Dieterbe

     def __getitem__(self, doc):
        import time
        # get similarities of doc to all documents in the corpus
        b = time.time()
        if self.normalize:
            doc = matutils.unitVec(doc)
        allSims = self.getSimilarities(doc)
        a = time.time()

        # return either all similarities as a list, or only self.numBest most similar, depending on settings from the constructor

Dieterbe

#!/bin/bash
if [ -z "$1" ]; then
	echo "pass a number as \$1 (storage nodes are numbered, i.e. 1 and 2)"
	exit 2
fi
name="crowbar_swift_$1"

# Create and Register the VM with VirtualBox
VBoxManage createvm --register --name "$name"

Dieterbe

description "Statsd upstart initscript"
author "Dieter Plaetinck <dieter@vimeo.com>"

# based on http://newcome.wordpress.com/2012/02/26/running-programs-as-linux-daemons-using-upstart/

# Stanzas
#
# Stanzas control when and how a process is started and stopped
# See a list of stanzas here: http://upstart.ubuntu.com/wiki/Stanzas#respawn

Dieterbe

// Dieter Plaetinck <dieter@vimeo.com>
// based on https://github.com/feedhenry/openstack-storage

var request = require('request');
var async = require('async');
var url = require('url');

var defaults = {
  openstackIdentityTokens: "/auth/v1.0"
};

Dieterbe

## graphing/trending dashboards (not alerting)
i see 3 main uses cases:

* interactively selecting datasources to satisfy a specific need ("i want to find out what went wrong yesterday 4-5PM on our memcache cluster, so i'm gonna have a look at different graphs in this timerange, each graph containing 1-N datapoints from various sources")
* trend analysis, prediction and anomaly detection
* more "fixed" dashboards, like amount of storage available/used on storage cluster, the past month. this point becomes less important if you can set up good alerting (based on datapoints or on predictions) but is still useful to have.

### must haves

* date/time range selection through UI widgets (datetime pickers)

Dieterbe

#!/bin/bash

# find-updated-wsp.sh: a tool to detect updated wsp files, useful for finding statsd daemons still writing metrics to graphite;
# especially useful when you tell statsd to write to new graphite servers, and you want to make sure nothing is writing data to the old graphite machine.
# why this way:
# * you can't just check for network traffic, statsd will stay connected even when it has no data to send
# * plain mtime of wsp files is not sufficient: statsd will keep writing the last known value to gauges, and 0's for inactive counters, this data should be ignored.
# * both statsd and graphite write stats of their own, updates of these files can be ignored.

# this script has two modes of operation, based on $1:

Dieterbe

#!/usr/bin/python2
import hmac
import sys
from hashlib import sha1
from time import time
method = 'GET'
base = sys.argv[1]
path = sys.argv[2]
key = sys.argv[3]
expires = int(time() + int(sys.argv[4]))

Dieterbe

#!/usr/bin/php
<?php
$method = 'GET';
$base = $argv[1];
$path = $argv[2];
$key = $argv[3];
$expires = time() + $argv[4];
$hmac_body = "$method\n$expires\n$path";
$sig = hash_hmac('sha1', $hmac_body, $key);
echo "$base$path?temp_url_sig=$sig&temp_url_expires=$expires\n";

Dieterbe

26c26
< from random import shuffle
---
> from random import random, shuffle
363a364
>         self.random = random
380c381,384
<             parts.append('@%s' % (sample_rate,))
---
>             if self.random() < sample_rate:

Dieterbe

#!/bin/bash
# dependencies: xdotool
# auto-advance html slides
# <dieter@vimeo.com>
html_file="$1"
BROWSER=chromium
slide=1

right () {
    slide=$((slide+1))