From e3c9ae204ffb152c151e9b61306ff8f16a2c1e0a Mon Sep 17 00:00:00 2001
From: Guillaume Lemaitre <g.lemaitre58@gmail.com>
Date: Thu, 6 Apr 2017 02:43:21 +0200
Subject: [PATCH] [MRG+1] DOC improve description and consistency of
random_state (#8689)
* DOC improve description of random_state in train_test_split
* DOC Make random_state consistent through documentation
* FIX reverse doc mistake
* FIX address comment of Tom
* DOC address comments
* DOC remove empty line
* DOC remove unecessary white spaces
---
sklearn/cluster/bicluster.py | 16 ++--
sklearn/cluster/k_means_.py | 54 ++++++++------
sklearn/cluster/mean_shift_.py | 7 +-
sklearn/cluster/spectral.py | 30 +++++---
sklearn/covariance/robust_covariance.py | 33 +++++----
sklearn/cross_validation.py | 53 ++++++++-----
sklearn/datasets/olivetti_faces.py | 8 +-
sklearn/datasets/samples_generator.py | 7 +-
sklearn/decomposition/dict_learning.py | 35 ++++++---
sklearn/decomposition/factor_analysis.py | 8 +-
sklearn/decomposition/fastica_.py | 14 +++-
sklearn/decomposition/kernel_pca.py | 8 +-
sklearn/decomposition/nmf.py | 29 +++++---
sklearn/decomposition/online_lda.py | 7 +-
sklearn/decomposition/pca.py | 16 ++--
sklearn/decomposition/sparse_pca.py | 14 +++-
sklearn/decomposition/truncated_svd.py | 8 +-
sklearn/dummy.py | 7 +-
sklearn/ensemble/base.py | 7 +-
sklearn/ensemble/gradient_boosting.py | 3 +-
sklearn/feature_extraction/image.py | 14 +++-
sklearn/feature_selection/mutual_info_.py | 22 ++++--
sklearn/gaussian_process/gaussian_process.py | 9 ++-
sklearn/gaussian_process/gpc.py | 19 +++--
sklearn/gaussian_process/gpr.py | 16 ++--
sklearn/grid_search.py | 12 ++-
sklearn/kernel_approximation.py | 19 +++--
sklearn/linear_model/coordinate_descent.py | 74 ++++++++++++-------
sklearn/linear_model/logistic.py | 38 +++++++---
sklearn/linear_model/passive_aggressive.py | 18 +++--
sklearn/linear_model/perceptron.py | 9 ++-
sklearn/linear_model/randomized_l1.py | 7 +-
sklearn/linear_model/ransac.py | 9 ++-
sklearn/linear_model/ridge.py | 27 ++++---
sklearn/linear_model/sag.py | 9 ++-
sklearn/linear_model/stochastic_gradient.py | 18 +++--
sklearn/linear_model/theil_sen.py | 9 ++-
sklearn/manifold/locally_linear.py | 24 +++---
sklearn/manifold/mds.py | 33 +++++----
sklearn/manifold/spectral_embedding_.py | 17 +++--
sklearn/manifold/t_sne.py | 10 ++-
sklearn/metrics/cluster/unsupervised.py | 10 ++-
sklearn/mixture/bayesian_mixture.py | 7 +-
sklearn/mixture/gaussian_mixture.py | 7 +-
sklearn/mixture/gmm.py | 7 +-
sklearn/model_selection/_search.py | 12 ++-
sklearn/model_selection/_split.py | 62 +++++++++++-----
sklearn/model_selection/_validation.py | 16 ++--
sklearn/multiclass.py | 8 +-
sklearn/neighbors/kde.py | 7 +-
.../neural_network/multilayer_perceptron.py | 14 +++-
sklearn/random_projection.py | 38 ++++++----
sklearn/svm/base.py | 10 ++-
sklearn/svm/classes.py | 45 +++++++----
sklearn/utils/__init__.py | 16 +++-
sklearn/utils/extmath.py | 16 +++-
56 files changed, 694 insertions(+), 358 deletions(-)
diff --git a/sklearn/cluster/bicluster.py b/sklearn/cluster/bicluster.py
index 8f6206f959..6d5b6e76ee 100644
--- a/sklearn/cluster/bicluster.py
+++ b/sklearn/cluster/bicluster.py
@@ -236,9 +236,11 @@ class SpectralCoclustering(BaseSpectral):
(n_cpus + 1 + n_jobs) are used. Thus for n_jobs = -2, all CPUs but one
are used.
- random_state : int seed, RandomState instance, or None (default)
- A pseudo random number generator used by the K-Means
- initialization.
+ random_state : int, RandomState instance or None, optional, default: None
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
Attributes
----------
@@ -366,9 +368,11 @@ class SpectralBiclustering(BaseSpectral):
(n_cpus + 1 + n_jobs) are used. Thus for n_jobs = -2, all CPUs but one
are used.
- random_state : int seed, RandomState instance, or None (default)
- A pseudo random number generator used by the K-Means
- initialization.
+ random_state : int, RandomState instance or None, optional, default: None
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
Attributes
----------
diff --git a/sklearn/cluster/k_means_.py b/sklearn/cluster/k_means_.py
index f33b3f65b7..680edc2672 100644
--- a/sklearn/cluster/k_means_.py
+++ b/sklearn/cluster/k_means_.py
@@ -230,10 +230,11 @@ def k_means(X, n_clusters, init='k-means++', precompute_distances='auto',
verbose : boolean, optional
Verbosity mode.
- random_state : integer or numpy.RandomState, optional
- The generator used to initialize the centers. If an integer is
- given, it fixes the seed. Defaults to the global numpy random
- number generator.
+ random_state : int, RandomState instance or None, optional, default: None
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
copy_x : boolean, optional
When pre-computing distances it is more numerically accurate to center
@@ -449,10 +450,11 @@ def _kmeans_single_lloyd(X, n_clusters, max_iter=300, init='k-means++',
precompute_distances : boolean, default: True
Precompute distances (faster but takes more memory).
- random_state : integer or numpy.RandomState, optional
- The generator used to initialize the centers. If an integer is
- given, it fixes the seed. Defaults to the global numpy random
- number generator.
+ random_state : int, RandomState instance or None, optional, default: None
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
Returns
-------
@@ -638,10 +640,11 @@ def _init_centroids(X, k, init, random_state=None, x_squared_norms=None,
init : {'k-means++', 'random' or ndarray or callable} optional
Method for initialization
- random_state : integer or numpy.RandomState, optional
- The generator used to initialize the centers. If an integer is
- given, it fixes the seed. Defaults to the global numpy random
- number generator.
+ random_state : int, RandomState instance or None, optional, default: None
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
x_squared_norms : array, shape (n_samples,), optional
Squared euclidean norm of each data point. Pass it if you have it at
@@ -766,10 +769,11 @@ class KMeans(BaseEstimator, ClusterMixin, TransformerMixin):
(n_cpus + 1 + n_jobs) are used. Thus for n_jobs = -2, all CPUs but one
are used.
- random_state : integer or numpy.RandomState, optional
- The generator used to initialize the centers. If an integer is
- given, it fixes the seed. Defaults to the global numpy random
- number generator.
+ random_state : int, RandomState instance or None, optional, default: None
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
verbose : int, default 0
Verbosity mode.
@@ -1008,10 +1012,11 @@ def _mini_batch_step(X, x_squared_norms, centers, counts,
the distances of each sample to its closest center.
May not be None when random_reassign is True.
- random_state : integer or numpy.RandomState, optional
- The generator used to initialize the centers. If an integer is
- given, it fixes the seed. Defaults to the global numpy random
- number generator.
+ random_state : int, RandomState instance or None, optional, default: None
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
random_reassign : boolean, optional
If True, centers with very low counts are randomly reassigned
@@ -1247,10 +1252,11 @@ class MiniBatchKMeans(KMeans):
Compute label assignment and inertia for the complete dataset
once the minibatch optimization has converged in fit.
- random_state : integer or numpy.RandomState, optional
- The generator used to initialize the centers. If an integer is
- given, it fixes the seed. Defaults to the global numpy random
- number generator.
+ random_state : int, RandomState instance or None, optional, default: None
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
reassignment_ratio : float, default: 0.01
Control the fraction of the maximum number of counts for a
diff --git a/sklearn/cluster/mean_shift_.py b/sklearn/cluster/mean_shift_.py
index 2d554c05ff..522e034a60 100644
--- a/sklearn/cluster/mean_shift_.py
+++ b/sklearn/cluster/mean_shift_.py
@@ -47,8 +47,11 @@ def estimate_bandwidth(X, quantile=0.3, n_samples=None, random_state=0,
n_samples : int, optional
The number of samples to use. If not given, all samples are used.
- random_state : int or RandomState
- Pseudo-random number generator state used for random sampling.
+ random_state : int, RandomState instance or None, optional (default=None)
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
n_jobs : int, optional (default = 1)
The number of parallel jobs to run for neighbors search.
diff --git a/sklearn/cluster/spectral.py b/sklearn/cluster/spectral.py
index 8b64ca9a6d..b3526622a7 100644
--- a/sklearn/cluster/spectral.py
+++ b/sklearn/cluster/spectral.py
@@ -39,9 +39,11 @@ def discretize(vectors, copy=True, max_svd_restarts=30, n_iter_max=20,
Maximum number of iterations to attempt in rotation and partition
matrix search if machine precision convergence is not reached
- random_state : int seed, RandomState instance, or None (default)
- A pseudo random number generator used for the initialization of the
- of the rotation matrix
+ random_state : int, RandomState instance or None, optional, default: None
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
Returns
-------
@@ -194,10 +196,13 @@ def spectral_clustering(affinity, n_clusters=8, n_components=None,
to be installed. It can be faster on very large, sparse problems,
but may also lead to instabilities
- random_state : int seed, RandomState instance, or None (default)
- A pseudo random number generator used for the initialization
- of the lobpcg eigen vectors decomposition when eigen_solver == 'amg'
- and by the K-Means initialization.
+ random_state : int, RandomState instance or None, optional, default: None
+ A pseudo random number generator used for the initialization of the
+ lobpcg eigen vectors decomposition when eigen_solver == 'amg' and by
+ the K-Means initialization. If int, random_state is the seed used by
+ the random number generator; If RandomState instance, random_state is
+ the random number generator; If None, the random number generator is
+ the RandomState instance used by `np.random`.
n_init : int, optional, default: 10
Number of time the k-means algorithm will be run with different
@@ -326,10 +331,13 @@ class SpectralClustering(BaseEstimator, ClusterMixin):
to be installed. It can be faster on very large, sparse problems,
but may also lead to instabilities
- random_state : int seed, RandomState instance, or None (default)
- A pseudo random number generator used for the initialization
- of the lobpcg eigen vectors decomposition when eigen_solver == 'amg'
- and by the K-Means initialization.
