在pyspark中创建一列，该列在第一行之后引用其自身

from pyspark.sql import SparkSession
from pyspark.sql.window import Window
from pyspark.sql.functions import lag, col

spark = SparkSession.builder.getOrCreate()

data = [(1, 'A'), (2, 'B'), (3, 'C'), (4, 'D'), (5, 'E')]
df = spark.createDataFrame(data, ['id', 'value'])
df.show()

+---+-----+
| id|value|
+---+-----+
|  1|    A|
|  2|    B|
|  3|    C|
|  4|    D|
|  5|    E|
+---+-----+

windowSpec = Window.orderBy('id')
df = df.withColumn('previous_value', lag(col('value')).over(windowSpec))
df.show()

+---+-----+--------------+
| id|value|previous_value|
+---+-----+--------------+
|  1|    A|          null|
|  2|    B|             A|
|  3|    C|             B|
|  4|    D|             C|
|  5|    E|             D|
+---+-----+--------------+