sklearn.model_selection (original) (raw)

Tools for model selection, such as cross validation and hyper-parameter tuning.

User guide. See the Cross-validation: evaluating estimator performance, Tuning the hyper-parameters of an estimator, and Learning curve sections for further details.

Splitters#

GroupKFold	K-fold iterator variant with non-overlapping groups.
GroupShuffleSplit	Shuffle-Group(s)-Out cross-validation iterator.
KFold	K-Fold cross-validator.
LeaveOneGroupOut	Leave One Group Out cross-validator.
LeaveOneOut	Leave-One-Out cross-validator.
LeavePGroupsOut	Leave P Group(s) Out cross-validator.
LeavePOut	Leave-P-Out cross-validator.
PredefinedSplit	Predefined split cross-validator.
RepeatedKFold	Repeated K-Fold cross validator.
RepeatedStratifiedKFold	Repeated Stratified K-Fold cross validator.
ShuffleSplit	Random permutation cross-validator.
StratifiedGroupKFold	Stratified K-Fold iterator variant with non-overlapping groups.
StratifiedKFold	Stratified K-Fold cross-validator.
StratifiedShuffleSplit	Stratified ShuffleSplit cross-validator.
TimeSeriesSplit	Time Series cross-validator.
check_cv	Input checker utility for building a cross-validator.
train_test_split	Split arrays or matrices into random train and test subsets.

Hyper-parameter optimizers#

GridSearchCV	Exhaustive search over specified parameter values for an estimator.
HalvingGridSearchCV	Search over specified parameter values with successive halving.
HalvingRandomSearchCV	Randomized search on hyper parameters.
ParameterGrid	Grid of parameters with a discrete number of values for each.
ParameterSampler	Generator on parameters sampled from given distributions.
RandomizedSearchCV	Randomized search on hyper parameters.

Post-fit model tuning#

FixedThresholdClassifier	Binary classifier that manually sets the decision threshold.
TunedThresholdClassifierCV	Classifier that post-tunes the decision threshold using cross-validation.

Model validation#

cross_val_predict	Generate cross-validated estimates for each input data point.
cross_val_score	Evaluate a score by cross-validation.
cross_validate	Evaluate metric(s) by cross-validation and also record fit/score times.
learning_curve	Learning curve.
permutation_test_score	Evaluate the significance of a cross-validated score with permutations.
validation_curve	Validation curve.

Visualization#

LearningCurveDisplay	Learning Curve visualization.
ValidationCurveDisplay	Validation Curve visualization.