将变量值中的日期列添加到Spark Dataframe

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

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

# 创建包含日期列的变量
date_column = ["2022-01-01", "2022-01-02", "2022-01-03"]

# 将变量转换为Spark Dataframe
df = spark.createDataFrame([(date,) for date in date_column], ["date_column"])

# 将日期列转换为日期类型
df = df.withColumn("date_column", to_date(df.date_column))

# 显示Dataframe
df.show()