使用pyspark根据多个列值删除记录

from pyspark.sql import SparkSession
from pyspark.sql.functions import col

spark = SparkSession.builder.getOrCreate()

data = [("John", "Doe", 25),
        ("Jane", "Smith", 30),
        ("John", "Smith", 35),
        ("Jane", "Doe", 40)]

df = spark.createDataFrame(data, ["first_name", "last_name", "age"])

conditions = (col("first_name") == "John") & (col("last_name") == "Smith")

df = df.filter(~conditions)

spark = SparkSession.builder.getOrCreate()

data = [("John", "Doe", 25),
        ("Jane", "Smith", 30),
        ("John", "Smith", 35),
        ("Jane", "Doe", 40)]

df = spark.createDataFrame(data, ["first_name", "last_name", "age"])
df.createOrReplaceTempView("people")

conditions = "first_name = 'John' AND last_name = 'Smith'"

df = spark.sql("SELECT * FROM people WHERE NOT(" + conditions + ")")