从 BigQuery 迁移到 ClickHouse Cloud

CREATE TABLE stackoverflow.posts (
    id INTEGER,
    posttypeid INTEGER,
    acceptedanswerid STRING,
    creationdate TIMESTAMP,
    score INTEGER,
    viewcount INTEGER,
    body STRING,
    owneruserid INTEGER,
    ownerdisplayname STRING,
    lasteditoruserid STRING,
    lasteditordisplayname STRING,
    lasteditdate TIMESTAMP,
    lastactivitydate TIMESTAMP,
    title STRING,
    tags STRING,
    answercount INTEGER,
    commentcount INTEGER,
    favoritecount INTEGER,
    conentlicense STRING,
    parentid STRING,
    communityowneddate TIMESTAMP,
    closeddate TIMESTAMP
);

CREATE TABLE stackoverflow.posts
(
   `Id` Int32,
   `PostTypeId` Enum('Question' = 1, 'Answer' = 2, 'Wiki' = 3, 'TagWikiExcerpt' = 4, 'TagWiki' = 5, 'ModeratorNomination' = 6, 'WikiPlaceholder' = 7, 'PrivilegeWiki' = 8),
   `AcceptedAnswerId` UInt32,
   `CreationDate` DateTime,
   `Score` Int32,
   `ViewCount` UInt32,
   `Body` String,
   `OwnerUserId` Int32,
   `OwnerDisplayName` String,
   `LastEditorUserId` Int32,
   `LastEditorDisplayName` String,
   `LastEditDate` DateTime,
   `LastActivityDate` DateTime,
   `Title` String,
   `Tags` String,
   `AnswerCount` UInt16,
   `CommentCount` UInt8,
   `FavoriteCount` UInt8,
   `ContentLicense`LowCardinality(String),
   `ParentId` String,
   `CommunityOwnedDate` DateTime,
   `ClosedDate` DateTime
)
ENGINE = MergeTree
ORDER BY tuple()
COMMENT 'Optimized types'

INSERT INTO stackoverflow.posts SELECT * FROM gcs( 'gs://clickhouse-public-datasets/stackoverflow/parquet/posts/*.parquet', NOSIGN);

CREATE TABLE posts
(
        `Id` Int32 CODEC(Delta(4), ZSTD(1)),
        `PostTypeId` Enum8('Question' = 1, 'Answer' = 2, 'Wiki' = 3, 'TagWikiExcerpt' = 4, 'TagWiki' = 5, 'ModeratorNomination' = 6, 'WikiPlaceholder' = 7, 'PrivilegeWiki' = 8),
        `AcceptedAnswerId` UInt32,
        `CreationDate` DateTime64(3, 'UTC'),
...
        `ClosedDate` DateTime64(3, 'UTC')
)
ENGINE = MergeTree
ORDER BY (PostTypeId, toDate(CreationDate), CreationDate)
PARTITION BY toYear(CreationDate)

SELECT DISTINCT partition
FROM system.parts
WHERE `table` = 'posts'

┌─partition─┐
│ 2008      │
│ 2009      │
│ 2010      │
│ 2011      │
│ 2012      │
│ 2013      │
│ 2014      │
│ 2015      │
│ 2016      │
│ 2017      │
│ 2018      │
│ 2019      │
│ 2020      │
│ 2021      │
│ 2022      │
│ 2023      │
│ 2024      │
└───────────┘

17 rows in set. Elapsed: 0.002 sec.

ALTER TABLE posts
(DROP PARTITION '2008')

Ok.

0 rows in set. Elapsed: 0.103 sec.

ALTER TABLE comments ADD PROJECTION comments_user_id (
SELECT * ORDER BY UserId
)

ALTER TABLE comments MATERIALIZE PROJECTION comments_user_id

SELECT
    parts_to_do,
    is_done,
    latest_fail_reason
FROM system.mutations
WHERE (`table` = 'comments') AND (command LIKE '%MATERIALIZE%')

   ┌─parts_to_do─┬─is_done─┬─latest_fail_reason─┐
1. │           1 │       0 │                    │
   └─────────────┴─────────┴────────────────────┘

1 row in set. Elapsed: 0.003 sec.

