Skip to content

[MRG] Limiting n_components by both n_features and n_samples instead of just n_features (Recreated PR) #8741

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 6 commits into from
Closed

[MRG] Limiting n_components by both n_features and n_samples instead of just n_features (Recreated PR) #8741

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
9875d89
fixed issue 8484
Mar 1, 2017
3544221
dealt with indentation issues flagged by flake8
Mar 6, 2017
0517109
code to handle n_components==None with arpack was missing
Mar 8, 2017
285f646
added non-regression tests for my previous changes in pca
Mar 8, 2017
f7cf9b0
minor change: reverted iterator name in test_pca
Apr 4, 2017
66b3402
changed AssertRaises to regex variant in test, and minor writing chan…
Apr 7, 2017
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
45 changes: 29 additions & 16 deletions sklearn/decomposition/pca.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -134,8 +134,11 @@ class PCA(_BasePCA):
to guess the dimension
if ``0 < n_components < 1`` and svd_solver == 'full', select the number
of components such that the amount of variance that needs to be
explained is greater than the percentage specified by n_components
n_components cannot be equal to n_features for svd_solver == 'arpack'.
explained is greater than the percentage specified by n_components.
If svd_solver == 'arpack', the number of components must be strictly
less than the minimum of n_features and n_samples:

n_components == min(n_samples, n_features)

copy : bool (default True)
If False, data passed to fit are overwritten and running
Expand Down Expand Up @@ -166,7 +169,7 @@ class PCA(_BasePCA):
arpack :
run SVD truncated to n_components calling ARPACK solver via
`scipy.sparse.linalg.svds`. It requires strictly
0 < n_components < X.shape[1]
0 < n_components < min(X.shape)
randomized :
run randomized SVD by the method of Halko et al.

Expand Down Expand Up @@ -205,7 +208,7 @@ class PCA(_BasePCA):
Percentage of variance explained by each of the selected components.

If ``n_components`` is not set then all components are stored and the
sum of explained variances is equal to 1.0.
sum of the ratios is equal to 1.0.

singular_values_ : array, shape (n_components,)
The singular values corresponding to each of the selected components.
Expand All @@ -221,7 +224,8 @@ class PCA(_BasePCA):
The estimated number of components. When n_components is set
to 'mle' or a number between 0 and 1 (with svd_solver == 'full') this
number is estimated from input data. Otherwise it equals the parameter
n_components, or n_features if n_components is None.
n_components, or the lesser value of n_features and n_samples
if n_components is None.

noise_variance_ : float
The estimated noise covariance following the Probabilistic PCA model
Expand Down Expand Up @@ -365,7 +369,10 @@ def _fit(self, X):

# Handle n_components==None
if self.n_components is None:
n_components = X.shape[1]
if self.svd_solver is not 'arpack':
n_components = min(X.shape)
else:
n_components = min(X.shape) - 1
else:
n_components = self.n_components

Expand Down Expand Up @@ -395,10 +402,11 @@ def _fit_full(self, X, n_components):
if n_samples < n_features:
raise ValueError("n_components='mle' is only supported "
"if n_samples >= n_features")
elif not 0 <= n_components <= n_features:
elif not 0 <= n_components <= min(n_samples, n_features):
raise ValueError("n_components=%r must be between 0 and "
"n_features=%r with svd_solver='full'"
% (n_components, n_features))
"min(n_samples, n_features)=%r with "
"svd_solver='full'"
% (n_components, min(n_samples, n_features)))

# Center data
self.mean_ = np.mean(X, axis=0)
Expand Down Expand Up @@ -453,14 +461,19 @@ def _fit_truncated(self, X, n_components, svd_solver):
raise ValueError("n_components=%r cannot be a string "
"with svd_solver='%s'"
% (n_components, svd_solver))
elif not 1 <= n_components <= n_features:
elif not 1 <= n_components <= min(n_samples, n_features):
raise ValueError("n_components=%r must be between 1 and "
"n_features=%r with svd_solver='%s'"
% (n_components, n_features, svd_solver))
elif svd_solver == 'arpack' and n_components == n_features:
"min(n_samples, n_features)=%r with "
"svd_solver='%s'"
% (n_components, min(n_samples, n_features),
svd_solver))
elif svd_solver == 'arpack' and n_components == min(n_samples,
n_features):
raise ValueError("n_components=%r must be stricly less than "
"n_features=%r with svd_solver='%s'"
% (n_components, n_features, svd_solver))
"min(n_samples, n_features)=%r with "
"svd_solver='%s'"
% (n_components, min(n_samples, n_features),
svd_solver))

random_state = check_random_state(self.random_state)

Expand Down Expand Up @@ -495,7 +508,7 @@ def _fit_truncated(self, X, n_components, svd_solver):
self.explained_variance_ratio_ = \
self.explained_variance_ / total_var.sum()
self.singular_values_ = S.copy() # Store the singular values.
if self.n_components_ < n_features:
if self.n_components_ < min(n_samples, n_features):
self.noise_variance_ = (total_var.sum() -
self.explained_variance_.sum())
else:
Expand Down
25 changes: 22 additions & 3 deletions sklearn/decomposition/tests/test_pca.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,6 +8,7 @@
from sklearn.utils.testing import assert_equal
from sklearn.utils.testing import assert_greater
from sklearn.utils.testing import assert_raises
from sklearn.utils.testing import assert_raises_regex
from sklearn.utils.testing import assert_no_warnings
from sklearn.utils.testing import assert_warns_message
from sklearn.utils.testing import ignore_warnings
Expand Down Expand Up @@ -340,11 +341,29 @@ def test_pca_inverse():


def test_pca_validation():
X = [[0, 1], [1, 0]]
# Ensures that extreme inputs for n_components common to all solvers
# (less than 0 or more than the lesser dimension of the input
# matrix X) raise errors.
X = np.array([[0, 1, 0], [1, 0, 0]])
for solver in solver_list:
for n_components in [-1, 3]:
assert_raises(ValueError,
PCA(n_components, svd_solver=solver).fit, X)
assert_raises_regex(ValueError,
"n_components\=.* must be between .* and min\("
"n_samples, n_features\)\=.* with svd_solver"
"\=\'(?:full|arpack|randomized|auto)\'$",
PCA(n_components, svd_solver=solver).fit, X)


def test_n_components_none():
# Ensures that n_components == None is handled correctly
X = iris.data
for solver in solver_list:
pca = PCA(svd_solver=solver)
pca.fit(X)
if solver == 'arpack':
assert_equal(pca.n_components_, min(X.shape)-1)
else:
assert_equal(pca.n_components_, min(X.shape))


def test_randomized_pca_check_projection():
Expand Down