[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M72ZPZFR3BPWRQFKNPENREEJ":3,"skill-same:01M72ZPZFR3BPWRQFKNPENREEJ":48},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M72ZPZFR3BPWRQFKNPENREEJ","clickhouse-io",null,"고성능 분석 워크로드를 위한 ClickHouse 데이터베이스 패턴, 쿼리 최적화, 분석 및 데이터 엔지니어링 모범 사례.","SriramGandhiS\u002FSkills","SriramGandhiS","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F211849986?v=4","01M72WQCW12BYX71C6WN584TTA","Sriram S","01M72WQCWTJ2RD0ET1X31AF1RC",1,"MIT","https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fskills\u002Feverything-claude-code\u002Fdocs\u002Fko-KR\u002Fskills\u002Fclickhouse-io\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: clickhouse-io\ndescription: 고성능 분석 워크로드를 위한 ClickHouse 데이터베이스 패턴, 쿼리 최적화, 분석 및 데이터 엔지니어링 모범 사례.\norigin: ECC\n---\n\n# ClickHouse 분석 패턴\n\n고성능 분석 및 데이터 엔지니어링을 위한 ClickHouse 전용 패턴.\n\n## 활성화 시점\n\n- ClickHouse 테이블 스키마 설계 시 (MergeTree 엔진 선택)\n- 분석 쿼리 작성 시 (집계, 윈도우 함수, 조인)\n- 쿼리 성능 최적화 시 (파티션 프루닝, 프로젝션, 구체화된 뷰)\n- 대량 데이터 수집 시 (배치 삽입, Kafka 통합)\n- PostgreSQL\u002FMySQL에서 ClickHouse로 분석 마이그레이션 시\n- 실시간 대시보드 또는 시계열 분석 구현 시\n\n## 개요\n\nClickHouse는 온라인 분석 처리(OLAP)를 위한 컬럼 지향 데이터베이스 관리 시스템(DBMS)입니다. 대규모 데이터셋에 대한 빠른 분석 쿼리에 최적화되어 있습니다.\n\n**주요 특징:**\n- 컬럼 지향 저장소\n- 데이터 압축\n- 병렬 쿼리 실행\n- 분산 쿼리\n- 실시간 분석\n\n## 테이블 설계 패턴\n\n### MergeTree 엔진 (가장 일반적)\n\n```sql\nCREATE TABLE markets_analytics (\n    date Date,\n    market_id String,\n    market_name String,\n    volume UInt64,\n    trades UInt32,\n    unique_traders UInt32,\n    avg_trade_size Float64,\n    created_at DateTime\n) ENGINE = MergeTree()\nPARTITION BY toYYYYMM(date)\nORDER BY (date, market_id)\nSETTINGS index_granularity = 8192;\n```\n\n### ReplacingMergeTree (중복 제거)\n\n```sql\n-- 중복이 있을 수 있는 데이터용 (예: 여러 소스에서 수집된 경우)\nCREATE TABLE user_events (\n    event_id String,\n    user_id String,\n    event_type String,\n    timestamp DateTime,\n    properties String\n) ENGINE = ReplacingMergeTree()\nPARTITION BY toYYYYMM(timestamp)\nORDER BY (user_id, event_id, timestamp)\nPRIMARY KEY (user_id, event_id);\n```\n\n### AggregatingMergeTree (사전 집계)\n\n```sql\n-- 집계 메트릭을 유지하기 위한 용도\nCREATE TABLE market_stats_hourly (\n    hour DateTime,\n    market_id String,\n    total_volume AggregateFunction(sum, UInt64),\n    total_trades AggregateFunction(count, UInt32),\n    unique_users AggregateFunction(uniq, String)\n) ENGINE = AggregatingMergeTree()\nPARTITION BY toYYYYMM(hour)\nORDER BY (hour, market_id);\n\n-- 집계된 데이터 조회\nSELECT\n    hour,\n    market_id,\n    sumMerge(total_volume) AS volume,\n    countMerge(total_trades) AS trades,\n    uniqMerge(unique_users) AS users\nFROM market_stats_hourly\nWHERE hour >= toStartOfHour(now() - INTERVAL 24 HOUR)\nGROUP BY hour, market_id\nORDER BY hour DESC;\n```\n\n## 쿼리 최적화 패턴\n\n### 효율적인 필터링\n\n```sql\n-- PASS: 좋음: 인덱스된 컬럼을 먼저 사용\nSELECT *\nFROM markets_analytics\nWHERE date >= '2025-01-01'\n  AND market_id = 'market-123'\n  AND volume > 1000\nORDER BY date DESC\nLIMIT 100;\n\n-- FAIL: 나쁨: 비인덱스 컬럼을 먼저 필터링\nSELECT *\nFROM markets_analytics\nWHERE volume > 1000\n  AND market_name LIKE '%election%'\n  AND date >= '2025-01-01';\n```\n\n### 집계\n\n```sql\n-- PASS: 좋음: ClickHouse 전용 집계 함수를 사용\nSELECT\n    toStartOfDay(created_at) AS day,\n    market_id,\n    sum(volume) AS total_volume,\n    count() AS total_trades,\n    uniq(trader_id) AS unique_traders,\n    avg(trade_size) AS avg_size\nFROM trades\nWHERE created_at >= today() - INTERVAL 7 DAY\nGROUP BY day, market_id\nORDER BY day DESC, total_volume DESC;\n\n-- PASS: 백분위수에는 quantile 사용 (percentile보다 효율적)\nSELECT\n    quantile(0.50)(trade_size) AS median,\n    quantile(0.95)(trade_size) AS p95,\n    quantile(0.99)(trade_size) AS p99\nFROM trades\nWHERE created_at >= now() - INTERVAL 1 HOUR;\n```\n\n### 윈도우 함수\n\n```sql\n-- 누적 합계 계산\nSELECT\n    date,\n    market_id,\n    volume,\n    sum(volume) OVER (\n        PARTITION BY market_id\n        ORDER BY date\n        ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW\n    ) AS cumulative_volume\nFROM markets_analytics\nWHERE date >= today() - INTERVAL 30 DAY\nORDER BY market_id, date;\n```\n\n## 데이터 삽입 패턴\n\n### 배치 삽입 (권장)\n\n```typescript\nimport { ClickHouse } from 'clickhouse'\n\nconst clickhouse = new ClickHouse({\n  url: process.env.CLICKHOUSE_URL,\n  port: 8123,\n  basicAuth: {\n    username: process.env.CLICKHOUSE_USER,\n    password: process.env.CLICKHOUSE_PASSWORD\n  }\n})\n\n\u002F\u002F PASS: 배치 삽입 (효율적)\nasync function bulkInsertTrades(trades: Trade[]) {\n  const rows = trades.map(trade => ({\n    id: trade.id,\n    market_id: trade.market_id,\n    user_id: trade.user_id,\n    amount: trade.amount,\n    timestamp: trade.timestamp.toISOString()\n  }))\n\n  await clickhouse.insert('trades', rows)\n}\n\n\u002F\u002F FAIL: 개별 삽입 (느림)\nasync function insertTrade(trade: Trade) {\n  \u002F\u002F 루프 안에서 이렇게 하지 마세요!\n  await clickhouse.query(`\n    INSERT INTO trades VALUES ('${trade.id}', ...)\n  `).toPromise()\n}\n```\n\n### 스트리밍 삽입\n\n```typescript\n\u002F\u002F 연속적인 데이터 수집용\nimport { createWriteStream } from 'fs'\nimport { pipeline } from 'stream\u002Fpromises'\n\nasync function streamInserts() {\n  const stream = clickhouse.insert('trades').stream()\n\n  for await (const batch of dataSource) {\n    stream.write(batch)\n  }\n\n  await stream.end()\n}\n```\n\n## 구체화된 뷰\n\n### 실시간 집계\n\n```sql\n-- 시간별 통계를 위한 materialized view 생성\nCREATE MATERIALIZED VIEW market_stats_hourly_mv\nTO market_stats_hourly\nAS SELECT\n    toStartOfHour(timestamp) AS hour,\n    market_id,\n    sumState(amount) AS total_volume,\n    countState() AS total_trades,\n    uniqState(user_id) AS unique_users\nFROM trades\nGROUP BY