nyov

class MySpider(Spider):
	# [...]
	
	# start requests from generator
	def start_requests(self):
		url = 'http://some.page.tld/%s/category'
		for page in xrange(1, 247):
			link = url % page
			yield Request(url=link)

IPrism

#!/bin/bash
### BEGIN INIT INFO
# Provides:          APPLICATION
# Required-Start:    $all
# Required-Stop:     $network $local_fs $syslog
# Default-Start:     2 3 4 5
# Default-Stop:      0 1 6
# Short-Description: Start the APPLICATION unicorns at boot
# Description:       Enable APPLICATION at boot time.
### END INIT INFO

zh

require 'em-redis'
require 'redis'
require 'redis/distributed'
require "fiber_pool"

class Redis
  class Distributed

    def initialize(urls, options = {})
      @tag = options.delete(:tag) || /^\{(.+?)\}/

gonz

gonz@bamboo:~ > git clone git://github.com/maccman/juggernaut.git
Cloning into juggernaut...
remote: Counting objects: 558, done.
remote: Compressing objects: 100% (258/258), done.
remote: Total 558 (delta 309), reused 481 (delta 255)
Receiving objects: 100% (558/558), 576.74 KiB | 135 KiB/s, done.
Resolving deltas: 100% (309/309), done.

gonz@bamboo:~ > cd juggernaut

dblock

module Mongoid
  class Criteria
    
    def each_by(by, &block)
      idx = 0
      total = 0
      set_limit = options[:limit]
      while ((results = ordered_clone.limit(by).skip(idx)) && results.any?)
        results.each do |result|
          return self if set_limit and set_limit >= total

csanz

#Drone Specs

Space Specs

• Flat Area
• Great wifi
• Hopefully High ceilings without any crazy wires (eg. 120ft high ceilings in Berlin)

Spare parts

yankov

mkdir project1
cd project1

sbt
set name := "project1"
set version := "1.0"
set scalaVersion := "2.9.3"
session save
exit

tovbinm

// Excercies from chapter 5: Strictness and laziness

def foldRight[A,B](z: => B)(s: Stream[A])(f: (A, => B) => B): B =
  s match {
    case hd #:: tail => f(hd, foldRight(z)(tail)(f))
    case _ => z
  }

def exists[A](s: Stream[A])(p: A => Boolean): Boolean =
	foldRight(false)(s)((x,a) => if (p(x)) true else a)

tovbinm

var AMP = 0.5; // amplitude
var len = 15; // seconds
e = new webkitAudioContext();
var source = e.createBufferSource();
var SR = e.sampleRate;
source.buffer = e.createBuffer(1, len * SR, SR);
var dat = source.buffer.getChannelData(0);
for (var i = 0; i < len * SR; i++) {
  dat[i] = AMP * (Math.random() * 2 - 1);
}

pprett

"""Parallel grid search for sklearn's GradientBoosting.

This script uses IPython.parallel to run cross-validated
grid search on an IPython cluster. Each cell on the parameter grid
will be evaluated ``K`` times - results are stored in MongoDB.

The procedure tunes the number of trees ``n_estimators`` by averaging
the staged scores of the GBRT model averaged over all K folds.

You need an IPython ipcluster to connect to - for local use simply