ruby
+
+  require "arrow-dataset"
+  url = URI("s3://bucket/path...")
+  table = Arrow::Table.load(url)
+
+= Location: RDBMS\n(('note:場所：RDBMS'))
+
+  # rouge ruby
+
+  require "arrow-activerecord"
+  User.all.to_arrow
+
+(('note:((<Red Arrow Active Record|URL:https://github.com/red-data-tools/red-arrow-activerecord>))'))\n
+(('note:((<URL:https://github.com/red-data-tools/red-arrow-activerecord>))'))
+
+= Location: Network\n(('note:場所：ネットワーク'))
+
+  # rouge ruby
+
+  require "arrow-flight"
+  client = ArrowFlight::Client.new(url)
+  info = client.list_flights[0]
+  reader = client.do_get(info.endpoints[0].ticket)
+  table = reader.read_all
+
+(('note:((<Introducing Apache Arrow Flight: A Framework for Fast Data Transport|URL:https://arrow.apache.org/blog/2019/10/13/introducing-arrow-flight/>))'))\n
+(('note:((<URL:https://arrow.apache.org/blog/2019/10/13/introducing-arrow-flight/>))'))
+
+= Large data\n(('note:大規模データ'))
+
+  * Apache Arrow format
+    * Designed for large data\n
+      (('note:大規模データ用に設計されている'))
+  * For large data\n
+    (('note:大規模データ用に必要なもの'))
+    * Fast load\n
+      (('note:高速にロードできること'))
+    * ...
+
+= Fast load: Benchmark\n(('note:高速ロード：ベンチマーク'))
+
+  # rouge ruby
+
+  require "datasets-arrow"
+  dataset = Datasets::PostalCodeJapan.new
+  table = dataset.to_arrow # 124271 records
+  n = 5
+  n.times do |i|
+    table.save("codes.#{i}.csv")
+    table.save("codes.#{i}.arrow")
+    CSV.read("codes.#{i}.csv")
+    Arrow::Table.load("codes.#{i}.csv")
+    Arrow::Table.load("codes.#{i}.arrow")
+    table = table.concatenate([table])
+  end
+
+= Fast load: Benchmark: All\n(('note:高速ロード：ベンチマーク：すべて'))
+
+  # charty
+  # backend = pyplot
+  # type = line
+  # x = N (times)
+  # y = Elapsed time (sec)
+  # color = Approach
+  # markers = true
+  # relative_height = 100
+  Approach,N (times),Elapsed time (sec)
+  Apache Arrow,1,0.000437
+  Apache Arrow,2,0.000421
+  Apache Arrow,3,0.000472
+  Apache Arrow,4,0.000573
+  Apache Arrow,5,0.000899
+  CSV: Red Arrow,1,0.012443
+  CSV: Red Arrow,2,0.021403
+  CSV: Red Arrow,3,0.040435
+  CSV: Red Arrow,4,0.074629
+  CSV: Red Arrow,5,0.138448
+  CSV: Ruby,1,0.828678
+  CSV: Ruby,2,1.840314
+  CSV: Ruby,3,3.797536
+  CSV: Ruby,4,8.205680
+  CSV: Ruby,5,19.850910
+
+== Slide properties
+
+: enable-title-on-image
+   false
+
+= Fast load: Benchmark: Red Arrow\n(('note:高速ロード：ベンチマーク：Red Arrow'))
+
+  # charty
+  # backend = pyplot
+  # type = line
+  # x = N (times)
+  # y = Elapsed time (sec)
+  # color = Approach
+  # markers = true
+  # relative_height = 100
+  Approach,N (times),Elapsed time (sec)
+  Apache Arrow,1,0.000437
+  Apache Arrow,2,0.000421
+  Apache Arrow,3,0.000472
+  Apache Arrow,4,0.000573
+  Apache Arrow,5,0.000899
+  CSV: Red Arrow,1,0.012443
+  CSV: Red Arrow,2,0.021403
+  CSV: Red Arrow,3,0.040435
+  CSV: Red Arrow,4,0.074629
+  CSV: Red Arrow,5,0.138448
+
+== Slide properties
+
+: enable-title-on-image
+   false
+
+= How to implement fast load\n(('note:高速ロードの実装方法'))
+
+  # img
+  # src = https://slide.rabbit-shocker.org/authors/kou/db-tech-showcase-online-2020/why-apache-arrow-format-is-fast.pdf
+  # relative_height = 80
+
+(('tag:center'))
+(('note:((<URL:https://slide.rabbit-shocker.org/authors/kou/db-tech-showcase-online-2020/>))'))
+
+= Read data with Red Arrow: Wrap up\n(('note:Red Arrowでデータ読み込み：まとめ'))
+
+  * Easy to read common formats\n
+    (('note:よくあるフォーマットのデータを簡単に読める'))
+  * Easy to read from common locations\n
+    (('note:よくある場所にあるデータを簡単に読める'))
+  * Large data ready\n
+    (('note:大規模データも扱える'))
+
+= 3. Explore data\n(('note:3. データ探索'))
+
+  * Preprocess data(('note:（データを前処理）'))
+    * Filter out needless data(('note:（不要なデータを除去）'))
+    * ...
