在BigQuery中按Google Analytics（分析）自定义维度进行过滤

时间：2018-11-16 17:06:03

标签： google-analytics google-bigquery standard-sql

我一直在尝试向BigQuery中的有效查询添加自定义维度过滤器。自定义维度及其嵌套无疑会增加查询的复杂性，但我过去已经能够弄清楚这一点。这次虽然我没有运气。

查询时间很长，但实际上是我们正在跟踪的结帐渠道。我已将自定义维度添加到我认为是必需的SELECT中，但出现错误“无法识别的名称：[274：9]处的PracticeName”。

#standardSQL
WITH
  ga_tables AS (
  SELECT
    CAST(CONCAT(SUBSTR(date,1,4),'-',SUBSTR(date,5,2),'-',SUBSTR(date,7,2)) AS DATE) AS Date,
    COUNT(DISTINCT s3_fullVisitorId) AS users,
    COUNT(s0_firstHit) AS product_views,
    COUNT(s1_firstHit) AS carts,
    COUNT(s2_firstHit) AS order_confirmation
  FROM (
    SELECT
      IFNULL(s3.date,
        IFNULL(s0.date,
          IFNULL(s1.date,
            s2.date))) AS date,
      s3.fullVisitorId s3_fullVisitorId,
      s0.fullVisitorId s0_fullVisitorId,
      s0.visitId,
      s0.firstHit s0_firstHit,
      s1.firstHit s1_firstHit,
      s2.firstHit s2_firstHit
    FROM (
        # user subquery
      SELECT
        date,
        fullVisitorId,
        visitId,
        (
        SELECT
          MAX(IF(index = 27,
              value,
              ''))
        FROM
          UNNEST(customDimensions)) AS PracticeName
      FROM
        `big-query-project-34643.162968675.ga_sessions_*` ga
      WHERE
        _TABLE_SUFFIX BETWEEN FORMAT_DATE('%Y%m%d', DATE_SUB(CURRENT_DATE(), INTERVAL 100 DAY))
        AND FORMAT_DATE('%Y%m%d', DATE_SUB(CURRENT_DATE(), INTERVAL 0 DAY))
        AND totals.visits = 1
      GROUP BY
        date,
        PracticeName,
        fullVisitorId,
        visitId) s3
    FULL OUTER JOIN ((
          # first subquery
        SELECT
          date,
          fullVisitorId,
          visitId,
          MIN(h.hitNumber) AS firstHit,
          (
          SELECT
            MAX(IF(index = 27,
                value,
                ''))
          FROM
            UNNEST(ga.customDimensions)) AS PracticeName
        FROM
          `big-query-project-34643.162968675.ga_sessions_*` ga,
          UNNEST(hits) AS h
        WHERE
          _TABLE_SUFFIX BETWEEN FORMAT_DATE('%Y%m%d', DATE_SUB(CURRENT_DATE(), INTERVAL 100 DAY))
          AND FORMAT_DATE('%Y%m%d', DATE_SUB(CURRENT_DATE(), INTERVAL 0 DAY))
          AND REGEXP_CONTAINS(h.page.pagePath, '/p/')
          AND totals.visits = 1
        GROUP BY
          date,
          PracticeName,
          fullVisitorId,
          visitId)) s0
    ON
      s3.fullVisitorId = s0.fullVisitorId
      AND s3.visitId = s0.visitId
    FULL OUTER JOIN ((
          # Second Subquery
        SELECT
          date,
          fullVisitorId,
          visitId,
          MIN(h.hitNumber) AS firstHit,
          (
          SELECT
            MAX(IF(index = 27,
                value,
                ''))
          FROM
            UNNEST(ga.customDimensions)) AS PracticeName
        FROM
          `big-query-project-34643.162968675.ga_sessions_*` ga,
          UNNEST(hits) AS h
        WHERE
          _TABLE_SUFFIX BETWEEN FORMAT_DATE('%Y%m%d', DATE_SUB(CURRENT_DATE(), INTERVAL 100 DAY))
          AND FORMAT_DATE('%Y%m%d', DATE_SUB(CURRENT_DATE(), INTERVAL 0 DAY))
          AND REGEXP_CONTAINS(h.page.pagePath, '/cart')
          AND totals.visits = 1
        GROUP BY
          date,
          PracticeName,
          fullVisitorId,
          visitId)) s1
    ON
      s0.fullVisitorId = s1.fullVisitorId
      AND s0.visitId = s1.visitId
    FULL OUTER JOIN ((
          # Third Subquery
        SELECT
          date,
          fullVisitorId,
          visitId,
          MIN(h.hitNumber) AS firstHit,
          (
          SELECT
            MAX(IF(index = 27,
                value,
                ''))
          FROM
            UNNEST(ga.customDimensions)) AS PracticeName
        FROM
          `big-query-project-34643.162968675.ga_sessions_*` ga,
          UNNEST(hits) AS h
        WHERE
          _TABLE_SUFFIX BETWEEN FORMAT_DATE('%Y%m%d', DATE_SUB(CURRENT_DATE(), INTERVAL 100 DAY))
          AND FORMAT_DATE('%Y%m%d', DATE_SUB(CURRENT_DATE(), INTERVAL 0 DAY))
