org.apache.spark.ml.feature.PythonBatchPredictDataSchema.scala Maven / Gradle / Ivy
The newest version!
/*
* 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.spark.ml.feature
import org.apache.spark.ml.linalg.MatrixUDT
import org.apache.spark.sql.DataFrame
import org.apache.spark.sql.types.{ArrayType, StructField, StructType}
/**
* Created by fchen on 2018/8/26.
*/
object PythonBatchPredictDataSchema {
/**
* 数据结构, size = batchSize
* {
* originalDatas: indexSeq
* combineFeatures: Matrix
* }
*/
val newSchema: (DataFrame) => StructType = df => {
StructType(Seq(
StructField("originalData", ArrayType(df.schema)),
StructField("newFeature", new MatrixUDT())
))
}
}