Better documented version of script1-local.pig

To make it easier for people to understand the "Query Phrase Popularity" example in the tutorial, I added comment lines to script1-local.pig to show samples from the intermediate relations. Should this be checked in?

/*

• Licensed to the Apache Software Foundation (ASF) under one
• or more contributor license agreements. See the NOTICE file
• distributed with this work for additional information
• regarding copyright ownership. The ASF licenses this file
• to you under the Apache License, Version 2.0 (the
• "License"); you may not use this file except in compliance
• with the License. You may obtain a copy of the License at
  *
• http://www.apache.org/licenses/LICENSE-2.0
  *
• Unless required by applicable law or agreed to in writing, software
• distributed under the License is distributed on an "AS IS" BASIS,
• WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
• See the License for the specific language governing permissions and
• limitations under the License.
  */

– Query Phrase Popularity (local mode)

– This script processes a search query log file from the Excite search engine and finds search phrases that occur with particular high frequency during certain times of the day.

– Register the tutorial JAR file so that the included UDFs can be called in the script.
REGISTER /tmp/tutorial.jar;

– Use the PigStorage function to load the excite log file into the raw bag as an array of records.
– Input: (user,time,query)
raw = LOAD 'excite-small.log' USING PigStorage('\t') AS (user, time, query);
--BED75271605EBD0C 970916001954 Yahoo chat
--BED75271605EBD0C 970916003523 Yahoo chat
--2B73EFE0F9FC9E0B 970916195507 http://educationalproducts.com
--CD37F95FC0886E1D 970916084059 www:http:/www.tti.com

– Call the NonURLDetector UDF to remove records if the query field is empty or a URL.
clean1 = FILTER raw BY org.apache.pig.tutorial.NonURLDetector(query);
--BED75271605EBD0C 970916001954 Yahoo chat
--BED75271605EBD0C 970916003523 Yahoo chat

– Call the ToLower UDF to change the query field to lowercase.
clean2 = FOREACH clean1 GENERATE user, time, org.apache.pig.tutorial.ToLower(query) as query;
--BED75271605EBD0C 970916001954 yahoo chat
--BED75271605EBD0C 970916003523 yahoo chat

– Because the log file only contains queries for a single day, we are only interested in the hour.
– The excite query log timestamp format is YYMMDDHHMMSS.
– Call the ExtractHour UDF to extract the hour (HH) from the time field.
houred = FOREACH clean2 GENERATE user, org.apache.pig.tutorial.ExtractHour(time) as hour, query;
--BED75271605EBD0C 00 yahoo chat
--BED75271605EBD0C 00 yahoo chat
--BED75271605EBD0C 00 yahoo chat
--BED75271605EBD0C 00 yahoo chat
--BED75271605EBD0C 00 yahoo chat
--BED75271605EBD0C 00 yahoo chat

– Call the NGramGenerator UDF to compose the n-grams of the query.
ngramed1 = FOREACH houred GENERATE user, hour, flatten(org.apache.pig.tutorial.NGramGenerator(query)) as ngram;
--BED75271605EBD0C 00 chat
--BED75271605EBD0C 00 yahoo
--BED75271605EBD0C 00 yahoo chat
--BED75271605EBD0C 00 chat
--BED75271605EBD0C 00 yahoo
--BED75271605EBD0C 00 yahoo chat

– Use the DISTINCT command to get the unique n-grams for all records.
ngramed2 = DISTINCT ngramed1;
--BED75271605EBD0C 00 chat
--BED75271605EBD0C 00 yahoo
--BED75271605EBD0C 00 yahoo chat

– Use the GROUP command to group records by n-gram and hour.
hour_frequency1 = GROUP ngramed2 BY (ngram, hour);
--(chat,00)

--(yahoo chat,00)

--(yahoo,00)

– Use the COUNT function to get the count (occurrences) of each n-gram.
hour_frequency2 = FOREACH hour_frequency1 GENERATE flatten($0), COUNT($1) as count;
--yahoo 00 1
--chat 00 1
--yahoo chat 00 1

– Use the GROUP command to group records by n-gram only.
– Each group now corresponds to a distinct n-gram and has the count for each hour.
uniq_frequency1 = GROUP hour_frequency2 BY group::ngram;
--yahoo

--chat

--yahoo chat

– For each group, identify the hour in which this n-gram is used with a particularly high frequency.
– Call the ScoreGenerator UDF to calculate a "popularity" score for the n-gram.
uniq_frequency2 = FOREACH uniq_frequency1 GENERATE flatten($0), flatten(org.apache.pig.tutorial.ScoreGenerator($1));
--chat 19 1.2126781251816656 2 1.2857142857142854
--chat 04 1.2126781251816656 2 1.2857142857142854
--chat 17 2.9104275004359965 3 1.2857142857142854
--new 07 2.4494897427831788 2 1.1428571428571426
--the 08 1.5895540678349904 4 1.9375
--the 09 0.0481683050859088 2 1.9375

– Use the FOREACH-GENERATE command to assign names to the fields.
uniq_frequency3 = FOREACH uniq_frequency2 GENERATE $1 as hour, $0 as ngram, $2 as score, $3 as count, $4 as mean;
--10 the 0.0481683050859088 2 1.9375
--19 chat 1.2126781251816656 2 1.2857142857142854
--04 chat 1.2126781251816656 2 1.2857142857142854
--17 chat 2.9104275004359965 3 1.2857142857142854
--14 city 2.2360679774997902 2 1.1666666666666665

– Use the FILTER command to move all records with a score less than or equal to 2.0.
filtered_uniq_frequency = FILTER uniq_frequency3 BY score > 2.0;
--08 s 2.545584412271571 3 1.3636363636363635
--19 in 2.1572774865200244 3 1.4285714285714284
--11 in 2.1572774865200244 3 1.4285714285714284
--10 to 2.6457513110645903 2 1.125
--19 car 2.23606797749979 3 1.3333333333333333
---...

– Use the ORDER command to sort the remaining records by hour and score.
ordered_uniq_frequency = ORDER filtered_uniq_frequency BY hour, score;
--07 new 2.4494897427831788 2 1.1428571428571426
--08 pictures 2.04939015319192 3 1.4999999999999998
--08 computer 2.4494897427831788 2 1.1428571428571426
--08 s 2.545584412271571 3 1.3636363636363635
--10 free 2.2657896674010605 4 1.923076923076923

– Use the PigStorage function to store the results.
– Output: (hour, n-gram, score, count, average_counts_among_all_hours)
STORE ordered_uniq_frequency INTO 'script1-local-results.out' USING PigStorage();