hour, market_id;\n\n-- materialized view 조회\nSELECT\n    hour,\n    market_id,\n    sumMerge(total_volume) AS volume,\n    countMerge(total_trades) AS trades,\n    uniqMerge(unique_users) AS users\nFROM market_stats_hourly\nWHERE hour >= now() - INTERVAL 24 HOUR\nGROUP BY hour, market_id;\n```\n\n## 성능 모니터링\n\n### 쿼리 성능\n\n```sql\n-- 느린 쿼리 확인\nSELECT\n    query_id,\n    user,\n    query,\n    query_duration_ms,\n    read_rows,\n    read_bytes,\n    memory_usage\nFROM system.query_log\nWHERE type = 'QueryFinish'\n  AND query_duration_ms > 1000\n  AND event_time >= now() - INTERVAL 1 HOUR\nORDER BY query_duration_ms DESC\nLIMIT 10;\n```\n\n### 테이블 통계\n\n```sql\n-- 테이블 크기 확인\nSELECT\n    database,\n    table,\n    formatReadableSize(sum(bytes)) AS size,\n    sum(rows) AS rows,\n    max(modification_time) AS latest_modification\nFROM system.parts\nWHERE active\nGROUP BY database, table\nORDER BY sum(bytes) DESC;\n```\n\n## 일반적인 분석 쿼리\n\n### 시계열 분석\n\n```sql\n-- 일간 활성 사용자\nSELECT\n    toDate(timestamp) AS date,\n    uniq(user_id) AS daily_active_users\nFROM events\nWHERE timestamp >= today() - INTERVAL 30 DAY\nGROUP BY date\nORDER BY date;\n\n-- 리텐션 분석\nSELECT\n    signup_date,\n    countIf(days_since_signup = 0) AS day_0,\n    countIf(days_since_signup = 1) AS day_1,\n    countIf(days_since_signup = 7) AS day_7,\n    countIf(days_since_signup = 30) AS day_30\nFROM (\n    SELECT\n        user_id,\n        min(toDate(timestamp)) AS signup_date,\n        toDate(timestamp) AS activity_date,\n        dateDiff('day', signup_date, activity_date) AS days_since_signup\n    FROM events\n    GROUP BY user_id, activity_date\n)\nGROUP BY signup_date\nORDER BY signup_date DESC;\n```\n\n### 퍼널 분석\n\n```sql\n-- 전환 퍼널\nSELECT\n    countIf(step = 'viewed_market') AS viewed,\n    countIf(step = 'clicked_trade') AS clicked,\n    countIf(step = 'completed_trade') AS completed,\n    round(clicked \u002F viewed * 100, 2) AS view_to_click_rate,\n    round(completed \u002F clicked * 100, 2) AS click_to_completion_rate\nFROM (\n    SELECT\n        user_id,\n        session_id,\n        event_type AS step\n    FROM events\n    WHERE event_date = today()\n)\nGROUP BY session_id;\n```\n\n### 코호트 분석\n\n```sql\n-- 가입 월별 사용자 코호트\nSELECT\n    toStartOfMonth(signup_date) AS cohort,\n    toStartOfMonth(activity_date) AS month,\n    dateDiff('month', cohort, month) AS months_since_signup,\n    count(DISTINCT user_id) AS active_users\nFROM (\n    SELECT\n        user_id,\n        min(toDate(timestamp)) OVER (PARTITION BY user_id) AS signup_date,\n        toDate(timestamp) AS activity_date\n    FROM events\n)\nGROUP BY cohort, month, months_since_signup\nORDER BY cohort, months_since_signup;\n```\n\n## 데이터 파이프라인 패턴\n\n### ETL 패턴\n\n```typescript\n\u002F\u002F 추출, 변환, 적재(ETL)\nasync function etlPipeline() {\n  \u002F\u002F 1. 