如何删除pyspark中列标题中的空格以及如何将字符串日期转换为日期时间格式

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

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

# 创建示例DataFrame
data = [("John Doe", "2022-01-01"), ("Jane Smith", "2022-02-01")]
df = spark.createDataFrame(data, ["Name", "Date"])

# 删除列标题中的空格
df = df.toDF(*(c.replace(" ", "_") for c in df.columns))

# 显示修改后的列标题
df.show()

+-----------+----------+
|Name       |Date      |
+-----------+----------+
|John Doe   |2022-01-01|
|Jane Smith |2022-02-01|
+-----------+----------+

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

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

# 创建示例DataFrame
data = [("John Doe", "2022-01-01"), ("Jane Smith", "2022-02-01")]
df = spark.createDataFrame(data, ["Name", "Date"])

# 将字符串日期转换为日期类型
df = df.withColumn("Date", to_date(col("Date"), "yyyy-MM-dd"))

# 将字符串日期转换为日期时间类型
df = df.withColumn("DateTime", to_timestamp(col("Date")))

# 显示转换后的结果
df.show()

+-----------+----------+-------------------+
|Name       |Date      |DateTime           |
+-----------+----------+-------------------+
|John Doe   |2022-01-01|2022-01-01 00:00:00|
|Jane Smith |2022-02-01|2022-02-01 00:00:00|
+-----------+----------+-------------------+