使用pyspark中的条件创建具有运行总额的列

from pyspark.sql import SparkSession
from pyspark.sql.functions import when, col

spark = SparkSession.builder.appName("Conditional Column").getOrCreate()

data = [("John", 100),
        ("Alice", 200),
        ("Bob", 300),
        ("Jane", 400)]

df = spark.createDataFrame(data, ["Name", "Amount"])

df = df.withColumn("Running Total", when(col("Name") == "John", col("Amount"))
                                    .otherwise(col("Amount") + col("Running Total").getItem(-1)))

df.show()

+-----+------+-------------+
| Name|Amount|Running Total|
+-----+------+-------------+
| John|   100|          100|
|Alice|   200|          300|
|  Bob|   300|          600|
| Jane|   400|         1000|
+-----+------+-------------+