spot-ml/src/main/scala/org/apache/spot/lda/SpotLDAResult.scala

/*
 * Licensed to the Apache Software Foundation (ASF) under one or more
 * contributor license agreements.  See the NOTICE file distributed with
 * this work for additional information regarding copyright ownership.
 * The ASF licenses this file to You under the Apache License, Version 2.0
 * (the "License"); you may not use this file except in compliance with
 * the License.  You may obtain a copy of the License at
 *
 *    http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

package org.apache.spot.lda

import org.apache.spark.mllib.linalg.{Matrix, Vector}
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.DataFrame

/**
  * LDA results formatted for Apache Spot scoring.
  *
  */
class SpotLDAResult(private final val helper: SpotLDAHelper,
                    final val topicDistributions: RDD[(Long, Vector)],
                    final val documentToTopicMix: DataFrame,
                    final val topicsMix: Matrix,
                    final val wordToTopicMix: Map[String, Array[Double]])

object SpotLDAResult {

  def apply(helper: SpotLDAHelper, topicDistributions: RDD[(Long, Vector)], topicsMix: Matrix): SpotLDAResult = {

    val documentToTopicMix: DataFrame = helper.formatDocumentDistribution(topicDistributions)
    val wordToTopicMix: Map[String, Array[Double]] = helper.formatTopicDistributions(topicsMix)

    new SpotLDAResult(helper, topicDistributions, documentToTopicMix, topicsMix, wordToTopicMix)
  }
}