第 1 章 准备数据

我们这次 Spark-sql 操作中所有的数据均来自 Hive.

首先在 Hive 中创建表, 并导入数据.

一共有 3 张表: 1 张用户行为表, 1 张城市表, 1 张产品表

CREATE TABLE `user_visit_action`(
  `date` string,
  `user_id` bigint,
  `session_id` string,
  `page_id` bigint,
  `action_time` string,
  `search_keyword` string,
  `click_category_id` bigint,
  `click_product_id` bigint,
  `order_category_ids` string,
  `order_product_ids` string,
  `pay_category_ids` string,
  `pay_product_ids` string,
  `city_id` bigint)
row format delimited fields terminated by '\t';
load data local inpath '/opt/module/datas/user_visit_action.txt' into table sparkpractice.user_visit_action;

CREATE TABLE `product_info`(
  `product_id` bigint,
  `product_name` string,
  `extend_info` string)
row format delimited fields terminated by '\t';
load data local inpath '/opt/module/datas/product_info.txt' into table sparkpractice.product_info;

CREATE TABLE `city_info`(
  `city_id` bigint,
  `city_name` string,
  `area` string)
row format delimited fields terminated by '\t';
load data local inpath '/opt/module/datas/city_info.txt' into table sparkpractice.city_info;