在PySpark中，从一个数据框中删除与另一个数据框中的行匹配的行

# 导入必要的库
from pyspark.sql import SparkSession

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

# 创建第一个数据框
data1 = [("Alice", 25), ("Bob", 30), ("Charlie", 35)]
df1 = spark.createDataFrame(data1, ["name", "age"])

# 创建第二个数据框
data2 = [("Alice", "Engineer"), ("Bob", "Doctor")]
df2 = spark.createDataFrame(data2, ["name", "profession"])

# 进行内连接操作
joined_df = df1.join(df2, on="name", how="inner")

# 筛选出需要删除的行
filtered_df = joined_df.filter(joined_df.profession.isNull())

# 删除筛选出的行
result_df = joined_df.drop(*filtered_df.columns)

# 打印结果
result_df.show()