+ random_state : int, RandomState instance or None, optional, default: None
+ A pseudo random number generator used for the initialization of the
+ lobpcg eigen vectors decomposition when eigen_solver == 'amg' and by
+ the K-Means initialization. If int, random_state is the seed used by
+ the random number generator; If RandomState instance, random_state is
+ the random number generator; If None, the random number generator is
+ the RandomState instance used by `np.random`.
n_init : int, optional, default: 10
Number of time the k-means algorithm will be run with different
diff --git a/sklearn/covariance/robust_covariance.py b/sklearn/covariance/robust_covariance.py
index 29cbd52e18..fdf0225dbd 100644
--- a/sklearn/covariance/robust_covariance.py
+++ b/sklearn/covariance/robust_covariance.py
@@ -55,9 +55,11 @@ def c_step(X, n_support, remaining_iterations=30, initial_estimates=None,
verbose : boolean, optional
Verbose mode.
- random_state : integer or numpy.RandomState, optional
- The random generator used. If an integer is given, it fixes the
- seed. Defaults to the global numpy random number generator.
+ random_state : int, RandomState instance or None, optional (default=None)
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
cov_computation_method : callable, default empirical_covariance
The function which will be used to compute the covariance.
@@ -214,9 +216,11 @@ def select_candidates(X, n_support, n_trials, select=1, n_iter=30,
Maximum number of iterations for the c_step procedure.
(2 is enough to be close to the final solution. "Never" exceeds 20).
- random_state : integer or numpy.RandomState, default None
- The random generator used. If an integer is given, it fixes the
- seed. Defaults to the global numpy random number generator.
+ random_state : int, RandomState instance or None, optional (default=None)
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
cov_computation_method : callable, default empirical_covariance
The function which will be used to compute the covariance.
@@ -311,10 +315,11 @@ def fast_mcd(X, support_fraction=None,
value of support_fraction will be used within the algorithm:
`[n_sample + n_features + 1] / 2`.
- random_state : integer or numpy.RandomState, optional
- The generator used to randomly subsample. If an integer is
- given, it fixes the seed. Defaults to the global numpy random
- number generator.
+ random_state : int, RandomState instance or None, optional (default=None)
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
cov_computation_method : callable, default empirical_covariance
The function which will be used to compute the covariance.
@@ -531,9 +536,11 @@ class MinCovDet(EmpiricalCovariance):
value of support_fraction will be used within the algorithm:
[n_sample + n_features + 1] / 2
- random_state : integer or numpy.RandomState, optional
- The random generator used. If an integer is given, it fixes the
- seed. Defaults to the global numpy random number generator.
+ random_state : int, RandomState instance or None, optional (default=None)
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
Attributes
----------
diff --git a/sklearn/cross_validation.py b/sklearn/cross_validation.py
index ff327a25e4..d56845637f 100644
--- a/sklearn/cross_validation.py
+++ b/sklearn/cross_validation.py
@@ -1,4 +1,3 @@
-
"""
The :mod:`sklearn.cross_validation` module includes utilities for cross-
validation and performance evaluation.
@@ -297,9 +296,11 @@ class KFold(_BaseKFold):
shuffle : boolean, optional
Whether to shuffle the data before splitting into batches.
- random_state : None, int or RandomState
- When shuffle=True, pseudo-random number generator state used for
- shuffling. If None, use default numpy RNG for shuffling.
+ random_state : int, RandomState instance or None, optional, default=None
+ If int, random_state is the seed used by the random number
+ generator; If RandomState instance, random_state is the random number
+ generator; If None, the random number generator is the RandomState
+ instance used by `np.random`. Used when ``shuffle`` == True.
Examples
--------
@@ -499,9 +500,11 @@ class StratifiedKFold(_BaseKFold):
Whether to shuffle each stratification of the data before splitting
into batches.
- random_state : None, int or RandomState
- When shuffle=True, pseudo-random number generator state used for
- shuffling. If None, use default numpy RNG for shuffling.
+ random_state : int, RandomState instance or None, optional, default=None
+ If int, random_state is the seed used by the random number
+ generator; If RandomState instance, random_state is the random number
+ generator; If None, the random number generator is the RandomState
+ instance used by `np.random`. Used when ``shuffle`` == True.
Examples
--------
@@ -822,8 +825,11 @@ class ShuffleSplit(BaseShuffleSplit):
int, represents the absolute number of train samples. If None,
the value is automatically set to the complement of the test size.
- random_state : int or RandomState
- Pseudo-random number generator state used for random sampling.
+ random_state : int, RandomState instance or None, optional (default None)
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
Examples
--------
@@ -1031,8 +1037,11 @@ class StratifiedShuffleSplit(BaseShuffleSplit):
int, represents the absolute number of train samples. If None,
the value is automatically set to the complement of the test size.
- random_state : int or RandomState
- Pseudo-random number generator state used for random sampling.
+ random_state : int, RandomState instance or None, optional (default None)
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
Examples
--------
@@ -1225,8 +1234,11 @@ class LabelShuffleSplit(ShuffleSplit):
int, represents the absolute number of train labels. If None,
the value is automatically set to the complement of the test size.
- random_state : int or RandomState
- Pseudo-random number generator state used for random sampling.
+ random_state : int, RandomState instance or None, optional (default None)
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
"""
def __init__(self, labels, n_iter=5, test_size=0.2, train_size=None,
@@ -1889,9 +1901,11 @@ def permutation_test_score(estimator, X, y, cv=None,
Labels constrain the permutation among groups of samples with
a same label.
- random_state : RandomState or an int seed (0 by default)
- A random number generator instance to define the state of the
- random permutations generator.
+ random_state : int, RandomState instance or None, optional (default=0)
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
verbose : integer, optional
The verbosity level.
@@ -1977,8 +1991,11 @@ def train_test_split(*arrays, **options):
int, represents the absolute number of train samples. If None,
the value is automatically set to the complement of the test size.
- random_state : int or RandomState
- Pseudo-random number generator state used for random sampling.
+ random_state : int, RandomState instance or None, optional (default=None)
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
stratify : array-like or None (default is None)
If not None, data is split in a stratified fashion, using this as
diff --git a/sklearn/datasets/olivetti_faces.py b/sklearn/datasets/olivetti_faces.py
index 7dfd4dec16..ac80d49e93 100644
--- a/sklearn/datasets/olivetti_faces.py
+++ b/sklearn/datasets/olivetti_faces.py
@@ -71,9 +71,11 @@ def fetch_olivetti_faces(data_home=None, shuffle=False, random_state=0,
If False, raise a IOError if the data is not locally available
instead of trying to download the data from the source site.
- random_state : optional, integer or RandomState object
- The seed or the random number generator used to shuffle the
- data.
+ random_state : int, RandomState instance or None, optional (default=0)
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
Returns
-------
diff --git a/sklearn/datasets/samples_generator.py b/sklearn/datasets/samples_generator.py
index e7f61b3227..7a4543aa20 100644
--- a/sklearn/datasets/samples_generator.py
+++ b/sklearn/datasets/samples_generator.py
@@ -1059,8 +1059,11 @@ def make_sparse_coded_signal(n_samples, n_components, n_features,
n_nonzero_coefs : int
number of active (non-zero) coefficients in each sample
- random_state : int or RandomState instance, optional (default=None)
- seed used by the pseudo random number generator
+ random_state : int, RandomState instance or None, optional (default=None)
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
Returns
-------
diff --git a/sklearn/decomposition/dict_learning.py b/sklearn/decomposition/dict_learning.py
index baf79544dd..154987a627 100644
--- a/sklearn/decomposition/dict_learning.py
+++ b/sklearn/decomposition/dict_learning.py
@@ -328,8 +328,11 @@ def _update_dict(dictionary, Y, code, verbose=False, return_r2=False,
Whether to compute and return the residual sum of squares corresponding
to the computed solution.
- random_state : int or RandomState
- Pseudo number generator state used for random sampling.
+ random_state : int, RandomState instance or None, optional (default=None)
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
Returns
-------
@@ -434,8 +437,11 @@ def dict_learning(X, n_components, alpha, max_iter=100, tol=1e-8,
verbose :
Degree of output the procedure will print.
- random_state : int or RandomState
- Pseudo number generator state used for random sampling.
+ random_state : int, RandomState instance or None, optional (default=None)
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
return_n_iter : bool
Whether or not to return the number of iterations.
@@ -616,8 +622,11 @@ def dict_learning_online(X, n_components=2, alpha=1, n_iter=100,
Number of previous iterations completed on the dictionary used for
initialization.
- random_state : int or RandomState
- Pseudo number generator state used for random sampling.
+ random_state : int, RandomState instance or None, optional (default=None)
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
return_inner_stats : boolean, optional
Return the inner statistics A (dictionary covariance) and B
@@ -1000,8 +1009,11 @@ class DictionaryLearning(BaseEstimator, SparseCodingMixin):
verbose :
degree of verbosity of the printed output
- random_state : int or RandomState
- Pseudo number generator state used for random sampling.
+ random_state : int, RandomState instance or None, optional (default=None)
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
Attributes
----------
@@ -1160,8 +1172,11 @@ class MiniBatchDictionaryLearning(BaseEstimator, SparseCodingMixin):
shuffle : bool,
whether to shuffle the samples before forming batches
- random_state : int or RandomState
- Pseudo number generator state used for random sampling.
+ random_state : int, RandomState instance or None, optional (default=None)
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
Attributes
----------
diff --git a/sklearn/decomposition/factor_analysis.py b/sklearn/decomposition/factor_analysis.py
index 16e198164a..3326ac197b 100644
--- a/sklearn/decomposition/factor_analysis.py
+++ b/sklearn/decomposition/factor_analysis.py
@@ -88,9 +88,11 @@ class FactorAnalysis(BaseEstimator, TransformerMixin):
Number of iterations for the power method. 3 by default. Only used
if ``svd_method`` equals 'randomized'
- random_state : int or RandomState
- Pseudo number generator state used for random sampling. Only used
- if ``svd_method`` equals 'randomized'
+ random_state : int, RandomState instance or None, optional (default=0)
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`. Only used when ``svd_method`` equals 'randomized'.
Attributes
----------
diff --git a/sklearn/decomposition/fastica_.py b/sklearn/decomposition/fastica_.py
index fbbbbec1b7..3cca0b7d6e 100644
--- a/sklearn/decomposition/fastica_.py
+++ b/sklearn/decomposition/fastica_.py
@@ -199,8 +199,11 @@ def fastica(X, n_components=None, algorithm="parallel", whiten=True,
Initial un-mixing array of dimension (n.comp,n.comp).
If None (default) then an array of normal r.v.'s is used.
- random_state : int or RandomState
- Pseudo number generator state used for random sampling.
+ random_state : int, RandomState instance or None, optional (default=None)
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
return_X_mean : bool, optional
If True, X_mean is returned too.
@@ -415,8 +418,11 @@ class FastICA(BaseEstimator, TransformerMixin):
w_init : None of an (n_components, n_components) ndarray
The mixing matrix to be used to initialize the algorithm.
- random_state : int or RandomState
- Pseudo number generator state used for random sampling.
