我被一个查询困住了：
CREATE TABLE public.bulk_sample (
serial_number character varying(255),
validation_date timestamp, -- timestamp of entry and exit
station_id integer,
direction integer -- 1 = Entry | 2 = Exit
);
INSERT INTO public.bulk_sample VALUES
('019b5526970fcfcf7813e9fe1acf8a41bcaf5a5a5c10870b3211d82f63fbf270', '2020-02-01 08:31:58', 120, 1)
, ('019b5526970fcfcf7813e9fe1acf8a41bcaf5a5a5c10870b3211d82f63fbf270', '2020-02-01 08:50:22', 113, 2)
, ('019b5526970fcfcf7813e9fe1acf8a41bcaf5a5a5c10870b3211d82f63fbf270', '2020-02-01 10:16:56', 113, 1)
, ('019b5526970fcfcf7813e9fe1acf8a41bcaf5a5a5c10870b3211d82f63fbf270', '2020-02-01 10:47:06', 120, 2)
, ('019b5526970fcfcf7813e9fe1acf8a41bcaf5a5a5c10870b3211d82f63fbf270', '2020-02-01 16:02:12', 120, 1)
, ('019b5526970fcfcf7813e9fe1acf8a41bcaf5a5a5c10870b3211d82f63fbf270', '2020-02-01 16:47:45', 102, 2)
, ('019b5526970fcfcf7813e9fe1acf8a41bcaf5a5a5c10870b3211d82f63fbf270', '2020-02-01 19:26:38', 102, 1)
, ('019b5526970fcfcf7813e9fe1acf8a41bcaf5a5a5c10870b3211d82f63fbf270', '2020-02-01 20:17:24', 120, 2)
, ('23cc9678e8cf834decb096ba36be0efee418402bce03aab52e69026adfec7663', '2020-02-01 07:58:20', 119, 1)
, ('23cc9678e8cf834decb096ba36be0efee418402bce03aab52e69026adfec7663', '2020-02-01 08:43:35', 104, 2)
, ('23cc9678e8cf834decb096ba36be0efee418402bce03aab52e69026adfec7663', '2020-02-01 16:38:10', 104, 1)
, ('23cc9678e8cf834decb096ba36be0efee418402bce03aab52e69026adfec7663', '2020-02-01 17:15:01', 119, 2)
, ('23cc9678e8cf834decb096ba36be0efee418402bce03aab52e69026adfec7663', '2020-02-01 17:42:29', 119, 1)
, ('23cc9678e8cf834decb096ba36be0efee418402bce03aab52e69026adfec7663', '2020-02-01 17:48:05', 120, 2)
, ('2a8f28bf0afc655210aa337aff016d33100282ac73cca660a397b924808499af', '2020-02-01 15:17:59', 120, 1)
, ('2a8f28bf0afc655210aa337aff016d33100282ac73cca660a397b924808499af', '2020-02-01 15:25:25', 118, 2)
, ('2a8f28bf0afc655210aa337aff016d33100282ac73cca660a397b924808499af', '2020-02-01 16:16:12', 118, 1)
, ('2a8f28bf0afc655210aa337aff016d33100282ac73cca660a397b924808499af', '2020-02-01 16:32:51', 120, 2)
, ('2a8f28bf0afc655210aa337aff016d33100282ac73cca660a397b924808499af', '2020-02-01 19:31:20', 120, 1)
, ('2a8f28bf0afc655210aa337aff016d33100282ac73cca660a397b924808499af', '2020-02-01 19:39:33', 118, 2)
, ('2a8f28bf0afc655210aa337aff016d33100282ac73cca660a397b924808499af', '2020-02-01 20:57:50', 118, 1)
, ('2a8f28bf0afc655210aa337aff016d33100282ac73cca660a397b924808499af', '2020-02-01 21:16:25', 120, 2)
;
我必须创建一个查询，其结果如下
source | dest | Count
120 | 113 | 1
113 | 120 | 1
我尝试了以下代码，但无法获得所需的结果：
SELECT serial_number
, count(*)
, min(validation_date) AS start_time
, CASE WHEN count(*) > 1 THEN max(validation_date) END AS end_time
FROM (
SELECT serial_number, validation_date, count(step OR NULL) OVER (ORDER BY serial_number,
validation_date) AS grp
FROM (
SELECT *
, lag(validation_date) OVER (PARTITION BY serial_number ORDER BY validation_date)
< validation_date - interval '60 min' AS step
FROM table1
where BETWEEN '2020-02-01 00:00:00' AND '2020-02-01 23:59:59'
) sub1
) sub2
GROUP BY serial_number, grp;
每次进出之间的时间间隔约为 55 分钟至 60 分钟。
我也尝试过内部联接，但无法按内部联接中的时间间隔进行分组
SELECT source.station_id AS source_station ,dest.station_id AS destination_station ,source.count FROM
(
SELECT serial_number,station_id,count(bulk_transaction_id) FROM table1
WHERE
direction = 1 AND
validation_date BETWEEN '2020-02-01 00:00:00' AND '2020-02-01 23:59:59'
GROUP BY serial_number,station_id
)source
INNER JOIN
(
SELECT serial_number,station_id,count(bulk_transaction_id) FROM table1
WHERE
direction = 2 AND
validation_date BETWEEN '2020-02-01 00:00:00' AND '2020-02-01 23:59:59'
GROUP BY serial_number,station_id
)dest
ON source.serial_number = dest.serial_number and source.station_id <> dest.station_id
挑战有时是进入日期为空，有时退出日期为空。