在PySpark中比较日期的新列

from pyspark.sql import SparkSession
from pyspark.sql.functions import col, when
from pyspark.sql.types import DateType

spark = SparkSession.builder.getOrCreate()

data = [("2022-01-01"), ("2022-02-01"), ("2022-03-01"), ("2022-04-01")]
df = spark.createDataFrame(data, ["date"])

df = df.withColumn("date", col("date").cast(DateType()))

current_date = spark.sql("SELECT current_date()").collect()[0][0]

df = df.withColumn("comparison", when(col("date") > current_date, "Future")
                                 .when(col("date") < current_date, "Past")
                                 .otherwise("Current"))

df.show()

+----------+-----------+
|      date| comparison|
+----------+-----------+
|2022-01-01|       Past|
|2022-02-01|       Past|
|2022-03-01|       Past|
|2022-04-01|     Future|
+----------+-----------+