모델 작성 SDK

// Spark

package com.adobe.platform.ml

import java.time.LocalDateTime

import com.adobe.platform.ml.config.ConfigProperties
import com.adobe.platform.query.QSOption
import org.apache.spark.ml.feature.StringIndexer
import org.apache.spark.sql.expressions.Window
import org.apache.spark.sql.functions._
import org.apache.spark.sql.types.{StructType, TimestampType}
import org.apache.spark.sql.{DataFrame, SparkSession}
import org.apache.spark.sql.Column

/**
 * Implementation of DataLoader which loads a DataFrame and prepares data
 */
class MyDataLoader extends DataLoader {

    final val PLATFORM_SDK_PQS_PACKAGE: String = "com.adobe.platform.query"
    final val PLATFORM_SDK_PQS_INTERACTIVE: String = "interactive"
    final val PLATFORM_SDK_PQS_BATCH: String = "batch"

    /**
    *
    * @param configProperties - Configuration Properties map
    * @param sparkSession     - SparkSession
    * @return                 - DataFrame which is loaded for training
    */


  def load_dataset(configProperties: ConfigProperties, sparkSession: SparkSession, taskId: String): DataFrame = {

    require(configProperties != null)
    require(sparkSession != null)

    // Read the configs
    val serviceToken: String = sparkSession.sparkContext.getConf.get("ML_FRAMEWORK_IMS_ML_TOKEN", "").toString
    val userToken: String = sparkSession.sparkContext.getConf.get("ML_FRAMEWORK_IMS_TOKEN", "").toString
    val orgId: String = sparkSession.sparkContext.getConf.get("ML_FRAMEWORK_IMS_ORG_ID", "").toString
    val apiKey: String = sparkSession.sparkContext.getConf.get("ML_FRAMEWORK_IMS_CLIENT_ID", "").toString

    val dataSetId: String = configProperties.get(taskId).getOrElse("")

    // Load the dataset
    var df = sparkSession.read.format(PLATFORM_SDK_PQS_PACKAGE)
      .option(QSOption.userToken, userToken)
      .option(QSOption.serviceToken, serviceToken)
      .option(QSOption.imsOrg, orgId)
      .option(QSOption.apiKey, apiKey)
      .option(QSOption.mode, PLATFORM_SDK_PQS_INTERACTIVE)
      .option(QSOption.datasetId, dataSetId)
      .load()
    df.show()
    df
    }
}

// Spark

package com.adobe.platform.ml

import com.adobe.platform.ml.config.ConfigProperties
import com.adobe.platform.ml.impl.Constants
import com.adobe.platform.ml.sdk.DataSaver
import com.adobe.platform.query.QSOption
import org.apache.spark.sql.DataFrame
import org.apache.spark.sql.functions._
import org.apache.spark.sql.types.TimestampType

/**
 * Implementation of DataSaver which stores a DataFrame to a Platform dataset
 */

class ScoringDataSaver extends DataSaver {

  final val PLATFORM_SDK_PQS_PACKAGE: String = "com.adobe.platform.query"
  final val PLATFORM_SDK_PQS_BATCH: String = "batch"

  /**
    * Method that saves the scoring data into a dataframe
    * @param configProperties  - Configuration Properties map
    * @param dataFrame         - Dataframe with the scoring results
    */

  override def save(configProperties: ConfigProperties, dataFrame: DataFrame): Unit =  {

    require(configProperties != null)
    require(dataFrame != null)

    val predictionColumn = configProperties.get(Constants.PREDICTION_COL).getOrElse(Constants.DEFAULT_PREDICTION)
    val sparkSession = dataFrame.sparkSession

    val serviceToken: String = sparkSession.sparkContext.getConf.get("ML_FRAMEWORK_IMS_ML_TOKEN", "").toString
    val userToken: String = sparkSession.sparkContext.getConf.get("ML_FRAMEWORK_IMS_TOKEN", "").toString
    val orgId: String = sparkSession.sparkContext.getConf.get("ML_FRAMEWORK_IMS_ORG_ID", "").toString
    val apiKey: String = sparkSession.sparkContext.getConf.get("ML_FRAMEWORK_IMS_CLIENT_ID", "").toString
    val tenantId:String = configProperties.get("tenantId").getOrElse("")
    val timestamp:String = "2019-01-01 00:00:00"

    val scoringResultsDataSetId: String = configProperties.get("scoringResultsDataSetId").getOrElse("")
    import sparkSession.implicits._

    var df = dataFrame.withColumn("date", $"date".cast("String"))

    var scored_df  = df.withColumn(tenantId, struct(df("date"), df("store"), df(predictionColumn)))
    scored_df = scored_df.withColumn("timestamp", lit(timestamp).cast(TimestampType))
    scored_df = scored_df.withColumn("_id", lit("empty"))
    scored_df = scored_df.withColumn("eventType", lit("empty"))

    scored_df.select(tenantId, "_id", "eventType", "timestamp").write.format(PLATFORM_SDK_PQS_PACKAGE)
      .option(QSOption.userToken, userToken)
      .option(QSOption.serviceToken, serviceToken)
      .option(QSOption.imsOrg, orgId)
      .option(QSOption.apiKey, apiKey)
      .option(QSOption.datasetId, scoringResultsDataSetId)
      .save()
    }
}