Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/11601#discussion_r55555741
--- Diff: mllib/src/main/scala/org/apache/spark/ml/feature/Imputer.scala ---
@@ -0,0 +1,288 @@
+/*
+ * 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.hadoop.fs.Path
+
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.ml.{Estimator, Model}
+import org.apache.spark.ml.param.{DoubleParam, Param, ParamMap, Params}
+import org.apache.spark.ml.param.shared.{HasInputCol, HasOutputCol}
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg._
+import org.apache.spark.sql.{DataFrame, Row}
+import org.apache.spark.sql.functions.{col, udf}
+import org.apache.spark.sql.types.{DoubleType, StructField, StructType}
+
+/**
+ * Params for [[Imputer]] and [[ImputerModel]].
+ */
+private[feature] trait ImputerParams extends Params with HasInputCol with
HasOutputCol {
+
+ /**
+ * The imputation strategy.
+ * If "mean", then replace missing values using the mean along the axis.
+ * If "median", then replace missing values using the median along the
axis.
+ * If "most", then replace missing using the most frequent value along
the axis.
+ * Default: mean
+ *
+ * @group param
+ */
+ val strategy: Param[String] = new Param(this, "strategy", "strategy for
imputation. " +
+ "If mean, then replace missing values using the mean along the axis." +
+ "If median, then replace missing values using the median along the
axis." +
+ "If most, then replace missing using the most frequent value along the
axis.")
+
+ /** @group getParam */
+ def getStrategy: String = $(strategy)
+
+ /**
+ * The placeholder for the missing values. All occurrences of
missingvalues will be imputed.
+ * Default: Double.NaN
+ *
+ * @group param
+ */
+ val missingValue: DoubleParam = new DoubleParam(this, "missingValue",
+ "The placeholder for the missing values. All occurrences of
missingvalues will be imputed")
+
+ /** @group getParam */
+ def getMissingValue: Double = $(missingValue)
+
+ /** Validates and transforms the input schema. */
+ protected def validateAndTransformSchema(schema: StructType): StructType
= {
+ validateParams()
+ val inputType = schema($(inputCol)).dataType
+ require(inputType.isInstanceOf[VectorUDT] ||
inputType.isInstanceOf[DoubleType],
+ s"Input column ${$(inputCol)} must of type Vector or Double")
+ require(!schema.fieldNames.contains($(outputCol)),
+ s"Output column ${$(outputCol)} already exists.")
+ val outputFields = schema.fields :+ StructField($(outputCol), new
VectorUDT, false)
+ StructType(outputFields)
+ }
+
+ override def validateParams(): Unit = {
+ require(Seq("mean", "median", "most").contains($(strategy)),
+ s"${$(strategy)} is not supported. Options are mean, median and
most")
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Imputation estimator for completing missing values, either using the
mean, the median or
+ * the most frequent value of the column in which the missing values are
located. This class
+ * also allows for different missing values encodings.
+ *
+ */
+@Experimental
+class Imputer @Since("2.0.0")(override val uid: String)
+ extends Estimator[ImputerModel] with ImputerParams with
DefaultParamsWritable {
+
+ @Since("2.0.0")
+ def this() = this(Identifiable.randomUID("imputer"))
+
+ /** @group setParam */
+ def setInputCol(value: String): this.type = set(inputCol, value)
+
+ /** @group setParam */
+ def setOutputCol(value: String): this.type = set(outputCol, value)
+
+ /** @group setParam */
+ def setStrategy(value: String): this.type = set(strategy, value)
+
+ /** @group setParam */
+ def setMissingValue(value: Double): this.type = set(missingValue, value)
+
+ setDefault(strategy -> "mean", missingValue -> Double.NaN)
+
+ override def fit(dataset: DataFrame): ImputerModel = {
+ val alternate = dataset.select($(inputCol)).schema.fields(0).dataType
match {
+ case DoubleType =>
+ val colStatistics = getColStatistics(dataset, $(inputCol))
+ Vectors.dense(Array(colStatistics))
--- End diff --
Perhaps `Vectors.dense(colStatistics)` is cleaner?
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
