将不等于的Spark数据帧与比较列的列表进行比较

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

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

# 创建示例数据
data = [("Alice", 25), ("Bob", 30), ("Charlie", 35)]
schema = StructType([
    StructField("name", StringType(), True),
    StructField("age", StringType(), True)
])
df = spark.createDataFrame(data, schema)

# 比较列的列表
compare_list = ["Alice", "Charlie"]

# 将比较列的列表转换为数据帧
compare_df = spark.createDataFrame([(name,) for name in compare_list], ["name"])

# 进行不等于的比较
result = df.filter(df["name"] != compare_df["name"])

# 显示结果
result.show()