• Example Search
• Project Search

• Java
• Python
• JavaScript
• TypeScript
• C++
• Scala
• Blog

• doddle-model-master
  • .github
    • PULL_REQUEST_TEMPLATE.md
    • ISSUE_TEMPLATE
      • feature_request.md
      • bug_report.md
    • CONTRIBUTING.md
  • src
    • main
      • resources
        • datasets
          • iris.csv
          • dummy_csv_reading.csv
          • breast_cancer.csv
          • boston_housing_prices.csv
          • high_school_test.csv
      • scala
        • io
          • picnicml
            • doddlemodel
              • package.scala
              • modelselection
                • GroupKFoldSplitter.scala
                • modelselection.scala
                • CrossValidation.scala
                • DataSplitter.scala
                • KFoldSplitter.scala
                • HyperparameterSearch.scala
              • typeclasses
                • Classifier.scala
                • Predictor.scala
                • Transformer.scala
                • Estimator.scala
                • Regressor.scala
              • dummy
                • classification
                  • StratifiedClassifier.scala
                  • MostFrequentClassifier.scala
                  • UniformClassifier.scala
                • regression
                  • MedianRegressor.scala
                  • MeanRegressor.scala
              • impute
                • MeanValueImputer.scala
                • MostFrequentValueImputer.scala
              • syntax
                • ClassifierSyntax.scala
                • RegressorSyntax.scala
                • TransformerSyntax.scala
                • PredictorSyntax.scala
                • OptionSyntax.scala
              • linear
                • typeclasses
                  • LinearModel.scala
                  • LinearClassifier.scala
                  • LinearRegressor.scala
                • PoissonRegression.scala
                • LogisticRegression.scala
                • SoftmaxClassifier.scala
                • LinearRegression.scala
              • data
                • ResourceDatasetLoaders.scala
                • package.scala
                • DatasetUtils.scala
                • CsvLoader.scala
                • Feature.scala
                • data.scala
              • preprocessing
                • Binarizer.scala
                • OneHotEncoder.scala
                • RangeScaler.scala
                • Normalizer.scala
                • Norms.scala
                • StandardScaler.scala
              • pipeline
                • package.scala
                • Pipeline.scala
              • metrics
                • ClassificationMetrics.scala
                • package.scala
                • RankingMetrics.scala
                • Metric.scala
                • RegressionMetrics.scala
      • scala-2.13+
        • io
          • picnicml
            • doddlemodel
              • CrossScalaCompat.scala
      • scala-2.12-
        • io
          • picnicml
            • doddlemodel
              • CrossScalaCompat.scala
    • test
      • scala
        • io
          • picnicml
            • doddlemodel
              • modelselection
                • GroupKFoldSplitterTest.scala
                • KFoldSplitterTest.scala
                • HyperparameterSearchTest.scala
              • integration
                • LogisticRegressionTest.scala
                • LinearRegressionTest.scala
                • SoftmaxClassifierTest.scala
                • PoissonRegressionTest.scala
              • TestingUtils.scala
              • dummy
                • classification
                  • StratifiedClassifierTest.scala
                  • MostFrequentClassifierTest.scala
                • regression
                  • MeanRegressorTest.scala
                  • MedianRegressorTest.scala
              • impute
                • MostFrequentValueImputerTest.scala
                • MeanValueImputerTest.scala
              • syntax
                • SyntaxTest.scala
              • linear
                • LinearRegressorTest.scala
                • LogisticRegressionTest.scala
                • LinearRegressionTest.scala
                • SoftmaxClassifierTest.scala
                • PoissonRegressionTest.scala
                • LinearClassifierTest.scala
              • data
                • ResourceDatasetLoadersTest.scala
                • DatasetUtilsTest.scala
                • CsvLoaderTest.scala
                • FeatureTest.scala
              • preprocessing
                • NormsTest.scala
                • BinarizerTest.scala
                • NormalizerTest.scala
                • OneHotEncoderTest.scala
                • StandardScalerTest.scala
                • RangeScalerTest.scala
              • pipeline
                • PipelineTest.scala
              • metrics
                • RankingMetricsTest.scala
                • ClassificationMetricsTest.scala
                • RegressionMetricsTest.scala
  • .circleci
    • config.yml
  • LICENSE
  • project
    • Dependencies.scala
    • build.properties
    • Version.scala
    • plugins.sbt
  • README.md
  • build.sbt
  • .gitignore

package io.picnicml.doddlemodel.linear.typeclasses

import breeze.linalg.{DenseMatrix, DenseVector}
import breeze.optimize.{DiffFunction, LBFGS}
import io.picnicml.doddlemodel.data.{Features, RealVector, Target}
import io.picnicml.doddlemodel.typeclasses.Predictor

trait LinearModel[A] {
  this: Predictor[A] =>

  /** Parameters (weights) of a linear model, i.e. the state of the model. */
  protected def w(model: A): Option[RealVector]

  /** A function that creates a new linear model with parameters w. */
  protected def copy(model: A, w: RealVector): A

  /** A stateless function that predicts a target variable. */
  protected def predictStateless(model: A, w: RealVector, x: Features): Target

  /** A stateless function that calculates the value of the loss function. */
  protected[linear] def lossStateless(model: A, w: RealVector, x: Features, y: Target): Float

  /** A stateless function that calculates the gradient of the loss function wrt. model parameters. */
  protected[linear] def lossGradStateless(model: A, w: RealVector, x: Features, y: Target): RealVector

  override def isFitted(model: A): Boolean = w(model).isDefined

  override def predictSafe(model: A, x: Features): Target =
    predictStateless(model, w(model).get, xWithBiasTerm(x))

  protected def maximumLikelihood(model: A, x: Features, y: Target, init: RealVector): RealVector = {
    val diffFunction = new DiffFunction[RealVector] {
      override def calculate(w: RealVector): (Double, RealVector) =
        (lossStateless(model, w, x, y).toDouble, lossGradStateless(model, w, x, y))
    }
    val lbfgs = new LBFGS[DenseVector[Float]](tolerance = 1e-4)
    lbfgs.minimize(diffFunction, init)
  }

  protected def xWithBiasTerm(x: Features): Features =
    DenseMatrix.horzcat(DenseMatrix.ones[Float](x.rows, 1), x)
}