当列文本包含的单词超过10个时，过滤pyspark DataFrame

from pyspark.sql import SparkSession
from pyspark.sql.functions import size, split, col

spark = SparkSession.builder.getOrCreate()

data = [("1", "This is a sample sentence with more than 10 words"),
        ("2", "Another example with more than 10 words in this text"),
        ("3", "Short sentence")]
df = spark.createDataFrame(data, ["id", "text"])
df.show()

+---+--------------------+
| id|                text|
+---+--------------------+
|  1|This is a sample ...|
|  2|Another example w...|
|  3|      Short sentence|
+---+--------------------+

df_filtered = df.filter(size(split(col("text"), " ")) > 10)
df_filtered.show()

+---+--------------------+
| id|                text|
+---+--------------------+
|  1|This is a sample ...|
|  2|Another example w...|
+---+--------------------+