def test_solver_auto(self):
# Uses "full"
U = self.rng.randn(100, 5)
V = self.rng.randn(100, 5)
X = U @ V.T
factors, loadings, _, _ = svd_pca(X,
output_dimension=5,
svd_solver="auto")
Y = loadings @ factors.T
normX = np.linalg.norm(X - Y)
assert normX < self.tol
# Uses "randomized"
U = self.rng.randn(501, 5)
V = self.rng.randn(100, 5)
X = U @ V.T
factors, loadings, _, _ = svd_pca(X,
output_dimension=5,
svd_solver="auto")
Y = loadings @ factors.T
normX = np.linalg.norm(X - Y)
assert normX < self.tol
# Uses full
U = self.rng.randn(501, 5)
V = self.rng.randn(100, 5)
X = U @ V.T
factors, loadings, _, _ = svd_pca(X,
output_dimension=81,
svd_solver="auto")
Y = loadings @ factors.T
normX = np.linalg.norm(X - Y)
assert normX < self.tol
def test_full(self, output_dimension, auto_transpose, centre,
u_based_decision):
factors, loadings, explained_variance, mean = svd_pca(
self.X,
output_dimension=output_dimension,
svd_solver="full",
auto_transpose=auto_transpose,
centre=centre,
u_based_decision=u_based_decision,
)
X = loadings @ factors.T
# Check the low-rank component MSE
normX = np.linalg.norm(X - self.X)
assert normX < self.tol
# Check singular values
explained_variance_norm = explained_variance / np.sum(
explained_variance)
np.testing.assert_allclose(explained_variance_norm[:self.rank].sum(),
1.0)
if centre is None:
assert mean is None
elif centre == "features":
np.testing.assert_allclose(mean, self.X_mean_1)
elif centre == "samples":
np.testing.assert_allclose(mean, self.X_mean_0)
def test_arpack_error(self):
pytest.importorskip("scipy", minversion="1.4.0")
with pytest.raises(ValueError,
match="requires output_dimension to be strictly"):
_ = svd_pca(self.X,
output_dimension=min(self.X.shape) + 1,
svd_solver="arpack")
def test_randomized(self, output_dimension, auto_transpose, centre):
factors, loadings, explained_variance, mean = svd_pca(
self.X,
output_dimension=output_dimension,
svd_solver="randomized",
auto_transpose=auto_transpose,
centre=centre,
)
X = loadings @ factors.T
# Check the low-rank component MSE
normX = np.linalg.norm(X - self.X)
assert normX < self.tol
# Check singular values
explained_variance_norm = explained_variance / np.sum(explained_variance)
np.testing.assert_allclose(explained_variance_norm[: self.rank].sum(), 1.0)
def decomposition(self, normalize_poissonian_noise=False,
algorithm = 'svd', output_dimension=None, centre = None,
auto_transpose = True, navigation_mask=None, signal_mask=None,
var_array=None, var_func=None, polyfit=None, on_peaks=False,
reproject=None, **kwargs):
"""Decomposition with a choice of algorithms
The results are stored in self.mva_results
Parameters
----------
normalize_poissonian_noise : bool
If True, scale the SI to normalize Poissonian noise
algorithm : 'svd' | 'fast_svd' | 'mlpca' | 'fast_mlpca' | 'nmf' |
'sparse_pca' | 'mini_batch_sparse_pca'
output_dimension : None or int
number of components to keep/calculate
centre : None | 'variables' | 'trials'
If None no centring is applied. If 'variable' the centring will be
performed in the variable axis. If 'trials', the centring will be
performed in the 'trials' axis. It only has effect when using the
svd or fast_svd algorithms
auto_transpose : bool
If True, automatically transposes the data to boost performance.
Only has effect when using the svd of fast_svd algorithms.
navigation_mask : boolean numpy array
signal_mask : boolean numpy array
var_array : numpy array
Array of variance for the maximum likelihood PCA algorithm
var_func : function or numpy array
If function, it will apply it to the dataset to obtain the
var_array. Alternatively, it can a an array with the coefficients
of a polynomial.
polyfit :
reproject : None | signal | navigation | both
If not None, the results of the decomposition will be projected in
the selected masked area.
