Skip to content

Commit 16a3f9d

Browse files
authored
Add files via upload
1 parent b8a2ecc commit 16a3f9d

File tree

4 files changed

+65
-0
lines changed

4 files changed

+65
-0
lines changed

analysis.hql.txt

+25
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,25 @@
1+
SELECT movies.MovieID,movies.Title,COUNT(DISTINCT ratings.UserID) as views
2+
FROM movies JOIN ratings ON (movies.MovieID = ratings.MovieID)
3+
GROUP BY movies.MovieID, movies.Title
4+
ORDER BY views DESC
5+
LIMIT 10;
6+
7+
SELECT movies.MovieID,movies.Title,AVG(ratings.Rating) as rtg,COUNT(DISTINCT ratings.UserID) as views
8+
FROM movies JOIN ratings ON (movies.MovieID = ratings.MovieID)
9+
GROUP BY movies.MovieID,movies.Title
10+
HAVING views >= 40
11+
ORDER BY rtg DESC
12+
LIMIT 20;
13+
14+
create temporary table movie_by_user_genre as
15+
select t1.*, t2.rating,t2.userid
16+
from movie_by_genre t1 left join ratings t2
17+
on t1.movieid = t2.movieid where t2.rating >= 4;
18+
19+
create temporary table user_by_genre_totalrating as
20+
select userid, genre, sum(rating) total_rating
21+
from movie_by_user_genre group by userid, genre;
22+
23+
select * from
24+
(select userid, genre, row_number() over (partition by userid order by total_rating desc) row_num
25+
from user_by_genre_totalrating) t where t.row_num <= 3;

movies.sql

+12
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,12 @@
1+
DROP DATABASE IF EXISTS movielens CASCADE;
2+
CREATE DATABASE movielens;
3+
USE movielens;
4+
CREATE EXTERNAL TABLE movies (MovieID INT,
5+
Title varchar(60),
6+
Genres varchar(60))
7+
ROW FORMAT DELIMITED FIELDS TERMINATED BY ','
8+
LINES TERMINATED BY "\n"
9+
STORED AS TEXTFILE
10+
LOCATION '/movielens/ml-1m/mvs.txt';
11+
LOAD DATA INPATH '/movielens/ml-1m/movies.csv' INTO TABLE movies;
12+
SELECT * FROM movies LIMIT 10;

ratings.sql

+13
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,13 @@
1+
USE movielens;
2+
3+
CREATE EXTERNAL TABLE ratings (UserID INT,
4+
MovieID INT,
5+
Rating INT,
6+
Timestamp2 STRING)
7+
ROW FORMAT DELIMITED FIELDS TERMINATED BY ','
8+
LINES TERMINATED BY "\n"
9+
STORED AS TEXTFILE
10+
LOCATION '/movielens/ml-1m/rts.txt';
11+
LOAD DATA INPATH '/movielens/ml-1m/ratings.csv' INTO TABLE ratings;
12+
13+
SELECT * FROM ratings LIMIT 10;

users.sql

+15
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,15 @@
1+
USE movielens;
2+
3+
CREATE EXTERNAL TABLE users (UserID INT,
4+
Gender STRING,
5+
Age INT,
6+
Occupation INT,
7+
ZIP INT)
8+
ROW FORMAT DELIMITED FIELDS TERMINATED BY ','
9+
LINES TERMINATED BY "\n"
10+
STORED AS TEXTFILE
11+
LOCATION '/movielens/ml-1m/usr.txt';
12+
13+
LOAD DATA INPATH '/movielens/ml-1m/users.csv' INTO TABLE users;
14+
15+
SELECT * FROM users LIMIT 10;

0 commit comments

Comments
 (0)