在PySpark Python中减去两个日期列

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

# 创建 SparkSession
spark = SparkSession.builder.appName("DateSubtraction").getOrCreate()

# 创建一个 DataFrame 示例
data = [
    ("Alice", "2023-01-01", "2023-01-10"),
    ("Bob", "2023-01-05", "2023-01-20"),
    ("Charlie", "2023-01-15", "2023-01-25")
]
columns = ["Name", "StartDate", "EndDate"]

df = spark.createDataFrame(data, columns)

# 将日期列转换为日期类型
df = df.withColumn("StartDate", col("StartDate").cast("date"))
df = df.withColumn("EndDate", col("EndDate").cast("date"))

# 计算两个日期之间的差值
df = df.withColumn("DateDifference", datediff(col("EndDate"), col("StartDate")))

# 显示结果
df.show()