ClickHouse 初體驗

參考資料:
https://clickhouse.tech/docs/en/getting-started/tutorial/

Download and Extract Table Data

curl https://datasets.clickhouse.tech/hits/tsv/hits_v1.tsv.xz | unxz --threads=`nproc` > hits_v1.tsv
curl https://datasets.clickhouse.tech/visits/tsv/visits_v1.tsv.xz | unxz --threads=`nproc` > visits_v1.tsv

Create Tables

clickhouse-client --query "CREATE DATABASE IF NOT EXISTS tutorial"

創(chuàng)建hits表

CREATE TABLE tutorial.hits_v1
(
    `WatchID` UInt64,
    `JavaEnable` UInt8,
    `Title` String,
    `GoodEvent` Int16,
    `EventTime` DateTime,
    `EventDate` Date,
    `CounterID` UInt32,
    `ClientIP` UInt32,
    `ClientIP6` FixedString(16),
    `RegionID` UInt32,
    `UserID` UInt64,
    `CounterClass` Int8,
    `OS` UInt8,
    `UserAgent` UInt8,
    `URL` String,
    `Referer` String,
    `URLDomain` String,
    `RefererDomain` String,
    `Refresh` UInt8,
    `IsRobot` UInt8,
    `RefererCategories` Array(UInt16),
    `URLCategories` Array(UInt16),
    `URLRegions` Array(UInt32),
    `RefererRegions` Array(UInt32),
    `ResolutionWidth` UInt16,
    `ResolutionHeight` UInt16,
    `ResolutionDepth` UInt8,
    `FlashMajor` UInt8,
    `FlashMinor` UInt8,
    `FlashMinor2` String,
    `NetMajor` UInt8,
    `NetMinor` UInt8,
    `UserAgentMajor` UInt16,
    `UserAgentMinor` FixedString(2),
    `CookieEnable` UInt8,
    `JavascriptEnable` UInt8,
    `IsMobile` UInt8,
    `MobilePhone` UInt8,
    `MobilePhoneModel` String,
    `Params` String,
    `IPNetworkID` UInt32,
    `TraficSourceID` Int8,
    `SearchEngineID` UInt16,
    `SearchPhrase` String,
    `AdvEngineID` UInt8,
    `IsArtifical` UInt8,
    `WindowClientWidth` UInt16,
    `WindowClientHeight` UInt16,
    `ClientTimeZone` Int16,
    `ClientEventTime` DateTime,
    `SilverlightVersion1` UInt8,
    `SilverlightVersion2` UInt8,
    `SilverlightVersion3` UInt32,
    `SilverlightVersion4` UInt16,
    `PageCharset` String,
    `CodeVersion` UInt32,
    `IsLink` UInt8,
    `IsDownload` UInt8,
    `IsNotBounce` UInt8,
    `FUniqID` UInt64,
    `HID` UInt32,
    `IsOldCounter` UInt8,
    `IsEvent` UInt8,
    `IsParameter` UInt8,
    `DontCountHits` UInt8,
    `WithHash` UInt8,
    `HitColor` FixedString(1),
    `UTCEventTime` DateTime,
    `Age` UInt8,
    `Sex` UInt8,
    `Income` UInt8,
    `Interests` UInt16,
    `Robotness` UInt8,
    `GeneralInterests` Array(UInt16),
    `RemoteIP` UInt32,
    `RemoteIP6` FixedString(16),
    `WindowName` Int32,
    `OpenerName` Int32,
    `HistoryLength` Int16,
    `BrowserLanguage` FixedString(2),
    `BrowserCountry` FixedString(2),
    `SocialNetwork` String,
    `SocialAction` String,
    `HTTPError` UInt16,
    `SendTiming` Int32,
    `DNSTiming` Int32,
    `ConnectTiming` Int32,
    `ResponseStartTiming` Int32,
    `ResponseEndTiming` Int32,
    `FetchTiming` Int32,
    `RedirectTiming` Int32,
    `DOMInteractiveTiming` Int32,
    `DOMContentLoadedTiming` Int32,
    `DOMCompleteTiming` Int32,
    `LoadEventStartTiming` Int32,
    `LoadEventEndTiming` Int32,
    `NSToDOMContentLoadedTiming` Int32,
    `FirstPaintTiming` Int32,
    `RedirectCount` Int8,
    `SocialSourceNetworkID` UInt8,
    `SocialSourcePage` String,
    `ParamPrice` Int64,
    `ParamOrderID` String,
    `ParamCurrency` FixedString(3),
    `ParamCurrencyID` UInt16,
    `GoalsReached` Array(UInt32),
    `OpenstatServiceName` String,
    `OpenstatCampaignID` String,
    `OpenstatAdID` String,
    `OpenstatSourceID` String,
    `UTMSource` String,
    `UTMMedium` String,
    `UTMCampaign` String,
    `UTMContent` String,
    `UTMTerm` String,
    `FromTag` String,
    `HasGCLID` UInt8,
    `RefererHash` UInt64,
    `URLHash` UInt64,
    `CLID` UInt32,
    `YCLID` UInt64,
    `ShareService` String,
    `ShareURL` String,
    `ShareTitle` String,
    `ParsedParams` Nested(
        Key1 String,
        Key2 String,
        Key3 String,
        Key4 String,
        Key5 String,
        ValueDouble Float64),
    `IslandID` FixedString(16),
    `RequestNum` UInt32,
    `RequestTry` UInt8
)
ENGINE = MergeTree()
PARTITION BY toYYYYMM(EventDate)
ORDER BY (CounterID, EventDate, intHash32(UserID))
SAMPLE BY intHash32(UserID)

