goldsmith

# set up flags for Numpy C extentions compiling
export CFLAGS="-arch i386 -arch x86_64"
export FFLAGS="-m32 -m64"
export LDFLAGS="-Wall -undefined dynamic_lookup -bundle -arch i386 -arch x86_64"
export CC=gcc-4.2
export CXX="g++ -arch i386 -arch x86_64"

pip install numpy
# success!

jackschultz

import nltk
import requests

FREEBASE_API_KEY = ''

class FindNames(object):

  def __init__(self, text, freebase_api_key):
    self.text = text
    self.key = freebase_api_key

joelittlejohn

(def t
  "trie containing the 100,000 most common english words"
  (with-open [r (clojure.java.io/reader "/tmp/words-100000")]
    (reduce #(assoc-in %1 %2 (sorted-map \0 nil)) (sorted-map) (line-seq r))))

(defn search [p m]
  "return a sorted sequence of all words in the trie m that start with the given prefix p"
  (let [n (get-in m p)
        next (mapcat #(search (str p (key %)) m) (dissoc n \0))]
    (if (contains? n \0) (cons p next) next)))

crowdmatt

Setting up Flume NG, listening to syslog over UDP, with an S3 Sink

My goal was to set up Flume on my web instances, and write all events into s3, so I could easily use other tools like Amazon Elastic Map Reduce, and Amazon Red Shift.

I didn't want to have to deal with log rotation myself, so I setup Flume to read from a syslog UDP source. In this case, Flume NG acts as a syslog server, so as long as Flume is running, my web application can simply write to it in syslog format on the specified port. Most languages have plugins for this.

At the time of this writing, I've been able to get Flume NG up and running on 3 ec2 instances, and all writing to the same bucket.

Install Flume NG on instances

samuelclay

(ns radix
  (:require [clojure.string :as string]))
(use 'clojure.java.io)
(use 'clojure.pprint)

(println "Loading names... ")
(time (def names
    (with-open 
      [rdr (reader 
            "/usr/share/dict/ProperNames")]

brandonb927

#!/bin/sh

###
# SOME COMMANDS WILL NOT WORK ON macOS (Sierra or newer)
# For Sierra or newer, see https://github.com/mathiasbynens/dotfiles/blob/master/.macos
###

# Alot of these configs have been taken from the various places
# on the web, most from here
# https://github.com/mathiasbynens/dotfiles/blob/5b3c8418ed42d93af2e647dc9d122f25cc034871/.osx

smougenot

  # stacktrace java as one message
  multiline {
    #type => "all" # no type means for all inputs
    pattern => "(^.+Exception: .+)|(^\s+at .+)|(^\s+... \d+ more)|(^\s*Caused by:.+)"
    what => "previous"
  }

jgeurts

####################################
# BASIC REQUIREMENTS
# http://graphite.wikidot.com/installation
# http://geek.michaelgrace.org/2011/09/how-to-install-graphite-on-ubuntu/
# Last tested & updated 10/13/2011
####################################

cd
sudo apt-get update
sudo apt-get upgrade

jboner

Latency Comparison Numbers (~2012)
----------------------------------
L1 cache reference                           0.5 ns
Branch mispredict                            5   ns
L2 cache reference                           7   ns                      14x L1 cache
Mutex lock/unlock                           25   ns
Main memory reference                      100   ns                      20x L2 cache, 200x L1 cache
Compress 1K bytes with Zippy             3,000   ns        3 us
Send 1K bytes over 1 Gbps network       10,000   ns       10 us
Read 4K randomly from SSD*             150,000   ns      150 us          ~1GB/sec SSD

methane

from time import sleep
from tornado.httpserver import HTTPServer
from tornado.ioloop import IOLoop
from tornado.web import Application, asynchronous, RequestHandler
from multiprocessing.pool import ThreadPool

_workers = ThreadPool(10)

def run_background(func, callback, args=(), kwds={}):
    def _callback(result):