`sklearn.decomposition`.NMF¶

class sklearn.decomposition.NMF(n_components=None, *, init=None, solver='cd', beta_loss='frobenius', tol=0.0001, max_iter=200, random_state=None, alpha=0.0, l1_ratio=0.0, verbose=0, shuffle=False)[source]¶

Non-Negative Matrix Factorization (NMF)

Find two non-negative matrices (W, H) whose product approximates the non- negative matrix X. This factorization can be used for example for dimensionality reduction, source separation or topic extraction.

The objective function is:

0.5 * ||X - WH||_Fro^2
+ alpha * l1_ratio * ||vec(W)||_1
+ alpha * l1_ratio * ||vec(H)||_1
+ 0.5 * alpha * (1 - l1_ratio) * ||W||_Fro^2
+ 0.5 * alpha * (1 - l1_ratio) * ||H||_Fro^2

Where:

||A||_Fro^2 = \sum_{i,j} A_{ij}^2 (Frobenius norm)
||vec(A)||_1 = \sum_{i,j} abs(A_{ij}) (Elementwise L1 norm)

For multiplicative-update (‘mu’) solver, the Frobenius norm (0.5 * ||X - WH||_Fro^2) can be changed into another beta-divergence loss, by changing the beta_loss parameter.

The objective function is minimized with an alternating minimization of W and H.

Read more in the User Guide.

Parameters

n_componentsint or None

Number of components, if n_components is not set all features are kept.

Method used to initialize the procedure. Default: None. Valid options:

None: ‘nndsvd’ if n_components <= min(n_samples, n_features),
otherwise random.
‘random’: non-negative random matrices, scaled with:
sqrt(X.mean() / n_components)
‘nndsvd’: Nonnegative Double Singular Value Decomposition (NNDSVD)
initialization (better for sparseness)
‘nndsvda’: NNDSVD with zeros filled with the average of X
(better when sparsity is not desired)
‘nndsvdar’: NNDSVD with zeros filled with small random values
(generally faster, less accurate alternative to NNDSVDa for when sparsity is not desired)
‘custom’: use custom matrices W and H

solver‘cd’ | ‘mu’

Numerical solver to use: ‘cd’ is a Coordinate Descent solver. ‘mu’ is a Multiplicative Update solver.

New in version 0.17: Coordinate Descent solver.

New in version 0.19: Multiplicative Update solver.

beta_lossfloat or string, default ‘frobenius’

String must be in {‘frobenius’, ‘kullback-leibler’, ‘itakura-saito’}. Beta divergence to be minimized, measuring the distance between X and the dot product WH. Note that values different from ‘frobenius’ (or 2) and ‘kullback-leibler’ (or 1) lead to significantly slower fits. Note that for beta_loss <= 0 (or ‘itakura-saito’), the input matrix X cannot contain zeros. Used only in ‘mu’ solver.

New in version 0.19.

tolfloat, default: 1e-4

Tolerance of the stopping condition.

max_iterinteger, default: 200

Maximum number of iterations before timing out.

random_stateint, RandomState instance, default=None

Used for initialisation (when init == ‘nndsvdar’ or ‘random’), and in Coordinate Descent. Pass an int for reproducible results across multiple function calls. See Glossary.

alphadouble, default: 0.

Constant that multiplies the regularization terms. Set it to zero to have no regularization.

New in version 0.17: alpha used in the Coordinate Descent solver.

l1_ratiodouble, default: 0.

The regularization mixing parameter, with 0 <= l1_ratio <= 1. For l1_ratio = 0 the penalty is an elementwise L2 penalty (aka Frobenius Norm). For l1_ratio = 1 it is an elementwise L1 penalty. For 0 < l1_ratio < 1, the penalty is a combination of L1 and L2.

New in version 0.17: Regularization parameter l1_ratio used in the Coordinate Descent solver.

verbosebool, default=False

Whether to be verbose.

shuffleboolean, default: False

If true, randomize the order of coordinates in the CD solver.

New in version 0.17: shuffle parameter used in the Coordinate Descent solver.

Attributes

components_array, [n_components, n_features]: Factorization matrix, sometimes called ‘dictionary’.
n_components_integer: The number of components. It is same as the n_components parameter if it was given. Otherwise, it will be same as the number of features.
reconstruction_err_number: Frobenius norm of the matrix difference, or beta-divergence, between the training data X and the reconstructed data WH from the fitted model.
n_iter_int: Actual number of iterations.

References

Cichocki, Andrzej, and P. H. A. N. Anh-Huy. “Fast local algorithms for large scale nonnegative matrix and tensor factorizations.” IEICE transactions on fundamentals of electronics, communications and computer sciences 92.3: 708-721, 2009.

Fevotte, C., & Idier, J. (2011). Algorithms for nonnegative matrix factorization with the beta-divergence. Neural Computation, 23(9).

Examples

>>> import numpy as np
>>> X = np.array([[1, 1], [2, 1], [3, 1.2], [4, 1], [5, 0.8], [6, 1]])
>>> from sklearn.decomposition import NMF
>>> model = NMF(n_components=2, init='random', random_state=0)
>>> W = model.fit_transform(X)
>>> H = model.components_

Methods

`fit`(X[, y])	Learn a NMF model for the data X.
`fit_transform`(X[, y, W, H])	Learn a NMF model for the data X and returns the transformed data.
`get_params`([deep])	Get parameters for this estimator.
`inverse_transform`(W)	Transform data back to its original space.
`set_params`(**params)	Set the parameters of this estimator.
`transform`(X)	Transform the data X according to the fitted NMF model

__init__(n_components=None, *, init=None, solver='cd', beta_loss='frobenius', tol=0.0001, max_iter=200, random_state=None, alpha=0.0, l1_ratio=0.0, verbose=0, shuffle=False)[source]¶: Initialize self. See help(type(self)) for accurate signature.

fit(X, y=None, **params)[source]¶

Learn a NMF model for the data X.

Parameters

X{array-like, sparse matrix}, shape (n_samples, n_features): Data matrix to be decomposed
yIgnored

Returns

self

fit_transform(X, y=None, W=None, H=None)[source]¶

Learn a NMF model for the data X and returns the transformed data.

This is more efficient than calling fit followed by transform.

Parameters

X{array-like, sparse matrix}, shape (n_samples, n_features): Data matrix to be decomposed
yIgnored
Warray-like, shape (n_samples, n_components): If init=’custom’, it is used as initial guess for the solution.
Harray-like, shape (n_components, n_features): If init=’custom’, it is used as initial guess for the solution.

Returns

Warray, shape (n_samples, n_components): Transformed data.

get_params(deep=True)[source]¶

Get parameters for this estimator.

Parameters

deepbool, default=True: If True, will return the parameters for this estimator and contained subobjects that are estimators.

Returns

paramsmapping of string to any: Parameter names mapped to their values.

inverse_transform(W)[source]¶

Transform data back to its original space.

Parameters

W{array-like, sparse matrix}, shape (n_samples, n_components): Transformed data matrix

Returns

X{array-like, sparse matrix}, shape (n_samples, n_features): Data matrix of original shape

New in version 0.18: ..

set_params(**params)[source]¶

Set the parameters of this estimator.

The method works on simple estimators as well as on nested objects (such as pipelines). The latter have parameters of the form <component>__<parameter> so that it’s possible to update each component of a nested object.

Parameters