1.创建orders表
CREATE TABLE orders (
order_id string, #订单id
user_id string, #用户id
eval_set string, #标测训练集还是预测集
order_number string, #下订单的排序
order_dow string, #0-6的星期几
order_hour_of_day string, #24小时
days_since_prior_order) #距离上一个订单多少天
ROW FORMAT DELIMITED
FIELDS TERMINATED BY '\t'
STORED AS TEXTFILE
加载数据
LOAD DATA LOCAL INPATH '/home/wl/hive/data/data/orders.csv' OVERWRITE INTO TABLE orders;
2.创建trains表
CREATE TABLE trains (
order_id string,
product_id string,
add_to_cart_order int,
reordered int)
ROW FORMAT DELIMITED
FIELDS TERMINATED BY '\t'
STORED AS TEXTFILE;
加载数据
LOAD DATA LOCAL INPATH '/home/wl/hive/data/data/order_products__train.csv' OVERWRITE INTO TABLE trains;
hadoop杀掉任务命令
hadoop job -kill job_15532189