Vectorized UDF

示例

下文提供两个示例展示如何使用Vectorized UDF。

• 示例一：使用Pyarrow进行向量化加速。

  import fabric_data as fabric
  from fabric_data.udf import RegisterType
  
  import pyarrow.compute as pc
  
  # 隐式注册UDF
  @fabric.udf.pyarrow(database="your-database", register_type=RegisterType.STAGED)
  def calculate_product(prices: fabric.PyarrowVector[float], quantities: fabric.PyarrowVector[int]) -> fabric.PyarrowVector[float]:    
      return fabric.PyarrowVector[float](pc.multiply(prices, quantities))
  
  # 使用UDF
  con = ibis.fabric.connect(...)
  t = con.table("your-table", database="your-database")
  expression = t.select(calculate_product(t.price, t.quantity).name("product column"))
  print(expression.execute())

• 示例二：使用Pandas进行向量化加速。

  import fabric_data as fabric
  from fabric_data.udf import RegisterType
  
  import pandas as pd
  
  # 隐式注册UDF
  @fabric.udf.pandas(database="your-database", register_type=RegisterType.STAGED)
  def calculate_product(prices: fabric.PandasVector[float], quantities: fabric.PandasVector[int]) -> fabric.PandasVector[float]:    
      return fabric.PandasVector[float](prices * quantities, dtype=pd.Float64Dtype())
  
  # 使用UDF
  con = ibis.fabric.connect(...)
  t = con.table("your-table", database="your-database")
  expression = t.select(calculate_product(t.price, t.quantity).name("product column"))
  print(expression.execute())