+ random_state : int, RandomState instance or None, optional (default=None)
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
Attributes
----------
diff --git a/sklearn/decomposition/kernel_pca.py b/sklearn/decomposition/kernel_pca.py
index 1fb6b55f43..2bd9a5bbdd 100644
--- a/sklearn/decomposition/kernel_pca.py
+++ b/sklearn/decomposition/kernel_pca.py
@@ -74,9 +74,11 @@ class KernelPCA(BaseEstimator, TransformerMixin):
When n_components is None, this parameter is ignored and components
with zero eigenvalues are removed regardless.
- random_state : int seed, RandomState instance, or None, default=None
- A pseudo random number generator used for the initialization of the
- residuals when eigen_solver == 'arpack'.
+ random_state : int, RandomState instance or None, optional (default=None)
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`. Used when ``eigen_solver`` == 'arpack'.
.. versionadded:: 0.18
diff --git a/sklearn/decomposition/nmf.py b/sklearn/decomposition/nmf.py
index 63026e3ad4..522bf150aa 100644
--- a/sklearn/decomposition/nmf.py
+++ b/sklearn/decomposition/nmf.py
@@ -268,9 +268,11 @@ def _initialize_nmf(X, n_components, init=None, eps=1e-6,
eps : float
Truncate all values less then this in output to zero.
- random_state : int seed, RandomState instance, or None (default)
- Random number generator seed control, used in 'nndsvdar' and
- 'random' modes.
+ random_state : int, RandomState instance or None, optional, default: None
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`. Used when ``random`` == 'nndsvdar' or 'random'.
Returns
-------
@@ -445,8 +447,11 @@ def _fit_coordinate_descent(X, W, H, tol=1e-4, max_iter=200, l1_reg_W=0,
shuffle : boolean, default: False
If true, randomize the order of coordinates in the CD solver.
- random_state : integer seed, RandomState instance, or None (default)
- Random number generator seed control.
+ random_state : int, RandomState instance or None, optional, default: None
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
Returns
-------
@@ -910,8 +915,11 @@ def non_negative_factorization(X, W=None, H=None, n_components=None,
Select whether the regularization affects the components (H), the
transformation (W), both or none of them.
- random_state : integer seed, RandomState instance, or None (default)
- Random number generator seed control.
+ random_state : int, RandomState instance or None, optional, default: None
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
verbose : integer, default: 0
The verbosity level.
@@ -1097,8 +1105,11 @@ class NMF(BaseEstimator, TransformerMixin):
max_iter : integer, default: 200
Maximum number of iterations before timing out.
- random_state : integer seed, RandomState instance, or None (default)
- Random number generator seed control.
+ random_state : int, RandomState instance or None, optional, default: None
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
alpha : double, default: 0.
Constant that multiplies the regularization terms. Set it to zero to
diff --git a/sklearn/decomposition/online_lda.py b/sklearn/decomposition/online_lda.py
index 8e0c5bfe6b..d24743b3e7 100644
--- a/sklearn/decomposition/online_lda.py
+++ b/sklearn/decomposition/online_lda.py
@@ -219,8 +219,11 @@ class LatentDirichletAllocation(BaseEstimator, TransformerMixin):
verbose : int, optional (default=0)
Verbosity level.
- random_state : int or RandomState instance or None, optional (default=None)
- Pseudo-random number generator seed control.
+ random_state : int, RandomState instance or None, optional (default=None)
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
Attributes
----------
diff --git a/sklearn/decomposition/pca.py b/sklearn/decomposition/pca.py
index f7cb01a422..eb11d9b032 100644
--- a/sklearn/decomposition/pca.py
+++ b/sklearn/decomposition/pca.py
@@ -183,9 +183,11 @@ class PCA(_BasePCA):
.. versionadded:: 0.18.0
- random_state : int or RandomState instance or None (default None)
- Pseudo Random Number generator seed control. If None, use the
- numpy.random singleton. Used by svd_solver == 'arpack' or 'randomized'.
+ random_state : int, RandomState instance or None, optional (default None)
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`. Used when ``svd_solver`` == 'arpack' or 'randomized'.
.. versionadded:: 0.18.0
@@ -601,9 +603,11 @@ class RandomizedPCA(BaseEstimator, TransformerMixin):
improve the predictive accuracy of the downstream estimators by
making their data respect some hard-wired assumptions.
- random_state : int or RandomState instance or None (default)
- Pseudo Random Number generator seed control. If None, use the
- numpy.random singleton.
+ random_state : int, RandomState instance or None, optional, default=None
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
Attributes
----------
diff --git a/sklearn/decomposition/sparse_pca.py b/sklearn/decomposition/sparse_pca.py
index e6fde97ccb..23d1163fdc 100644
--- a/sklearn/decomposition/sparse_pca.py
+++ b/sklearn/decomposition/sparse_pca.py
@@ -60,8 +60,11 @@ class SparsePCA(BaseEstimator, TransformerMixin):
verbose :
Degree of verbosity of the printed output.
- random_state : int or RandomState
- Pseudo number generator state used for random sampling.
+ random_state : int, RandomState instance or None, optional (default=None)
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
Attributes
----------
@@ -228,8 +231,11 @@ class MiniBatchSparsePCA(SparsePCA):
Lasso solution (linear_model.Lasso). Lars will be faster if
the estimated components are sparse.
- random_state : int or RandomState
- Pseudo number generator state used for random sampling.
+ random_state : int, RandomState instance or None, optional (default=None)
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
Attributes
----------
diff --git a/sklearn/decomposition/truncated_svd.py b/sklearn/decomposition/truncated_svd.py
index 5d029d1205..7ab20926f9 100644
--- a/sklearn/decomposition/truncated_svd.py
+++ b/sklearn/decomposition/truncated_svd.py
@@ -59,9 +59,11 @@ class TruncatedSVD(BaseEstimator, TransformerMixin):
The default is larger than the default in `randomized_svd` to handle
sparse matrices that may have large slowly decaying spectrum.
- random_state : int or RandomState, optional
- (Seed for) pseudo-random number generator. If not given, the
- numpy.random singleton is used.
+ random_state : int, RandomState instance or None, optional, default = None
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
tol : float, optional
Tolerance for ARPACK. 0 means machine precision. Ignored by randomized
diff --git a/sklearn/dummy.py b/sklearn/dummy.py
index 84d42e7177..90a43791c8 100644
--- a/sklearn/dummy.py
+++ b/sklearn/dummy.py
@@ -47,8 +47,11 @@ class DummyClassifier(BaseEstimator, ClassifierMixin):
Dummy Classifier now supports prior fitting strategy using
parameter *prior*.
- random_state : int seed, RandomState instance, or None (default)
- The seed of the pseudo random number generator to use.
+ random_state : int, RandomState instance or None, optional, default=None
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
constant : int or str or array of shape = [n_outputs]
The explicit constant as predicted by the "constant" strategy. This
diff --git a/sklearn/ensemble/base.py b/sklearn/ensemble/base.py
index 165124d624..5e9d6e2e1f 100644
--- a/sklearn/ensemble/base.py
+++ b/sklearn/ensemble/base.py
@@ -29,8 +29,11 @@ def _set_random_states(estimator, random_state=None):
Estimator with potential randomness managed by random_state
parameters.
- random_state : numpy.RandomState or int, optional
- Random state used to generate integer values.
+ random_state : int, RandomState instance or None, optional (default=None)
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
Notes
-----
diff --git a/sklearn/ensemble/gradient_boosting.py b/sklearn/ensemble/gradient_boosting.py
index f5eb1001b2..2c18d338dc 100644
--- a/sklearn/ensemble/gradient_boosting.py
+++ b/sklearn/ensemble/gradient_boosting.py
@@ -1767,8 +1767,7 @@ class GradientBoostingRegressor(BaseGradientBoosting, RegressorMixin):
warm_start : bool, default: False
When set to ``True``, reuse the solution of the previous call to fit
and add more estimators to the ensemble, otherwise, just erase the
- p
-revious solution.
+ previous solution.
random_state : int, RandomState instance or None, optional (default=None)
If int, random_state is the seed used by the random number generator;
diff --git a/sklearn/feature_extraction/image.py b/sklearn/feature_extraction/image.py
index 694c624f11..708424cb3f 100644
--- a/sklearn/feature_extraction/image.py
+++ b/sklearn/feature_extraction/image.py
@@ -319,9 +319,12 @@ def extract_patches_2d(image, patch_size, max_patches=None, random_state=None):
between 0 and 1, it is taken to be a proportion of the total number
of patches.
- random_state : int or RandomState
+ random_state : int, RandomState instance or None, optional (default=None)
Pseudo number generator state used for random sampling to use if
- `max_patches` is not None.
+ `max_patches` is not None. If int, random_state is the seed used by
+ the random number generator; If RandomState instance, random_state is
+ the random number generator; If None, the random number generator is
+ the RandomState instance used by `np.random`.
Returns
-------
@@ -450,8 +453,11 @@ class PatchExtractor(BaseEstimator):
float in (0, 1), it is taken to mean a proportion of the total number
of patches.
- random_state : int or RandomState
- Pseudo number generator state used for random sampling.
+ random_state : int, RandomState instance or None, optional (default=None)
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
"""
def __init__(self, patch_size=None, max_patches=None, random_state=None):
diff --git a/sklearn/feature_selection/mutual_info_.py b/sklearn/feature_selection/mutual_info_.py
index b72e884704..0637f784c5 100644
--- a/sklearn/feature_selection/mutual_info_.py
+++ b/sklearn/feature_selection/mutual_info_.py
@@ -224,9 +224,13 @@ def _estimate_mi(X, y, discrete_features='auto', discrete_target=False,
Whether to make a copy of the given data. If set to False, the initial
data will be overwritten.
- random_state : int seed, RandomState instance or None, default None
+ random_state : int, RandomState instance or None, optional, default None
The seed of the pseudo random number generator for adding small noise
- to continuous variables in order to remove repeated values.
+ to continuous variables in order to remove repeated values. If int,
+ random_state is the seed used by the random number generator; If
+ RandomState instance, random_state is the random number generator; If
+ None, the random number generator is the RandomState instance used by
+ `np.random`.
Returns
-------
@@ -327,9 +331,13 @@ def mutual_info_regression(X, y, discrete_features='auto', n_neighbors=3,
Whether to make a copy of the given data. If set to False, the initial
data will be overwritten.
- random_state : int seed, RandomState instance or None, default None
+ random_state : int, RandomState instance or None, optional, default None
The seed of the pseudo random number generator for adding small noise
to continuous variables in order to remove repeated values.
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
Returns
-------
@@ -402,9 +410,13 @@ def mutual_info_classif(X, y, discrete_features='auto', n_neighbors=3,
Whether to make a copy of the given data. If set to False, the initial
data will be overwritten.
- random_state : int seed, RandomState instance or None, default None
+ random_state : int, RandomState instance or None, optional, default None
The seed of the pseudo random number generator for adding small noise
- to continuous variables in order to remove repeated values.