EXPLAIN indexes = 1
SELECT avg(Score)
FROM comments
WHERE UserId = 8592047

    ┌─explain─────────────────────────────────────────────┐
 1. │ Expression ((Projection + Before ORDER BY))         │
 2. │   Aggregating                                       │
 3. │   Filter                                            │
 4. │           ReadFromMergeTree (comments_user_id)      │
 5. │           Indexes:                                  │
 6. │           PrimaryKey                                │
 7. │           Keys:                                     │
 8. │           UserId                                    │
 9. │           Condition: (UserId in [8592047, 8592047]) │
10. │           Parts: 2/2                                │
11. │           Granules: 2/11360                         │
    └─────────────────────────────────────────────────────┘

11 rows in set. Elapsed: 0.004 sec.

SELECT
    OwnerDisplayName,
    sum(ViewCount) AS total_views
FROM stackoverflow.posts
WHERE (PostTypeId = 'Question') AND (OwnerDisplayName != '')
GROUP BY OwnerDisplayName
HAVING count() > 10
ORDER BY total_views DESC
LIMIT 5

   ┌─OwnerDisplayName─┬─total_views─┐
1. │ Joan Venge       │    25520387 │
2. │ Ray Vega         │    21576470 │
3. │ anon             │    19814224 │
4. │ Tim              │    19028260 │
5. │ John             │    17638812 │
   └──────────────────┴─────────────┘

5 rows in set. Elapsed: 0.076 sec. Processed 24.35 million rows, 140.21 MB (320.82 million rows/s., 1.85 GB/s.)
Peak memory usage: 323.37 MiB.

-- ClickHouse
SELECT
    arrayJoin(arrayFilter(t -> (t != ''), splitByChar('|', Tags))) AS tags,
    sum(ViewCount) AS views
FROM stackoverflow.posts
GROUP BY tags
ORDER BY views DESC
LIMIT 5

   ┌─tags───────┬──────views─┐
1. │ javascript │ 8190916894 │
2. │ python     │ 8175132834 │
3. │ java       │ 7258379211 │
4. │ c#         │ 5476932513 │
5. │ android    │ 4258320338 │
   └────────────┴────────────┘

5 rows in set. Elapsed: 0.318 sec. Processed 59.82 million rows, 1.45 GB (188.01 million rows/s., 4.54 GB/s.)
Peak memory usage: 567.41 MiB.

-- ClickHouse
SELECT
    toYear(CreationDate) AS Year,
    argMax(Title, ViewCount) AS MostViewedQuestionTitle,
    max(ViewCount) AS MaxViewCount
FROM stackoverflow.posts
WHERE PostTypeId = 'Question'
GROUP BY Year
ORDER BY Year ASC
FORMAT Vertical

Row 1:
──────
Year:                    2008
MostViewedQuestionTitle: How to find the index for a given item in a list?
MaxViewCount:            6316987

Row 2:
──────
Year:                    2009
MostViewedQuestionTitle: How do I undo the most recent local commits in Git?
MaxViewCount:            13962748

...

Row 16:
───────
Year:                    2023
MostViewedQuestionTitle: How do I solve "error: externally-managed-environment" every time I use pip 3?
MaxViewCount:            506822

Row 17:
───────
Year:                    2024
MostViewedQuestionTitle: Warning "Third-party cookie will be blocked. Learn more in the Issues tab"
MaxViewCount:            66975

17 rows in set. Elapsed: 0.225 sec. Processed 24.35 million rows, 1.86 GB (107.99 million rows/s., 8.26 GB/s.)
峰值内存占用: 377.26 MiB.

SELECT
    arrayJoin(arrayFilter(t -> (t != ''), splitByChar('|', Tags))) AS tag,
    countIf(toYear(CreationDate) = 2023) AS count_2023,
    countIf(toYear(CreationDate) = 2022) AS count_2022,
    ((count_2023 - count_2022) / count_2022) * 100 AS percent_change
FROM stackoverflow.posts
WHERE toYear(CreationDate) IN (2022, 2023)
GROUP BY tag
HAVING (count_2022 > 10000) AND (count_2023 > 10000)
ORDER BY percent_change DESC
LIMIT 5

┌─tag─────────┬─count_2023─┬─count_2022─┬──────percent_change─┐
│ next.js     │      13788 │      10520 │   31.06463878326996 │
│ spring-boot │      16573 │      17721 │  -6.478189718413183 │
│ .net        │      11458 │      12968 │ -11.644046884639112 │
│ azure       │      11996 │      14049 │ -14.613139725247349 │
│ docker      │      13885 │      16877 │  -17.72826924216389 │
└─────────────┴────────────┴────────────┴─────────────────────┘

5 rows in set. Elapsed: 0.096 sec. Processed 5.08 million rows, 155.73 MB (53.10 million rows/s., 1.63 GB/s.)
Peak memory usage: 410.37 MiB.