在Pyspark中选择日期间隔超过6个月的记录

from pyspark.sql import SparkSession
from pyspark.sql.functions import datediff, expr
from pyspark.sql.types import DateType

spark = SparkSession.builder.appName("DateIntervalFilter").getOrCreate()

df = spark.read.csv("path/to/data.csv", header=True, inferSchema=True)

df = df.withColumn("date_column", df["date_column"].cast(DateType()))

df_filtered = df.filter(datediff(expr("current_date()"), df["date_column"]) > 180)

df_filtered.show()