在pyspark dataframe中查找连续数据

from pyspark.sql import SparkSession
from pyspark.sql.functions import lag, col, when
from pyspark.sql.window import Window

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

# 创建示例数据
data = [(1, 10), (2, 20), (3, 30), (4, 40), (5, 50), (6, 60), (7, 70), (8, 80), (9, 90), (10, 100)]
df = spark.createDataFrame(data, ["id", "value"])

# 创建窗口
window = Window.orderBy("id")

# 添加连续标记列
df = df.withColumn("lag_value", lag("value").over(window))
df = df.withColumn("is_continuous", when(col("value") - col("lag_value") == 10, 1).otherwise(0))

# 显示结果
df.show()

+---+-----+---------+-------------+
| id|value|lag_value|is_continuous|
+---+-----+---------+-------------+
|  1|   10|     null|            0|
|  2|   20|       10|            1|
|  3|   30|       20|            1|
|  4|   40|       30|            1|
|  5|   50|       40|            1|
|  6|   60|       50|            1|
|  7|   70|       60|            1|
|  8|   80|       70|            1|
|  9|   90|       80|            1|
| 10|  100|       90|            1|
+---+-----+---------+-------------+