louismullie

Benchmark.bm do |x|
  
  types = {
    banana: 0.2,
    lemon: 0.4,
    orange: 0.4
  }
  
  x.report("select") do
    1.upto(10000) do 

louismullie

# :"test" is faster than "test".intern ...
Benchmark.bm do |x|
  test = 'test'
  x.report { 1000000.times  { "test".intern } }
  x.report { 1000000.times { :"test" } }
end
#       user     system      total        real
#   0.430000   0.000000   0.430000 (  0.429735)
#   0.080000   0.000000   0.080000 (  0.082169)

louismullie

require 'benchmark'
Benchmark.bm do |x|
  empty = []
  not_empty = [:foo, :bar, :baz]
  # (size == 0) is faster than empty? for both empty
  # and non-empty arrays.
  x.report { 1000000.times  { empty.size == 0 } }
  x.report { 1000000.times { not_empty.size == 0 } }
  #    user     system      total        real
  # 0.100000   0.000000   0.100000 (  0.098931)

louismullie

require 'benchmark'

array = (1..1_000_000).to_a
hash = Hash[array.map {|x| [x, nil]}]

Benchmark.bm(15) do |x|
    x.report("Array.include?") { 1000.times { array.include?(500_000) } }
    x.report("Hash.include?") { 1000.times { hash.include?(500_000) } }
end
#                      user     system      total        real

louismullie

      # ClawsC5 = 0
      # Brown = 1
      # Penn = 2
      # Negra = 3
      # Penn Chinese = 4
      # "Simplified" Stanford French Tags = 5

      [

        'Adjective', ['AJ0', 'JJ', 'JJ', '', 'JJ', 'A'],

louismullie

<?xml version="1.0" encoding="us-ascii" standalone="no" ?>
<treat>
<sentence id='70222715664980'  language='eng' tag_set='penn' dependencies=''> <word id='70222715690540'  stem='Happi' tag='NN' tag_opt='' tag_set='penn' category='noun' dependencies=''>Happiness</word>
 <word id='70222715689240'  stem='is' tag='VBZ' tag_opt='' tag_set='penn' category='verb' dependencies=''>is</word>
 <word id='70222715688060'  stem='not' tag='RB' tag_opt='' tag_set='penn' category='adverb' dependencies=''>not</word>
 <word id='70222715686880'  stem='an' tag='DT' tag_opt='' tag_set='penn' category='determiner' dependencies=''>an</word>
 <word id='70222715685640'  stem='ideal' tag='NN' tag_opt='' tag_set='penn' category='noun' dependencies=''>ideal</word>
 <word id='70222715684460'  stem='of' tag='IN' tag_opt='' tag_set='penn' category='preposition' dependencies=''>of</word>
 <word id='70222715683260'  stem='reason' tag='NN' tag_opt='' tag_set='penn' category='noun' dependencies=''>reason</word>
 <punctuation id='70222715698440'

louismullie

 require 'date'
 Treat.sweeten!
 s = Section  "2011/12/23 \n - Obama and Sarkozy met on January 1st to investigate the possibility of a new rescue plan. President Sarkozy is to meet Merkel next Tuesday in Berlin."
 
 s.do(
  :chunk, :segment, :parse, :time, :date,
  :visualize => [
    :dot, {
      :file => 'test-date-time-extraction.dot',
      :colors => {

louismullie

    require 'treat'
    Treat.sweeten!
    p = Paragraph "Obama and Sarkozy met on January 1st to investigate the possibility of a new rescue plan." +
        "President Sarkozy is to meet Merkel next Tuesday in Berlin."

    p.do(
      :coreferences,
      :visualize => [
        :dot, {
          :file => 'ner-coref-extraction.dot',

louismullie

<?php
    function send($host, $method, $path, $data, $useragent = null)
    {
        $str_data = '';
        foreach ($data as $key => $value)
        {
            if ($str_data != '') $str_data .= '&';
            $str_data .= rawurlencode($key) . '=' . rawurlencode($value);
        } 
        // Supply a default method of GET if the one passed was empty

louismullie

require 'benchmark'
require 'set'

a = ['a', 'b', 'c', 'd', 'e', 'f', 'g']
h = {'a' => 1, 'b' => 1, 'c' => 1, 'd' => 1,
     'e' => 1, 'f' => 1, 'g' => 1}

s = Set.new(a)

Benchmark.bm do |x|