指标统计之自建集群数据实现 UV/PV 统计

# 浏览记录
{
  "record_type":0,  # 0 表示浏览记录
  "user_id": 6, 
  "client_ip": "100.0.0.6", 
  "product_id": 101, 
  "create_time": "2021-09-06 16:00:00"
}

# 购买记录
{
  "record_type":1, # 1 表示购买记录
  "user_id": 6, 
  "client_ip": "100.0.0.8", 
  "product_id": 101, 
  "create_time": "2021-09-08 18:00:00"
}

 CREATE TABLE `input_web_record` (
    `record_type`    INT,
    `user_id`        INT,
    `client_ip`      VARCHAR,
    `product_id`     INT,
    `create_time`    TIMESTAMP,
    `times`          AS create_time,
    WATERMARK FOR times AS times - INTERVAL '10' MINUTE 
 ) WITH (
     'connector' = 'kafka',        -- 可选 'kafka','kafka-0.11'. 注意选择对应的内置  Connector
     'topic' = 'uvpv-demo',  
     'scan.startup.mode' = 'earliest-offset', 
     'properties.bootstrap.servers' = '10.1.0.10:9092',  
     'properties.group.id' = 'WebRecordGroup',  -- 必选参数, 一定要指定 Group ID
     'format' = 'json',
     'json.ignore-parse-errors' = 'true',       -- 忽略 JSON 结构解析异常
     'json.fail-on-missing-field' = 'false'     -- 如果设置为 true, 则遇到缺失字段会报错 设置为 false 则缺失字段设置为 null
 );

-- UV sink
CREATE TABLE `output_uv` (  
 `userids`          STRING,
 `user_id`          STRING
) WITH (
  'connector' = 'redis',          
  'command' = 'sadd',              -- 使用集合保存uv（支持命令：set、lpush、sadd、hset、zadd）
  'nodes' = '192.28.28.217:6379',  -- redis连接地址,集群模式多个节点使用'',''分隔。
  'password' = 'yourpassword'   
);

-- PV sink
CREATE TABLE `output_pv` (  
 `pagevisits`       STRING,
 `product_id`       STRING,
 `hour_count`       BIGINT
) WITH (
  'connector' = 'redis',          
  'command' = 'lpush',              -- 使用列表保存pv（支持命令：set、lpush、sadd、hset、zadd）
  'nodes' = '192.28.28.217:6379',   -- redis连接地址,集群模式多个节点使用'',''分隔。
  'password' = 'yourpassword'   
);

-- 转化率 sink
CREATE TABLE `output_conversion_rate` (  
 `conversion_rate`  STRING,
 `rate`             STRING
) WITH (
  'connector' = 'redis',        
  'command' = 'set',              -- 使用列表保存pv（支持命令：set、lpush、sadd、hset、zadd）
  'nodes' = '192.28.28.217:6379', -- redis连接地址,集群模式多个节点使用'',''分隔。
  'password' = 'yourpassword'   
);

-- 加工得到 UV 指标，统计所有时间内的 UV
INSERT INTO output_uv 
SELECT 
  'userids'                AS `userids`,
  CAST(user_id AS string)  AS user_id 
FROM input_web_record ;

-- 加工并得到 PV 指标，统计每 10 分钟内的 PV
INSERT INTO output_pv 
SELECT 
  'pagevisits'               AS `pagevisits`, 
  CAST(product_id AS string) AS product_id, 
  SUM(product_id) AS hour_count
FROM input_web_record WHERE record_type = 0 
GROUP BY 
  HOP(times, INTERVAL '5' MINUTE, INTERVAL '10' MINUTE), 
  product_id, 
  user_id;

-- 加工并得到转化率指标，统计每 10 分钟内的转化率
INSERT INTO output_conversion_rate 
SELECT 
  'conversion_rate' AS `conversion_rate`, 
  CAST( (((SELECT COUNT(1) FROM input_web_record WHERE record_type=0)*1.0)/SUM(a.product_id)) as string) 
FROM (SELECT * FROM input_web_record where record_type = 1) AS a
GROUP BY  
  HOP(times, INTERVAL '5' MINUTE, INTERVAL '10' MINUTE), 
  product_id;