See also
--------
plot_decomposition_factors, plot_decomposition_scores, plot_lev
"""
# backup the original data
if on_peaks:
if hasattr(self.mapped_parameters,'peak_chars'):
self._data_before_treatments = \
self.mapped_parameters.peak_chars.copy()
else:
print """No peak characteristics found. You must run the
peak_char_stack function to obtain these before
you can run PCA or ICA on them."""
else:
self._data_before_treatments = self.data.copy()
if algorithm == 'mlpca':
if normalize_poissonian_noise is True:
messages.warning(
"It makes no sense to do normalize_poissonian_noise with "
"the MLPCA algorithm. Therefore, "
"normalize_poissonian_noise is set to False")
normalize_poissonian_noise = False
if output_dimension is None:
messages.warning_exit("With the mlpca algorithm the "
"output_dimension must be expecified")
# Apply pre-treatments
# Transform the data in a line spectrum
self._unfolded4decomposition = self.unfold_if_multidim()
if hasattr(navigation_mask, 'ravel'):
navigation_mask = navigation_mask.ravel()
if hasattr(signal_mask, 'ravel'):
signal_mask = signal_mask.ravel()
# Normalize the poissonian noise
# TODO this function can change the masks and this can cause
# problems when reprojecting
if normalize_poissonian_noise is True:
if reproject is None:
navigation_mask, signal_mask = \
self.normalize_poissonian_noise(
navigation_mask=navigation_mask,
signal_mask=signal_mask,
return_masks = True)
elif reproject == 'both':
_, _ = \
self.normalize_poissonian_noise(return_masks = True)
elif reproject == 'navigation':
_, signal_mask = \
self.normalize_poissonian_noise(return_masks = True,
signal_mask=signal_mask,)
elif reproject == 'signal':
navigation_mask, _ = \
self.normalize_poissonian_noise(return_masks = True,
navigation_mask=navigation_mask,)
messages.information('Performing decomposition analysis')
if on_peaks:
dc = self.mapped_parameters.peak_chars
else:
# The data must be transposed both for Images and Spectra
dc = self.data
#set the output target (peak results or not?)
target = self._get_target(on_peaks)
# Transform the None masks in slices to get the right behaviour
if navigation_mask is None:
navigation_mask = slice(None)
if signal_mask is None:
signal_mask = slice(None)
# Reset the explained_variance which is not set by all the algorithms
explained_variance = None
explained_variance_ratio = None
mean = None
if algorithm == 'svd':
factors, scores, explained_variance, mean = svd_pca(
dc[:,signal_mask][navigation_mask,:], centre = centre,
auto_transpose = auto_transpose)
elif algorithm == 'fast_svd':
factors, scores, explained_variance, mean = svd_pca(
dc[:,signal_mask][navigation_mask,:],
fast = True, output_dimension = output_dimension, centre = centre,
auto_transpose = auto_transpose)
elif algorithm == 'sklearn_pca':
sk = sklearn.decomposition.PCA(**kwargs)
sk.n_components = output_dimension
scores = sk.fit_transform((dc[:,signal_mask][navigation_mask,:]))
factors = sk.components_.T
explained_variance = sk.explained_variance_
mean = sk.mean_
centre = 'trials'
elif algorithm == 'nmf':
sk = sklearn.decomposition.NMF(**kwargs)
sk.n_components = output_dimension
scores = sk.fit_transform((dc[:,signal_mask][navigation_mask,:]))
factors = sk.components_.T
elif algorithm == 'sparse_pca':
sk = sklearn.decomposition.SparsePCA(output_dimension, **kwargs)
scores = sk.fit_transform(dc[:,signal_mask][navigation_mask,:])
factors = sk.components_.T
elif algorithm == 'mini_batch_sparse_pca':
sk = sklearn.decomposition.MiniBatchSparsePCA(output_dimension,
**kwargs)
scores = sk.fit_transform(dc[:,signal_mask][navigation_mask,:])
factors = sk.components_.T
elif algorithm == 'mlpca' or algorithm == 'fast_mlpca':
print "Performing the MLPCA training"
if output_dimension is None:
messages.warning_exit(
"For MLPCA it is mandatory to define the output_dimension")
if var_array is None and var_func is None:
messages.information('No variance array provided.'
