NLP处理-Spark中的HashTF与CountVectorizer模型

清疚 2023-07-20 10:56 63阅读 0赞

[http://spark.apache.org/docs/latest/ml-features.html\#tf-idf][http_spark.apache.org_docs_latest_ml-features.html_tf-idf]

import org.apache.spark.ml.feature.\_  
import org.apache.spark.ml.linalg.SparseVector  
import org.apache.spark.sql.SparkSession  
   
import scala.collection.mutable  
import scala.io.Source  
   
/\*\*  
  \* Created by xubc on 2017/6/3.  
  \*/  
object TestX \{  
   
  def main(args: Array\[String\]): Unit = \{  
    val spark = SparkSession.builder  
        .master("local\[5\]")  
        .appName(this.getClass.getName().stripSuffix("$"))  
        .getOrCreate()  
    val sentenceData = spark.createDataFrame(Seq(  
      (0.0, "Hi I heard about are Spark"),  
      (1.0, "I wish Java could use case spark classes"),  
      (2.0, "Logistic regression regression models are neat I")  
    )).toDF("label", "sentence")  
   
    val tokenizer = new Tokenizer().setInputCol("sentence").setOutputCol("words")  
    val wordsData = tokenizer.transform(sentenceData)  
   
    // HashingTF bow模型  
//    val hashingTF = new HashingTF()  
//      .setInputCol("words").setOutputCol("rawFeatures").setNumFeatures(100)  
//    val featurizedData = hashingTF.transform(wordsData)  
   
    // CountVectorizer bow模型  
    val cvModel: CountVectorizerModel = new CountVectorizer()  
      .setInputCol("words").setOutputCol("rawFeatures")  
      .fit(wordsData)  
    val featurizedData = cvModel.transform(wordsData)  
   
   
    val idf = new IDF().setInputCol("rawFeatures").setOutputCol("features")  
    val idfModel = idf.fit(featurizedData)  
   
    val rescaledData = idfModel.transform(featurizedData)  
    rescaledData.printSchema()  
   
    val vocabulary = cvModel.vocabulary  
    println(vocabulary.mkString(","))  
    rescaledData.show(false)  
    rescaledData.foreach(e => \{  
      val label = e.getAs\[Double\]("label")  
      val str = e.getAs\[String\]("sentence")  
      val words = e.getAs\[mutable.WrappedArray\[String\]\]("words").mkString(",")  
      val tf = e.getAs\[SparseVector\]("rawFeatures")  
      val originWords = tf.indices.map(i => vocabulary(i)).mkString(",")  
      val idf = e.getAs\[SparseVector\]("features")  
      println(  
        s"""$label   $str  
           | $words  
           | $tf    $originWords  
           | $idf""".stripMargin)  
    \})  
  \}  
\}

[http_spark.apache.org_docs_latest_ml-features.html_tf-idf]: http://spark.apache.org/docs/latest/ml-features.html#tf-idf