在Spark DataFrame列中获取不同的单词

from pyspark.sql import SparkSession
from pyspark.sql.functions import explode, split

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

data = spark.read.text("path_to_file")

words = data.select(explode(split(data.value, " ")).alias("word"))

distinct_words = words.distinct()

distinct_words.show()