'Supposing poissonian data')
var_array = dc[:,signal_mask][navigation_mask,:]
if var_array is not None and var_func is not None:
messages.warning_exit(
"You have defined both the var_func and var_array keywords"
"Please, define just one of them")
if var_func is not None:
if hasattr(var_func, '__call__'):
var_array = var_func(dc[signal_mask,...][:,navigation_mask])
else:
try:
var_array = np.polyval(polyfit,dc[signal_mask,
navigation_mask])
except:
messages.warning_exit(
'var_func must be either a function or an array'
'defining the coefficients of a polynom')
if algorithm == 'mlpca':
fast = False
else:
fast = True
U,S,V,Sobj, ErrFlag = mlpca(
dc[:,signal_mask][navigation_mask,:],
var_array, output_dimension, fast = fast)
scores = U * S
factors = V
explained_variance_ratio = S ** 2 / Sobj
explained_variance = S ** 2 / len(factors)
else:
messages.information('Error: Algorithm not recognised. '
'Nothing done')
return False
# We must calculate the ratio here because otherwise the sum information
# can be lost if the user call crop_decomposition_dimension
if explained_variance is not None and explained_variance_ratio is None:
explained_variance_ratio = \
explained_variance / explained_variance.sum()
# Store the results in mva_results
target.factors = factors
target.scores = scores
target.explained_variance = explained_variance
target.explained_variance_ratio = explained_variance_ratio
target.decomposition_algorithm = algorithm
target.poissonian_noise_normalized = \
normalize_poissonian_noise
target.output_dimension = output_dimension
target.unfolded = self._unfolded4decomposition
target.centre = centre
target.mean = mean
if output_dimension and factors.shape[1] != output_dimension:
target.crop_decomposition_dimension(output_dimension)
# Delete the unmixing information, because it'll refer to a previous
# decompositions
target.unmixing_matrix = None
target.ica_algorithm = None
if self._unfolded4decomposition is True:
target.original_shape = self._shape_before_unfolding
# Reproject
if mean is None:
mean = 0
if reproject in ('navigation', 'both'):
if algorithm not in ('nmf', 'sparse_pca', 'mini_batch_sparse_pca'):
scores_ = np.dot(dc[:,signal_mask] - mean, factors)
else:
scores_ = sk.transform(dc[:,signal_mask])
target.scores = scores_
if reproject in ('signal', 'both'):
if algorithm not in ('nmf', 'sparse_pca', 'mini_batch_sparse_pca'):
factors = np.dot(np.linalg.pinv(scores),
dc[navigation_mask,:] - mean).T
target.factors = factors
else:
messages.information("Reprojecting the signal is not yet "
"supported for this algorithm")
if reproject == 'both':
reproject = 'signal'
else:
reproject = None
# Rescale the results if the noise was normalized
if normalize_poissonian_noise is True:
target.factors[:] *= self._root_bH.T
target.scores[:] *= self._root_aG
# Set the pixels that were not processed to nan
if not isinstance(signal_mask, slice):
target.signal_mask = signal_mask
if reproject not in ('both', 'signal'):
factors = np.zeros((dc.shape[-1], target.factors.shape[1]))
factors[signal_mask == True,:] = target.factors
factors[signal_mask == False,:] = np.nan
target.factors = factors
if not isinstance(navigation_mask, slice):
target.navigation_mask = navigation_mask
if reproject not in ('both', 'navigation'):
scores = np.zeros((dc.shape[0], target.scores.shape[1]))
scores[navigation_mask == True,:] = target.scores
scores[navigation_mask == False,:] = np.nan
target.scores = scores
#undo any pre-treatments
self.undo_treatments(on_peaks)
if self._unfolded4decomposition is True:
self.fold()
self._unfolded4decomposition is False
def decomposition(self,
normalize_poissonian_noise=False,
algorithm='svd',
output_dimension=None,
centre=None,
auto_transpose=True,
navigation_mask=None,
signal_mask=None,
var_array=None,
var_func=None,
polyfit=None,
reproject=None,
**kwargs):
"""Decomposition with a choice of algorithms
The results are stored in self.learning_results
Parameters
----------
normalize_poissonian_noise : bool
If True, scale the SI to normalize Poissonian noise
algorithm : 'svd' | 'fast_svd' | 'mlpca' | 'fast_mlpca' | 'nmf' |
'sparse_pca' | 'mini_batch_sparse_pca'
output_dimension : None or int
number of components to keep/calculate
centre : None | 'variables' | 'trials'
If None no centring is applied. If 'variable' the centring will be
performed in the variable axis. If 'trials', the centring will be
performed in the 'trials' axis. It only has effect when using the
svd or fast_svd algorithms
auto_transpose : bool
If True, automatically transposes the data to boost performance.
