Make DataFrame.from_activerecord faster (#468)

* Make Daru::DataFrame.from_activerecord faster

* Avoid DataFrame#add_row in each block

* Add a benchmark of from_activerecord

* Fix rubocop error

benchmarks/db_loading.rb

@@ -0,0 +1,34 @@
+$:.unshift File.expand_path("../../lib", __FILE__)
+
+require 'benchmark'
+require 'daru'
+require 'sqlite3'
+require 'dbi'
+require 'active_record'
+
+db_name = 'daru_test.sqlite'
+FileUtils.rm(db_name) if File.file?(db_name)
+
+SQLite3::Database.new(db_name).tap do |db|
+  db.execute "create table accounts(id integer, name varchar, age integer, primary key(id))"
+
+  values = 1.upto(100_000).map { |i| %!(#{i},"name_#{i}",#{rand(100)})! }.join(",")
+  db.execute "insert into accounts values #{values}"
+end
+
+ActiveRecord::Base.establish_connection("sqlite3:#{db_name}")
+ActiveRecord::Base.connection
+
+class Account < ActiveRecord::Base; end
+
+Benchmark.bm do |x|
+  x.report("DataFrame.from_sql") do
+    Daru::DataFrame.from_sql(ActiveRecord::Base.connection, "SELECT * FROM accounts")
+  end
+
+  x.report("DataFrame.from_activerecord") do
+    Daru::DataFrame.from_activerecord(Account.all)
+  end
+end
+
+FileUtils.rm(db_name)

lib/daru/io/io.rb

@@ -34,7 +34,7 @@ def try_string_to_number(s)
     end
   end
 
-  module IO # rubocop:disable Metrics/ModuleLength
+  module IO
     class << self
       # Functions for loading/writing Excel files.
 
@@ -134,23 +134,11 @@ def dataframe_write_sql ds, dbh, table
       #
       # @return A dataframe containing the data in the given relation
       def from_activerecord(relation, *fields)
-        if fields.empty?
-          records = relation.map do |record|
-            record.attributes.symbolize_keys
-          end
-          return Daru::DataFrame.new(records)
-        else
-          fields = fields.map(&:to_sym)
-        end
+        fields = relation.klass.column_names if fields.empty?
+        fields = fields.map(&:to_sym)
 
-        vectors = fields.map { |name| [name, Daru::Vector.new([], name: name)] }.to_h
-
-        Daru::DataFrame.new(vectors, order: fields).tap do |df|
-          relation.pluck(*fields).each do |record|
-            df.add_row(Array(record))
-          end
-          df.update
-        end
+        result = relation.pluck(*fields).transpose
+        Daru::DataFrame.new(result, order: fields).tap(&:update)
       end
 
       # Loading data from plain text files