+ to continuous variables in order to remove repeated values. If int,
+ random_state is the seed used by the random number generator; If
+ RandomState instance, random_state is the random number generator; If
+ None, the random number generator is the RandomState instance used by
+ `np.random`.
Returns
-------
diff --git a/sklearn/gaussian_process/gaussian_process.py b/sklearn/gaussian_process/gaussian_process.py
index 0d1b6d4fff..7adac552a5 100644
--- a/sklearn/gaussian_process/gaussian_process.py
+++ b/sklearn/gaussian_process/gaussian_process.py
@@ -169,11 +169,12 @@ class GaussianProcess(BaseEstimator, RegressorMixin):
exponential distribution (log-uniform on [thetaL, thetaU]).
Default does not use random starting point (random_start = 1).
- random_state : integer or numpy.RandomState, optional
+ random_state : int, RandomState instance or None, optional (default=None)
The generator used to shuffle the sequence of coordinates of theta in
- the Welch optimizer. If an integer is given, it fixes the seed.
- Defaults to the global numpy random number generator.
-
+ the Welch optimizer. If int, random_state is the seed used by the
+ random number generator; If RandomState instance, random_state is the
+ random number generator; If None, the random number generator is the
+ RandomState instance used by `np.random`.
Attributes
----------
diff --git a/sklearn/gaussian_process/gpc.py b/sklearn/gaussian_process/gpc.py
index bbb1feda98..6f491b376e 100644
--- a/sklearn/gaussian_process/gpc.py
+++ b/sklearn/gaussian_process/gpc.py
@@ -106,10 +106,11 @@ class _BinaryGaussianProcessClassifierLaplace(BaseEstimator):
which might cause predictions to change if the data is modified
externally.
- random_state : integer or numpy.RandomState, optional
- The generator used to initialize the centers. If an integer is
- given, it fixes the seed. Defaults to the global numpy random
- number generator.
+ random_state : int, RandomState instance or None, optional (default: None)
+ The generator used to initialize the centers. If int, random_state is
+ the seed used by the random number generator; If RandomState instance,
+ random_state is the random number generator; If None, the random number
+ generator is the RandomState instance used by `np.random`.
Attributes
----------
@@ -510,10 +511,12 @@ class GaussianProcessClassifier(BaseEstimator, ClassifierMixin):
which might cause predictions to change if the data is modified
externally.
- random_state : integer or numpy.RandomState, optional
- The generator used to initialize the centers. If an integer is
- given, it fixes the seed. Defaults to the global numpy random
- number generator.
+ random_state : int, RandomState instance or None, optional (default: None)
+ The generator used to initialize the centers.
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
multi_class : string, default : "one_vs_rest"
Specifies how multi-class classification problems are handled.
diff --git a/sklearn/gaussian_process/gpr.py b/sklearn/gaussian_process/gpr.py
index cbf65a8430..4ee8e556c7 100644
--- a/sklearn/gaussian_process/gpr.py
+++ b/sklearn/gaussian_process/gpr.py
@@ -103,10 +103,11 @@ class GaussianProcessRegressor(BaseEstimator, RegressorMixin):
which might cause predictions to change if the data is modified
externally.
- random_state : integer or numpy.RandomState, optional
- The generator used to initialize the centers. If an integer is
- given, it fixes the seed. Defaults to the global numpy random
- number generator.
+ random_state : int, RandomState instance or None, optional (default: None)
+ The generator used to initialize the centers. If int, random_state is
+ the seed used by the random number generator; If RandomState instance,
+ random_state is the random number generator; If None, the random number
+ generator is the RandomState instance used by `np.random`.
Attributes
----------
@@ -336,8 +337,11 @@ class GaussianProcessRegressor(BaseEstimator, RegressorMixin):
n_samples : int, default: 1
The number of samples drawn from the Gaussian process
- random_state : RandomState or an int seed (0 by default)
- A random number generator instance
+ random_state : int, RandomState instance or None, optional (default=0)
+ If int, random_state is the seed used by the random number
+ generator; If RandomState instance, random_state is the
+ random number generator; If None, the random number
+ generator is the RandomState instance used by `np.random`.
Returns
-------
diff --git a/sklearn/grid_search.py b/sklearn/grid_search.py
index 5bdff14f83..2f432362e3 100644
--- a/sklearn/grid_search.py
+++ b/sklearn/grid_search.py
@@ -200,9 +200,13 @@ class ParameterSampler(object):
n_iter : integer
Number of parameter settings that are produced.
- random_state : int or RandomState
+ random_state : int, RandomState instance or None, optional (default=None)
Pseudo random number generator state used for random uniform sampling
from lists of possible values instead of scipy.stats distributions.
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
Returns
-------
@@ -954,9 +958,13 @@ class RandomizedSearchCV(BaseSearchCV):
verbose : integer
Controls the verbosity: the higher, the more messages.
- random_state : int or RandomState
+ random_state : int, RandomState instance or None, optional, default=None
Pseudo random number generator state used for random uniform sampling
from lists of possible values instead of scipy.stats distributions.
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
error_score : 'raise' (default) or numeric
Value to assign to the score if an error occurs in estimator fitting.
diff --git a/sklearn/kernel_approximation.py b/sklearn/kernel_approximation.py
index a47016e448..3fef755dfd 100644
--- a/sklearn/kernel_approximation.py
+++ b/sklearn/kernel_approximation.py
@@ -38,9 +38,11 @@ class RBFSampler(BaseEstimator, TransformerMixin):
Number of Monte Carlo samples per original feature.
Equals the dimensionality of the computed feature space.
- random_state : {int, RandomState}, optional
+ random_state : int, RandomState instance or None, optional (default=None)
If int, random_state is the seed used by the random number generator;
- if RandomState instance, random_state is the random number generator.
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
Notes
-----
@@ -124,9 +126,11 @@ class SkewedChi2Sampler(BaseEstimator, TransformerMixin):
number of Monte Carlo samples per original feature.
Equals the dimensionality of the computed feature space.
- random_state : {int, RandomState}, optional
+ random_state : int, RandomState instance or None, optional (default=None)
If int, random_state is the seed used by the random number generator;
- if RandomState instance, random_state is the random number generator.
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
References
----------
@@ -394,10 +398,11 @@ class Nystroem(BaseEstimator, TransformerMixin):
Additional parameters (keyword arguments) for kernel function passed
as callable object.
- random_state : {int, RandomState}, optional
+ random_state : int, RandomState instance or None, optional (default=None)
If int, random_state is the seed used by the random number generator;
- if RandomState instance, random_state is the random number generator.
-
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
Attributes
----------
diff --git a/sklearn/linear_model/coordinate_descent.py b/sklearn/linear_model/coordinate_descent.py
index 95cafb29e7..a2eb3be475 100644
--- a/sklearn/linear_model/coordinate_descent.py
+++ b/sklearn/linear_model/coordinate_descent.py
@@ -582,9 +582,12 @@ class ElasticNet(LinearModel, RegressorMixin):
(setting to 'random') often leads to significantly faster convergence
especially when tol is higher than 1e-4.
- random_state : int, RandomState instance, or None (default)
- The seed of the pseudo random number generator that selects
- a random feature to update. Useful only when selection is set to
+ random_state : int, RandomState instance or None, optional, default None
+ The seed of the pseudo random number generator that selects a random
+ feature to update. If int, random_state is the seed used by the random
+ number generator; If RandomState instance, random_state is the random
+ number generator; If None, the random number generator is the
+ RandomState instance used by `np.random`. Used when ``selection`` ==
'random'.
Attributes
@@ -829,9 +832,12 @@ class Lasso(ElasticNet):
(setting to 'random') often leads to significantly faster convergence
especially when tol is higher than 1e-4.
- random_state : int, RandomState instance, or None (default)
- The seed of the pseudo random number generator that selects
- a random feature to update. Useful only when selection is set to
+ random_state : int, RandomState instance or None, optional, default None
+ The seed of the pseudo random number generator that selects a random
+ feature to update. If int, random_state is the seed used by the random
+ number generator; If RandomState instance, random_state is the random
+ number generator; If None, the random number generator is the
+ RandomState instance used by `np.random`. Used when ``selection`` ==
'random'.
Attributes
@@ -1266,9 +1272,12 @@ class LassoCV(LinearModelCV, RegressorMixin):
(setting to 'random') often leads to significantly faster convergence
especially when tol is higher than 1e-4.
- random_state : int, RandomState instance, or None (default)
- The seed of the pseudo random number generator that selects
- a random feature to update. Useful only when selection is set to
+ random_state : int, RandomState instance or None, optional, default None
+ The seed of the pseudo random number generator that selects a random
+ feature to update. If int, random_state is the seed used by the random
+ number generator; If RandomState instance, random_state is the random
+ number generator; If None, the random number generator is the
+ RandomState instance used by `np.random`. Used when ``selection`` ==
'random'.
fit_intercept : boolean, default True
@@ -1418,9 +1427,12 @@ class ElasticNetCV(LinearModelCV, RegressorMixin):
(setting to 'random') often leads to significantly faster convergence
especially when tol is higher than 1e-4.
- random_state : int, RandomState instance, or None (default)
- The seed of the pseudo random number generator that selects
- a random feature to update. Useful only when selection is set to
+ random_state : int, RandomState instance or None, optional, default None
+ The seed of the pseudo random number generator that selects a random
+ feature to update. If int, random_state is the seed used by the random
+ number generator; If RandomState instance, random_state is the random
+ number generator; If None, the random number generator is the
+ RandomState instance used by `np.random`. Used when ``selection`` ==
'random'.
fit_intercept : boolean
@@ -1588,9 +1600,12 @@ class MultiTaskElasticNet(Lasso):
(setting to 'random') often leads to significantly faster convergence
especially when tol is higher than 1e-4.
- random_state : int, RandomState instance, or None (default)
- The seed of the pseudo random number generator that selects
- a random feature to update. Useful only when selection is set to
+ random_state : int, RandomState instance or None, optional, default None
+ The seed of the pseudo random number generator that selects a random
+ feature to update. If int, random_state is the seed used by the random
+ number generator; If RandomState instance, random_state is the random
+ number generator; If None, the random number generator is the
+ RandomState instance used by `np.random`. Used when ``selection`` ==
'random'.
Attributes
@@ -1772,9 +1787,12 @@ class MultiTaskLasso(MultiTaskElasticNet):
(setting to 'random') often leads to significantly faster convergence
especially when tol is higher than 1e-4
- random_state : int, RandomState instance, or None (default)
- The seed of the pseudo random number generator that selects
- a random feature to update. Useful only when selection is set to
+ random_state : int, RandomState instance or None, optional, default None
+ The seed of the pseudo random number generator that selects a random
+ feature to update. If int, random_state is the seed used by the random
+ number generator; If RandomState instance, random_state is the random
+ number generator; If None, the random number generator is the
+ RandomState instance used by `np.random`. Used when ``selection`` ==
'random'.
Attributes
@@ -1925,9 +1943,12 @@ class MultiTaskElasticNetCV(LinearModelCV, RegressorMixin):
(setting to 'random') often leads to significantly faster convergence
especially when tol is higher than 1e-4.
