在PySpark中将等值日字符串转换为日期格式

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

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

# 创建示例数据
data = [("2022-01-01",), ("2022-02-01",), ("2022-03-01",)]
df = spark.createDataFrame(data, ["date_str"])

# 将字符串列转换为日期类型
df = df.withColumn("date", to_date(df.date_str, "yyyy-MM-dd"))

# 显示结果
df.show()

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