①建立mydata資料庫，建立表userbehavior

# 建立資料庫
CREATE DATABASE IF NOT EXISTS mydata CHARSET utf8;
USE mydata;
# 建立表userbehavior
CREATE TABLE userbehavior (
  user_id INT (10),
  item_id INT (10),
  category_id INT (10),
  behavior_type VARCHAR (10),
  timestamps VARCHAR (20)
) ;

②匯入已經下載好的csv資料

SHOW VARIABLES LIKE '%local%';
SET GLOBAL local_infile=1;
LOAD DATA LOCAL INFILE 'E:/dataset/UserBehavior.csv' 
INTO TABLE userbehavior 
FIELDS TERMINATED BY ','
IGNORE	1 LINES;

#檢視內容，檢查表結構
SELECT * FROM userbehavior LIMIT 10;
SELECT COUNT(*) FROM userbehavior;   -- 100150806
DESC user_behavior;
 

③本次只選取前100萬行資料，為了選取方便，我們新增序列號ID

// 新增序列號ID
ALTER TABLE userbehavior ADD id INT(8) FIRST;
ALTER TABLE userbehavior MODIFY id INT(8) PRIMARY KEY AUTO_INCREMENT;
#刪除表中id大於100萬的資料
DELETE FROM userbehavior WHERE id>1000000;