Big Data Project

 

[cloudera@quickstart ~]$ hadoop fs -mkdir /user/cloudera/movies

[cloudera@quickstart ~]$ hadoop fs -mkdir movies/credits

[cloudera@quickstart ~]$ hadoop fs -mkdir movies/titles

[cloudera@quickstart ~]$ hadoop fs -put /home/cloudera/Desktop/shared/credits.csv /user/cloudera/movies/credits

[cloudera@quickstart ~]$ hadoop fs -put /home/cloudera/Desktop/shared/titles.csv /user/cloudera/movies/titles

[cloudera@quickstart ~]$ hadoop fs -cat /user/cloudera/movies/credits/credits.csv | head

[cloudera@quickstart ~]$ hadoop fs -cat /user/cloudera/movies/titles/titles.csv | head

[cloudera@quickstart ~]$ hadoop fs -cat /user/cloudera/movies/credits/credits.csv | wc -l

[cloudera@quickstart ~]$ hadoop fs -cat /user/cloudera/movies/titles/titles.csv | wc -l

mysql> create table if not exists credits

    -> ( person_id int,

    -> id varchar(100),

    -> name varchar(100),

    -> characters varchar(300),

    -> roles varchar(50)

    -> );

create table if not exists titels

    -> (id varchar(100),

    -> title varchar(200),

    -> type varchar(10),

    -> description varchar(2000),

    -> release_year int,

    -> age_certification varchar(10),

    -> runtime int,

    -> genres varchar(500),

    -> production_countries varchar(100),

    -> seasons int,

    -> imdb_id varchar(100),

    -> imdb_score float,

    -> imdb_votes int,

    -> tmdb_popularity float,

    -> tmdb_score float

    -> );