· 7 years ago · Nov 08, 2018, 02:18 AM
1hadoop fs -ls
2hadoop fs -rm -r myinput
3hadoop fs -rm -r output_max_store
4hadoop fs -put data/purchases.txt myinput
5hs code/mapper.py code/reducer.py myinput output
6hadoop fs -get output/part-00000 data/mylocalfile.txt
7cat data/mylocalfile.txt
8
9hadoop fs -rm -r forum_node
10hadoop fs -rm -r forum_users
11hadoop fs -put forum_node.tsv forum_node
12hadoop fs -put forum_users.tsv forum_users
13
14
15hive
16create database forum;
17use forum;
18
19drop table forum_node;
20CREATE EXTERNAL TABLE IF NOT EXISTS forum_node (
21 id STRING,
22title STRING,
23tagnames STRING,
24author_id STRING,
25body STRING,
26node_type STRING,
27parent_id STRING,
28abs_parent_id STRING,
29added_at STRING,
30score STRING,
31state_string STRING,
32last_edited_id STRING,
33last_activity_by_id STRING,
34last_activity_at STRING,
35active_revision_id STRING,
36extra STRING,
37extra_ref_id STRING,
38extra_count STRING,
39marked STRING )
40ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t'
41STORED AS TEXTFILE location '/user/training/forum_node_table'
42tblproperties ("skip.header.line.count"="1");
43
44LOAD DATA INPATH '/user/training/forum_node' OVERWRITE INTO TABLE forum_node;