Only has effect when using the svd of fast_svd algorithms.
navigation_mask : boolean numpy array
The navigation locations marked as True are not used in the
decompostion.
signal_mask : boolean numpy array
The signal locations marked as True are not used in the
decomposition.
var_array : numpy array
Array of variance for the maximum likelihood PCA algorithm
var_func : function or numpy array
If function, it will apply it to the dataset to obtain the
var_array. Alternatively, it can a an array with the coefficients
of a polynomial.
polyfit :
reproject : None | signal | navigation | both
If not None, the results of the decomposition will be projected in
the selected masked area.
See also
--------
plot_decomposition_factors, plot_decomposition_loadings, plot_lev
"""
# Check if it is the wrong data type
if self.data.dtype.char not in ['e', 'f', 'd']: # If not float
messages.warning(
'To perform a decomposition the data must be of the float '
'type. You can change the type using the change_dtype method'
' e.g. s.change_dtype(\'float64\')\n'
'Nothing done.')
return
if self.axes_manager.navigation_size < 2:
raise AttributeError("It is not possible to decompose a dataset "
"with navigation_size < 2")
# backup the original data
self._data_before_treatments = self.data.copy()
if algorithm == 'mlpca':
if normalize_poissonian_noise is True:
messages.warning(
"It makes no sense to do normalize_poissonian_noise with "
"the MLPCA algorithm. Therefore, "
"normalize_poissonian_noise is set to False")
normalize_poissonian_noise = False
if output_dimension is None:
raise ValueError("With the mlpca algorithm the "
"output_dimension must be expecified")
# Apply pre-treatments
# Transform the data in a line spectrum
self._unfolded4decomposition = self.unfold()
try:
if hasattr(navigation_mask, 'ravel'):
navigation_mask = navigation_mask.ravel()
if hasattr(signal_mask, 'ravel'):
signal_mask = signal_mask.ravel()
# Normalize the poissonian noise
# TODO this function can change the masks and this can cause
# problems when reprojecting
if normalize_poissonian_noise is True:
self.normalize_poissonian_noise(
navigation_mask=navigation_mask,
signal_mask=signal_mask,)
messages.information('Performing decomposition analysis')
# The rest of the code assumes that the first data axis
# is the navigation axis. We transpose the data if that is not the
# case.
dc = (self.data if self.axes_manager[0].index_in_array == 0
else self.data.T)
# set the output target (peak results or not?)
target = self.learning_results
# Transform the None masks in slices to get the right behaviour
if navigation_mask is None:
navigation_mask = slice(None)
else:
navigation_mask = ~navigation_mask
if signal_mask is None:
signal_mask = slice(None)
else:
signal_mask = ~signal_mask
# WARNING: signal_mask and navigation_mask values are now their
# negaties i.e. True -> False and viceversa. However, the
# stored value (at the end of the method) coincides with the
# input masks
# Reset the explained_variance which is not set by all the
# algorithms
explained_variance = None
explained_variance_ratio = None
mean = None
if algorithm == 'svd':
factors, loadings, explained_variance, mean = svd_pca(
dc[:, signal_mask][navigation_mask, :], centre=centre,
auto_transpose=auto_transpose)
elif algorithm == 'fast_svd':
factors, loadings, explained_variance, mean = svd_pca(
dc[:, signal_mask][navigation_mask, :],
fast=True,
output_dimension=output_dimension,
centre=centre,
auto_transpose=auto_transpose)
elif algorithm == 'sklearn_pca':
if import_sklearn.sklearn_installed is False:
raise ImportError(
'sklearn is not installed. Nothing done')
sk = import_sklearn.sklearn.decomposition.PCA(**kwargs)
sk.n_components = output_dimension
loadings = sk.fit_transform((
dc[:, signal_mask][navigation_mask, :]))
factors = sk.components_.T
explained_variance = sk.explained_variance_
mean = sk.mean_
centre = 'trials'
elif algorithm == 'nmf':
if import_sklearn.sklearn_installed is False:
raise ImportError(
'sklearn is not installed. Nothing done')
sk = import_sklearn.sklearn.decomposition.NMF(**kwargs)
sk.n_components = output_dimension
loadings = sk.fit_transform((
dc[:, signal_mask][navigation_mask, :]))
factors = sk.components_.T
elif algorithm == 'sparse_pca':
if import_sklearn.sklearn_installed is False:
raise ImportError(
'sklearn is not installed. Nothing done')
sk = import_sklearn.sklearn.decomposition.SparsePCA(
output_dimension, **kwargs)
loadings = sk.fit_transform(
dc[:, signal_mask][navigation_mask, :])
factors = sk.components_.T
elif algorithm == 'mini_batch_sparse_pca':
if import_sklearn.sklearn_installed is False:
raise ImportError(
'sklearn is not installed. Nothing done')
sk = import_sklearn.sklearn.decomposition.MiniBatchSparsePCA(
output_dimension, **kwargs)
loadings = sk.fit_transform(
dc[:, signal_mask][navigation_mask, :])
factors = sk.components_.T
elif algorithm == 'mlpca' or algorithm == 'fast_mlpca':
print "Performing the MLPCA training"
if output_dimension is None:
raise ValueError(
"For MLPCA it is mandatory to define the "
"output_dimension")
if var_array is None and var_func is None:
messages.information('No variance array provided.'
