Pyspark:如何转换dataframe列中的json字符串

from pyspark.sql import SparkSession
from pyspark.sql.functions import from_json
from pyspark.sql.types import StructType, StructField, StringType

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

data = [
    ('{"name":"John", "age":30, "city":"New York"}'),
    ('{"name":"Alice", "age":25, "city":"San Francisco"}'),
    ('{"name":"Bob", "age":35, "city":"Los Angeles"}')
]

df = spark.createDataFrame(data, StringType()).toDF("json_string")

schema = StructType([
    StructField("name", StringType(), True),
    StructField("age", StringType(), True),
    StructField("city", StringType(), True)
])

df = df.withColumn("json_struct", from_json(df.json_string, schema))

df = df.select("json_struct.name", "json_struct.age", "json_struct.city")