+  * Summarize data and visualize them\n
+    (('note:（データを要約して可視化）'))
+  * ...
+
+Red Arrow can be used for some operations\n
+(('note:いくつかの操作でRed Arrowを使える'))
+
+= Filter: Red Arrow\n(('note:絞り込み：Red Arrow'))
+
+  # rouge ruby
+
+  table = Datasets::PostalCodeJapan.new.to_arrow
+  table.n_rows # 124271
+  filtered_table = table.slice do |slicer|
+    slicer.prefecture == "東京都" # Tokyo
+  end
+  filtered_table.n_rows # 3887
+
+= Filter: Performance\n(('note:絞り込み：性能'))
+
+  # rouge ruby
+
+  dataset = Datasets::PostalCodeJapan.new
+  arrow_dataset = dataset.to_arrow
+  dataset.find_all do |row|
+    row.prefecture == "東京都" # Tokyo
+  end # 1.256s
+  arrow_dataset.slice do |slicer|
+    slicer.prefecture == "東京都" # Tokyo
+  end # 0.001s
+
+= Filter: Performance\n(('note:絞り込み：性能'))
+
+  # charty
+  # backend = pyplot
+  # type = bar
+  # x = Elapsed time (sec)
+  # y = Implementation
+  # relative_height = 100
+  Implementation,Elapsed time (sec)
+  Ruby,1.2567864
+  Arrow,0.001395
+
+== Slide properties
+
+: enable-title-on-image
+   false
+
+= Apache Arrow data: Interchangeable\n(('note:Apache Arrow data：交換可能'))
+
+  * With low cost thanks to fast load\n
+    (('note:高速ロードできるので低コスト'))
+  * Apache Arrow data ready systems are increasing\n
+    (('note:Apache Arrowデータを扱えるシステムは増加中'))
+    * e.g. DuckDB: in-process SQL OLAP DBMS\n
+      (('note:(SQLite like DBMS for OLAP)'))\n
+      (('note:OLAP: OnLine Analytical Processing'))\n
+      (('note:例：DuckDB：同一プロセス内で動くデータ分析用SQL DB管理システム'))
+
+= Filter: DuckDB\n(('note:絞り込み：DuckDB'))
+
+  # rouge ruby
+
+  require "arrow-duckdb"
+  codes = Datasets::PostalCodeJapan.new.to_arrow
+  db = DuckDB::Database.open
+  c = db.connect
+  c.register("codes", codes) do # Use codes without copy
+    c.query("SELECT * FROM codes WHERE prefecture = ?",
+            "東京都", # Tokyo
+            output: :arrow) # Output as Apache Arrow data
+     .to_table.n_rows # 3887
+  end
+
+= Summarize: Group + aggregation\n(('note:要約：グループ化して集計'))
+
+  # rouge ruby
+
+  iris = Datasets::Iris.new.to_arrow
+  iris.group(:label).count(:sepal_length)
+  # 	count(sepal_length)	label
+  # 0	                 50	Iris-setosa
+  # 1	                 50	Iris-versicolor
+  # 2	                 50	Iris-virginica
+
+= Visualize: Charty\n(('note:可視化：Charty'))
+
+  # rouge ruby
+
+  require "charty"
+  Charty.backends.use("pyplot")
+  Charty.scatter_plot(data: iris,
+                      x: :sepal_length,
+                      y: :sepal_width,
+                      color: :label)
+        .save("iris.png")
+
+= Visualize: Charty: Result\n(('note:可視化：Charty：結果'))
+
+  # img
+  # src = images/iris.png
+  # relative_height = 100
+
+== Slide properties
+
+: enable-title-on-image
+   false
+
+= 4. Use insight\n(('note:4. 知見を活用'))
+
+  * Write report\n(('note:（レポートにまとめたり）'))
+  * Build a model\n(('note:（モデルを作ったり）'))
+  * ...
+
+No Red Arrow support in this area for now\n
+(('note:Can be used for passing data to other tools like DuckDB and Charty'))\n
+(('note:今のところこのあたりにはRed Arrowを使えない'))\n
+(('note:DuckDBやChartyにデータを渡すように他のツールにデータを渡すためには使える'))
+
+= Data processing and Red Arrow\n(('note:Red Arrowでデータ処理'))
+
+  * Red Arrow helps us in some areas\n
+    (('note:いくつかの領域ではRed Arrowを使える'))
+    * Collect, read and explore data\n
+      (('note:データを収集して読み込んで探索するとか'))
+  * Some tools can integrate with Red Arrow\n
+    (('note:いくつかのツールはRed Arrowと連携できる'))
+    * Fluentd, DuckDB, Charty, ...