'Supposing poissonian data')
var_array = dc[:, signal_mask][navigation_mask, :]
if var_array is not None and var_func is not None:
raise ValueError(
"You have defined both the var_func and var_array "
"keywords."
"Please, define just one of them")
if var_func is not None:
if hasattr(var_func, '__call__'):
var_array = var_func(
dc[signal_mask, ...][:, navigation_mask])
else:
try:
var_array = np.polyval(
polyfit, dc[
signal_mask, navigation_mask])
except:
raise ValueError(
'var_func must be either a function or an '
'array defining the coefficients of a polynom')
if algorithm == 'mlpca':
fast = False
else:
fast = True
U, S, V, Sobj, ErrFlag = mlpca(
dc[:, signal_mask][navigation_mask, :],
var_array, output_dimension, fast=fast)
loadings = U * S
factors = V
explained_variance_ratio = S ** 2 / Sobj
explained_variance = S ** 2 / len(factors)
else:
raise ValueError('Algorithm not recognised. '
'Nothing done')
# We must calculate the ratio here because otherwise the sum
# information can be lost if the user call
# crop_decomposition_dimension
if explained_variance is not None and \
explained_variance_ratio is None:
explained_variance_ratio = \
explained_variance / explained_variance.sum()
# Store the results in learning_results
target.factors = factors
target.loadings = loadings
target.explained_variance = explained_variance
target.explained_variance_ratio = explained_variance_ratio
target.decomposition_algorithm = algorithm
target.poissonian_noise_normalized = \
normalize_poissonian_noise
target.output_dimension = output_dimension
target.unfolded = self._unfolded4decomposition
target.centre = centre
target.mean = mean
if output_dimension and factors.shape[1] != output_dimension:
target.crop_decomposition_dimension(output_dimension)
# Delete the unmixing information, because it'll refer to a
# previous decomposition
target.unmixing_matrix = None
target.bss_algorithm = None
if self._unfolded4decomposition is True:
folding = \
self.metadata._HyperSpy.Folding
target.original_shape = folding.original_shape
# Reproject
if mean is None:
mean = 0
if reproject in ('navigation', 'both'):
if algorithm not in ('nmf', 'sparse_pca',
'mini_batch_sparse_pca'):
loadings_ = np.dot(dc[:, signal_mask] - mean, factors)
else:
loadings_ = sk.transform(dc[:, signal_mask])
target.loadings = loadings_
if reproject in ('signal', 'both'):
if algorithm not in ('nmf', 'sparse_pca',
'mini_batch_sparse_pca'):
factors = np.dot(np.linalg.pinv(loadings),
dc[navigation_mask, :] - mean).T
target.factors = factors
else:
messages.information("Reprojecting the signal is not yet "
"supported for this algorithm")
if reproject == 'both':
reproject = 'signal'
else:
reproject = None
# Rescale the results if the noise was normalized
if normalize_poissonian_noise is True:
target.factors[:] *= self._root_bH.T
target.loadings[:] *= self._root_aG
# Set the pixels that were not processed to nan
if not isinstance(signal_mask, slice):
# Store the (inverted, as inputed) signal mask
target.signal_mask = ~signal_mask.reshape(
self.axes_manager._signal_shape_in_array)
if reproject not in ('both', 'signal'):
factors = np.zeros((dc.shape[-1], target.factors.shape[1]))
factors[signal_mask, :] = target.factors
factors[~signal_mask, :] = np.nan
target.factors = factors
if not isinstance(navigation_mask, slice):
# Store the (inverted, as inputed) navigation mask
target.navigation_mask = ~navigation_mask.reshape(
self.axes_manager._navigation_shape_in_array)
if reproject not in ('both', 'navigation'):
