将嵌套字典转换为Pyspark Dataframe

# 导入必要的库
from pyspark.sql import SparkSession
from pyspark.sql.types import StructType, StructField, StringType

# 创建SparkSession
spark = SparkSession.builder.appName("NestedDictToDataframe").getOrCreate()

# 嵌套字典示例
nested_dict = {
  "name": "John",
  "age": 30,
  "address": {
    "street": "123 Main St",
    "city": "New York",
    "state": "NY"
  }
}

# 定义Schema
schema = StructType([
    StructField("name", StringType(), True),
    StructField("age", StringType(), True),
    StructField("address", StructType([
        StructField("street", StringType(), True),
        StructField("city", StringType(), True),
        StructField("state", StringType(), True)
    ]), True)
])

# 将嵌套字典转换为Dataframe
dataframe = spark.createDataFrame([nested_dict], schema)

# 显示Dataframe内容
dataframe.show()