- random_state : int, RandomState instance, or None (default)
- The seed of the pseudo random number generator that selects
- a random feature to update. Useful only when selection is set to
+ random_state : int, RandomState instance or None, optional, default None
+ The seed of the pseudo random number generator that selects a random
+ feature to update. If int, random_state is the seed used by the random
+ number generator; If RandomState instance, random_state is the random
+ number generator; If None, the random number generator is the
+ RandomState instance used by `np.random`. Used when ``selection`` ==
'random'.
Attributes
@@ -2089,10 +2110,13 @@ class MultiTaskLassoCV(LinearModelCV, RegressorMixin):
(setting to 'random') often leads to significantly faster convergence
especially when tol is higher than 1e-4.
- random_state : int, RandomState instance, or None (default)
- The seed of the pseudo random number generator that selects
- a random feature to update. Useful only when selection is set to
- 'random'.
+ random_state : int, RandomState instance or None, optional, default None
+ The seed of the pseudo random number generator that selects a random
+ feature to update. If int, random_state is the seed used by the random
+ number generator; If RandomState instance, random_state is the random
+ number generator; If None, the random number generator is the
+ RandomState instance used by `np.random`. Used when ``selection`` ==
+ 'random'/
Attributes
----------
diff --git a/sklearn/linear_model/logistic.py b/sklearn/linear_model/logistic.py
index 196d7f697d..fa7bc7f32e 100644
--- a/sklearn/linear_model/logistic.py
+++ b/sklearn/linear_model/logistic.py
@@ -543,9 +543,13 @@ def logistic_regression_path(X, y, pos_class=None, Cs=10, fit_intercept=True,
the entire probability distribution. Works only for the 'lbfgs' and
'newton-cg' solvers.
- random_state : int seed, RandomState instance, or None (default)
- The seed of the pseudo random number generator to use when
- shuffling the data. Used only in solvers 'sag' and 'liblinear'.
+ random_state : int, RandomState instance or None, optional, default None
+ The seed of the pseudo random number generator to use when shuffling
+ the data. If int, random_state is the seed used by the random number
+ generator; If RandomState instance, random_state is the random number
+ generator; If None, the random number generator is the RandomState
+ instance used by `np.random`. Used when ``solver`` == 'sag' or
+ 'liblinear'.
check_input : bool, default True
If False, the input arrays X and y will not be checked.
@@ -860,9 +864,13 @@ def _log_reg_scoring_path(X, y, train, test, pos_class=None, Cs=10,
the entire probability distribution. Does not work for
liblinear solver.
- random_state : int seed, RandomState instance, or None (default)
- The seed of the pseudo random number generator to use when
- shuffling the data. Used only in solvers 'sag' and 'liblinear'.
+ random_state : int, RandomState instance or None, optional, default None
+ The seed of the pseudo random number generator to use when shuffling
+ the data. If int, random_state is the seed used by the random number
+ generator; If RandomState instance, random_state is the random number
+ generator; If None, the random number generator is the RandomState
+ instance used by `np.random`. Used when ``solver`` == 'sag' and
+ 'liblinear'.
max_squared_sum : float, default None
Maximum squared sum of X over samples. Used only in SAG solver.
@@ -1024,9 +1032,13 @@ class LogisticRegression(BaseEstimator, LinearClassifierMixin,
Useful only for the newton-cg, sag and lbfgs solvers.
Maximum number of iterations taken for the solvers to converge.
- random_state : int seed, RandomState instance, default: None
- The seed of the pseudo random number generator to use when
- shuffling the data. Used only in solvers 'sag' and 'liblinear'.
+ random_state : int, RandomState instance or None, optional, default: None
+ The seed of the pseudo random number generator to use when shuffling
+ the data. If int, random_state is the seed used by the random number
+ generator; If RandomState instance, random_state is the random number
+ generator; If None, the random number generator is the RandomState
+ instance used by `np.random`. Used when ``solver`` == 'sag' or
+ 'liblinear'.
solver : {'newton-cg', 'lbfgs', 'liblinear', 'sag', 'saga'},
default: 'liblinear'
@@ -1470,9 +1482,11 @@ class LogisticRegressionCV(LogisticRegression, BaseEstimator,
To lessen the effect of regularization on synthetic feature weight
(and therefore on the intercept) intercept_scaling has to be increased.
- random_state : int seed, RandomState instance, or None (default)
- The seed of the pseudo random number generator to use when
- shuffling the data.
+ random_state : int, RandomState instance or None, optional, default None
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
Attributes
----------
diff --git a/sklearn/linear_model/passive_aggressive.py b/sklearn/linear_model/passive_aggressive.py
index 376ca92e93..941f398bd6 100644
--- a/sklearn/linear_model/passive_aggressive.py
+++ b/sklearn/linear_model/passive_aggressive.py
@@ -28,9 +28,12 @@ class PassiveAggressiveClassifier(BaseSGDClassifier):
shuffle : bool, default=True
Whether or not the training data should be shuffled after each epoch.
- random_state : int seed, RandomState instance, or None (default)
- The seed of the pseudo random number generator to use when
- shuffling the data.
+ random_state : int, RandomState instance or None, optional, default=None
+ The seed of the pseudo random number generator to use when shuffling
+ the data. If int, random_state is the seed used by the random number
+ generator; If RandomState instance, random_state is the random number
+ generator; If None, the random number generator is the RandomState
+ instance used by `np.random`.
verbose : integer, optional
The verbosity level
@@ -204,9 +207,12 @@ class PassiveAggressiveRegressor(BaseSGDRegressor):
shuffle : bool, default=True
Whether or not the training data should be shuffled after each epoch.
- random_state : int seed, RandomState instance, or None (default)
- The seed of the pseudo random number generator to use when
- shuffling the data.
+ random_state : int, RandomState instance or None, optional, default=None
+ The seed of the pseudo random number generator to use when shuffling
+ the data. If int, random_state is the seed used by the random number
+ generator; If RandomState instance, random_state is the random number
+ generator; If None, the random number generator is the RandomState
+ instance used by `np.random`.
verbose : integer, optional
The verbosity level
diff --git a/sklearn/linear_model/perceptron.py b/sklearn/linear_model/perceptron.py
index d597181765..0b11049fc3 100644
--- a/sklearn/linear_model/perceptron.py
+++ b/sklearn/linear_model/perceptron.py
@@ -30,9 +30,12 @@ class Perceptron(BaseSGDClassifier):
shuffle : bool, optional, default True
Whether or not the training data should be shuffled after each epoch.
- random_state : int seed, RandomState instance, or None (default)
- The seed of the pseudo random number generator to use when
- shuffling the data.
+ random_state : int, RandomState instance or None, optional, default None
+ The seed of the pseudo random number generator to use when shuffling
+ the data. If int, random_state is the seed used by the random number
+ generator; If RandomState instance, random_state is the random number
+ generator; If None, the random number generator is the RandomState
+ instance used by `np.random`.
verbose : integer, optional
The verbosity level
diff --git a/sklearn/linear_model/randomized_l1.py b/sklearn/linear_model/randomized_l1.py
index 8f8f5c12ef..6ebf95d253 100644
--- a/sklearn/linear_model/randomized_l1.py
+++ b/sklearn/linear_model/randomized_l1.py
@@ -575,8 +575,11 @@ def lasso_stability_path(X, y, scaling=0.5, random_state=None,
The alpha parameter in the stability selection article used to
randomly scale the features. Should be between 0 and 1.
- random_state : integer or numpy.random.RandomState, optional
- The generator used to randomize the design.
+ random_state : int, RandomState instance or None, optional, default=None
+ The generator used to randomize the design. If int, random_state is
+ the seed used by the random number generator; If RandomState instance,
+ random_state is the random number generator; If None, the random number
+ generator is the RandomState instance used by `np.random`.
n_resampling : int, optional, default=200
Number of randomized models.
diff --git a/sklearn/linear_model/ransac.py b/sklearn/linear_model/ransac.py
index e4e391cb10..ec23d9a16d 100644
--- a/sklearn/linear_model/ransac.py
+++ b/sklearn/linear_model/ransac.py
@@ -158,10 +158,11 @@ class RANSACRegressor(BaseEstimator, MetaEstimatorMixin, RegressorMixin):
If the loss on a sample is greater than the ``residual_threshold``, then
this sample is classified as an outlier.
- random_state : integer or numpy.RandomState, optional
- The generator used to initialize the centers. If an integer is
- given, it fixes the seed. Defaults to the global numpy random
- number generator.
+ random_state : int, RandomState instance or None, optional, default None
+ The generator used to initialize the centers. If int, random_state is
+ the seed used by the random number generator; If RandomState instance,
+ random_state is the random number generator; If None, the random number
+ generator is the RandomState instance used by `np.random`.
Attributes
----------
diff --git a/sklearn/linear_model/ridge.py b/sklearn/linear_model/ridge.py
index 9715e2aaef..398016b886 100644
--- a/sklearn/linear_model/ridge.py
+++ b/sklearn/linear_model/ridge.py
@@ -275,9 +275,12 @@ def ridge_regression(X, y, alpha, sample_weight=None, solver='auto',
Verbosity level. Setting verbose > 0 will display additional
information depending on the solver used.
- random_state : int seed, RandomState instance, or None (default)
- The seed of the pseudo random number generator to use when
- shuffling the data. Used only in 'sag' solver.
+ random_state : int, RandomState instance or None, optional, default None
+ The seed of the pseudo random number generator to use when shuffling
+ the data. If int, random_state is the seed used by the random number
+ generator; If RandomState instance, random_state is the random number
+ generator; If None, the random number generator is the RandomState
+ instance used by `np.random`. Used when ``solver`` == 'sag'.
return_n_iter : boolean, default False
If True, the method also returns `n_iter`, the actual number of
@@ -580,9 +583,12 @@ class Ridge(_BaseRidge, RegressorMixin):
tol : float
Precision of the solution.
- random_state : int seed, RandomState instance, or None (default)
- The seed of the pseudo random number generator to use when
- shuffling the data. Used only in 'sag' solver.
+ random_state : int, RandomState instance or None, optional, default None
+ The seed of the pseudo random number generator to use when shuffling
+ the data. If int, random_state is the seed used by the random number
+ generator; If RandomState instance, random_state is the random number
+ generator; If None, the random number generator is the RandomState
+ instance used by `np.random`. Used when ``solver`` == 'sag'.
.. versionadded:: 0.17
*random_state* to support Stochastic Average Gradient.
@@ -728,9 +734,12 @@ class RidgeClassifier(LinearClassifierMixin, _BaseRidge):
tol : float
Precision of the solution.
- random_state : int seed, RandomState instance, or None (default)
- The seed of the pseudo random number generator to use when
- shuffling the data. Used in 'sag' solver.
+ random_state : int, RandomState instance or None, optional, default None
+ The seed of the pseudo random number generator to use when shuffling
+ the data. If int, random_state is the seed used by the random number
+ generator; If RandomState instance, random_state is the random number
+ generator; If None, the random number generator is the RandomState
+ instance used by `np.random`. Used when ``solver`` == 'sag'.