          AND REGEXP_CONTAINS(h.page.pagePath, '/orderconfirmation')
          AND totals.visits = 1
        GROUP BY
          date,
          PracticeName,
          fullVisitorId,
          visitId)) s2
    ON
      s1.fullVisitorId = s2.fullVisitorId
      AND s1.visitId = s2.visitId)
  GROUP BY
    date
  UNION ALL
  SELECT
    CAST(CONCAT(SUBSTR(date,1,4),'-',SUBSTR(date,5,2),'-',SUBSTR(date,7,2)) AS DATE) AS Date,
    COUNT(DISTINCT s3_fullVisitorId) AS users,
    COUNT(s0_firstHit) AS product_views,
    COUNT(s1_firstHit) AS order_details,
    COUNT(s2_firstHit) AS order_confirmation
  FROM (
    SELECT
      IFNULL(s3.date,
        IFNULL(s0.date,
          IFNULL(s1.date,
            s2.date))) AS date,
      s3.fullVisitorId s3_fullVisitorId,
      s0.fullVisitorId s0_fullVisitorId,
      s0.visitId,
      s0.firstHit s0_firstHit,
      s1.firstHit s1_firstHit,
      s2.firstHit s2_firstHit
    FROM (
        # user subquery
      SELECT
        date,
        fullVisitorId,
        visitId,
        (
        SELECT
          MAX(IF(index = 27,
              value,
              ''))
        FROM
          UNNEST(gart.customDimensions)) AS PracticeName
      FROM
        `big-query-project-34643.162968675.ga_exportKey_view_2` gart
      WHERE
        totals.visits = 1
      GROUP BY
        date,
        PracticeName,
        fullVisitorId,
        visitId) s3
    FULL OUTER JOIN ((
          # first subquery
        SELECT
          date,
          fullVisitorId,
          visitId,
          MIN(h.hitNumber) AS firstHit,
          (
          SELECT
            MAX(IF(index = 27,
                value,
                ''))
          FROM
            UNNEST(gart.customDimensions)) AS PracticeName
        FROM
          `big-query-project-34643.162968675.ga_exportKey_view_2` gart,
          UNNEST(hits) AS h
        WHERE
          REGEXP_CONTAINS(h.page.pagePath, '/p/')
          AND totals.visits = 1
        GROUP BY
          date,
          PracticeName,
          fullVisitorId,
          visitId)) s0
    ON
      s3.fullVisitorId = s0.fullVisitorId
      AND s3.visitId = s0.visitId
    FULL OUTER JOIN ((
          # Second Subquery
        SELECT
          date,
          fullVisitorId,
          visitId,
          MIN(h.hitNumber) AS firstHit,
          (
          SELECT
            MAX(IF(index = 27,
                value,
                ''))
          FROM
            UNNEST(gart.customDimensions)) AS PracticeName
        FROM
          `big-query-project-34643.162968675.ga_exportKey_view_2` gart,
          UNNEST(hits) AS h
        WHERE
          REGEXP_CONTAINS(h.page.pagePath, '/cart')
          AND totals.visits = 1
        GROUP BY
          date,
          PracticeName,
          fullVisitorId,
          visitId)) s1
    ON
      s0.fullVisitorId = s1.fullVisitorId
      AND s0.visitId = s1.visitId
    FULL OUTER JOIN ((
          # Third Subquery
        SELECT
          date,
          fullVisitorId,
          visitId,
          MIN(h.hitNumber) AS firstHit,
          (
          SELECT
            MAX(IF(index = 27,
                value,
                ''))
          FROM
            UNNEST(gart.customDimensions)) AS PracticeName
        FROM
          `big-query-project-34643.162968675.ga_exportKey_view_2` gart,
          UNNEST(hits) AS h
        WHERE
          REGEXP_CONTAINS(h.page.pagePath, '/orderconfirmation')
          AND totals.visits = 1
        GROUP BY
          date,
          PracticeName,
          fullVisitorId,
          visitId)) s2
    ON
      s1.fullVisitorId = s2.fullVisitorId
      AND s1.visitId = s2.visitId)
  GROUP BY
    date)
SELECT
  Date AS Date,
  SUM(users) AS users,
  SUM(product_views) AS product_views,
  SUM(carts) AS Carts,
  SUM(order_confirmation) AS order_confirmation
FROM
  ga_tables
WHERE
  LOWER(PracticeName) NOT LIKE '%demo%'
  AND PracticeName NOT LIKE 'asdf'
GROUP BY
  Date
ORDER BY
  Date DESC

