如何在pyspark中计算一个函数内不同日期范围的id？

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

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

# 创建示例数据
data = spark.createDataFrame([
    ("2022-01-01", 1),
    ("2022-01-02", 2),
    ("2022-01-03", 3),
    ("2022-01-04", 4),
    ("2022-01-05", 5)
], ["date", "id"])

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

# 显示数据
data.show()

+----------+---+
|      date| id|
+----------+---+
|2022-01-01|  1|
|2022-01-02|  2|
|2022-01-03|  3|
|2022-01-04|  4|
|2022-01-05|  5|
+----------+---+

# 注册DataFrame为临时表
data.createOrReplaceTempView("data_table")

# 使用Spark SQL计算不同日期范围内的id总和
result = spark.sql("""
    SELECT SUM(id) AS total_id
    FROM data_table
    WHERE date >= '2022-01-01' AND date <= '2022-01-03'
""")

# 显示结果
result.show()

+--------+
|total_id|
+--------+
|       6|
+--------+

WHERE date >= '2022-01-02' AND date <= '2022-01-04'