ETL vs ELT 2026: 데이터 파이프라인 아키텍처 심층 분석 및 면접 대비

# etl_pipeline.py
# Traditional ETL pattern with intermediate transformation

import pandas as pd
from sqlalchemy import create_engine

def extract_from_source(connection_string: str, query: str) -> pd.DataFrame:
    """Pull data from source database."""
    engine = create_engine(connection_string)
    return pd.read_sql(query, engine)

def transform_data(df: pd.DataFrame) -> pd.DataFrame:
    """Clean and reshape data before loading.
    
    This runs on the ETL server, not the warehouse.
    """
    # Remove duplicates based on business key
    df = df.drop_duplicates(subset=['customer_id', 'order_date'])
    
    # Convert date strings to proper datetime
    df['order_date'] = pd.to_datetime(df['order_date'])
    
    # Calculate derived metrics
    df['order_total'] = df['quantity'] * df['unit_price']
    df['order_month'] = df['order_date'].dt.to_period('M')
    
    # Filter to relevant records only
    df = df[df['order_status'] != 'cancelled']
    
    return df

def load_to_warehouse(df: pd.DataFrame, warehouse_conn: str, table: str):
    """Load transformed data to destination."""
    engine = create_engine(warehouse_conn)
    df.to_sql(table, engine, if_exists='append', index=False)

# Pipeline execution
raw_orders = extract_from_source(SOURCE_CONN, "SELECT * FROM orders")
clean_orders = transform_data(raw_orders)
load_to_warehouse(clean_orders, WAREHOUSE_CONN, 'fact_orders')

-- models/staging/stg_orders.sql
-- dbt model: first transformation layer on raw data

with source as (
    -- Reference the raw table loaded by the extraction tool
    select * from {{ source('salesforce', 'orders') }}
),

renamed as (
    select
        id as order_id,
        customer_id,
        cast(order_date as date) as order_date,
        quantity,
        unit_price,
        order_status,
        -- Calculate derived fields in SQL
        quantity * unit_price as order_total,
        date_trunc('month', cast(order_date as date)) as order_month
    from source
    where order_status != 'cancelled'
)

select * from renamed

-- models/marts/fct_monthly_revenue.sql
-- Aggregated fact table built from staging model

with orders as (
    select * from {{ ref('stg_orders') }}
),

monthly_agg as (
    select
        order_month,
        count(distinct customer_id) as unique_customers,
        count(order_id) as total_orders,
        sum(order_total) as revenue
    from orders
    group by order_month
)

select * from monthly_agg

# airflow/dags/hybrid_pipeline.py
# DAG combining extraction, lightweight ETL, and warehouse ELT

from airflow import DAG
from airflow.providers.airbyte.operators.airbyte import AirbyteTriggerSyncOperator
from airflow.providers.dbt.cloud.operators.dbt import DbtCloudRunJobOperator
from datetime import datetime

with DAG(
    dag_id='hybrid_etl_elt_pipeline',
    start_date=datetime(2026, 1, 1),
    schedule='@daily',
    catchup=False
) as dag:
    
    # Step 1: Extract and load with Airbyte
    # Minor transforms happen here: type casting, PII hashing
    sync_salesforce = AirbyteTriggerSyncOperator(
        task_id='sync_salesforce_orders',
        airbyte_conn_id='airbyte_default',
        connection_id='salesforce-to-snowflake',
        asynchronous=False
    )
    
    # Step 2: Transform in warehouse with dbt
    # Heavy aggregations, joins, business logic
    run_dbt_models = DbtCloudRunJobOperator(
        task_id='run_dbt_transformations',
        dbt_cloud_conn_id='dbt_cloud',
        job_id=12345,
        wait_for_termination=True
    )
    
    sync_salesforce >> run_dbt_models

-- Schema evolution handling in dbt
-- Use VARIANT/JSON columns to absorb unknown fields

with raw_events as (
    select
        event_id,
        event_payload,  -- JSON column from source
        received_at
    from {{ source('app', 'raw_events') }}
),

parsed as (
    select
        event_id,
        event_payload:user_id::string as user_id,
        event_payload:event_type::string as event_type,
        -- New fields appear in JSON without breaking the model
        event_payload:metadata::variant as metadata,
        received_at
    from raw_events
)

select * from parsed

# great_expectations checkpoint for ELT quality gates
# Runs after dbt completes, before downstream dashboards refresh

import great_expectations as gx

context = gx.get_context()

checkpoint = context.checkpoints.get("daily_orders_checkpoint")

result = checkpoint.run(
    batch_parameters={"year": 2026, "month": 9},
    expectation_suite_name="orders_suite"
)

if not result.success:
    # Block downstream refresh, alert data team
    raise ValueError(f"Data quality check failed: {result.describe()}")