Analyse des données de Stack Overflow avec ClickHouse

CREATE DATABASE stackoverflow

CREATE TABLE stackoverflow.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'),
    `Score` Int32,
    `ViewCount` UInt32 CODEC(Delta(4), ZSTD(1)),
    `Body` String,
    `OwnerUserId` Int32,
    `OwnerDisplayName` String,
    `LastEditorUserId` Int32,
    `LastEditorDisplayName` String,
    `LastEditDate` DateTime64(3, 'UTC') CODEC(Delta(8), ZSTD(1)),
    `LastActivityDate` DateTime64(3, 'UTC'),
    `Title` String,
    `Tags` String,
    `AnswerCount` UInt16 CODEC(Delta(2), ZSTD(1)),
    `CommentCount` UInt8,
    `FavoriteCount` UInt8,
    `ContentLicense` LowCardinality(String),
    `ParentId` String,
    `CommunityOwnedDate` DateTime64(3, 'UTC'),
    `ClosedDate` DateTime64(3, 'UTC')
)
ENGINE = MergeTree
PARTITION BY toYear(CreationDate)
ORDER BY (PostTypeId, toDate(CreationDate), CreationDate)

INSERT INTO stackoverflow.posts SELECT * FROM s3('https://datasets-documentation.s3.eu-west-3.amazonaws.com/stackoverflow/parquet/posts/*.parquet')

0 rows in set. Elapsed: 265.466 sec. Processed 59.82 million rows, 38.07 GB (225.34 thousand rows/s., 143.42 MB/s.)

CREATE TABLE stackoverflow.votes
(
    `Id` UInt32,
    `PostId` Int32,
    `VoteTypeId` UInt8,
    `CreationDate` DateTime64(3, 'UTC'),
    `UserId` Int32,
    `BountyAmount` UInt8
)
ENGINE = MergeTree
ORDER BY (VoteTypeId, CreationDate, PostId, UserId)

INSERT INTO stackoverflow.votes SELECT * FROM s3('https://datasets-documentation.s3.eu-west-3.amazonaws.com/stackoverflow/parquet/votes/*.parquet')

0 rows in set. Elapsed: 21.605 sec. Processed 238.98 million rows, 2.13 GB (11.06 million rows/s., 98.46 MB/s.)

CREATE TABLE stackoverflow.comments
(
    `Id` UInt32,
    `PostId` UInt32,
    `Score` UInt16,
    `Text` String,
    `CreationDate` DateTime64(3, 'UTC'),
    `UserId` Int32,
    `UserDisplayName` LowCardinality(String)
)
ENGINE = MergeTree
ORDER BY CreationDate

INSERT INTO stackoverflow.comments SELECT * FROM s3('https://datasets-documentation.s3.eu-west-3.amazonaws.com/stackoverflow/parquet/comments/*.parquet')

0 rows in set. Elapsed: 56.593 sec. Processed 90.38 million rows, 11.14 GB (1.60 million rows/s., 196.78 MB/s.)

CREATE TABLE stackoverflow.users
(
    `Id` Int32,
    `Reputation` LowCardinality(String),
    `CreationDate` DateTime64(3, 'UTC') CODEC(Delta(8), ZSTD(1)),
    `DisplayName` String,
    `LastAccessDate` DateTime64(3, 'UTC'),
    `AboutMe` String,
    `Views` UInt32,
    `UpVotes` UInt32,
    `DownVotes` UInt32,
    `WebsiteUrl` String,
    `Location` LowCardinality(String),
    `AccountId` Int32
)
ENGINE = MergeTree
ORDER BY (Id, CreationDate)

INSERT INTO stackoverflow.users SELECT * FROM s3('https://datasets-documentation.s3.eu-west-3.amazonaws.com/stackoverflow/parquet/users.parquet')

0 rows in set. Elapsed: 10.988 sec. Processed 22.48 million rows, 1.36 GB (2.05 million rows/s., 124.10 MB/s.)

CREATE TABLE stackoverflow.badges
(
    `Id` UInt32,
    `UserId` Int32,
    `Name` LowCardinality(String),
    `Date` DateTime64(3, 'UTC'),
    `Class` Enum8('Gold' = 1, 'Silver' = 2, 'Bronze' = 3),
    `TagBased` Bool
)
ENGINE = MergeTree
ORDER BY UserId

INSERT INTO stackoverflow.badges SELECT * FROM s3('https://datasets-documentation.s3.eu-west-3.amazonaws.com/stackoverflow/parquet/badges.parquet')

0 rows in set. Elapsed: 6.635 sec. Processed 51.29 million rows, 797.05 MB (7.73 million rows/s., 120.13 MB/s.)

