将json对象转换为pyspark dataframe

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

spark = SparkSession.builder.getOrCreate()

json_schema = StructType([
    StructField("field1", StringType(), True),
    StructField("field2", StringType(), True),
    ...
])

json_data = [
    {"field1": "value1", "field2": "value2", ...},
    {"field1": "value3", "field2": "value4", ...},
    ...
]

df = spark.createDataFrame(json_data, schema=json_schema)

df.show()
df.select("field1").filter(df.field2 == "value2").show()
...