Initial commit (3f3d5c0c) · Commits · examples / Analyzing Big Data with Hadoop AWS and EMR

Analyzing Big Data with Hadoop, AWS, and EMR - Working Files/Chapter 1/No Work Files.rtf

0 → 100755

+7 −0

Changes for Analyzing Big Data with Hadoop, AWS, and EMR - Working Files/Chapter 1/No Work Files.rtf: 7 added lines, 0 removed lines.
Original line number	Diff line number	Diff line
		{\rtf1\ansi\ansicpg1252\cocoartf1038\cocoasubrtf350
		{\fonttbl\f0\fswiss\fcharset0 Helvetica;}
		{\colortbl;\red255\green255\blue255;}
		\margl1440\margr1440\vieww9000\viewh8400\viewkind0
		\pard\tx720\tx1440\tx2160\tx2880\tx3600\tx4320\tx5040\tx5760\tx6480\tx7200\tx7920\tx8640\ql\qnatural\pardirnatural

		\f0\fs24 \cf0 No work files for this lesson...}
		No newline at end of file

0 → 100755

+7 −0

Changes for Analyzing Big Data with Hadoop, AWS, and EMR - Working Files/Chapter 2/No Work Files.rtf: 7 added lines, 0 removed lines.
Original line number	Diff line number	Diff line
		{\rtf1\ansi\ansicpg1252\cocoartf1038\cocoasubrtf350
		{\fonttbl\f0\fswiss\fcharset0 Helvetica;}
		{\colortbl;\red255\green255\blue255;}
		\margl1440\margr1440\vieww9000\viewh8400\viewkind0
		\pard\tx720\tx1440\tx2160\tx2880\tx3600\tx4320\tx5040\tx5760\tx6480\tx7200\tx7920\tx8640\ql\qnatural\pardirnatural

		\f0\fs24 \cf0 No work files for this lesson...}
		No newline at end of file

0 → 100755

+23 −0

Changes for Analyzing Big Data with Hadoop, AWS, and EMR - Working Files/Chapter 3/TopMovies.hql: 23 added lines, 0 removed lines.
Original line number	Diff line number	Diff line
		create database if not exists movielens;

		use movielens;

		create external table if not exists ratings (
		user_id int,
		movie_id int,
		rating int,
		rating_time int )
		row format delimited
		fields terminated by '\t'
		stored as textfile
		location 's3://media.sundog-soft.com/hadoop/ratings';

		select movie_id, count(*) as ratingCount from ratings group by movie_id order by ratingCount DESC;

		create table if not exists top_movies
		row format delimited
		fields terminated by ','
		stored as textfile
		location '/user/hadoop/topmovies' as
		select movie_id, count(*) as ratingCount from movielens.ratings group by movie_id;

0 → 100755

+7 −0

Changes for Analyzing Big Data with Hadoop, AWS, and EMR - Working Files/Chapter 3/TopMovies.pig: 7 added lines, 0 removed lines.
Original line number	Diff line number	Diff line
		fs -rmr /user/hadoop/topMoviesOut
		topmovies = LOAD '/user/hadoop/topmovies' USING PigStorage(',') AS (movie_id:int, rating_count:int);
		metadata = LOAD 's3://media.sundog-soft.com/hadoop/ml-100k/u.item' USING PigStorage('\|') AS (movie_id:int, movieTitle:chararray, releaseDate:chararray, videoRelease:chararray, imdbLink:chararray);
		topMoviesWithNames= JOIN topmovies BY movie_id, metadata BY movie_id;
		topMoviesWithNamesSorted = ORDER topMoviesWithNames BY topmovies::rating_count DESC;
		STORE topMoviesWithNamesSorted INTO '/user/hadoop/topMoviesOut' USING PigStorage('\|');

0 → 100755

+23 −0

Changes for Analyzing Big Data with Hadoop, AWS, and EMR - Working Files/Chapter 4/TopMovies.hql: 23 added lines, 0 removed lines.
Original line number	Diff line number	Diff line
		create database if not exists movielens;

		use movielens;

		create external table if not exists ratings (
		user_id int,
		movie_id int,
		rating int,
		rating_time int )
		row format delimited
		fields terminated by '\t'
		stored as textfile
		location 's3://media.sundog-soft.com/hadoop/ratings';

		select movie_id, count(*) as ratingCount from ratings group by movie_id order by ratingCount DESC;

		create table if not exists top_movies
		row format delimited
		fields terminated by ','
		stored as textfile
		location '/user/hadoop/topmovies' as
		select movie_id, count(*) as ratingCount from movielens.ratings group by movie_id;