CREATE TABLE stackoverflow.postlinks
(
    `Id` UInt64,
    `CreationDate` DateTime64(3, 'UTC'),
    `PostId` Int32,
    `RelatedPostId` Int32,
    `LinkTypeId` Enum8('Linked' = 1, 'Duplicate' = 3)
)
ENGINE = MergeTree
ORDER BY (PostId, RelatedPostId)

INSERT INTO stackoverflow.postlinks SELECT * FROM s3('https://datasets-documentation.s3.eu-west-3.amazonaws.com/stackoverflow/parquet/postlinks.parquet')

0 rows in set. Elapsed: 1.534 sec. Processed 6.55 million rows, 129.70 MB (4.27 million rows/s., 84.57 MB/s.)

CREATE TABLE stackoverflow.posthistory
(
    `Id` UInt64,
    `PostHistoryTypeId` UInt8,
    `PostId` Int32,
    `RevisionGUID` String,
    `CreationDate` DateTime64(3, 'UTC'),
    `UserId` Int32,
    `Text` String,
    `ContentLicense` LowCardinality(String),
    `Comment` String,
    `UserDisplayName` String
)
ENGINE = MergeTree
ORDER BY (CreationDate, PostId)

INSERT INTO stackoverflow.posthistory SELECT * FROM s3('https://datasets-documentation.s3.eu-west-3.amazonaws.com/stackoverflow/parquet/posthistory/*.parquet')

0 rows in set. Elapsed: 422.795 sec. Processed 160.79 million rows, 67.08 GB (380.30 thousand rows/s., 158.67 MB/s.)

wget https://archive.org/download/stackexchange/stackoverflow.com-Badges.7z
wget https://archive.org/download/stackexchange/stackoverflow.com-Comments.7z
wget https://archive.org/download/stackexchange/stackoverflow.com-PostHistory.7z
wget https://archive.org/download/stackexchange/stackoverflow.com-PostLinks.7z
wget https://archive.org/download/stackexchange/stackoverflow.com-Posts.7z
wget https://archive.org/download/stackexchange/stackoverflow.com-Users.7z
wget https://archive.org/download/stackexchange/stackoverflow.com-Votes.7z

sudo apt install jq
pip install yq

p7zip -d stackoverflow.com-Posts.7z

mkdir posts
cd posts
# the following splits the input xml file into sub files of 10000 rows
tail +3 ../Posts.xml | head -n -1 | split -l 10000 --filter='{ printf "<rows>\n"; cat - ; printf "</rows>\n"; } > $FILE' -

find . -maxdepth 1 -type f -exec xq -c '.rows.row[]' {} \; | sed -e 's:"@:":g' > posts_v2.json

clickhouse local --query "SELECT * FROM file('posts.json', JSONEachRow, 'Id Int32, PostTypeId UInt8, AcceptedAnswerId UInt32, CreationDate DateTime64(3, \'UTC\'), Score Int32, ViewCount UInt32, Body String, OwnerUserId Int32, OwnerDisplayName String, LastEditorUserId Int32, LastEditorDisplayName String, LastEditDate DateTime64(3, \'UTC\'), LastActivityDate DateTime64(3, \'UTC\'), Title String, Tags String, AnswerCount UInt16, CommentCount UInt8, FavoriteCount UInt8, ContentLicense String, ParentId String, CommunityOwnedDate DateTime64(3, \'UTC\'), ClosedDate DateTime64(3, \'UTC\')') FORMAT Native" | clickhouse client --host <host> --secure --password <password> --query "INSERT INTO stackoverflow.posts_v2 FORMAT Native"

SELECT
    arrayJoin(arrayFilter(t -> (t != ''), splitByChar('|', Tags))) AS Tags,
    count() AS c
FROM stackoverflow.posts
GROUP BY Tags
ORDER BY c DESC
LIMIT 10

┌─Tags───────┬───────c─┐
│ javascript │ 2527130 │
│ python     │ 2189638 │
│ java       │ 1916156 │
│ c#         │ 1614236 │
│ php        │ 1463901 │
│ android    │ 1416442 │
│ html       │ 1186567 │
│ jquery     │ 1034621 │
│ c++        │  806202 │
│ css        │  803755 │
└────────────┴─────────┘

10 rows in set. Elapsed: 1.013 sec. Processed 59.82 million rows, 1.21 GB (59.07 million rows/s., 1.19 GB/s.)
Peak memory usage: 224.03 MiB.

