natbusa

{0: 'tench, Tinca tinca',
 1: 'goldfish, Carassius auratus',
 2: 'great white shark, white shark, man-eater, man-eating shark, Carcharodon carcharias',
 3: 'tiger shark, Galeocerdo cuvieri',
 4: 'hammerhead, hammerhead shark',
 5: 'electric ray, crampfish, numbfish, torpedo',
 6: 'stingray',
 7: 'cock',
 8: 'hen',
 9: 'ostrich, Struthio camelus',

natbusa

Build docker image

$ cd /path/to/Dockerfile
$ sudo docker build .

View running processes

natbusa

import re

def trailing_digits(str):
  m = re.search('^[0-9]*', str)
  return (str[m.start():m.end()], str[m.end():])

#> trailing_digits('1234 hollywood boulevard')
#> ('1234', ' hollywood boulevard')

natbusa

natbusa

natbusa

natbusa

// $SPARK_HOME/bin/spark-shell --master spark://localhost:7077  --packages com.datastax.spark:spark-cassandra-connector_2.10:1.5.0-M2 --conf spark.cassandra.connection.host=localhost

// let's do some data data science, 
// Idea: 
//
// venues exhibit a typical visit pattern during the week. 
// Some venues are more checked in during the weekends, other during midweek.
// Let's apply machine learning to cluster venues which exhibit 
// the same visiting behavior during the week.

natbusa

// creation flow

POST /api/actors

{
   "data" : {
      "type": "actors",
      "attributes": {
        "type":   "threashold",
        "params": {

natbusa

from httpMethods import *

# Create the graph (profiling tags)

# get (as a http client) every 10 seconds json and emit it on
post('/api/actors',
     {
          "type":"httpclient",
          "trigger": null,      # can also be omitted altogether
          "collect":null,       # can also be omitted altogether

natbusa

$> cat data.txt | grep "streming is awesome" > results.txt