+
+= Red Arrow and Ruby 3.0
+
+  * MemoryView support
+  * Ractor support
+
+= MemoryView
+
+  # blockquote
+
+  MemoryView provides the features to share multidimensional homogeneous arrays of fixed-size element on memory among extension libraries.
+
+(('note:MemoryViewは多次元数値配列（数値はすべて同じ型）を共有する機能を提供します。'))
+
+(('note:((<URL:https://docs.ruby-lang.org/en/master/doc/memory_view_md.html>))'))\n
+(('note:((<URL:https://tech.speee.jp/entry/2020/12/24/093131>)) (Japanese)'))
+
+= Numeric arrays in Red Arrow\n(('note:Red Arrow内の数値配列'))
+
+  * (({Arrow::NumericArray})) family
+    * 1-dimensional numeric array\n
+      (('note:1次元数値配列'))
+  * (({Arrow::Tensor}))
+    * Multidimensional homogeneous numeric arrays\n
+      (('note:多次元数値配列'))
+
+= MemoryView: Red Arrow
+
+  * (({Arrow::NumericArray})) family
+    * Export as MemoryView: Support\n
+      (('note:MemoryViewとしてエクスポート：対応済み'))
+    * Import from MemoryView: Not yet\n
+      (('note:MemoryViewをインポート：未対応'))
+  * (({Arrow::Tensor}))
+    * Export/Import: Not yet\n
+      (('note:エクスポート・インポート：未対応'))
+
+(('note:Join Red Data Tools to work on this!'))\n
+(('note:対応を進めたい人はRed Data Toolsに来てね！'))
+
+= MemoryView: C++
+
+  * Some problems are found by this work\n
+    (('note:Red Arrowの対応作業でいくつかの問題が見つかった'))
+    * Can't use (({private})) as member name\n
+      (('note:メンバー名に(({private}))を使えない'))
+    * Can't assign to (({const})) variable with cast\n
+      (('note:キャストしても(({const}))変数に代入できない'))
+  * Ruby 3.1 will fix them\n
+    (('note:Ruby 3.1では直っているはず'))
+
+= Ractor
+
+  # blockquote
+
+  Ractor is designed to provide a parallel execution feature of Ruby without thread-safety concerns.
+
+(('note:Ractorはスレッドセーフかどうかを気にせずに並列実行するための機能です。'))
+
+(('note:((<URL:https://docs.ruby-lang.org/en/master/doc/ractor_md.html>))'))\n
+(('note:((<URL:https://techlife.cookpad.com/entry/2020/12/26/131858>)) (Japanese)'))
+
+= Red Arrow and concurrency\n(('note:Red Arrowと並列性'))
+
+  * Red Arrow data are immutable\n
+    (('note:Red Arrowデータは変更不可'))
+  * Ractor can share frozen objects\n
+    (('note:Ractorはfrozenなオブジェクトを共有可能'))
+
+= Ractor: Red Arrow
+
+  # rouge ruby
+
+  require "datasets-arrow"
+  table = Datasets::PostalCodeJapan.new.to_arrow
+  Ractor.make_shareable(table)
+  Ractor.new(table) do |t|
+    t.slice do |slicer|
+      slicer.prefecture == "東京都" # Tokyo
+    end
+  end
+
+= Ractor: Red Arrow: Benchmark
+
+  # rouge ruby
+
+  n_ractors = 4
+  n_jobs_per_ractor = 1000
+  n_jobs = n_ractors * n_jobs_per_ractor
+  n_jobs.times do
+    table.slice {|s| s.prefecture == "東京都"}
+  end
+  n_ractors.times.collect do
+    Ractor.new(table, n_jobs_per_ractor) do |t, n|
+      n.times {t.slice {|s| s.prefecture == "東京都"}}
+    end
+  end.each(&:take)
+
+= Ractor: Red Arrow: Benchmark
+
+  # charty
+  # backend = pyplot
+  # type = bar
+  # x = Elapsed time (sec)
+  # y = Approach
+  # relative_height = 100
+  Approach,Elapsed time (sec)
+  Sequential,4.573742
+  Ractor,1.454987
+
+== Slide properties
+
+: enable-title-on-image
+   false
+
+= Wrap up\n(('note:まとめ'))
+
+  * Ruby can be used\n
+    in some data processing work\n
+    (('note:いくつかのデータ処理作業にRubyを使える'))
+    * Red Arrow helps you!\n
+      (('note:Red Arrowが有用なケースがあるはず！'))
+  * Ruby 3.0 has useful features for data processing work\n
+    (('note:Ruby 3.0にはデータ処理作業に有用な機能があるよ'))
+    * Red Arrow starts supporting them\n
+      (('note:Red Arrowはそれらのサポートを進めている'))
+
+= Goal of this talk\n(('note:このトークのゴール'))
+
+  * You want to use Ruby\n
+    for some data processing\n
+    (('note:いくつかのデータ処理でRubyを使いたくなる'))
+  * You join Red Data Tools project\n
+    (('note:あなたがRed Data Toolsプロジェクトに参加する'))
+
+= Feature work\n(('note:今後の仕事'))
+
+  * Implement DataFusion bindings by adding C API to DataFusion\n
+    (('note:DataFusionにC APIを追加してバインディングを実装'))
+    * DataFusion: Apache Arrow native query execution framework written in Rust\n
+      (('note:((<URL:https://github.com/apache/arrow-datafusion/>))'))\n
+      (('note:DataFusion：Rust実装のApache Arrowベースのクエリー実行フレームワーク'))
+  * Add Active Record like API to Red Arrow\n
+    (('note:Red ArrowにActive Record風のAPIを追加'))
+  * Improve MemoryView/Ractor support\n
+    (('note:MemoryView/Ractorサポートを進める'))
+
+= Red Data Tools
+
+(('tag:center'))
+(('tag:x-large'))
+Join us!