SELECT
    any(OwnerUserId) UserId,
    OwnerDisplayName,
    count() AS c
FROM stackoverflow.posts WHERE OwnerDisplayName != '' AND PostTypeId='Answer' AND OwnerUserId != 0
GROUP BY OwnerDisplayName
ORDER BY c DESC
LIMIT 5

┌─UserId─┬─OwnerDisplayName─┬────c─┐
│  22656 │ Jon Skeet        │ 2727 │
│  23354 │ Marc Gravell     │ 2150 │
│  12950 │ tvanfosson       │ 1530 │
│   3043 │ Joel Coehoorn    │ 1438 │
│  10661 │ S.Lott           │ 1087 │
└────────┴──────────────────┴──────┘

5 rows in set. Elapsed: 0.154 sec. Processed 35.83 million rows, 193.39 MB (232.33 million rows/s., 1.25 GB/s.)
Peak memory usage: 206.45 MiB.

SELECT
    Id,
    Title,
    ViewCount,
    AnswerCount
FROM stackoverflow.posts
WHERE Title ILIKE '%ClickHouse%'
ORDER BY ViewCount DESC
LIMIT 10

┌───────Id─┬─Title────────────────────────────────────────────────────────────────────────────┬─ViewCount─┬─AnswerCount─┐
│ 52355143 │ Is it possible to delete old records from clickhouse table?                      │     41462 │           3 │
│ 37954203 │ Clickhouse Data Import                                                           │     38735 │           3 │
│ 37901642 │ Updating data in Clickhouse                                                      │     36236 │           6 │
│ 58422110 │ Pandas: How to insert dataframe into Clickhouse                                  │     29731 │           4 │
│ 63621318 │ DBeaver - Clickhouse - SQL Error [159] .. Read timed out                         │     27350 │           1 │
│ 47591813 │ How to filter clickhouse table by array column contents?                         │     27078 │           2 │
│ 58728436 │ How to search the string in query with case insensitive on Clickhouse database?  │     26567 │           3 │
│ 65316905 │ Clickhouse: DB::Exception: Memory limit (for query) exceeded                     │     24899 │           2 │
│ 49944865 │ How to add a column in clickhouse                                                │     24424 │           1 │
│ 59712399 │ How to cast date Strings to DateTime format with extended parsing in ClickHouse? │     22620 │           1 │
└──────────┴──────────────────────────────────────────────────────────────────────────────────┴───────────┴─────────────┘

10 rows in set. Elapsed: 0.472 sec. Processed 59.82 million rows, 1.91 GB (126.63 million rows/s., 4.03 GB/s.)
Peak memory usage: 240.01 MiB.

SELECT
    Id,
    Title,
    UpVotes,
    DownVotes,
    abs(UpVotes - DownVotes) AS Controversial_ratio
FROM stackoverflow.posts
INNER JOIN
(
    SELECT
        PostId,
        countIf(VoteTypeId = 2) AS UpVotes,
        countIf(VoteTypeId = 3) AS DownVotes
    FROM stackoverflow.votes
    GROUP BY PostId
    HAVING (UpVotes > 10) AND (DownVotes > 10)
) AS votes ON posts.Id = votes.PostId
WHERE Title != ''
ORDER BY Controversial_ratio ASC
LIMIT 3

┌───────Id─┬─Title─────────────────────────────────────────────┬─UpVotes─┬─DownVotes─┬─Controversial_ratio─┐
│   583177 │ VB.NET Infinite For Loop                          │      12 │        12 │                   0 │
│  9756797 │ Read console input as enumerable - one statement? │      16 │        16 │                   0 │
│ 13329132 │ What's the point of ARGV in Ruby?                 │      22 │        22 │                   0 │
└──────────┴───────────────────────────────────────────────────┴─────────┴───────────┴─────────────────────┘

3 rows in set. Elapsed: 4.779 sec. Processed 298.80 million rows, 3.16 GB (62.52 million rows/s., 661.05 MB/s.)
Peak memory usage: 6.05 GiB.