一、hive用本地檔案進行詞頻統計

1.準備本地txt檔案

mkdir wc
cd wc
echo "hadoop hbase" > f1.txt
echo "hadoop hive" > f2.txt

2.啟動hadoop，啟動hive

start-all.sh
hive

3.建立資料庫，建立文字表

use hive;
create table if not exists wctext(line string); 
show tables;

4.對映本地檔案的資料到文字表中

load data local inpath '/home/hadoop/wc/f1.txt' into table wctext;
load data local inpath '/home/hadoop/wc/f2.txt' into table wctext;
select * from wctext;
 

5.hql語句進行詞頻統計交將結果儲存到結果表中

SELECT word, count(1) AS count FROM  (SELECT explode(split(line, ‘ ’)) AS word FROM wctext) w GROUP BY word ORDER BY word;
create table wc as SELECT word, count(1) AS count FROM  (SELECT explode(split(line, ' ')) AS word FROM wctext) w GROUP BY word ORDER BY word;

6.檢視統計結果

select * from wc;

二、hive用HDFS上的檔案進行詞頻統計

1.準備電子書或其它大的文字檔案

2.將文字檔案上傳到HDFS上

hdfs dfs -put ~/wc/f3.txt /input

3.建立文字表

create table if not exists docs(line string);
show tables;

4.對映HDFS中的檔案資料到文字表中

load data inpath '/input/f3.txt' into table docs;

5.hql語句進行詞頻統計交將結果儲存到結果表中

create table wctest as SELECT word, count(1) AS count FROM  (SELECT explode(split(line, ' ')) AS word FROM docs) w GROUP BY word ORDER BY word;
SELECT word, count(1) AS count FROM  (SELECT explode(split(line, ‘ ’)) AS word FROM docs) w GROUP BY word ORDER BY word;
 

6.檢視統計結果

select * from wctest;