Github user gatorsmile commented on a diff in the pull request: https://github.com/apache/spark/pull/21054#discussion_r186616594 --- Diff: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/regression.scala --- @@ -0,0 +1,190 @@ +/* + * 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.sql.catalyst.expressions.aggregate + +import org.apache.spark.sql.catalyst.dsl.expressions._ +import org.apache.spark.sql.catalyst.expressions._ +import org.apache.spark.sql.types.{AbstractDataType, DoubleType} + +/** + * Base trait for all regression functions. + */ +trait RegrLike extends AggregateFunction with ImplicitCastInputTypes { + def y: Expression + def x: Expression + + override def children: Seq[Expression] = Seq(y, x) + override def inputTypes: Seq[AbstractDataType] = Seq(DoubleType, DoubleType) + + protected def updateIfNotNull(exprs: Seq[Expression]): Seq[Expression] = { + assert(aggBufferAttributes.length == exprs.length) + val nullableChildren = children.filter(_.nullable) + if (nullableChildren.isEmpty) { + exprs + } else { + exprs.zip(aggBufferAttributes).map { case (e, a) => + If(nullableChildren.map(IsNull).reduce(Or), a, e) + } + } + } +} + + +@ExpressionDescription( + usage = "_FUNC_(y, x) - Returns the number of non-null pairs.", + since = "2.4.0") +case class RegrCount(y: Expression, x: Expression) + extends CountLike with RegrLike { + + override lazy val updateExpressions: Seq[Expression] = updateIfNotNull(Seq(count + 1L)) + + override def prettyName: String = "regr_count" +} + + +@ExpressionDescription( + usage = "_FUNC_(y, x) - Returns SUM(x*x)-SUM(x)*SUM(x)/N. Any pair with a NULL is ignored.", --- End diff -- It is reasonable to follow Hive. Personally, I like DB2 or Oracle, because normally these commercial dbms is more professional. : )
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org