枚举排序的PySpark数据帧中的序列

from pyspark.sql import SparkSession
from pyspark.sql.functions import row_number
from pyspark.sql.window import Window

spark = SparkSession.builder.getOrCreate()

data = [("Alice", 25), ("Bob", 30), ("Charlie", 35), ("David", 40)]
df = spark.createDataFrame(data, ["Name", "Age"])

windowSpec = Window.orderBy("Age")
df = df.withColumn("Sequence", row_number().over(windowSpec))

df.show()

+-------+---+--------+
|   Name|Age|Sequence|
+-------+---+--------+
|  Alice| 25|       1|
|    Bob| 30|       2|
|Charlie| 35|       3|
|  David| 40|       4|
+-------+---+--------+