任何帮助弄清楚这一点的人将不胜感激。

1 个答案:

答案 0 :(得分：1)

您正在尝试在where子句中使用练习名称，但在最终版本的ga_tables中不可用。看一下代码的顶部。看起来您有工作漏斗，然后您决定在此处添加自定义维度，但并未将其添加到应有的所有位置。

WITH
  ga_tables AS (
  SELECT
    CAST(CONCAT(SUBSTR(date,1,4),'-',SUBSTR(date,5,2),'-',SUBSTR(date,7,2)) AS date) AS date,
    PracticeName,
    COUNT(DISTINCT s3_fullvisitorid) AS users,
    COUNT(s0_firsthit) AS product_views,
    COUNT(s1_firsthit) AS carts,
    COUNT(s2_firsthit) AS order_confirmation
  FROM (
    SELECT
      ifnull(s3.date,
        ifnull(s0.date,
          ifnull(s1.date,
            s2.date))) AS date,
      s0.practicename PracticeName,
      s3.fullvisitorid s3_fullvisitorid,
      s0.fullvisitorid s0_fullvisitorid,
      s0.visitid,
      s0.firsthit s0_firsthit,
      s1.firsthit s1_firsthit,
      s2.firsthit s2_firsthit
    FROM (
      SELECT
        date,
        fullvisitorid,
        visitid,
        (
        SELECT
          MAX(IF(index = 27,
              value,
              ''))
        FROM
          UNNEST(customdimensions)) AS practicename
      FROM
        `virtual-core-194015.157925963.ga_sessions_*` ga
      WHERE
        _table_suffix BETWEEN FORMAT_DATE('%Y%m%d', DATE_SUB(CURRENT_DATE(), INTERVAL 100 day))
        AND FORMAT_DATE('%Y%m%d', DATE_SUB(CURRENT_DATE(), INTERVAL 0 day))
        AND totals.visits = 1
      GROUP BY
        date,
        practicename,
        fullvisitorid,
        visitid) s3
    FULL OUTER JOIN ((
        SELECT
          date,
          fullvisitorid,
          visitid,
          MIN(h.hitnumber) AS firsthit,
          (
          SELECT
            MAX(IF(index = 27,
                value,
                ''))
          FROM
            UNNEST(ga.customdimensions)) AS practicename
        FROM
          `virtual-core-194015.157925963.ga_sessions_*` ga,
          UNNEST(hits) AS h
        WHERE
          _table_suffix BETWEEN FORMAT_DATE('%Y%m%d', DATE_SUB(CURRENT_DATE(), INTERVAL 100 day))
          AND FORMAT_DATE('%Y%m%d', DATE_SUB(CURRENT_DATE(), INTERVAL 0 day))
          AND REGEXP_CONTAINS(h.page.pagepath, '/p/')
          AND totals.visits = 1
        GROUP BY
          date,
          practicename,
          fullvisitorid,
          visitid)) s0
    ON
      s3.fullvisitorid = s0.fullvisitorid
      AND s3.visitid = s0.visitid
    FULL OUTER JOIN ((
        SELECT
          date,
          fullvisitorid,
          visitid,
          MIN(h.hitnumber) AS firsthit,
          (
          SELECT
            MAX(IF(index = 27,
                value,
                ''))
          FROM
            UNNEST(ga.customdimensions)) AS practicename
        FROM
          `virtual-core-194015.157925963.ga_sessions_*` ga,
          UNNEST(hits) AS h
        WHERE
          _table_suffix BETWEEN FORMAT_DATE('%Y%m%d', DATE_SUB(CURRENT_DATE(), INTERVAL 100 day))
          AND FORMAT_DATE('%Y%m%d', DATE_SUB(CURRENT_DATE(), INTERVAL 0 day))
          AND REGEXP_CONTAINS(h.page.pagepath, '/cart')
          AND totals.visits = 1
        GROUP BY
          date,
          practicename,
          fullvisitorid,
          visitid)) s1
    ON
      s0.fullvisitorid = s1.fullvisitorid
      AND s0.visitid = s1.visitid
    FULL OUTER JOIN (( # third subquery
        SELECT
          date,
          fullvisitorid,
          visitid,
          MIN(h.hitnumber) AS firsthit,
          (
          SELECT
            MAX(IF(index = 27,
                value,
                ''))
          FROM
            UNNEST(ga.customdimensions)) AS practicename
        FROM
          `virtual-core-194015.157925963.ga_sessions_*` ga,
          UNNEST(hits) AS h
        WHERE
          _table_suffix BETWEEN FORMAT_DATE('%Y%m%d', DATE_SUB(CURRENT_DATE(), INTERVAL 100 day))
          AND FORMAT_DATE('%Y%m%d', DATE_SUB(CURRENT_DATE(), INTERVAL 0 day))
          AND REGEXP_CONTAINS(h.page.pagepath, '/orderconfirmation')
          AND totals.visits = 1
        GROUP BY
          date,
          practicename,
          fullvisitorid,
          visitid)) s2
    ON
      s1.fullvisitorid = s2.fullvisitorid
      AND s1.visitid = s2.visitid)
  GROUP BY
    date,2
  UNION ALL
  SELECT
    CAST(CONCAT(SUBSTR(date,1,4),'-',SUBSTR(date,5,2),'-',SUBSTR(date,7,2)) AS date) AS date,
    practicename,
    COUNT(DISTINCT s3_fullvisitorid) AS users,
    COUNT(s0_firsthit) AS product_views,
    COUNT(s1_firsthit) AS order_details,
    COUNT(s2_firsthit) AS order_confirmation
  FROM (
    SELECT
      ifnull(s3.date,
        ifnull(s0.date,
          ifnull(s1.date,
            s2.date))) AS date,
      s0.practicename practicename,
      s3.fullvisitorid s3_fullvisitorid,
      s0.fullvisitorid s0_fullvisitorid,
      s0.visitid,
      s0.firsthit s0_firsthit,
      s1.firsthit s1_firsthit,
      s2.firsthit s2_firsthit
    FROM ( # USER subquery
      SELECT
        date,
        fullvisitorid,
        visitid,