Attributes
----------
diff --git a/sklearn/linear_model/sag.py b/sklearn/linear_model/sag.py
index 61bda1b66f..9bf807a182 100644
--- a/sklearn/linear_model/sag.py
+++ b/sklearn/linear_model/sag.py
@@ -144,9 +144,12 @@ def sag_solver(X, y, sample_weight=None, loss='log', alpha=1., beta=0.,
verbose : integer, optional
The verbosity level.
- random_state : int seed, RandomState instance, or None (default)
- The seed of the pseudo random number generator to use when
- shuffling the data.
+ random_state : int, RandomState instance or None, optional, default None
+ The seed of the pseudo random number generator to use when shuffling
+ the data. If int, random_state is the seed used by the random number
+ generator; If RandomState instance, random_state is the random number
+ generator; If None, the random number generator is the RandomState
+ instance used by `np.random`.
check_input : bool, default True
If False, the input arrays X and y will not be checked.
diff --git a/sklearn/linear_model/stochastic_gradient.py b/sklearn/linear_model/stochastic_gradient.py
index c234b8eb94..b3c6140847 100644
--- a/sklearn/linear_model/stochastic_gradient.py
+++ b/sklearn/linear_model/stochastic_gradient.py
@@ -608,9 +608,12 @@ class SGDClassifier(BaseSGDClassifier):
Whether or not the training data should be shuffled after each epoch.
Defaults to True.
- random_state : int seed, RandomState instance, or None (default)
- The seed of the pseudo random number generator to use when
- shuffling the data.
+ random_state : int, RandomState instance or None, optional (default=None)
+ The seed of the pseudo random number generator to use when shuffling
+ the data. If int, random_state is the seed used by the random number
+ generator; If RandomState instance, random_state is the random number
+ generator; If None, the random number generator is the RandomState
+ instance used by `np.random`.
verbose : integer, optional
The verbosity level
@@ -1134,9 +1137,12 @@ class SGDRegressor(BaseSGDRegressor):
Whether or not the training data should be shuffled after each epoch.
Defaults to True.
- random_state : int seed, RandomState instance, or None (default)
- The seed of the pseudo random number generator to use when
- shuffling the data.
+ random_state : int, RandomState instance or None, optional (default=None)
+ The seed of the pseudo random number generator to use when shuffling
+ the data. If int, random_state is the seed used by the random number
+ generator; If RandomState instance, random_state is the random number
+ generator; If None, the random number generator is the RandomState
+ instance used by `np.random`.
verbose : integer, optional
The verbosity level.
diff --git a/sklearn/linear_model/theil_sen.py b/sklearn/linear_model/theil_sen.py
index 23b3c106c9..b51f7d6dd3 100644
--- a/sklearn/linear_model/theil_sen.py
+++ b/sklearn/linear_model/theil_sen.py
@@ -243,9 +243,12 @@ class TheilSenRegressor(LinearModel, RegressorMixin):
tol : float, optional, default 1.e-3
Tolerance when calculating spatial median.
- random_state : RandomState or an int seed, optional, default None
- A random number generator instance to define the state of the
- random permutations generator.
+ random_state : int, RandomState instance or None, optional, default None
+ A random number generator instance to define the state of the random
+ permutations generator. If int, random_state is the seed used by the
+ random number generator; If RandomState instance, random_state is the
+ random number generator; If None, the random number generator is the
+ RandomState instance used by `np.random`.
n_jobs : integer, optional, default 1
Number of CPUs to use during the cross validation. If ``-1``, use
diff --git a/sklearn/manifold/locally_linear.py b/sklearn/manifold/locally_linear.py
index 367710edc6..82c4b61254 100644
--- a/sklearn/manifold/locally_linear.py
+++ b/sklearn/manifold/locally_linear.py
@@ -140,9 +140,11 @@ def null_space(M, k, k_skip=1, eigen_solver='arpack', tol=1E-6, max_iter=100,
max_iter : maximum number of iterations for 'arpack' method
not used if eigen_solver=='dense'
- random_state : numpy.RandomState or int, optional
- The generator or seed used to determine the starting vector for arpack
- iterations. Defaults to numpy.random.
+ random_state : int, RandomState instance or None, optional (default=None)
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`. Used when ``solver`` == 'arpack'.
"""
if eigen_solver == 'auto':
@@ -245,9 +247,11 @@ def locally_linear_embedding(
Tolerance for modified LLE method.
Only used if method == 'modified'
- random_state : numpy.RandomState or int, optional
- The generator or seed used to determine the starting vector for arpack
- iterations. Defaults to numpy.random.
+ random_state : int, RandomState instance or None, optional (default=None)
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`. Used when ``solver`` == 'arpack'.
n_jobs : int, optional (default = 1)
The number of parallel jobs to run for neighbors search.
@@ -568,9 +572,11 @@ class LocallyLinearEmbedding(BaseEstimator, TransformerMixin):
algorithm to use for nearest neighbors search,
passed to neighbors.NearestNeighbors instance
- random_state : numpy.RandomState or int, optional
- The generator or seed used to determine the starting vector for arpack
- iterations. Defaults to numpy.random.
+ random_state : int, RandomState instance or None, optional (default=None)
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`. Used when ``eigen_solver`` == 'arpack'.
n_jobs : int, optional (default = 1)
The number of parallel jobs to run.
diff --git a/sklearn/manifold/mds.py b/sklearn/manifold/mds.py
index b2fe62040b..5f7327ef4d 100644
--- a/sklearn/manifold/mds.py
+++ b/sklearn/manifold/mds.py
@@ -19,8 +19,7 @@ from ..isotonic import IsotonicRegression
def _smacof_single(dissimilarities, metric=True, n_components=2, init=None,
max_iter=300, verbose=0, eps=1e-3, random_state=None):
- """
- Computes multidimensional scaling using SMACOF algorithm
+ """Computes multidimensional scaling using SMACOF algorithm
Parameters
----------
@@ -50,10 +49,11 @@ def _smacof_single(dissimilarities, metric=True, n_components=2, init=None,
Relative tolerance with respect to stress at which to declare
convergence.
- random_state : integer or numpy.RandomState, optional
- The generator used to initialize the centers. If an integer is
- given, it fixes the seed. Defaults to the global numpy random
- number generator.
+ random_state : int, RandomState instance or None, optional, default: None
+ The generator used to initialize the centers. If int, random_state is
+ the seed used by the random number generator; If RandomState instance,
+ random_state is the random number generator; If None, the random number
+ generator is the RandomState instance used by `np.random`.
Returns
-------
@@ -134,8 +134,7 @@ def _smacof_single(dissimilarities, metric=True, n_components=2, init=None,
def smacof(dissimilarities, metric=True, n_components=2, init=None, n_init=8,
n_jobs=1, max_iter=300, verbose=0, eps=1e-3, random_state=None,
return_n_iter=False):
- """
- Computes multidimensional scaling using the SMACOF algorithm.
+ """Computes multidimensional scaling using the SMACOF algorithm.
The SMACOF (Scaling by MAjorizing a COmplicated Function) algorithm is a
multidimensional scaling algorithm which minimizes an objective function
@@ -198,10 +197,11 @@ def smacof(dissimilarities, metric=True, n_components=2, init=None, n_init=8,
Relative tolerance with respect to stress at which to declare
convergence.
- random_state : integer or numpy.RandomState, optional, default: None
- The generator used to initialize the centers. If an integer is given,
- it fixes the seed. Defaults to the global numpy random number
- generator.
+ random_state : int, RandomState instance or None, optional, default: None
+ The generator used to initialize the centers. If int, random_state is
+ the seed used by the random number generator; If RandomState instance,
+ random_state is the random number generator; If None, the random number
+ generator is the RandomState instance used by `np.random`.
return_n_iter : bool, optional, default: False
Whether or not to return the number of iterations.
@@ -314,10 +314,11 @@ class MDS(BaseEstimator):
(``n_cpus + 1 + n_jobs``) are used. Thus for ``n_jobs = -2``, all CPUs
but one are used.
- random_state : integer or numpy.RandomState, optional, default: None
- The generator used to initialize the centers. If an integer is given,
- it fixes the seed. Defaults to the global numpy random number
- generator.
+ random_state : int, RandomState instance or None, optional, default: None
+ The generator used to initialize the centers. If int, random_state is
+ the seed used by the random number generator; If RandomState instance,
+ random_state is the random number generator; If None, the random number
+ generator is the RandomState instance used by `np.random`.
dissimilarity : 'euclidean' | 'precomputed', optional, default: 'euclidean'
Dissimilarity measure to use:
diff --git a/sklearn/manifold/spectral_embedding_.py b/sklearn/manifold/spectral_embedding_.py
index 6250565645..31c90aa8b3 100644
--- a/sklearn/manifold/spectral_embedding_.py
+++ b/sklearn/manifold/spectral_embedding_.py
@@ -166,10 +166,13 @@ def spectral_embedding(adjacency, n_components=8, eigen_solver=None,
to be installed. It can be faster on very large, sparse problems,
but may also lead to instabilities.
- random_state : int seed, RandomState instance, or None (default)
+ random_state : int, RandomState instance or None, optional, default: None
A pseudo random number generator used for the initialization of the
- lobpcg eigenvectors decomposition when eigen_solver == 'amg'.
- By default, arpack is used.
+ lobpcg eigenvectors decomposition. If int, random_state is the seed
+ used by the random number generator; If RandomState instance,
+ random_state is the random number generator; If None, the random number
+ generator is the RandomState instance used by `np.random`. Used when
+ ``solver`` == 'amg'.
eigen_tol : float, optional, default=0.0
Stopping criterion for eigendecomposition of the Laplacian matrix
@@ -345,9 +348,13 @@ class SpectralEmbedding(BaseEstimator):
to be installed. It can be faster on very large, sparse problems,
but may also lead to instabilities.
- random_state : int seed, RandomState instance, or None, default : None
+ random_state : int, RandomState instance or None, optional, default: None
A pseudo random number generator used for the initialization of the
- lobpcg eigenvectors decomposition when eigen_solver == 'amg'.
+ lobpcg eigenvectors. If int, random_state is the seed used by the
+ random number generator; If RandomState instance, random_state is the
+ random number generator; If None, the random number generator is the
+ RandomState instance used by `np.random`. Used when ``solver`` ==
+ 'amg'.
affinity : string or callable, default : "nearest_neighbors"
How to construct the affinity matrix.
diff --git a/sklearn/manifold/t_sne.py b/sklearn/manifold/t_sne.py
index a124753cb0..83d42c444f 100644
--- a/sklearn/manifold/t_sne.py
+++ b/sklearn/manifold/t_sne.py
@@ -582,10 +582,12 @@ class TSNE(BaseEstimator):
verbose : int, optional (default: 0)
Verbosity level.
- random_state : int or RandomState instance or None (default)
- Pseudo Random Number generator seed control. If None, use the
- numpy.random singleton. Note that different initializations
- might result in different local minima of the cost function.
