如何使用PySpark计算数据帧组的TF-IDF

from pyspark.ml.feature import HashingTF, IDF, Tokenizer
from pyspark.sql import SparkSession

spark = SparkSession.builder.appName("TF-IDF").getOrCreate()

data = spark.createDataFrame([
    (0, "This is a sentence"),
    (1, "This is another sentence"),
    (2, "Yet another sentence")
], ["id", "sentence"])

tokenizer = Tokenizer(inputCol="sentence", outputCol="words")
wordsData = tokenizer.transform(data)

hashingTF = HashingTF(inputCol="words", outputCol="rawFeatures", numFeatures=20)
featurizedData = hashingTF.transform(wordsData)

idf = IDF(inputCol="rawFeatures", outputCol="features")
idfModel = idf.fit(featurizedData)
rescaledData = idfModel.transform(featurizedData)

rescaledData.select("id", "words", "features").show(truncate=False)