PySpark:获取最近3天的数据

from pyspark.sql import SparkSession
from pyspark.sql.functions import col, current_date, date_sub

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

# 读取数据
data = spark.read.format("csv").option("header", "true").load("data.csv")

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

# 获取最近3天的日期
current_date = current_date()
start_date = date_sub(current_date, 3)

# 过滤数据
filtered_data = data.filter((col("date") >= start_date) & (col("date") <= current_date))

# 显示结果
filtered_data.show()