소스에서 추출\n  const rawData = await extractFromPostgres()\n\n  \u002F\u002F 2. 변환\n  const transformed = rawData.map(row => ({\n    date: new Date(row.created_at).toISOString().split('T')[0],\n    market_id: row.market_slug,\n    volume: parseFloat(row.total_volume),\n    trades: parseInt(row.trade_count)\n  }))\n\n  \u002F\u002F 3. ClickHouse에 적재\n  await bulkInsertToClickHouse(transformed)\n}\n\n\u002F\u002F 주기적으로 실행\nlet etlRunning = false\n\nsetInterval(async () => {\n  if (etlRunning) return\n\n  etlRunning = true\n  try {\n    await etlPipeline()\n  } finally {\n    etlRunning = false\n  }\n}, 60 * 60 * 1000)  \u002F\u002F Every hour\n```\n\n### 변경 데이터 캡처 (CDC)\n\n```typescript\n\u002F\u002F PostgreSQL 변경을 수신하고 ClickHouse와 동기화\nimport { Client } from 'pg'\n\nconst pgClient = new Client({ connectionString: process.env.DATABASE_URL })\n\npgClient.query('LISTEN market_updates')\n\npgClient.on('notification', async (msg) => {\n  const update = JSON.parse(msg.payload)\n\n  await clickhouse.insert('market_updates', [\n    {\n      market_id: update.id,\n      event_type: update.operation,  \u002F\u002F INSERT, UPDATE, DELETE\n      timestamp: new Date(),\n      data: JSON.stringify(update.new_data)\n    }\n  ])\n})\n```\n\n## 모범 사례\n\n### 1. 파티셔닝 전략\n- 시간별 파티셔닝 (보통 월 또는 일)\n- 파티션이 너무 많은 것 방지 (성능 영향)\n- 파티션 키에 DATE 타입 사용\n\n### 2. 정렬 키\n- 가장 자주 필터링되는 컬럼을 먼저 배치\n- 카디널리티 고려 (높은 카디널리티 먼저)\n- 정렬이 압축에 영향을 미침\n\n### 3. 데이터 타입\n- 가장 작은 적절한 타입 사용 (UInt32 vs UInt64)\n- 반복되는 문자열에 LowCardinality 사용\n- 범주형 데이터에 Enum 사용\n\n### 4. 피해야 할 것\n- SELECT * (컬럼을 명시)\n- FINAL (쿼리 전에 데이터를 병합)\n- 너무 많은 JOIN (분석을 위해 비정규화)\n- 작은 빈번한 삽입 (배치 처리)\n\n### 5. 모니터링\n- 쿼리 성능 추적\n- 디스크 사용량 모니터링\n- 병합 작업 확인\n- 슬로우 쿼리 로그 검토\n\n**기억하세요**: ClickHouse는 분석 워크로드에 탁월합니다. 쿼리 패턴에 맞게 테이블을 설계하고, 배치 삽입을 사용하며, 실시간 집계를 위해 구체화된 뷰를 활용하세요.\n","# ClickHouse 분석 패턴\n\n고성능 분석 및 데이터 엔지니어링을 위한 ClickHouse 전용 패턴.\n\n## 활성화 시점\n\n- ClickHouse 테이블 스키마 설계 시 (MergeTree 엔진 선택)\n- 분석 쿼리 작성 시 (집계, 윈도우 함수, 조인)\n- 쿼리 성능 최적화 시 (파티션 프루닝, 프로젝션, 구체화된 뷰)\n- 대량 데이터 수집 시 (배치 삽입, Kafka 통합)\n- PostgreSQL\u002FMySQL에서 ClickHouse로 분석 마이그레이션 시\n- 실시간 대시보드 또는 시계열 분석 구현 시\n\n## 개요\n\nClickHouse는 온라인 분석 처리(OLAP)를 위한 컬럼 지향 데이터베이스 관리 시스템(DBMS)입니다. 대규모 데이터셋에 대한 빠른 분석 쿼리에 최적화되어 있습니다.\n\n**주요 특징:**\n- 컬럼 지향 저장소\n- 데이터 압축\n- 병렬 쿼리 실행\n- 분산 쿼리\n- 실시간 분석\n\n## 테이블 설계 패턴\n\n### MergeTree 엔진 (가장 일반적)\n\n```sql\nCREATE TABLE markets_analytics (\n    date Date,\n    market_id String,\n    market_name String,\n    volume UInt64,\n    trades UInt32,\n    unique_traders UInt32,\n    avg_trade_size Float64,\n    created_at DateTime\n) ENGINE = MergeTree()\nPARTITION BY toYYYYMM(date)\nORDER BY (date, market_id)\nSETTINGS index_granularity = 8192;\n```\n\n### ReplacingMergeTree (중복 제거)\n\n```sql\n-- 중복이 있을 수 있는 데이터용 (예: 여러 소스에서 수집된 경우)\nCREATE TABLE user_events (\n    event_id String,\n    