+
+(('note:((<URL:https://red-data-tools.github.io/>))'))\n
+(('note:((<URL:https://gitter.im/red-data-tools/en>))'))
+
+(('note:((<URL:https://red-data-tools.github.io/ja/>))'))\n
+(('note:((<URL:https://gitter.im/red-data-tools/ja>))'))
+
+= OSS Gate on-boarding\n(('note:OSS Gateオンボーディング'))
+
+  * Supports accepting newcomers by OSS projects such as Ruby & Red Arrow\n
+    (('note:RubyやRed ArrowといったOSSプロジェクトが新人を受け入れることを支援'))
+  * Contact me!(('note:興味がある人は私に教えて！'))
+    * (('tag:x-small'))OSS project members who want to accept newcomers\n
+      (('note:新人を受け入れたいOSSプロジェクトのメンバー'))
+    * (('tag:x-small'))Companies which want to support OSS Gate on-boarding\n
+      (('note:OSS Gateオンボーディングを支援したい会社'))
+
+(('note:((<URL:https://oss-gate.github.io/on-boarding/>))'))
+
+= ClearCode Inc.
+
+  * Recruitment: Developer to work on Red Arrow related business\n
+    (('note:採用情報：Red Arrow関連のビジネスをする開発者'))
+    * (('note:((<URL:https://www.clear-code.com/recruitment/>))'))
+  * Business: Apache Arrow/Red Arrow related technical support/consulting:\n
+    (('note:仕事：Apache Arrow/Red Arrow関連の技術サポート・コンサルティング'))
+    * (('note:((<URL:https://www.clear-code.com/contact/>))'))

data/theme.rb

@@ -0,0 +1 @@
+include_theme("clear-code")

metadata

@@ -0,0 +1,92 @@
+--- !ruby/object:Gem::Specification
+name: rabbit-slide-kou-rubykaigi-takeout-2021
+version: !ruby/object:Gem::Version
+  version: 2021.9.11.0
+platform: ruby
+authors:
+- Sutou Kouhei
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2021-08-23 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rabbit
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 2.0.2
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 2.0.2
+- !ruby/object:Gem::Dependency
+  name: rabbit-theme-clear-code
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+description: |-
+  To use Ruby for data processing widely, Apache Arrow support is important. We can do the followings with Apache Arrow:
+
+    * Super fast large data interchange and processing
+    * Reading/writing data in several famous formats such as CSV and Apache Parquet
+    * Reading/writing partitioned large data on cloud storage such as Amazon S3
+
+  This talk describes the followings:
+
+    * What is Apache Arrow
+    * How to use Apache Arrow with Ruby
+    * How to integrate with Ruby 3.0 features such as MemoryView and Ractor
+email:
+- kou@clear-code.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".rabbit"
+- README.rd
+- Rakefile
+- config.yaml
+- images/apache-arrow-commits-kou.png
+- images/clear-code-rubykaigi-takeout-2021-gold-sponsor.png
+- images/iris.png
+- pdf/rubykaigi-takeout-2021-red-arrow.pdf
+- red-arrow.rab
+- theme.rb
+homepage: https://slide.rabbit-shocker.org/authors/kou/rubykaigi-takeout-2021/
+licenses:
+- CC-BY-SA-4.0
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.3.0.dev
+signing_key: 
+specification_version: 4
+summary: Red Arrow - Ruby and Apache Arrow
+test_files: []