取决于值条件的字典数组总和pyspark (spark结构流)

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

spark = SparkSession.builder.appName("DictionaryArraySum").getOrCreate()

data = [
    (1, [{"key": "A", "value": 10}, {"key": "B", "value": 20}]),
    (2, [{"key": "C", "value": 30}, {"key": "D", "value": 40}]),
    (3, [{"key": "E", "value": 50}, {"key": "F", "value": 60}])
]

df = spark.createDataFrame(data, ["id", "dictionary_array"])

sum_df = df.select("id", sum(col("dictionary_array.value")).alias("sum"))

sum_df.show()