preprocessing

Type Members

1. class MinMaxScaler extends Transformer[MinMaxScaler]

   

   Scales observations, so that all features are in a user-specified range.

   Scales observations, so that all features are in a user-specified range. By default for MinMaxScaler transformer range = [0,1].

   This transformer takes a subtype of Vector of values and maps it to a scaled subtype of Vector such that each feature lies between a user-specified range.

   This transformer can be prepended to all Transformer and org.apache.flink.ml.pipeline.Predictor implementations which expect as input a subtype of Vector or a LabeledVector.

   Example:

   1. val trainingDS: DataSet[Vector] = env.fromCollection(data)
      val transformer = MinMaxScaler().setMin(-1.0)
      transformer.fit(trainingDS)
      val transformedDS = transformer.transform(trainingDS)

      Parameters

      - Min: The minimum value of the range of the transformed data set; by default equal to 0 - Max: The maximum value of the range of the transformed data set; by default equal to 1

2. class PolynomialFeatures extends Transformer[PolynomialFeatures]

   

   Maps a vector into the polynomial feature space.

   Maps a vector into the polynomial feature space.

   This transformer takes a a vector of values (x, y, z, ...) and maps it into the polynomial feature space of degree d. That is to say, it calculates the following representation:

   (x, y, z, x2, xy, y2, yz, z2, x3, x2y, x2z, xyz, ...)^T

   This transformer can be prepended to all org.apache.flink.ml.pipeline.Transformer and org.apache.flink.ml.pipeline.Predictor implementations which expect an input of LabeledVector.

   Example:

   1. val trainingDS: DataSet[LabeledVector] = ...
      val polyFeatures = PolynomialFeatures()
        .setDegree(3)
      val mlr = MultipleLinearRegression()
      val pipeline = polyFeatures.chainPredictor(mlr)
      pipeline.fit(trainingDS)

      Parameters

      • org.apache.flink.ml.preprocessing.PolynomialFeatures.Degree: Maximum polynomial degree

3. class StandardScaler extends Transformer[StandardScaler]

   

   Scales observations, so that all features have a user-specified mean and standard deviation.

   Scales observations, so that all features have a user-specified mean and standard deviation. By default for StandardScaler transformer mean=0.0 and std=1.0.

   This transformer takes a subtype of Vector of values and maps it to a scaled subtype of Vector such that each feature has a user-specified mean and standard deviation.

   This transformer can be prepended to all Transformer and org.apache.flink.ml.pipeline.Predictor implementations which expect as input a subtype of Vector.

   Example:

   1. val trainingDS: DataSet[Vector] = env.fromCollection(data)
      val transformer = StandardScaler().setMean(10.0).setStd(2.0)
      transformer.fit(trainingDS)
      val transformedDS = transformer.transform(trainingDS)

      Parameters

      - Mean: The mean value of transformed data set; by default equal to 0 - Std: The standard deviation of the transformed data set; by default equal to 1