使用hive根据数据文件夹ml-1m中三个.dat文件，完成如下功能 （1） 创建相应数据库和数据表，上传数据（ （2）求被评分次数最多的10部电影，并给出评分次数（电影名，评分次数） （3）分别求男性，女性当中评分最高（按平均分算）的10部电影（性别，电影名，影评分）评论次数大于等于50次 （4）求movieid = 2116这部电影各年龄段（因为年龄就只有7个，就按这个7个分就好了）的平均影评（年龄段，影评分） （5）求最喜欢看电影（影评次数最多）的那位女性评最高分的10部电影的平均影评分（观影者，电影名，影评分） （6）求好片（平均评分>=4.0）最多的那个年份的最好看的10部电影 （7）求1997年上映的电影中，评分最高的10部Comedy类电影 （8）该影评库中各种类型电影中评价最高的5部电影（类型，电影名，平均影评分） （9）各年评分最高的电影类型（年份，类型，影评分） （10）每个地区最高评分的电影名，把结果存入HDFS（地区，电影名，影评分）

（1）创建相应数据库和数据表，上传数据

首先需要在Hive中创建数据库和数据表，然后将数据上传到对应的数据表中。

-- 创建数据库
CREATE DATABASE IF NOT EXISTS movie_db;
-- 切换到该数据库
USE movie_db;

-- 创建数据表
CREATE TABLE IF NOT EXISTS movies (
    movieid INT,
    title STRING,
    genres STRING
)
ROW FORMAT DELIMITED
FIELDS TERMINATED BY '::'
STORED AS TEXTFILE;

CREATE TABLE IF NOT EXISTS ratings (
    userid INT,
    movieid INT,
    rating FLOAT,
    timestamp STRING
)
ROW FORMAT DELIMITED
FIELDS TERMINATED BY '::'
STORED AS TEXTFILE;

CREATE TABLE IF NOT EXISTS users (
    userid INT,
    gender STRING,
    age INT,
    occupation INT,
    zipcode STRING
)
ROW FORMAT DELIMITED
FIELDS TERMINATED BY '::'
STORED AS TEXTFILE;

-- 将数据上传到对应的数据表中
LOAD DATA LOCAL INPATH '/path/to/ml-1m/movies.dat' OVERWRITE INTO TABLE movies;
LOAD DATA LOCAL INPATH '/path/to/ml-1m/ratings.dat' OVERWRITE INTO TABLE ratings;
LOAD DATA LOCAL INPATH '/path/to/ml-1m/users.dat' OVERWRITE INTO TABLE users;

（2）求被评分次数最多的10部电影，并给出评分次数（电影名，评分次数）

SELECT m.title, COUNT(r.movieid) AS rating_count
FROM movies m JOIN ratings r ON m.movieid = r.movieid
GROUP BY m.title
ORDER BY rating_count DESC
LIMIT 10;

（3）分别求男性，女性当中评分最高（按平均分算）的10部电影（性别，电影名，影评分）评论次数大于等于50次

SELECT u.gender, m.title, AVG(r.rating) AS avg_rating
FROM movies m JOIN ratings r ON m.movieid = r.movieid
JOIN users u ON r.userid = u.userid
WHERE u.gender = 'F' AND r.userid IN (
    SELECT userid
    FROM ratings
    GROUP BY userid
    HAVING COUNT(movieid) >= 50
) OR u.gender = 'M' AND r.userid IN (
    SELECT userid
    FROM ratings
    GROUP BY userid
    HAVING COUNT(movieid) >= 50
)
GROUP BY u.gender, m.title
HAVING COUNT(r.movieid) >= 50
ORDER BY u.gender, avg_rating DESC
LIMIT 10;

（4）求movieid = 2116这部电影各年龄段（因为年龄就只有7个，就按这个7个分就好了）的平均影评（年龄段，影评分）

SELECT
    CASE
        WHEN age BETWEEN 1 AND 18 THEN '1-18'
        WHEN age BETWEEN 18 AND 24 THEN '18-24'
        WHEN age BETWEEN 25 AND 34 THEN '25-34'
        WHEN age BETWEEN 35 AND 44 THEN '35-44'
        WHEN age BETWEEN 45 AND 49 THEN '45-49'
        WHEN age BETWEEN 50 AND 55 THEN '50-55'
        ELSE '56+'
    END AS age_group,
    AVG(r.rating) AS avg_rating
FROM ratings r JOIN users u ON r.userid = u.userid
WHERE r.movieid = 2116
GROUP BY age_group;

（5）求最喜欢看电影（影评次数最多）的那位女性评最高分的10部电影的平均影评分（观影者，电影名，影评分）

SELECT u.userid, m.title, AVG(r.rating) AS avg_rating
FROM movies m JOIN ratings r ON m.movieid = r.movieid
JOIN users u ON r.userid = u.userid
WHERE u.gender = 'F' AND r.userid IN (
    SELECT userid
    FROM ratings
    GROUP BY userid
    ORDER BY COUNT(movieid) DESC
    LIMIT 1
)
GROUP BY u.userid, m.title
HAVING COUNT(r.movieid) >= 50
ORDER BY avg_rating DESC
LIMIT 10;

（6）求好片（平均评分>=4.0）最多的那个年份的最好看的10部电影

SELECT m.title, AVG(r.rating) AS avg_rating, COUNT(r.movieid) AS rating_count, SUBSTR(r.timestamp, 1, 4) AS year
FROM movies m JOIN ratings r ON m.movieid = r.movieid
WHERE AVG(r.rating) >= 4.0
GROUP BY m.title, year
ORDER BY rating_count DESC, avg_rating DESC
LIMIT 10;

（7）求1997年上映的电影中，评分最高的10部Comedy类电影

SELECT m.title, AVG(r.rating) AS avg_rating
FROM movies m JOIN ratings r ON m.movieid = r.movieid
WHERE m.genres LIKE '%Comedy%' AND SUBSTR(r.timestamp, 1, 4) = '1997'
GROUP BY m.title
ORDER BY avg_rating DESC
LIMIT 10;

（8）该影评库中各种类型电影中评价最高的5部电影（类型，电影名，平均影评分）

SELECT m.genres, m.title, AVG(r.rating) AS avg_rating
FROM movies m JOIN ratings r ON m.movieid = r.movieid
GROUP BY m.genres, m.title
HAVING COUNT(r.movieid) >= 100
ORDER BY m.genres, avg_rating DESC
LIMIT 5;

（9）各年评分最高的电影类型（年份，类型，影评分）

SELECT SUBSTR(r.timestamp, 1, 4) AS year, m.genres, MAX(avg_rating) AS max_rating
FROM (
    SELECT movieid, AVG(rating) AS avg_rating
    FROM ratings
    GROUP BY movieid
) r JOIN movies m ON r.movieid = m.movieid
GROUP BY year, m.genres;

（10）每个地区最高评分的电影名，把结果存入HDFS（地区，电影名，影评分）

INSERT OVERWRITE DIRECTORY '/path/to/output'
SELECT u.zipcode, m.title, AVG(r.rating) AS avg_rating
FROM movies m JOIN ratings r ON m.movieid = r.movieid
JOIN users u ON r.userid = u.userid
GROUP BY u.zipcode, m.title
HAVING COUNT(r.movieid) >= 50
ORDER BY u.zipcode, avg_rating DESC;