MS-Fabric - Use Apache Spark to work with files in a lakehouse(2)

테이블 만들기

 

df.write.format("delta").saveAsTable("salesorders")
spark.sql("DESCRIBE EXTENDED salesorders").show(truncate=False)

 

 

 

table 값 확인

df = spark.sql("select * from sales_orders.dbo.salesorders LIMIT 1000")
#df = spark.sql("select * from salesorders LIMIT 1000")
display(df)

 

 

 

노트북에서 쿼리 실행 확인

%%sql
SELECT YEAR(OrderDate) AS OrderYear,
SUM((UnitPrice * Quantity) + Tax) AS GrossRevenue
FROM salesorders
GROUP BY YEAR(OrderDate)
ORDER BY OrderYear

 

 

 

기본 제공하는 차트기능 사용 예시

%%sql
 SELECT * FROM salesorders

 

 

bar chart 선택 후 아래와 같이 설정

 

 

 

쿼리 문자열 실행

 sqlQuery = "SELECT CAST(YEAR(OrderDate) AS CHAR(4)) AS OrderYear, \
                 SUM((UnitPrice * Quantity) + Tax) AS GrossRevenue \
             FROM salesorders \
             GROUP BY CAST(YEAR(OrderDate) AS CHAR(4)) \
             ORDER BY OrderYear"
 df_spark = spark.sql(sqlQuery)
 df_spark.show()