[GitHub] [spark] LuciferYang commented on a diff in pull request #40255: [SPARK-42558][CONNECT] Implement `DataFrameStatFunctions` except `bloomFilter` functions

["LuciferYang (via GitHub)" <gi...@apache.org>]

LuciferYang commented on code in PR #40255:
URL: https://github.com/apache/spark/pull/40255#discussion_r1125591758


##########
connector/connect/client/jvm/src/main/scala/org/apache/spark/sql/DataFrameStatFunctions.scala:
##########
@@ -0,0 +1,605 @@
+/*
+ * 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
+
+import java.{lang => jl, util => ju}
+
+import scala.collection.JavaConverters._
+
+import org.apache.spark.connect.proto.{Relation, StatSampleBy}
+import org.apache.spark.sql.DataFrameStatFunctions.approxQuantileResultEncoder
+import org.apache.spark.sql.catalyst.encoders.AgnosticEncoders.{ArrayEncoder, BinaryEncoder, PrimitiveDoubleEncoder}
+import org.apache.spark.sql.functions.lit
+import org.apache.spark.util.sketch.CountMinSketch
+
+/**
+ * Statistic functions for `DataFrame`s.
+ *
+ * @since 3.4.0
+ */
+final class DataFrameStatFunctions private[sql] (sparkSession: SparkSession, root: Relation) {
+
+  /**
+   * Calculates the approximate quantiles of a numerical column of a DataFrame.
+   *
+   * The result of this algorithm has the following deterministic bound: If the DataFrame has N
+   * elements and if we request the quantile at probability `p` up to error `err`, then the
+   * algorithm will return a sample `x` from the DataFrame so that the *exact* rank of `x` is
+   * close to (p * N). More precisely,
+   *
+   * {{{
+   *   floor((p - err) * N) <= rank(x) <= ceil((p + err) * N)
+   * }}}
+   *
+   * This method implements a variation of the Greenwald-Khanna algorithm (with some speed
+   * optimizations). The algorithm was first present in <a
+   * href="https://doi.org/10.1145/375663.375670"> Space-efficient Online Computation of Quantile
+   * Summaries</a> by Greenwald and Khanna.
+   *
+   * @param col
+   *   the name of the numerical column
+   * @param probabilities
+   *   a list of quantile probabilities Each number must belong to [0, 1]. For example 0 is the
+   *   minimum, 0.5 is the median, 1 is the maximum.
+   * @param relativeError
+   *   The relative target precision to achieve (greater than or equal to 0). If set to zero, the
+   *   exact quantiles are computed, which could be very expensive. Note that values greater than
+   *   1 are accepted but give the same result as 1.
+   * @return
+   *   the approximate quantiles at the given probabilities
+   *
+   * @note
+   *   null and NaN values will be removed from the numerical column before calculation. If the
+   *   dataframe is empty or the column only contains null or NaN, an empty array is returned.
+   *
+   * @since 3.4.0
+   */
+  def approxQuantile(
+      col: String,
+      probabilities: Array[Double],
+      relativeError: Double): Array[Double] = {
+    approxQuantile(Array(col), probabilities, relativeError).head
+  }
+
+  /**
+   * Calculates the approximate quantiles of numerical columns of a DataFrame.
+   * @see
+   *   `approxQuantile(col:Str* approxQuantile)` for detailed description.
+   *
+   * @param cols
+   *   the names of the numerical columns
+   * @param probabilities
+   *   a list of quantile probabilities Each number must belong to [0, 1]. For example 0 is the
+   *   minimum, 0.5 is the median, 1 is the maximum.
+   * @param relativeError
+   *   The relative target precision to achieve (greater than or equal to 0). If set to zero, the
+   *   exact quantiles are computed, which could be very expensive. Note that values greater than
+   *   1 are accepted but give the same result as 1.
+   * @return
+   *   the approximate quantiles at the given probabilities of each column
+   *
+   * @note
+   *   null and NaN values will be ignored in numerical columns before calculation. For columns
+   *   only containing null or NaN values, an empty array is returned.
+   *
+   * @since 3.4.0
+   */
+  def approxQuantile(
+      cols: Array[String],
+      probabilities: Array[Double],
+      relativeError: Double): Array[Array[Double]] = {
+    require(
+      probabilities.forall(p => p >= 0.0 && p <= 1.0),
+      "percentile should be in the range [0.0, 1.0]")
+    require(relativeError >= 0, s"Relative Error must be non-negative but got $relativeError")
+    sparkSession
+      .newDataset(approxQuantileResultEncoder) { builder =>
+        val approxQuantileBuilder = builder.getApproxQuantileBuilder
+          .setInput(root)
+          .setRelativeError(relativeError)
+        cols.foreach(approxQuantileBuilder.addCols)
+        probabilities.foreach(approxQuantileBuilder.addProbabilities)
+      }
+      .head()
+  }
+
+  /**
+   * Python-friendly version of [[approxQuantile()]]
+   */
+  private[spark] def approxQuantile(

Review Comment:
   already removed



-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org