user_id String,\n    event_type String,\n    timestamp DateTime,\n    properties String\n) ENGINE = ReplacingMergeTree()\nPARTITION BY toYYYYMM(timestamp)\nORDER BY (user_id, event_id, timestamp)\nPRIMARY KEY (user_id, event_id);\n```\n\n### AggregatingMergeTree (사전 집계)\n\n```sql\n-- 집계 메트릭을 유지하기 위한 용도\nCREATE TABLE market_stats_hourly (\n    hour DateTime,\n    market_id String,\n    total_volume AggregateFunction(sum, UInt64),\n    total_trades AggregateFunction(count, UInt32),\n    unique_users AggregateFunction(uniq, String)\n) ENGINE = AggregatingMergeTree()\nPARTITION BY toYYYYMM(hour)\nORDER BY (hour, market_id);\n\n-- 집계된 데이터 조회\nSELECT\n    hour,\n    market_id,\n    sumMerge(total_volume) AS volume,\n    countMerge(total_trades) AS trades,\n    uniqMerge(unique_users) AS users\nFROM market_stats_hourly\nWHERE hour >= toStartOfHour(now() - INTERVAL 24 HOUR)\nGROUP BY hour, market_id\nORDER BY hour DESC;\n```\n\n## 쿼리 최적화 패턴\n\n### 효율적인 필터링\n\n```sql\n-- PASS: 좋음: 인덱스된 컬럼을 먼저 사용\nSELECT *\nFROM markets_analytics\nWHERE date >= '2025-01-01'\n  AND market_id = 'market-123'\n  AND volume > 1000\nORDER BY date DESC\nLIMIT 100;\n\n-- FAIL: 나쁨: 비인덱스 컬럼을 먼저 필터링\nSELECT *\nFROM markets_analytics\nWHERE volume > 1000\n  AND market_name LIKE '%election%'\n  AND date >= '2025-01-01';\n```\n\n### 집계\n\n```sql\n-- PASS: 좋음: ClickHouse 전용 집계 함수를 사용\nSELECT\n    toStartOfDay(created_at) AS day,\n    market_id,\n    sum(volume) AS total_volume,\n    count() AS total_trades,\n    uniq(trader_id) AS unique_traders,\n    avg(trade_size) AS avg_size\nFROM trades\nWHERE created_at >= today() - INTERVAL 7 DAY\nGROUP BY day, market_id\nORDER BY day DESC, total_volume DESC;\n\n-- PASS: 백분위수에는 quantile 사용 (percentile보다 효율적)\nSELECT\n    quantile(0.50)(trade_size) AS median,\n    quantile(0.95)(trade_size) AS p95,\n    quantile(0.99)(trade_size) AS p99\nFROM trades\nWHERE created_at >= now() - INTERVAL 1 HOUR;\n```\n\n### 윈도우 함수\n\n```sql\n-- 누적 합계 계산\nSELECT\n    date,\n    market_id,\n    volume,\n    sum(volume) OVER (\n        PARTITION BY market_id\n        ORDER BY date\n        ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW\n    ) AS cumulative_volume\nFROM markets_analytics\nWHERE date >= today() - INTERVAL 30 DAY\nORDER BY market_id, date;\n```\n\n## 데이터 삽입 패턴\n\n### 배치 삽입 (권장)\n\n```typescript\nimport { ClickHouse } from 'clickhouse'\n\nconst clickhouse = new ClickHouse({\n  url: process.env.CLICKHOUSE_URL,\n  port: 8123,\n  basicAuth: {\n    username: process.env.CLICKHOUSE_USER,\n    password: process.env.CLICKHOUSE_PASSWORD\n  }\n})\n\n\u002F\u002F PASS: 배치 삽입 (효율적)\nasync function bulkInsertTrades(trades: Trade[]) {\n  const rows = trades.map(trade => ({\n    id: trade.id,\n    market_id: trade.market_id,\n    user_id: trade.user_id,\n    amount: trade.amount,\n    timestamp: trade.timestamp.toISOString()\n  }))\n\n  await clickhouse.insert('trades', rows)\n}\n\n\u002F\u002F FAIL: 개별 삽입 (느림)\nasync function insertTrade(trade: Trade) {\n  \u002F\u002F 루프 안에서 이렇게 하지 마세요!