創(chuàng)建visits 表

CREATE TABLE tutorial.visits_v1
(
    `CounterID` UInt32,
    `StartDate` Date,
    `Sign` Int8,
    `IsNew` UInt8,
    `VisitID` UInt64,
    `UserID` UInt64,
    `StartTime` DateTime,
    `Duration` UInt32,
    `UTCStartTime` DateTime,
    `PageViews` Int32,
    `Hits` Int32,
    `IsBounce` UInt8,
    `Referer` String,
    `StartURL` String,
    `RefererDomain` String,
    `StartURLDomain` String,
    `EndURL` String,
    `LinkURL` String,
    `IsDownload` UInt8,
    `TraficSourceID` Int8,
    `SearchEngineID` UInt16,
    `SearchPhrase` String,
    `AdvEngineID` UInt8,
    `PlaceID` Int32,
    `RefererCategories` Array(UInt16),
    `URLCategories` Array(UInt16),
    `URLRegions` Array(UInt32),
    `RefererRegions` Array(UInt32),
    `IsYandex` UInt8,
    `GoalReachesDepth` Int32,
    `GoalReachesURL` Int32,
    `GoalReachesAny` Int32,
    `SocialSourceNetworkID` UInt8,
    `SocialSourcePage` String,
    `MobilePhoneModel` String,
    `ClientEventTime` DateTime,
    `RegionID` UInt32,
    `ClientIP` UInt32,
    `ClientIP6` FixedString(16),
    `RemoteIP` UInt32,
    `RemoteIP6` FixedString(16),
    `IPNetworkID` UInt32,
    `SilverlightVersion3` UInt32,
    `CodeVersion` UInt32,
    `ResolutionWidth` UInt16,
    `ResolutionHeight` UInt16,
    `UserAgentMajor` UInt16,
    `UserAgentMinor` UInt16,
    `WindowClientWidth` UInt16,
    `WindowClientHeight` UInt16,
    `SilverlightVersion2` UInt8,
    `SilverlightVersion4` UInt16,
    `FlashVersion3` UInt16,
    `FlashVersion4` UInt16,
    `ClientTimeZone` Int16,
    `OS` UInt8,
    `UserAgent` UInt8,
    `ResolutionDepth` UInt8,
    `FlashMajor` UInt8,
    `FlashMinor` UInt8,
    `NetMajor` UInt8,
    `NetMinor` UInt8,
    `MobilePhone` UInt8,
    `SilverlightVersion1` UInt8,
    `Age` UInt8,
    `Sex` UInt8,
    `Income` UInt8,
    `JavaEnable` UInt8,
    `CookieEnable` UInt8,
    `JavascriptEnable` UInt8,
    `IsMobile` UInt8,
    `BrowserLanguage` UInt16,
    `BrowserCountry` UInt16,
    `Interests` UInt16,
    `Robotness` UInt8,
    `GeneralInterests` Array(UInt16),
    `Params` Array(String),
    `Goals` Nested(
        ID UInt32,
        Serial UInt32,
        EventTime DateTime,
        Price Int64,
        OrderID String,
        CurrencyID UInt32),
    `WatchIDs` Array(UInt64),
    `ParamSumPrice` Int64,
    `ParamCurrency` FixedString(3),
    `ParamCurrencyID` UInt16,
    `ClickLogID` UInt64,
    `ClickEventID` Int32,
    `ClickGoodEvent` Int32,
    `ClickEventTime` DateTime,
    `ClickPriorityID` Int32,
    `ClickPhraseID` Int32,
    `ClickPageID` Int32,
    `ClickPlaceID` Int32,
    `ClickTypeID` Int32,
    `ClickResourceID` Int32,
    `ClickCost` UInt32,
    `ClickClientIP` UInt32,
    `ClickDomainID` UInt32,
    `ClickURL` String,
    `ClickAttempt` UInt8,
    `ClickOrderID` UInt32,
    `ClickBannerID` UInt32,
    `ClickMarketCategoryID` UInt32,
    `ClickMarketPP` UInt32,
    `ClickMarketCategoryName` String,
    `ClickMarketPPName` String,
    `ClickAWAPSCampaignName` String,
    `ClickPageName` String,
    `ClickTargetType` UInt16,
    `ClickTargetPhraseID` UInt64,
    `ClickContextType` UInt8,
    `ClickSelectType` Int8,
    `ClickOptions` String,
    `ClickGroupBannerID` Int32,
    `OpenstatServiceName` String,
    `OpenstatCampaignID` String,
    `OpenstatAdID` String,
    `OpenstatSourceID` String,
    `UTMSource` String,
    `UTMMedium` String,
    `UTMCampaign` String,
    `UTMContent` String,
    `UTMTerm` String,
    `FromTag` String,
    `HasGCLID` UInt8,
    `FirstVisit` DateTime,
    `PredLastVisit` Date,
    `LastVisit` Date,
    `TotalVisits` UInt32,
    `TraficSource` Nested(
        ID Int8,
        SearchEngineID UInt16,
        AdvEngineID UInt8,
        PlaceID UInt16,
        SocialSourceNetworkID UInt8,
        Domain String,
        SearchPhrase String,
        SocialSourcePage String),
    `Attendance` FixedString(16),
    `CLID` UInt32,
    `YCLID` UInt64,
    `NormalizedRefererHash` UInt64,
    `SearchPhraseHash` UInt64,
    `RefererDomainHash` UInt64,
    `NormalizedStartURLHash` UInt64,
    `StartURLDomainHash` UInt64,
    `NormalizedEndURLHash` UInt64,
    `TopLevelDomain` UInt64,
    `URLScheme` UInt64,
    `OpenstatServiceNameHash` UInt64,
    `OpenstatCampaignIDHash` UInt64,
    `OpenstatAdIDHash` UInt64,
    `OpenstatSourceIDHash` UInt64,
    `UTMSourceHash` UInt64,
    `UTMMediumHash` UInt64,
    `UTMCampaignHash` UInt64,
    `UTMContentHash` UInt64,
    `UTMTermHash` UInt64,
    `FromHash` UInt64,
    `WebVisorEnabled` UInt8,
    `WebVisorActivity` UInt32,
    `ParsedParams` Nested(
        Key1 String,
        Key2 String,
        Key3 String,
        Key4 String,
        Key5 String,
        ValueDouble Float64),
    `Market` Nested(
        Type UInt8,
        GoalID UInt32,
        OrderID String,
        OrderPrice Int64,
        PP UInt32,
        DirectPlaceID UInt32,
        DirectOrderID UInt32,
        DirectBannerID UInt32,
        GoodID String,
        GoodName String,
        GoodQuantity Int32,
        GoodPrice Int64),
    `IslandID` FixedString(16)
)
ENGINE = CollapsingMergeTree(Sign)
PARTITION BY toYYYYMM(StartDate)
ORDER BY (CounterID, StartDate, intHash32(UserID), VisitID)
SAMPLE BY intHash32(UserID)

