ClickHouse-官方数据集使用

准备clickhouse官方数据集

上传并解压

unxz hits_v1.tsv.xz
unxz visits_v1.tsv.xz
hits_v1.tsv:130+字段,880w+数据,7.3G
visits_v1.tsv:180+字段,160w+数据,2.5G

创建表并导入数据

进入client
clickhouse-client -m —password

创建库:

CREATE DATABASE IF NOT EXISTS datasets;

创建表(visits_v1):

CREATE TABLE datasets.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)
SETTINGS index_granularity = 8192;

导入数据

cat visits_v1.tsv | clickhouse-client -m --password --query "INSERT INTO datasets.visits_v1 FORMAT TSV" --max_insert_block_size=100000
 

手动触发合并

date1002 :) OPTIMIZE TABLE datasets.visits_v1 FINAL;
OPTIMIZE TABLE datasets.visits_v1 FINAL
Query id: 658968fa-2355-46d2-abe3-2b6b67e89870
Ok.
0 rows in set. Elapsed: 7.343 sec. 

查询表数据

date1002 :) select count(*) from datasets.visits_v1;
SELECT count(*)
FROM datasets.visits_v1
Query id: ecee6bce-f180-497c-b385-ed9bcc4e80e9
┌─count()─┐
│ 1676861 │
└─────────┘
1 rows in set. Elapsed: 0.002 sec. 

创建表(hits_v1)

CREATE TABLE datasets.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)
SETTINGS index_granularity = 8192

导入数据

cat hits_v1.tsv | clickhouse-client -m --password --query "INSERT INTO datasets.hits_v1 FORMAT TSV" --max_insert_block_size=100000

手动触发合并

date1002 :) OPTIMIZE TABLE datasets.hits_v1 FINAL;
OPTIMIZE TABLE datasets.hits_v1 FINAL
Query id: 0d82686d-c0ac-474d-8355-6ba98214995c
Ok.
0 rows in set. Elapsed: 19.446 sec. 

查询数据

date1002 :) select count(1) from datasets.hits_v1;
SELECT count(1)
FROM datasets.hits_v1
Query id: b34d588c-34f9-4eb1-80c1-eac635b59dea
┌─count()─┐
│ 8873898 │
└─────────┘
1 rows in set. Elapsed: 0.003 sec. 

完成,尽情使用。

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值