loadings = np.zeros(
(dc.shape[0], target.loadings.shape[1]))
loadings[navigation_mask, :] = target.loadings
loadings[~navigation_mask, :] = np.nan
target.loadings = loadings
finally:
# undo any pre-treatments
self.undo_treatments()
if self._unfolded4decomposition is True:
self.fold()
self._unfolded4decomposition is False
def decomposition(self,
normalize_poissonian_noise=False,
algorithm = 'svd',
output_dimension=None,
centre=None,
auto_transpose=True,
navigation_mask=None,
signal_mask=None,
var_array=None,
var_func=None,
polyfit=None,
reproject=None,
**kwargs):
"""Decomposition with a choice of algorithms
The results are stored in self.learning_results
Parameters
----------
normalize_poissonian_noise : bool
If True, scale the SI to normalize Poissonian noise
algorithm : 'svd' | 'fast_svd' | 'mlpca' | 'fast_mlpca' | 'nmf' |
'sparse_pca' | 'mini_batch_sparse_pca'
output_dimension : None or int
number of components to keep/calculate
centre : None | 'variables' | 'trials'
If None no centring is applied. If 'variable' the centring will be
performed in the variable axis. If 'trials', the centring will be
performed in the 'trials' axis. It only has effect when using the
svd or fast_svd algorithms
auto_transpose : bool
If True, automatically transposes the data to boost performance.
Only has effect when using the svd of fast_svd algorithms.
navigation_mask : boolean numpy array
The navigation locations marked as True are not used in the
decompostion.
signal_mask : boolean numpy array
The signal locations marked as True are not used in the
decomposition.
var_array : numpy array
Array of variance for the maximum likelihood PCA algorithm
var_func : function or numpy array
If function, it will apply it to the dataset to obtain the
var_array. Alternatively, it can a an array with the coefficients
of a polynomial.
polyfit :
reproject : None | signal | navigation | both
If not None, the results of the decomposition will be projected in
the selected masked area.
See also
--------
plot_decomposition_factors, plot_decomposition_loadings, plot_lev
"""
# Check if it is the wrong data type
if self.data.dtype.char not in ['e', 'f', 'd']: # If not float
messages.warning(
'To perform a decomposition the data must be of the float type.'
' You can change the type using the change_dtype method'
' e.g. s.change_dtype(\'float64\')\n'
'Nothing done.')
return
# backup the original data
self._data_before_treatments = self.data.copy()
if algorithm == 'mlpca':
if normalize_poissonian_noise is True:
messages.warning(
"It makes no sense to do normalize_poissonian_noise with "
"the MLPCA algorithm. Therefore, "
"normalize_poissonian_noise is set to False")
normalize_poissonian_noise = False
if output_dimension is None:
messages.warning_exit("With the mlpca algorithm the "
"output_dimension must be expecified")
# Apply pre-treatments
# Transform the data in a line spectrum
self._unfolded4decomposition = self.unfold_if_multidim()
try:
if hasattr(navigation_mask, 'ravel'):
navigation_mask = navigation_mask.ravel()
if hasattr(signal_mask, 'ravel'):
signal_mask = signal_mask.ravel()
# Normalize the poissonian noise
# TODO this function can change the masks and this can cause
# problems when reprojecting
if normalize_poissonian_noise is True:
self.normalize_poissonian_noise(
navigation_mask=navigation_mask,
signal_mask=signal_mask,)
messages.information('Performing decomposition analysis')
dc = self.data
#set the output target (peak results or not?)
