sklearn

README

sklearn

Very partial port of scikit-learn to go

for now, ported only some estimators including

• LinearRegression
• LogisticRegression
• bayesian ridge regression
• MLPRegressor
• MLPClassifier

You'll also find

• some metrics MeanSquaredError,MeanAbsoluteError,R2Score,AccuracyScore, ...
• some preprocessing MinMaxScaler,StandardScaler,OneHotEncoder,PolynomialFeatures
• Pipeline and MakePipeline
• some interpolation stuff like in scipy.interpolate: interp1d,interp2d,CubicSpline
• all estimators can use following
  • solvers: sgd,adagrad,rmsprop,adadelta,adam + all gonum/optimize methods
  • loss functions: square,cross-entropy
  • activation functions: identity,logistic,tanh,relu

All of this is

• a personal project to get a deeper understanding of how all of this magic works
• a recent work still in progress, subject to refactoring, so interfaces may change, especially args to NewXXX
• processed with gofmt, golint, go vet
• unit tested but coverage should reach 90%
• underdocumented but python sklearn documentation should be sufficient

Many thanks to gonum and scikit-learn contributors

PRs are welcome

Best regards

Documentation

Overview

sklearn is a (very partial) port or scikit-learn in go package sklearn itself is empty but you wil find well known structs and interfaces in sub packages base,datasets,linear_model,metrics,neural_network,preprocessing