\n  await clickhouse.query(`\n    INSERT INTO trades VALUES ('${trade.id}', ...)\n  `).toPromise()\n}\n```\n\n### 스트리밍 삽입\n\n```typescript\n\u002F\u002F 연속적인 데이터 수집용\nimport { createWriteStream } from 'fs'\nimport { pipeline } from 'stream\u002Fpromises'\n\nasync function streamInserts() {\n  const stream = clickhouse.insert('trades').stream()\n\n  for await (const batch of dataSource) {\n    stream.write(batch)\n  }\n\n  await stream.end()\n}\n```\n\n## 구체화된 뷰\n\n### 실시간 집계\n\n```sql\n-- 시간별 통계를 위한 materialized view 생성\nCREATE MATERIALIZED VIEW market_stats_hourly_mv\nTO market_stats_hourly\nAS SELECT\n    toStartOfHour(timestamp) AS hour,\n    market_id,\n    sumState(amount) AS total_volume,\n    countState() AS total_trades,\n    uniqState(user_id) AS unique_users\nFROM trades\nGROUP BY hour, market_id;\n\n-- materialized view 조회\nSELECT\n    hour,\n    market_id,\n    sumMerge(total_volume) AS volume,\n    countMerge(total_trades) AS trades,\n    uniqMerge(unique_users) AS users\nFROM market_stats_hourly\nWHERE hour >= now() - INTERVAL 24 HOUR\nGROUP BY hour, market_id;\n```\n\n## 성능 모니터링\n\n### 쿼리 성능\n\n```sql\n-- 느린 쿼리 확인\nSELECT\n    query_id,\n    user,\n    query,\n    query_duration_ms,\n    read_rows,\n    read_bytes,\n    memory_usage\nFROM system.query_log\nWHERE type = 'QueryFinish'\n  AND query_duration_ms > 1000\n  AND event_time >= now() - INTERVAL 1 HOUR\nORDER BY query_duration_ms DESC\nLIMIT 10;\n```\n\n### 테이블 통계\n\n```sql\n-- 테이블 크기 확인\nSELECT\n    database,\n    table,\n    formatReadableSize(sum(bytes)) AS size,\n    sum(rows) AS rows,\n    max(modification_time) AS latest_modification\nFROM system.parts\nWHERE active\nGROUP BY database, table\nORDER BY sum(bytes) DESC;\n```\n\n## 일반적인 분석 쿼리\n\n### 시계열 분석\n\n```sql\n-- 일간 활성 사용자\nSELECT\n    toDate(timestamp) AS date,\n    uniq(user_id) AS daily_active_users\nFROM events\nWHERE timestamp >= today() - INTERVAL 30 DAY\nGROUP BY date\nORDER BY date;\n\n-- 리텐션 분석\nSELECT\n    signup_date,\n    countIf(days_since_signup = 0) AS day_0,\n    countIf(days_since_signup = 1) AS day_1,\n    countIf(days_since_signup = 7) AS day_7,\n    countIf(days_since_signup = 30) AS day_30\nFROM (\n    SELECT\n        user_id,\n        min(toDate(timestamp)) AS signup_date,\n        toDate(timestamp) AS activity_date,\n        dateDiff('day', signup_date, activity_date) AS days_since_signup\n    FROM events\n    GROUP BY user_id, activity_date\n)\nGROUP BY signup_date\nORDER BY signup_date DESC;\n```\n\n### 퍼널 분석\n\n```sql\n-- 전환 퍼널\nSELECT\n    countIf(step = 'viewed_market') AS viewed,\n    countIf(step = 'clicked_trade') AS clicked,\n    