本文整理汇总了Scala中org.apache.spark.ml.param._类的典型用法代码示例。如果您正苦于以下问题:Scala _类的具体用法?Scala _怎么用?Scala _使用的例子?那么恭喜您, 这里精选的类代码示例或许可以为您提供帮助。
在下文中一共展示了_类的2个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Scala代码示例。
示例1: setFunction
//设置package包名称以及导入依赖的类
package spark.feature
import org.apache.spark.ml.Transformer
import org.apache.spark.ml.attribute.AttributeGroup
import org.apache.spark.ml.param.{ParamMap, _}
import org.apache.spark.ml.util._
import org.apache.spark.sql.functions.{col, udf}
import org.apache.spark.sql.types.StructType
import org.apache.spark.sql.{DataFrame, UserDefinedFunction}
def setFunction(value: String=>Double) = set(function, value)
def getFunction() = $(function)
override def transform(dataset: DataFrame): DataFrame = {
val outputSchema = transformSchema(dataset.schema)
val metadata = outputSchema($(outputCol)).metadata
val dummy = udf { x: Any => $(expr) }
var data = dataset.select(col("*"), dummy(col($(inputCols).head)).as("0"))
val substitute: (String => ((String, Double) => String)) = name => (exp, elem) => exp.replace(name, elem.toString)
def subst(v: String) = udf(substitute(v))
$(inputCols).view.zipWithIndex foreach { case (v, i) => data = data.select(col("*"), subst(v)(data(i.toString), data(v)).as((i + 1).toString)).drop(i.toString) }
val eval = udf($(function))
data.select(col("*"), eval(data($(inputCols).length.toString)).as($(outputCol), metadata)).drop($(inputCols).length.toString)
}
override def transformSchema(schema: StructType): StructType = {
// TODO: Assertions on inputCols
val attrGroup = new AttributeGroup($(outputCol), $(numFeatures))
val col = attrGroup.toStructField()
require(!schema.fieldNames.contains(col.name), s"Column ${col.name} already exists.")
StructType(schema.fields :+ col)
}
override def copy(extra: ParamMap): FeatureFuTransformer = defaultCopy(extra)
}
示例2: getOutputCol
//设置package包名称以及导入依赖的类
package spark.progress
import org.apache.spark.ml.Transformer
import org.apache.spark.ml.attribute.AttributeGroup
import org.apache.spark.ml.param.{ParamMap, _}
import org.apache.spark.ml.util._
import org.apache.spark.sql.functions._
import org.apache.spark.sql.types.StructType
import org.apache.spark.sql.{DataFrame, Row}
def getOutputCol() = $(outputcol)
def getExpr() = $(expr)
def getInputCols() = $(inputcols).toArray
def getNumFeatures() = $(numFeatures)
def getFunction() = $(function)
override def transform(dataset: DataFrame): DataFrame = {
val outputSchema = transformSchema(dataset.schema)
val metadata = outputSchema($(outputcol)).metadata
val f = udf {(r: Row) => {
val exp = $(expr)
for (i <- 1 to $(numFeatures)) {
exp.replace(dataset.columns.toSeq(i), r.getInt(i).toString)
}
$(function)(exp)
}}
val x = lit($(expr))
dataset.select(col("*"), f(struct(dataset.columns.map(dataset(_)) : _*)).as($(outputcol), metadata))
}
override def transformSchema(schema: StructType): StructType = {
val attrGroup = new AttributeGroup($(outputcol), $(numFeatures))
val col = attrGroup.toStructField()
require(!schema.fieldNames.contains(col.name), s"Column ${col.name} already exists.")
StructType(schema.fields :+ col)
}
override def copy(extra: ParamMap): ExpressionEval = defaultCopy(extra)
}