Cleaned up bootstrap file

bootstrap.sql

@@ -1,4 +1,11 @@
-# UNIGRAM SETUP
+-- These queries serve the purposes of setting up various nodes with normalized/
+-- sanitized versions of the n-gram entries, containing only the fields that are
+-- relevant to our query workload.
+--
+-- We chose to perform our queries on three m1.xlarge nodes: one for unigrams,
+-- one for bigrams, and one for trigrams.
+
+-- UNIGRAM SETUP
 CREATE EXTERNAL TABLE unigrams_raw (
     gram string,
     year int,
@@ -19,7 +26,7 @@ CREATE TABLE unigrams (
 INSERT OVERWRITE TABLE unigrams
 SELECT lower(gram), year, occurrences FROM unigrams_raw WHERE gram REGEXP "^[A-Za-z+'-]+$";
 
-# BIGRAM SETUP
+-- BIGRAM SETUP
 CREATE EXTERNAL TABLE bigrams_raw (
     gram string,
     year int,
@@ -40,7 +47,7 @@ CREATE TABLE bigrams (
 INSERT OVERWRITE TABLE bigrams
 SELECT lower(gram), year, occurrences FROM bigrams_raw WHERE gram REGEXP "^[A-Za-z+'-]+ [A-Za-z+'-]+$";
 
-# TRIGRAM SETUP
+-- TRIGRAM SETUP
 CREATE EXTERNAL TABLE trigrams_raw (
     gram string,
     year int,
@@ -61,30 +68,3 @@ CREATE TABLE trigrams (
 
 INSERT OVERWRITE TABLE trigrams
 SELECT lower(gram) AS g, occurrences, pages, books FROM trigrams_raw WHERE gram REGEXP "^[A-Za-z+'-]+ [A-Za-z+'-]+ [A-Za-z+'-]+$" DISTRIBUTE BY g;
-
-###############################
-# UNIGRAMS TEARDOWN (to save state)
-CREATE TABLE unigrams_saved (
-    gram string,
-    year int,
-    occurrences bigint
-)
-ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t'
-STORED AS SEQUENCEFILE
-LOCATION 's3://cs158-aberke-hadoop/saved/1gram/';
-
-INSERT OVERWRITE TABLE unigrams_saved
-SELECT * FROM unigrams;
-
-# BIGRAMS TEARDOWN
-CREATE TABLE bigrams_saved (
-    gram string,
-    year int,
-    occurrences bigint
-)
-ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t'
-STORED AS SEQUENCEFILE
-LOCATION 's3://cs158-aberke-hadoop/saved/2gram/';
-
-INSERT OVERWRITE TABLE bigrams_saved
-SELECT * FROM bigrams;