+ random_state : int, RandomState instance or None, optional (default: None)
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`. Note that different initializations might result in
+ different local minima of the cost function.
method : string (default: 'barnes_hut')
By default the gradient calculation algorithm uses Barnes-Hut
diff --git a/sklearn/metrics/cluster/unsupervised.py b/sklearn/metrics/cluster/unsupervised.py
index 606ffcddf8..3be683ae08 100644
--- a/sklearn/metrics/cluster/unsupervised.py
+++ b/sklearn/metrics/cluster/unsupervised.py
@@ -62,10 +62,12 @@ def silhouette_score(X, labels, metric='euclidean', sample_size=None,
on a random subset of the data.
If ``sample_size is None``, no sampling is used.
- random_state : integer or numpy.RandomState, optional
- The generator used to randomly select a subset of samples if
- ``sample_size is not None``. If an integer is given, it fixes the seed.
- Defaults to the global numpy random number generator.
+ random_state : int, RandomState instance or None, optional (default=None)
+ The generator used to randomly select a subset of samples. If int,
+ random_state is the seed used by the random number generator; If
+ RandomState instance, random_state is the random number generator; If
+ None, the random number generator is the RandomState instance used by
+ `np.random`. Used when ``sample_size is not None``.
**kwds : optional keyword parameters
Any further parameters are passed directly to the distance function.
diff --git a/sklearn/mixture/bayesian_mixture.py b/sklearn/mixture/bayesian_mixture.py
index 497b339a4f..24c0ae62e4 100644
--- a/sklearn/mixture/bayesian_mixture.py
+++ b/sklearn/mixture/bayesian_mixture.py
@@ -163,8 +163,11 @@ class BayesianGaussianMixture(BaseMixture):
(n_features) if 'diag',
float if 'spherical'
- random_state : RandomState or an int seed, defaults to None.
- A random number generator instance.
+ random_state : int, RandomState instance or None, optional (default=None)
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
warm_start : bool, default to False.
If 'warm_start' is True, the solution of the last fitting is used as
diff --git a/sklearn/mixture/gaussian_mixture.py b/sklearn/mixture/gaussian_mixture.py
index edbfc08c4e..eced540724 100644
--- a/sklearn/mixture/gaussian_mixture.py
+++ b/sklearn/mixture/gaussian_mixture.py
@@ -500,8 +500,11 @@ class GaussianMixture(BaseMixture):
(n_components, n_features) if 'diag',
(n_components, n_features, n_features) if 'full'
- random_state : RandomState or an int seed, defaults to None.
- A random number generator instance.
+ random_state : int, RandomState instance or None, optional (default=None)
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
warm_start : bool, default to False.
If 'warm_start' is True, the solution of the last fitting is used as
diff --git a/sklearn/mixture/gmm.py b/sklearn/mixture/gmm.py
index 024981bda8..5b2dece572 100644
--- a/sklearn/mixture/gmm.py
+++ b/sklearn/mixture/gmm.py
@@ -152,8 +152,11 @@ class _GMMBase(BaseEstimator):
use. Must be one of 'spherical', 'tied', 'diag', 'full'.
Defaults to 'diag'.
- random_state : RandomState or an int seed (None by default)
- A random number generator instance
+ random_state : int, RandomState instance or None, optional (default=None)
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
min_covar : float, optional
Floor on the diagonal of the covariance matrix to prevent
diff --git a/sklearn/model_selection/_search.py b/sklearn/model_selection/_search.py
index 3b8a0ed882..98d9e32017 100644
--- a/sklearn/model_selection/_search.py
+++ b/sklearn/model_selection/_search.py
@@ -192,9 +192,13 @@ class ParameterSampler(object):
n_iter : integer
Number of parameter settings that are produced.
- random_state : int or RandomState
+ random_state : int, RandomState instance or None, optional (default=None)
Pseudo random number generator state used for random uniform sampling
from lists of possible values instead of scipy.stats distributions.
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
Returns
-------
@@ -1054,9 +1058,13 @@ class RandomizedSearchCV(BaseSearchCV):
verbose : integer
Controls the verbosity: the higher, the more messages.
- random_state : int or RandomState
+ random_state : int, RandomState instance or None, optional, default=None
Pseudo random number generator state used for random uniform sampling
from lists of possible values instead of scipy.stats distributions.
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
error_score : 'raise' (default) or numeric
Value to assign to the score if an error occurs in estimator fitting.
diff --git a/sklearn/model_selection/_split.py b/sklearn/model_selection/_split.py
index 992c4f6d81..0eb51be93f 100644
--- a/sklearn/model_selection/_split.py
+++ b/sklearn/model_selection/_split.py
@@ -364,9 +364,11 @@ class KFold(_BaseKFold):
shuffle : boolean, optional
Whether to shuffle the data before splitting into batches.
- random_state : None, int or RandomState
- When shuffle=True, pseudo-random number generator state used for
- shuffling. If None, use default numpy RNG for shuffling.
+ random_state : int, RandomState instance or None, optional, default=None
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`. Used when ``shuffle`` == True.
Examples
--------
@@ -531,9 +533,11 @@ class StratifiedKFold(_BaseKFold):
Whether to shuffle each stratification of the data before splitting
into batches.
- random_state : None, int or RandomState
- When shuffle=True, pseudo-random number generator state used for
- shuffling. If None, use default numpy RNG for shuffling.
+ random_state : int, RandomState instance or None, optional, default=None
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`. Used when ``shuffle`` == True.
Examples
--------
@@ -934,9 +938,11 @@ class _RepeatedSplits(with_metaclass(ABCMeta)):
n_repeats : int, default=10
Number of times cross-validator needs to be repeated.
- random_state : None, int or RandomState, default=None
- Random state to be used to generate random state for each
- repetition.
+ random_state : int, RandomState instance or None, optional, default=None
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
**cvargs : additional params
Constructor parameters for cv. Must not contain random_state
@@ -1007,9 +1013,11 @@ class RepeatedKFold(_RepeatedSplits):
n_repeats : int, default=10
Number of times cross-validator needs to be repeated.
- random_state : None, int or RandomState, default=None
- Random state to be used to generate random state for each
- repetition.
+ random_state : int, RandomState instance or None, optional, default=None
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
Examples
--------
@@ -1180,8 +1188,11 @@ class ShuffleSplit(BaseShuffleSplit):
int, represents the absolute number of train samples. If None,
the value is automatically set to the complement of the test size.
- random_state : int or RandomState
- Pseudo-random number generator state used for random sampling.
+ random_state : int, RandomState instance or None, optional (default=None)
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
Examples
--------
@@ -1262,8 +1273,12 @@ class GroupShuffleSplit(ShuffleSplit):
int, represents the absolute number of train groups. If None,
the value is automatically set to the complement of the test size.
- random_state : int or RandomState
- Pseudo-random number generator state used for random sampling.
+ random_state : int, RandomState instance or None, optional (default=None)
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
+
'''
def __init__(self, n_splits=5, test_size=0.2, train_size=None,
@@ -1389,8 +1404,12 @@ class StratifiedShuffleSplit(BaseShuffleSplit):
int, represents the absolute number of train samples. If None,
the value is automatically set to the complement of the test size.
- random_state : int or RandomState
- Pseudo-random number generator state used for random sampling.
+ random_state : int, RandomState instance or None, optional (default=None)
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
+
Examples
--------
@@ -1795,8 +1814,11 @@ def train_test_split(*arrays, **options):
int, represents the absolute number of train samples. If None,
the value is automatically set to the complement of the test size.
- random_state : int or RandomState
- Pseudo-random number generator state used for random sampling.
+ random_state : int, RandomState instance or None, optional (default=None)
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
stratify : array-like or None (default is None)
If not None, data is split in a stratified fashion, using this as
diff --git a/sklearn/model_selection/_validation.py b/sklearn/model_selection/_validation.py
index e65720b709..e105f0d0b1 100644
--- a/sklearn/model_selection/_validation.py
+++ b/sklearn/model_selection/_validation.py
@@ -580,9 +580,11 @@ def permutation_test_score(estimator, X, y, groups=None, cv=None,
The number of CPUs to use to do the computation. -1 means
'all CPUs'.
- random_state : RandomState or an int seed (0 by default)
- A random number generator instance to define the state of the
- random permutations generator.
+ random_state : int, RandomState instance or None, optional (default=0)
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
verbose : integer, optional
The verbosity level.
@@ -743,9 +745,11 @@ def learning_curve(estimator, X, y, groups=None,
Whether to shuffle training data before taking prefixes of it
based on``train_sizes``.
- random_state : None, int or RandomState
- When shuffle=True, pseudo-random number generator state used for
- shuffling. If None, use default numpy RNG for shuffling.
+ random_state : int, RandomState instance or None, optional (default=None)
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`. Used when ``shuffle`` == 'True'.
-------
train_sizes_abs : array, shape = (n_unique_ticks,), dtype int
diff --git a/sklearn/multiclass.py b/sklearn/multiclass.py
index 3de5ee319c..8f9788e6a4 100644
--- a/sklearn/multiclass.py
+++ b/sklearn/multiclass.py
@@ -640,9 +640,11 @@ class OutputCodeClassifier(BaseEstimator, ClassifierMixin, MetaEstimatorMixin):
one-vs-the-rest. A number greater than 1 will require more classifiers
than one-vs-the-rest.
- random_state : numpy.RandomState, optional
- The generator used to initialize the codebook. Defaults to
- numpy.random.
+ random_state : int, RandomState instance or None, optional, default: None
+ The generator used to initialize the codebook. If int, random_state is
+ the seed used by the random number generator; If RandomState instance,
+ random_state is the random number generator; If None, the random number
+ generator is the RandomState instance used by `np.random`.
n_jobs : int, optional, default: 1
The number of jobs to use for the computation. If -1 all CPUs are used.
diff --git a/sklearn/neighbors/kde.py b/sklearn/neighbors/kde.py
index dfb349a8dc..3cfdbc6304 100644
--- a/sklearn/neighbors/kde.py
+++ b/sklearn/neighbors/kde.py
@@ -184,8 +184,11 @@ class KernelDensity(BaseEstimator):
n_samples : int, optional
Number of samples to generate. Defaults to 1.
- random_state : RandomState or an int seed (0 by default)
- A random number generator instance.
+ random_state : int, RandomState instance or None. default to None
+ If int, random_state is the seed used by the random number
+ generator; If RandomState instance, random_state is the random
+ number generator; If None, the random number generator is the
+ RandomState instance used by `np.random`.
Returns
-------
diff --git a/sklearn/neural_network/multilayer_perceptron.py b/sklearn/neural_network/multilayer_perceptron.py
index 720a3fef21..1d329f8074 100644
--- a/sklearn/neural_network/multilayer_perceptron.py
+++ b/sklearn/neural_network/multilayer_perceptron.py
@@ -755,8 +755,11 @@ class MLPClassifier(BaseMultilayerPerceptron, ClassifierMixin):
Maximum number of iterations. The solver iterates until convergence
(determined by 'tol') or this number of iterations.
