OCR 오류와 효율적인 문자열 일치를 위해 Apache Spark를 어떻게 사용할 수 있습니까?

<code class="scala">import org.apache.spark.ml.feature.RegexTokenizer

val tokenizer = new RegexTokenizer().setPattern("").setInputCol("text").setMinTokenLength(1).setOutputCol("tokens")</code>

<code class="scala">import org.apache.spark.ml.feature.NGram

val ngram = new NGram().setN(3).setInputCol("tokens").setOutputCol("ngrams")</code>

<code class="scala">import org.apache.spark.ml.feature.HashingTF

val vectorizer = new HashingTF().setInputCol("ngrams").setOutputCol("vectors")</code>

<code class="scala">import org.apache.spark.ml.feature.{MinHashLSH, MinHashLSHModel}

val lsh = new MinHashLSH().setInputCol("vectors").setOutputCol("lsh")</code>

<code class="scala">import org.apache.spark.ml.Pipeline

val pipeline = new Pipeline().setStages(Array(tokenizer, ngram, vectorizer, lsh))</code>

<code class="scala">val query = Seq("Hello there 7l | real|y like Spark!").toDF("text")
val db = Seq(
  "Hello there ?! I really like Spark ❤️!", 
  "Can anyone suggest an efficient algorithm"
).toDF("text")

val model = pipeline.fit(db)</code>

<code class="scala">val dbHashed = model.transform(db)
val queryHashed = model.transform(query)

model.stages.last.asInstanceOf[MinHashLSHModel]
  .approxSimilarityJoin(dbHashed, queryHashed, 0.75).show</code>