在RDD上强制使用模式，同时将其转换为DataFrame

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

# 创建SparkSession
spark = SparkSession.builder.getOrCreate()

# 定义模式
schema = StructType([
    StructField("name", StringType(), True),
    StructField("age", StringType(), True),
    StructField("city", StringType(), True)
])

# 创建RDD
rdd = spark.sparkContext.parallelize([("Alice", "25", "New York"), ("Bob", "30", "San Francisco")])

# 映射到Row对象
row_rdd = rdd.map(lambda x: Row(name=x[0], age=x[1], city=x[2]))

# 转换为DataFrame
df = spark.createDataFrame(row_rdd, schema)