countIf(step = 'completed_trade') AS completed,\n    round(clicked \u002F viewed * 100, 2) AS view_to_click_rate,\n    round(completed \u002F clicked * 100, 2) AS click_to_completion_rate\nFROM (\n    SELECT\n        user_id,\n        session_id,\n        event_type AS step\n    FROM events\n    WHERE event_date = today()\n)\nGROUP BY session_id;\n```\n\n### 코호트 분석\n\n```sql\n-- 가입 월별 사용자 코호트\nSELECT\n    toStartOfMonth(signup_date) AS cohort,\n    toStartOfMonth(activity_date) AS month,\n    dateDiff('month', cohort, month) AS months_since_signup,\n    count(DISTINCT user_id) AS active_users\nFROM (\n    SELECT\n        user_id,\n        min(toDate(timestamp)) OVER (PARTITION BY user_id) AS signup_date,\n        toDate(timestamp) AS activity_date\n    FROM events\n)\nGROUP BY cohort, month, months_since_signup\nORDER BY cohort, months_since_signup;\n```\n\n## 데이터 파이프라인 패턴\n\n### ETL 패턴\n\n```typescript\n\u002F\u002F 추출, 변환, 적재(ETL)\nasync function etlPipeline() {\n  \u002F\u002F 1. 소스에서 추출\n  const rawData = await extractFromPostgres()\n\n  \u002F\u002F 2. 변환\n  const transformed = rawData.map(row => ({\n    date: new Date(row.created_at).toISOString().split('T')[0],\n    market_id: row.market_slug,\n    volume: parseFloat(row.total_volume),\n    trades: parseInt(row.trade_count)\n  }))\n\n  \u002F\u002F 3. ClickHouse에 적재\n  await bulkInsertToClickHouse(transformed)\n}\n\n\u002F\u002F 주기적으로 실행\nlet etlRunning = false\n\nsetInterval(async () => {\n  if (etlRunning) return\n\n  etlRunning = true\n  try {\n    await etlPipeline()\n  } finally {\n    etlRunning = false\n  }\n}, 60 * 60 * 1000)  \u002F\u002F Every hour\n```\n\n### 변경 데이터 캡처 (CDC)\n\n```typescript\n\u002F\u002F PostgreSQL 변경을 수신하고 ClickHouse와 동기화\nimport { Client } from 'pg'\n\nconst pgClient = new Client({ connectionString: process.env.DATABASE_URL })\n\npgClient.query('LISTEN market_updates')\n\npgClient.on('notification', async (msg) => {\n  const update = JSON.parse(msg.payload)\n\n  await clickhouse.insert('market_updates', [\n    {\n      market_id: update.id,\n      event_type: update.operation,  \u002F\u002F INSERT, UPDATE, DELETE\n      timestamp: new Date(),\n      data: JSON.stringify(update.new_data)\n    }\n  ])\n})\n```\n\n## 모범 사례\n\n### 1. 파티셔닝 전략\n- 시간별 파티셔닝 (보통 월 또는 일)\n- 파티션이 너무 많은 것 방지 (성능 영향)\n- 파티션 키에 DATE 타입 사용\n\n### 2. 정렬 키\n- 가장 자주 필터링되는 컬럼을 먼저 배치\n- 카디널리티 고려 (높은 카디널리티 먼저)\n- 정렬이 압축에 영향을 미침\n\n### 3. 데이터 타입\n- 가장 작은 적절한 타입 사용 (UInt32 vs UInt64)\n- 반복되는 문자열에 LowCardinality 사용\n- 범주형 데이터에 Enum 사용\n\n### 4. 피해야 할 것\n- SELECT * (컬럼을 명시)\n- FINAL (쿼리 전에 데이터를 병합)\n- 너무 많은 JOIN (분석을 위해 비정규화)\n- 작은 빈번한 삽입 (배치 처리)\n\n### 5. 모니터링\n- 쿼리 성능 추적\n- 디스크 사용량 모니터링\n- 병합 작업 확인\n- 슬로우 쿼리 로그 검토\n\n**기억하세요**: ClickHouse는 분석 워크로드에 탁월합니다. 쿼리 패턴에 맞게 테이블을 설계하고, 배치 삽입을 사용하며, 실시간 집계를 위해 구체화된 뷰를 활용하세요.