AutoMLPipeline.SKPreprocessors.SKPreprocessor
— TypeSKPreprocessor(preprocessor::String,args::Dict=Dict())
A wrapper for Scikitlearn preprocessor functions. Invoking skpreprocessors()
will list the acceptable and supported functions. Please check Scikitlearn documentation for arguments to pass.
Implements fit!
and transform!
.
AutoMLPipeline.SKLearners.SKLearner
— TypeSKLearner(learner::String, args::Dict=Dict())
A Scikitlearn wrapper to load the different machine learning models. Invoking sklearners()
will list the available learners. Please consult Scikitlearn documentation for arguments to pass.
Implements fit!
and transform!
.
AutoMLPipeline.SKLearners.sklearners
— Methodfunction sklearners()
List the available scikitlearn machine learners.
AMLPipelineBase.CrossValidators.crossvalidate
— Methodcrossvalidate(pl::Machine,X::DataFrame,Y::Vector,sfunc::String="balanced_accuracy_score",nfolds=10)
Runs K-fold cross-validation using balanced accuracy as the default. It support the following metrics for classification:
- "accuracy_score"
- "balancedaccuracyscore"
- "cohenkappascore"
- "jaccard_score"
- "matthews_corrcoef"
- "hamming_loss"
- "zerooneloss"
- "f1_score"
- "precision_score"
- "recall_score"
and the following metrics for regression:
- "meansquarederror"
- "meansquaredlog_error"
- "medianabsoluteerror"
- "r2_score"
- "max_error"
- "explainedvariancescore"