DuckDB 심화 — 대규모 데이터 분석과 Python 통합

Pandas 통합

import duckdb
import pandas as pd

df = pd.read_csv("sales.csv")

# Pandas DataFrame을 직접 쿼리
result = duckdb.sql("""
  SELECT category,
    SUM(amount) as total,
    AVG(amount) as avg_amount,
    COUNT(*) as count
  FROM df
  GROUP BY category
  HAVING total > 10000
  ORDER BY total DESC
""").df()  # 결과를 다시 DataFrame으로

윈도우 함수

SELECT name, department, salary,
  RANK() OVER (PARTITION BY department ORDER BY salary DESC) as rank
FROM employees