org.deeplearning4j.spark.ml.util.SchemaUtils.scala Maven / Gradle / Ivy

Go to download
Show more of this group Show more artifacts with this name
Show all versions of dl4j-spark-ml Show documentation
The newest version!
/*
 * Copyright 2015 Skymind,Inc.
 *
 *    Licensed 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.deeplearning4j.spark.ml.util

import org.apache.spark.sql.types.{DataType, StructField, StructType}


/**
 * Utils for handling schemas.
 */
private[spark] object SchemaUtils {

  // TODO: Move the utility methods to SQL.

  /**
   * Check whether the given schema contains a column of the required data type.
   * @param colName  column name
   * @param dataType  required column data type
   */
  def checkColumnType(schema: StructType, colName: String, dataType: DataType): Unit = {
    val actualDataType = schema(colName).dataType
    require(actualDataType.equals(dataType),
      s"Column $colName must be of type $dataType but was actually $actualDataType.")
  }

  /**
   * Appends a new column to the input schema. This fails if the given output column already exists.
   * @param schema input schema
   * @param colName new column name. If this column name is an empty string "", this method returns
   *                the input schema unchanged. This allows users to disable output columns.
   * @param dataType new column data type
   * @return new schema with the input column appended
   */
  def appendColumn(
                    schema: StructType,
                    colName: String,
                    dataType: DataType): StructType = {
    if (colName.isEmpty) return schema
    val fieldNames = schema.fieldNames
    require(!fieldNames.contains(colName), s"Column $colName already exists.")
    val outputFields = schema.fields :+ StructField(colName, dataType, nullable = false)
    StructType(outputFields)
  }

  /**
   * Appends a new column to the input schema. This fails if the given output column already exists.
   * @param schema input schema
   * @param col New column schema
   * @return new schema with the input column appended
   */
  def appendColumn(schema: StructType, col: StructField): StructType = {
    require(!schema.fieldNames.contains(col.name), s"Column ${col.name} already exists.")
    StructType(schema.fields :+ col)
  }
}