从PySpark查询日期之间的竖排

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

spark = SparkSession.builder.appName("DateFiltering").getOrCreate()

df = spark.read.format("csv").option("header", "true").load("path/to/dataset.csv")

df = df.withColumn("date_column", date_format(col("date_column"), "yyyy-MM-dd"))

start_date = "2022-01-01"
end_date = "2022-01-31"

filtered_df = df.filter((col("date_column") >= start_date) & (col("date_column") <= end_date))

filtered_df.show()