sklearn.datasets.make_multilabel_classification(n_samples=100, n_features=20, *, n_classes=5, n_labels=2, length=50, allow_unlabeled=True, sparse=False, return_indicator='dense', return_distributions=False, random_state=None)[source]

Generate a random multilabel classification problem.

For each sample, the generative process is:
  • pick the number of labels: n ~ Poisson(n_labels)

  • n times, choose a class c: c ~ Multinomial(theta)

  • pick the document length: k ~ Poisson(length)

  • k times, choose a word: w ~ Multinomial(theta_c)

In the above process, rejection sampling is used to make sure that n is never zero or more than n_classes, and that the document length is never zero. Likewise, we reject classes which have already been chosen.

For an example of usage, see Plot randomly generated multilabel dataset.

Read more in the User Guide.

n_samplesint, default=100

The number of samples.

n_featuresint, default=20

The total number of features.

n_classesint, default=5

The number of classes of the classification problem.

n_labelsint, default=2

The average number of labels per instance. More precisely, the number of labels per sample is drawn from a Poisson distribution with n_labels as its expected value, but samples are bounded (using rejection sampling) by n_classes, and must be nonzero if allow_unlabeled is False.

lengthint, default=50

The sum of the features (number of words if documents) is drawn from a Poisson distribution with this expected value.

allow_unlabeledbool, default=True

If True, some instances might not belong to any class.

sparsebool, default=False

If True, return a sparse feature matrix.

New in version 0.17: parameter to allow sparse output.

return_indicator{‘dense’, ‘sparse’} or False, default=’dense’

If 'dense' return Y in the dense binary indicator format. If 'sparse' return Y in the sparse binary indicator format. False returns a list of lists of labels.

return_distributionsbool, default=False

If True, return the prior class probability and conditional probabilities of features given classes, from which the data was drawn.

random_stateint, RandomState instance or None, default=None

Determines random number generation for dataset creation. Pass an int for reproducible output across multiple function calls. See Glossary.

Xndarray of shape (n_samples, n_features)

The generated samples.

Y{ndarray, sparse matrix} of shape (n_samples, n_classes)

The label sets. Sparse matrix should be of CSR format.

p_cndarray of shape (n_classes,)

The probability of each class being drawn. Only returned if return_distributions=True.

p_w_cndarray of shape (n_features, n_classes)

The probability of each feature being drawn given each class. Only returned if return_distributions=True.


>>> from sklearn.datasets import make_multilabel_classification
>>> X, y = make_multilabel_classification(n_labels=3, random_state=42)
>>> X.shape
(100, 20)
>>> y.shape
(100, 5)
>>> list(y[:3])
[array([1, 1, 0, 1, 0]), array([0, 1, 1, 1, 0]), array([0, 1, 0, 0, 0])]

Examples using sklearn.datasets.make_multilabel_classification

Plot randomly generated multilabel dataset

Plot randomly generated multilabel dataset

Multilabel classification

Multilabel classification