juliensimon

PairFunction<String, String, String> keyFunc = 
	new PairFunction<String, String, String>() { 
		public Tuple2<String, String> call(String x) {
			return new Tuple2<String, String>(x.split(" ")[0], x.split(" ")[1]); 
		}
	};

JavaPairRDD<String, String> pairRDD = inputRDD.mapToPair(keyFunc);

juliensimon

JavaPairRDD<String, String> pairRDD = 
	inputRDD.mapToPair(x-> new Tuple2<String,String>(x.split(" ")[0], x.split(" ")[1]));

juliensimon

#!/bin/bash

# Author: Julien Simon <[email protected]>

# ECS tool in the spirit of ecs-cli :)
# default cluster should be configured : ecs-cli configure

if [ -z $1 ]
then
	echo "ecs-find services : list services running on the current cluster"

juliensimon

#!/bin/bash

# Author: Julien Simon <[email protected]>

# Connect to a Redshift cluster using psql

if ([ -z $1 ] || [ -z $2 ] || [ -z $3 ])
then
	echo "Usage: psqlRedshift CLUSTER_NAME DATABASE_NAME USER_NAME"
	exit

juliensimon

AWS re:Invent 2014 | (MBL202) NEW LAUNCH: Getting Started with AWS Lambda
https://www.youtube.com/watch?v=UFj27laTWQA

AWS re:Invent 2015 | (DEV203) Amazon API Gateway & AWS Lambda to Build Secure and Scalable APIs
https://www.youtube.com/watch?v=ZBxWZ9bgd44

AWS re:Invent 2015 | (DVO209) JAWS: The Monstrously Scalable Serverless Framework
https://www.youtube.com/watch?v=D_U6luQ6I90
https://github.com/serverless/serverless

juliensimon

import os, boto3

defaultRegion = 'us-east-1'
defaultUrl = 'https://polly.us-east-1.amazonaws.com'

def connectToPolly(regionName=defaultRegion, endpointUrl=defaultUrl):
    return boto3.client('polly', region_name=regionName, endpoint_url=endpointUrl)

def speak(polly, text, format='mp3', voice='Brian'):
    resp = polly.synthesize_speech(OutputFormat=format, Text=text, VoiceId=voice)

juliensimon

#!/usr/bin/env python
# -*- coding: utf-8 -*-

import os, boto3

defaultRegion = 'us-east-1'
defaultUrl = 'https://polly.us-east-1.amazonaws.com'

def connectToPolly(regionName=defaultRegion, endpointUrl=defaultUrl):
    return boto3.client('polly', region_name=regionName, endpoint_url=endpointUrl)

juliensimon

***
*** Inscrivez vous aux webinaires 2017 : https://attendee.gotowebinar.com/register/7239291589398918401 
***

Webinaire "Présentation des principaux services AWS" :
https://www.youtube.com/watch?v=FC--jteXU_8
http://www.slideshare.net/JulienSIMON5/presentation-des-services-aws 

Webinaire "Modèle de sécurité AWS" :
https://www.youtube.com/watch?v=1QeKH-5nTIc 

juliensimon

CREATE EXTERNAL TABLE IF NOT EXISTS gdelt.events (
  `globaleventid` INT,`day` INT,`monthyear` INT,`year` INT,`fractiondate` FLOAT,
  `actor1code` string,`actor1name` string,`actor1countrycode` string,`actor1knowngroupcode` string,
  `actor1ethniccode` string,`actor1religion1code` string,`actor1religion2code` string,
  `actor1type1code` string,`actor1type2code` string,`actor1type3code` string,
  `actor2code` string,`actor2name` string,`actor2countrycode` string,`actor2knowngroupcode` string,
  `actor2ethniccode` string,`actor2religion1code` string,`actor2religion2code` string,
  `actor2type1code` string,`actor2type2code` string,`actor2type3code` string,
  `isrootevent` BOOLEAN,`eventcode` string,`eventbasecode` string,`eventrootcode` string,
  `quadclass` INT,`goldsteinscale` FLOAT,`nummentions` INT,`numsources` INT,`numarticles` INT,`avgtone` FLOAT,

juliensimon

-- Count total events
SELECT COUNT(*) as nb_events FROM gdelt.events;

nb_events
440374991

-- Find the number of events per year
SELECT year,
       COUNT(globaleventid) AS nb_events
FROM gdelt.events