\n",{"name":5,"origin":24,"description":7},"ECC","master","d6ca01da0f24a3b0e26e4a8b7b66cbd25d429f5d","skills\u002Feverything-claude-code\u002Fdocs\u002Fko-KR\u002Fskills\u002Fclickhouse-io",0,"https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills","https:\u002F\u002Fgithub.com\u002FSriramGandhiS","https:\u002F\u002Fsriram.website\u002F","Curious guy who keeps tinkering until something works","2026-05-20 16:21:34",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add SriramGandhiS\u002FSkills --skill clickhouse-io",{"tool":40,"command":41},"bunx","bunx skills add SriramGandhiS\u002FSkills --skill clickhouse-io",{"tool":43,"command":44},"pnpm","pnpm dlx skills add SriramGandhiS\u002FSkills --skill clickhouse-io","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fskills\u002Feverything-claude-code\u002Fdocs\u002Fko-KR\u002Fskills\u002Fclickhouse-io\u002FSKILL.md",true,[],[49,56,61,67,74,81],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":19},"01M732609EPJWV13PVTX3GT4TM","webgpu-threejs-tsl","Comprehensive guide for developing WebGPU-enabled Three.js applications using TSL (Three.js Shading Language). Covers WebGPU renderer setup, TSL syntax and node materials, compute shaders, post-processing effects, and WGSL integration. Use this skill when working with Three.js WebGPU, TSL shaders, node materials, or GPU compute in Three.js.","https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fwebgpu-threejs-tsl\u002Fskills\u002Fwebgpu-threejs-tsl\u002FSKILL.md",[],[],{"skillNo":57,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M7325XM47AGWB6K6C4VXKE6B","https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fwebgpu-threejs-tsl\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M7325WP6DES69JKC840VMFEP","verification-loop","https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fweb-assets\u002Fdocs\u002Fzh-TW\u002Fskills\u002Fverification-loop\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M7325TFQF1DZTQ6J3WGQQ1VR","tdd-workflow","Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.","https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fweb-assets\u002Fdocs\u002Fzh-TW\u002Fskills\u002Ftdd-workflow\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M7325RGV9AY9PK92D2V8KKPW","strategic-compact","Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.","https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fweb-assets\u002Fdocs\u002Fzh-TW\u002Fskills\u002Fstrategic-compact\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M7325MZC28SE86E7NMCNEFS4","security-review","Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment\u002Fsensitive features. Provides comprehensive security checklist and patterns.","https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fweb-assets\u002Fdocs\u002Fzh-TW\u002Fskills\u002Fsecurity-review\u002FSKILL.md",[],[]]