- random_state : int or RandomState, optional, default None
- State or seed for random number generator.
+ random_state : int, RandomState instance or None, optional, default None
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
shuffle : bool, optional, default True
Whether to shuffle samples in each iteration. Only used when
@@ -1126,8 +1129,11 @@ class MLPRegressor(BaseMultilayerPerceptron, RegressorMixin):
Maximum number of iterations. The solver iterates until convergence
(determined by 'tol') or this number of iterations.
- random_state : int or RandomState, optional, default None
- State or seed for random number generator.
+ random_state : int, RandomState instance or None, optional, default None
+ If int, random_state is the seed used by the random number generator;
+ If RandomState instance, random_state is the random number generator;
+ If None, the random number generator is the RandomState instance used
+ by `np.random`.
shuffle : bool, optional, default True
Whether to shuffle samples in each iteration. Only used when
diff --git a/sklearn/random_projection.py b/sklearn/random_projection.py
index 0d47b2886f..1ec4d0d21e 100644
--- a/sklearn/random_projection.py
+++ b/sklearn/random_projection.py
@@ -154,7 +154,7 @@ def _check_input_size(n_components, n_features):
def gaussian_random_matrix(n_components, n_features, random_state=None):
- """ Generate a dense Gaussian random matrix.
+ """Generate a dense Gaussian random matrix.
The components of the random matrix are drawn from
@@ -170,9 +170,12 @@ def gaussian_random_matrix(n_components, n_features, random_state=None):
n_features : int,
Dimensionality of the original source space.
- random_state : int, RandomState instance or None (default=None)
- Control the pseudo random number generator used to generate the
- matrix at fit time.
+ random_state : int, RandomState instance or None, optional (default=None)
+ Control the pseudo random number generator used to generate the matrix
+ at fit time. If int, random_state is the seed used by the random
+ number generator; If RandomState instance, random_state is the random
+ number generator; If None, the random number generator is the
+ RandomState instance used by `np.random`.
Returns
-------
@@ -226,9 +229,12 @@ def sparse_random_matrix(n_components, n_features, density='auto',
Use density = 1 / 3.0 if you want to reproduce the results from
Achlioptas, 2001.
- random_state : integer, RandomState instance or None (default=None)
- Control the pseudo random number generator used to generate the
- matrix at fit time.
+ random_state : int, RandomState instance or None, optional (default=None)
+ Control the pseudo random number generator used to generate the matrix
+ at fit time. If int, random_state is the seed used by the random
+ number generator; If RandomState instance, random_state is the random
+ number generator; If None, the random number generator is the
+ RandomState instance used by `np.random`.
Returns
-------
@@ -446,9 +452,12 @@ class GaussianRandomProjection(BaseRandomProjection):
Smaller values lead to better embedding and higher number of
dimensions (n_components) in the target projection space.
- random_state : integer, RandomState instance or None (default=None)
- Control the pseudo random number generator used to generate the
- matrix at fit time.
+ random_state : int, RandomState instance or None, optional (default=None)
+ Control the pseudo random number generator used to generate the matrix
+ at fit time. If int, random_state is the seed used by the random
+ number generator; If RandomState instance, random_state is the random
+ number generator; If None, the random number generator is the
+ RandomState instance used by `np.random`.
Attributes
----------
@@ -552,9 +561,12 @@ class SparseRandomProjection(BaseRandomProjection):
If False, the projected data uses a sparse representation if
the input is sparse.
- random_state : integer, RandomState instance or None (default=None)
- Control the pseudo random number generator used to generate the
- matrix at fit time.
+ random_state : int, RandomState instance or None, optional (default=None)
+ Control the pseudo random number generator used to generate the matrix
+ at fit time. If int, random_state is the seed used by the random
+ number generator; If RandomState instance, random_state is the random
+ number generator; If None, the random number generator is the
+ RandomState instance used by `np.random`.
Attributes
----------
diff --git a/sklearn/svm/base.py b/sklearn/svm/base.py
index cff4c35a58..208a69f372 100644
--- a/sklearn/svm/base.py
+++ b/sklearn/svm/base.py
@@ -804,9 +804,13 @@ def _fit_liblinear(X, y, C, fit_intercept, intercept_scaling, class_weight,
tol : float
Stopping condition.
- random_state : int seed, RandomState instance, or None (default)
- The seed of the pseudo random number generator to use when
- shuffling the data.
+ random_state : int, RandomState instance or None, optional (default=None)
+ The seed of the pseudo random number generator to use when shuffling
+ the data. If int, random_state is the seed used by the random number
+ generator; If RandomState instance, random_state is the random number
+ generator; If None, the random number generator is the RandomState
+ instance used by `np.random`.
+
multi_class : str, {'ovr', 'crammer_singer'}
`ovr` trains n_classes one-vs-rest classifiers, while `crammer_singer`
diff --git a/sklearn/svm/classes.py b/sklearn/svm/classes.py
index 7e920011d0..2de3029cb2 100644
--- a/sklearn/svm/classes.py
+++ b/sklearn/svm/classes.py
@@ -86,9 +86,12 @@ class LinearSVC(BaseEstimator, LinearClassifierMixin,
per-process runtime setting in liblinear that, if enabled, may not work
properly in a multithreaded context.
- random_state : int seed, RandomState instance, or None (default=None)
- The seed of the pseudo random number generator to use when
- shuffling the data.
+ random_state : int, RandomState instance or None, optional (default=None)
+ The seed of the pseudo random number generator to use when shuffling
+ the data. If int, random_state is the seed used by the random number
+ generator; If RandomState instance, random_state is the random number
+ generator; If None, the random number generator is the RandomState
+ instance used by `np.random`.
max_iter : int, (default=1000)
The maximum number of iterations to be run.
@@ -277,9 +280,12 @@ class LinearSVR(LinearModel, RegressorMixin):
per-process runtime setting in liblinear that, if enabled, may not work
properly in a multithreaded context.
- random_state : int seed, RandomState instance, or None (default=None)
- The seed of the pseudo random number generator to use when
- shuffling the data.
+ random_state : int, RandomState instance or None, optional (default=None)
+ The seed of the pseudo random number generator to use when shuffling
+ the data. If int, random_state is the seed used by the random number
+ generator; If RandomState instance, random_state is the random number
+ generator; If None, the random number generator is the RandomState
+ instance used by `np.random`.
max_iter : int, (default=1000)
The maximum number of iterations to be run.
@@ -468,9 +474,12 @@ class SVC(BaseSVC):
.. versionchanged:: 0.17
Deprecated *decision_function_shape='ovo' and None*.
- random_state : int seed, RandomState instance, or None (default)
- The seed of the pseudo random number generator to use when
- shuffling the data for probability estimation.
+ random_state : int, RandomState instance or None, optional (default=None)
+ The seed of the pseudo random number generator to use when shuffling
+ the data. If int, random_state is the seed used by the random number
+ generator; If RandomState instance, random_state is the random number
+ generator; If None, the random number generator is the RandomState
+ instance used by `np.random`.
Attributes
----------
@@ -621,9 +630,12 @@ class NuSVC(BaseSVC):
.. versionchanged:: 0.17
Deprecated *decision_function_shape='ovo' and None*.
- random_state : int seed, RandomState instance, or None (default)
- The seed of the pseudo random number generator to use when
- shuffling the data for probability estimation.
+ random_state : int, RandomState instance or None, optional (default=None)
+ The seed of the pseudo random number generator to use when shuffling
+ the data. If int, random_state is the seed used by the random number
+ generator; If RandomState instance, random_state is the random number
+ generator; If None, the random number generator is the RandomState
+ instance used by `np.random`.
Attributes
----------
@@ -972,9 +984,12 @@ class OneClassSVM(BaseLibSVM):
max_iter : int, optional (default=-1)
Hard limit on iterations within solver, or -1 for no limit.
- random_state : int seed, RandomState instance, or None (default)
- The seed of the pseudo random number generator to use when
- shuffling the data for probability estimation.
+ random_state : int, RandomState instance or None, optional (default=None)
+ The seed of the pseudo random number generator to use when shuffling
+ the data. If int, random_state is the seed used by the random number
+ generator; If RandomState instance, random_state is the random number
+ generator; If None, the random number generator is the RandomState
+ instance used by `np.random`.
Attributes
----------
diff --git a/sklearn/utils/__init__.py b/sklearn/utils/__init__.py
index 0bc4d6de33..b3e41e1c13 100644
--- a/sklearn/utils/__init__.py
+++ b/sklearn/utils/__init__.py
@@ -175,8 +175,12 @@ def resample(*arrays, **options):
If replace is False it should not be larger than the length of
arrays.
- random_state : int or RandomState instance
- Control the shuffling for reproducible behavior.
+ random_state : int, RandomState instance or None, optional (default=None)
+ The seed of the pseudo random number generator to use when shuffling
+ the data. If int, random_state is the seed used by the random number
+ generator; If RandomState instance, random_state is the random number
+ generator; If None, the random number generator is the RandomState
+ instance used by `np.random`.
Returns
-------
@@ -271,8 +275,12 @@ def shuffle(*arrays, **options):
Indexable data-structures can be arrays, lists, dataframes or scipy
sparse matrices with consistent first dimension.
- random_state : int or RandomState instance
- Control the shuffling for reproducible behavior.
+ random_state : int, RandomState instance or None, optional (default=None)
+ The seed of the pseudo random number generator to use when shuffling
+ the data. If int, random_state is the seed used by the random number
+ generator; If RandomState instance, random_state is the random number
+ generator; If None, the random number generator is the RandomState
+ instance used by `np.random`.
n_samples : int, None by default
Number of samples to generate. If left to None this is
diff --git a/sklearn/utils/extmath.py b/sklearn/utils/extmath.py
index df1f56dbcb..d797950ba8 100644
--- a/sklearn/utils/extmath.py
+++ b/sklearn/utils/extmath.py
@@ -215,8 +215,12 @@ def randomized_range_finder(A, size, n_iter,
.. versionadded:: 0.18
- random_state : RandomState or an int seed (0 by default)
- A random number generator instance
+ random_state : int, RandomState instance or None, optional (default=None)
+ The seed of the pseudo random number generator to use when shuffling
+ the data. If int, random_state is the seed used by the random number
+ generator; If RandomState instance, random_state is the random number
+ generator; If None, the random number generator is the RandomState
+ instance used by `np.random`.
Returns
-------
@@ -320,8 +324,12 @@ def randomized_svd(M, n_components, n_oversamples=10, n_iter='auto',
set to `True`, the sign ambiguity is resolved by making the largest
loadings for each component in the left singular vectors positive.
- random_state : RandomState or an int seed (0 by default)
- A random number generator instance to make behavior
+ random_state : int, RandomState instance or None, optional (default=None)
+ The seed of the pseudo random number generator to use when shuffling
+ the data. If int, random_state is the seed used by the random number
+ generator; If RandomState instance, random_state is the random number
+ generator; If None, the random number generator is the RandomState
+ instance used by `np.random`.
Notes
-----
--
GitLab