evalml.preprocessing.SMOTETomekCVSplit

class evalml.preprocessing.SMOTETomekCVSplit(sampling_strategy='auto', n_splits=3, shuffle=True, n_jobs=- 1, random_seed=0)

Splits the data into KFold cross validation sets and uses SMOTE + Tomek links to balance the training data. Keeps the validation data the same. Works only on continuous, numeric data.

Methods

__init__	Create a TV or CV data splitter instance
get_n_splits	Returns the number of splits of this object.
split	Splits and returns the sampled training data using the data sampler provided.
transform_sample	Transforms the input data with the balancing strategy.

Class Inheritance

evalml.preprocessing.KMeansSMOTETVSplit.transform_sample evalml.preprocessing.SMOTETomekCVSplit.__init__