andry1

from data_requirements import DataRequirements
from data_source import DataSource
from sentiment_redshift import RedshiftRavenPackDataProvider, Equity
from pandas import to_datetime
import pandas as pd
from collections import namedtuple
from sqlalchemy import create_engine
import pytz

redshift = create_engine('redshift+psycopg2://masteruser:M4steruser@marketdata-test.cq0v4ljf3cuw.us-east-1.redshift.amazonaws.com:5439/dev', echo=True)

andry1

#!/usr/bin/env groovy

//@Grab('com.tinkerpop.blueprints:blueprints-core:2.6.0')
//import com.tinkerpop.blueprints.impls.tg.TinkerGraph
@Grab('com.thinkaurelius.titan:titan-all:0.5.4')
import com.thinkaurelius.titan.core.TitanFactory
import com.tinkerpop.blueprints.Vertex
@Grab('com.xlson.groovycsv:groovycsv:1.0')
import static com.xlson.groovycsv.CsvParser.parseCsv
import com.tinkerpop.blueprints.util.io.graphson.GraphSONWriter

andry1

andry1

---
  - hosts: druid
    sudo: yes
    tasks:
      - name: Create partitions
        command: /sbin/parted --script /dev/{{ item }} mklabel gpt
        command: /sbin/parted --script /dev/{{ item }} mkpart primary 0% 100%
        with_items:
          - sda
          - sdb

andry1

andry1

{
"Acrobatics": "Acrobatics",
"Aerobatics": "Aerobatics",
"Air Racing": "Air Racing",
"Alpine Skiing": "Alpine Skiing",
"American Handball": "American Handball",
"Archery": "Archery",
"Arena Football": "Arena Football",
"Arm Wrestling": "Arm Wrestling",
"Artistic Cycling": "Artistic Cycling",

andry1

#!/usr/bin/env ruby

require 'json'
require 'json/add/core'
require 'open-uri'
require 'pp'

api_results = JSON open('http://www.sport195.com/api/service/-/profiles/sports?per_page=10000').read
english_translations = JSON open('./english_translations.json').read

andry1

#!/usr/bin/env ruby

require 'colorize'

regions = ARGF.each_line.collect do |l|
  l.chomp!
  next if l.length < 1
  l
end.compact

andry1

#!/usr/bin/env ruby

#
# HOW TO USE:
#
# $ gem install activerecord
# $ irb
# irb> require './oozie_db.rb'
# irb> coord = Coordinator.find("BIG-LONG-ID-C")
# irb> coord.coordinator_actions.map(&:missing_dependencies).select {|d| d != ""} # => Find all actions with missing dependencies

andry1

SET mapreduce.output.fileoutputformat.compress true
SET mapreduce.output.fileoutputformat.compress.codec org.apache.hadoop.io.compress.SnappyCodec
SET mapreduce.output.fileoutputformat.compress.type BLOCK
SET pig.exec.mapPartAgg true
SET mapreduce.job.queuename testing

xfp_all = LOAD 'chris_295640.impression' USING org.apache.hcatalog.pig.HCatLoader();
xfp_partition = FILTER xfp_all BY year=='2013' AND month=='06' AND day=='19' AND hour=='20';
xfp = FILTER xfp_partition BY lineitemid != 0 AND time != 'Time';