        (
        SELECT
          MAX(IF(index = 27,
              value,
              ''))
        FROM
          UNNEST(gart.customdimensions)) AS practicename
      FROM
        `virtual-core-194015.157925963.ga_sessions_*` gart
      WHERE
        totals.visits = 1
      GROUP BY
        date,
        practicename,
        fullvisitorid,
        visitid) s3

    FULL OUTER JOIN (( # first subquery
        SELECT
          date,
          fullvisitorid,
          visitid,
          MIN(h.hitnumber) AS firsthit,
          (
          SELECT
            MAX(IF(index = 27,
                value,
                ''))
          FROM
            UNNEST(gart.customdimensions)) AS practicename
        FROM
          `virtual-core-194015.157925963.ga_sessions_*` gart,
          UNNEST(hits) AS h
        WHERE
          REGEXP_CONTAINS(h.page.pagepath, '/p/')
          AND totals.visits = 1
        GROUP BY
          date,
          practicename,
          fullvisitorid,
          visitid)) s0
    ON
      s3.fullvisitorid = s0.fullvisitorid
      AND s3.visitid = s0.visitid
    FULL OUTER JOIN (( # second subquery
        SELECT
          date,
          fullvisitorid,
          visitid,
          MIN(h.hitnumber) AS firsthit,
          (
          SELECT
            MAX(IF(index = 27,
                value,
                ''))
          FROM
            UNNEST(gart.customdimensions)) AS practicename
        FROM
          `virtual-core-194015.157925963.ga_sessions_*` gart,
          UNNEST(hits) AS h
        WHERE
          REGEXP_CONTAINS(h.page.pagepath, '/cart')
          AND totals.visits = 1
        GROUP BY
          date,
          practicename,
          fullvisitorid,
          visitid)) s1
    ON
      s0.fullvisitorid = s1.fullvisitorid
      AND s0.visitid = s1.visitid
    FULL OUTER JOIN (( # third subquery
        SELECT
          date,
          fullvisitorid,
          visitid,
          MIN(h.hitnumber) AS firsthit,
          (
          SELECT
            MAX(IF(index = 27,
                value,
                ''))
          FROM
            UNNEST(gart.customdimensions)) AS practicename
        FROM
          `virtual-core-194015.157925963.ga_sessions_*` gart,
          UNNEST(hits) AS h
        WHERE
          REGEXP_CONTAINS(h.page.pagepath, '/orderconfirmation')
          AND totals.visits = 1
        GROUP BY
          date,
          practicename,
          fullvisitorid,
          visitid)) s2
    ON
      s1.fullvisitorid = s2.fullvisitorid
      AND s1.visitid = s2.visitid)
  GROUP BY
    date,practicename)
SELECT
  date AS date,
  SUM(users) AS users,
  SUM(product_views) AS product_views,
  SUM(carts) AS carts,
  SUM(order_confirmation) AS order_confirmation
FROM
  ga_tables
WHERE
  LOWER(PracticeName) NOT LIKE '%demo%'
  AND PracticeName NOT LIKE 'asdf'
GROUP BY
  date
ORDER BY
  date DESC
相关问题
最新问题