導入數據

clickhouse-client --query "INSERT INTO tutorial.hits_v1 FORMAT TSV" --max_insert_block_size=100000 < hits_v1.tsv
clickhouse-client --query "INSERT INTO tutorial.visits_v1 FORMAT TSV" --max_insert_block_size=100000 < visits_v1.tsv

clickhouse-client --query "OPTIMIZE TABLE tutorial.hits_v1 FINAL"
clickhouse-client --query "OPTIMIZE TABLE tutorial.visits_v1 FINAL"
clickhouse-client --query "SELECT COUNT(*) FROM tutorial.hits_v1"
clickhouse-client --query "SELECT COUNT(*) FROM tutorial.visits_v1"

Example Queries

SELECT
    StartURL AS URL,
    AVG(Duration) AS AvgDuration
FROM tutorial.visits_v1
WHERE StartDate BETWEEN '2014-03-23' AND '2014-03-30'
GROUP BY URL
ORDER BY AvgDuration DESC
LIMIT 10

10 rows in set. Elapsed: 0.219 sec. Processed 1.45 million rows, 114.59 MB (6.63 million rows/s., 522.71 MB/s.)

SELECT
    sum(Sign) AS visits,
    sumIf(Sign, has(Goals.ID, 1105530)) AS goal_visits,
    (100. * goal_visits) / visits AS goal_percent
FROM tutorial.visits_v1
WHERE (CounterID = 912887) AND (toYYYYMM(StartDate) = 201403) AND (domain(StartURL) = 'yandex.ru')

1 rows in set. Elapsed: 0.048 sec. Processed 40.05 thousand rows, 4.94 MB (841.00 thousand rows/s., 103.82 MB/s.)

