pyspark额外的列，其中日期转换为1、2、3

from pyspark.sql import SparkSession
from pyspark.sql.functions import date_format, to_date

spark = SparkSession.builder.getOrCreate()

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

+----------+
|      date|
+----------+
|2022-01-01|
|2022-02-01|
|2022-03-01|
+----------+

df = df.withColumn("converted_date", date_format(to_date("date"), "d"))
df.show()

+----------+--------------+
|      date|converted_date|
+----------+--------------+
|2022-01-01|             1|
|2022-02-01|             2|
|2022-03-01|             3|
+----------+--------------+