diff --git a/files/init_db.sql b/files/init_db.sql index 0f1eb80c97cf0df273a177b947dedf3b7831b022..fefaf4c18448627cdb0d99567d8c7e90511317ae 100644 --- a/files/init_db.sql +++ b/files/init_db.sql @@ -33,7 +33,8 @@ CREATE EXTERNAL TABLE IF NOT EXISTS anime ( ROW FORMAT DELIMITED FIELDS TERMINATED BY ',' LINES TERMINATED BY '\n' -STORED AS TEXTFILE; +STORED AS TEXTFILE +LOCATION '/dataset/anime-dataset-2023.csv'; CREATE EXTERNAL TABLE IF NOT EXISTS users ( mal_id INT, @@ -56,7 +57,8 @@ CREATE EXTERNAL TABLE IF NOT EXISTS users ( ROW FORMAT DELIMITED FIELDS TERMINATED BY ',' LINES TERMINATED BY '\n' -STORED AS TEXTFILE; +STORED AS TEXTFILE +LOCATION '/dataset/users-score-2023.csv'; CREATE EXTERNAL TABLE IF NOT EXISTS score ( @@ -67,20 +69,8 @@ CREATE EXTERNAL TABLE IF NOT EXISTS score ( ROW FORMAT DELIMITED FIELDS TERMINATED BY ',' LINES TERMINATED BY '\n' -STORED AS TEXTFILE; --------------------------------- +STORED AS TEXTFILE +LOCATION '/dataset/user-filtered.csv'; -CREATE TABLE IF NOT EXISTS users_score_2023 ( - user_id INT, - username STRING, - anime_id INT, - anime_title STRING, - rating INT -) -ROW FORMAT DELIMITED -FIELDS TERMINATED BY ',' -LINES TERMINATED BY '\n' -STORED AS TEXTFILE; ------------------------------- diff --git a/files/others_tables.sql b/files/others_tables.sql new file mode 100644 index 0000000000000000000000000000000000000000..b8d841e83d2b38bf00ffe46c0c5badbe718cd4a6 --- /dev/null +++ b/files/others_tables.sql @@ -0,0 +1,19 @@ +-------------------------------- + +CREATE TABLE IF NOT EXISTS users_score_2023 ( + user_id INT, + username STRING, + anime_id INT, + anime_title STRING, + rating INT +) +ROW FORMAT DELIMITED +FIELDS TERMINATED BY ',' +LINES TERMINATED BY '\n' +STORED AS TEXTFILE; + +------------------------------ +SELECT x.table +FROM users u +JOIN score s ON u.user_id = s.user_id +JOIN anime a ON u.anime_id = a.anime_id;