附錄

常用命令
show databases;

?著作權歸作者所有,轉載或內容合作請聯(lián)系作者
  • 序言:七十年代末梢莽,一起剝皮案震驚了整個濱河市,隨后出現(xiàn)的幾起案子,更是在濱河造成了極大的恐慌丢早,老刑警劉巖傻盟,帶你破解...
    沈念sama閱讀 217,734評論 6 505
  • 序言:濱河連續(xù)發(fā)生了三起死亡事件馆蠕,死亡現(xiàn)場離奇詭異刽锤,居然都是意外死亡帘不,警方通過查閱死者的電腦和手機掂摔,發(fā)現(xiàn)死者居然都...
    沈念sama閱讀 92,931評論 3 394
  • 文/潘曉璐 我一進店門术羔,熙熙樓的掌柜王于貴愁眉苦臉地迎上來,“玉大人乙漓,你說我怎么就攤上這事级历。” “怎么了叭披?”我有些...
    開封第一講書人閱讀 164,133評論 0 354
  • 文/不壞的土叔 我叫張陵寥殖,是天一觀的道長。 經常有香客問我涩蜘,道長嚼贡,這世上最難降的妖魔是什么? 我笑而不...
    開封第一講書人閱讀 58,532評論 1 293
  • 正文 為了忘掉前任同诫,我火速辦了婚禮粤策,結果婚禮上,老公的妹妹穿的比我還像新娘误窖。我一直安慰自己叮盘,他們只是感情好,可當我...
    茶點故事閱讀 67,585評論 6 392
  • 文/花漫 我一把揭開白布霹俺。 她就那樣靜靜地躺著柔吼,像睡著了一般。 火紅的嫁衣襯著肌膚如雪丙唧。 梳的紋絲不亂的頭發(fā)上愈魏,一...
    開封第一講書人閱讀 51,462評論 1 302
  • 那天,我揣著相機與錄音,去河邊找鬼培漏。 笑死溪厘,一個胖子當著我的面吹牛,可吹牛的內容都是我干的北苟。 我是一名探鬼主播桩匪,決...
    沈念sama閱讀 40,262評論 3 418
  • 文/蒼蘭香墨 我猛地睜開眼,長吁一口氣:“原來是場噩夢啊……” “哼友鼻!你這毒婦竟也來了傻昙?” 一聲冷哼從身側響起,我...
    開封第一講書人閱讀 39,153評論 0 276
  • 序言:老撾萬榮一對情侶失蹤彩扔,失蹤者是張志新(化名)和其女友劉穎妆档,沒想到半個月后,有當地人在樹林里發(fā)現(xiàn)了一具尸體虫碉,經...
    沈念sama閱讀 45,587評論 1 314
  • 正文 獨居荒郊野嶺守林人離奇死亡贾惦,尸身上長有42處帶血的膿包…… 初始之章·張勛 以下內容為張勛視角 年9月15日...
    茶點故事閱讀 37,792評論 3 336
  • 正文 我和宋清朗相戀三年,在試婚紗的時候發(fā)現(xiàn)自己被綠了敦捧。 大學時的朋友給我發(fā)了我未婚夫和他白月光在一起吃飯的照片须板。...
    茶點故事閱讀 39,919評論 1 348
  • 序言:一個原本活蹦亂跳的男人離奇死亡,死狀恐怖兢卵,靈堂內的尸體忽然破棺而出习瑰,到底是詐尸還是另有隱情,我是刑警寧澤秽荤,帶...
    沈念sama閱讀 35,635評論 5 345
  • 正文 年R本政府宣布甜奄,位于F島的核電站,受9級特大地震影響窃款,放射性物質發(fā)生泄漏课兄。R本人自食惡果不足惜,卻給世界環(huán)境...
    茶點故事閱讀 41,237評論 3 329
  • 文/蒙蒙 一晨继、第九天 我趴在偏房一處隱蔽的房頂上張望烟阐。 院中可真熱鬧,春花似錦紊扬、人聲如沸曲饱。這莊子的主人今日做“春日...
    開封第一講書人閱讀 31,855評論 0 22
  • 文/蒼蘭香墨 我抬頭看了看天上的太陽。三九已至楔敌,卻和暖如春啤挎,著一層夾襖步出監(jiān)牢的瞬間,已是汗流浹背。 一陣腳步聲響...
    開封第一講書人閱讀 32,983評論 1 269
  • 我被黑心中介騙來泰國打工庆聘, 沒想到剛下飛機就差點兒被人妖公主榨干…… 1. 我叫王不留胜臊,地道東北人。 一個月前我還...
    沈念sama閱讀 48,048評論 3 370
  • 正文 我出身青樓伙判,卻偏偏與公主長得像象对,于是被迫代替她去往敵國和親。 傳聞我的和親對象是個殘疾皇子宴抚,可洞房花燭夜當晚...
    茶點故事閱讀 44,864評論 2 354

推薦閱讀更多精彩內容