Github user liancheng commented on a diff in the pull request: https://github.com/apache/spark/pull/14868#discussion_r76761692 --- Diff: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/ApproximatePercentile.scala --- @@ -0,0 +1,304 @@ +/* + * 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.AnalysisException +import org.apache.spark.sql.catalyst.{InternalRow, ScalaReflectionLock} +import org.apache.spark.sql.catalyst.analysis.TypeCheckResult +import org.apache.spark.sql.catalyst.analysis.TypeCheckResult.{TypeCheckFailure, TypeCheckSuccess} +import org.apache.spark.sql.catalyst.encoders.ExpressionEncoder +import org.apache.spark.sql.catalyst.expressions._ +import org.apache.spark.sql.catalyst.expressions.aggregate.ApproximatePercentile.{PercentileDigest, PercentileDigestSerializer} +import org.apache.spark.sql.catalyst.util.{ArrayData, GenericArrayData} +import org.apache.spark.sql.catalyst.util.QuantileSummaries +import org.apache.spark.sql.catalyst.util.QuantileSummaries.{defaultCompressThreshold, Stats} +import org.apache.spark.sql.types._ + +/** + * The ApproximatePercentile function returns the approximate percentile(s) of a column at the given + * percentage(s). A percentile is a watermark value below which a given percentage of the column + * values fall. For example, the percentile of column `col` at percentage 50% is the median of + * column `col`. + * + * This function supports partial aggregation. + * + * @param child child expression that can produce column value with `child.eval(inputRow)` + * @param percentageExpression Expression that represents a single percentage value or + * a array of percentage values. Each percentage value must be between + * 0.0 and 1.0. + * @param accuracyExpression Integer literal expression of approximation accuracy. Higher value + * yield better accuracy, the default value is + * DEFAULT_PERCENTILE_ACCURACY. + */ +@ExpressionDescription( + usage = + """ + _FUNC_(col, percentage [, accuracy]) - Returns the approximate percentile value of numeric + column `col` at the given percentage. The value of percentage must be between 0.0 + and 1.0. The `accuracy` parameter (default: 10000) is a positive integer literal which + controls approximation accuracy at the cost of memory. Higher value of `accuracy` yield --- End diff -- Nit: yield => yields
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org