target = self.learning_results
# Transform the None masks in slices to get the right behaviour
if navigation_mask is None:
navigation_mask = slice(None)
else:
navigation_mask = ~navigation_mask
if signal_mask is None:
signal_mask = slice(None)
else:
signal_mask = ~signal_mask
# WARNING: signal_mask and navigation_mask values are now their
# negaties i.e. True -> False and viceversa. However, the
# stored value (at the end of the method) coincides with the
# input masks
# Reset the explained_variance which is not set by all the
# algorithms
explained_variance = None
explained_variance_ratio = None
mean = None
if algorithm == 'svd':
factors, loadings, explained_variance, mean = svd_pca(
dc[:,signal_mask][navigation_mask,:], centre = centre,
auto_transpose = auto_transpose)
elif algorithm == 'fast_svd':
factors, loadings, explained_variance, mean = svd_pca(
dc[:,signal_mask][navigation_mask,:],
fast=True,
output_dimension=output_dimension,
centre=centre,
auto_transpose=auto_transpose)
elif algorithm == 'sklearn_pca':
if sklearn_installed is False:
raise ImportError(
'sklearn is not installed. Nothing done')
sk = sklearn.decomposition.PCA(**kwargs)
sk.n_components = output_dimension
loadings = sk.fit_transform((
dc[:,signal_mask][navigation_mask,:]))
factors = sk.components_.T
explained_variance = sk.explained_variance_
mean = sk.mean_
centre = 'trials'
elif algorithm == 'nmf':
if sklearn_installed is False:
raise ImportError(
'sklearn is not installed. Nothing done')
sk = sklearn.decomposition.NMF(**kwargs)
sk.n_components = output_dimension
loadings = sk.fit_transform((
dc[:,signal_mask][navigation_mask,:]))
factors = sk.components_.T
elif algorithm == 'sparse_pca':
if sklearn_installed is False:
raise ImportError(
'sklearn is not installed. Nothing done')
sk = sklearn.decomposition.SparsePCA(
output_dimension, **kwargs)
loadings = sk.fit_transform(
dc[:,signal_mask][navigation_mask,:])
factors = sk.components_.T
elif algorithm == 'mini_batch_sparse_pca':
if sklearn_installed is False:
raise ImportError(
'sklearn is not installed. Nothing done')
sk = sklearn.decomposition.MiniBatchSparsePCA(
output_dimension, **kwargs)
loadings = sk.fit_transform(
dc[:,signal_mask][navigation_mask,:])
factors = sk.components_.T
elif algorithm == 'mlpca' or algorithm == 'fast_mlpca':
print "Performing the MLPCA training"
if output_dimension is None:
messages.warning_exit(
"For MLPCA it is mandatory to define the "
"output_dimension")
if var_array is None and var_func is None:
messages.information('No variance array provided.'
'Supposing poissonian data')
var_array = dc[:,signal_mask][navigation_mask,:]
if var_array is not None and var_func is not None:
messages.warning_exit(
"You have defined both the var_func and var_array "
"keywords."
"Please, define just one of them")
if var_func is not None:
if hasattr(var_func, '__call__'):
var_array = var_func(
dc[signal_mask,...][:,navigation_mask])
else:
try:
var_array = np.polyval(polyfit,dc[signal_mask,
navigation_mask])
except:
messages.warning_exit(
'var_func must be either a function or an array'
'defining the coefficients of a polynom')
if algorithm == 'mlpca':
fast = False
else:
fast = True
U,S,V,Sobj, ErrFlag = mlpca(
dc[:,signal_mask][navigation_mask,:],
var_array, output_dimension, fast = fast)
loadings = U * S
factors = V
explained_variance_ratio = S ** 2 / Sobj
explained_variance = S ** 2 / len(factors)
else:
raise ValueError('Algorithm not recognised. '
'Nothing done')
# We must calculate the ratio here because otherwise the sum
# information can be lost if the user call
# crop_decomposition_dimension
if explained_variance is not None and \
explained_variance_ratio is None:
explained_variance_ratio = \
explained_variance / explained_variance.sum()
# Store the results in learning_results
target.factors = factors
target.loadings = loadings
target.explained_variance = explained_variance
target.explained_variance_ratio = explained_variance_ratio
target.decomposition_algorithm = algorithm
target.poissonian_noise_normalized = \
normalize_poissonian_noise
target.output_dimension = output_dimension
target.unfolded = self._unfolded4decomposition
target.centre = centre
target.mean = mean
if output_dimension and factors.shape[1] != output_dimension:
target.crop_decomposition_dimension(output_dimension)
# Delete the unmixing information, because it'll refer to a previous
# decompositions
target.unmixing_matrix = None
target.bss_algorithm = None
if self._unfolded4decomposition is True:
folding = \
self.mapped_parameters._internal_parameters.folding
target.original_shape = folding.original_shape
# Reproject
if mean is None:
mean = 0
if reproject in ('navigation', 'both'):
if algorithm not in ('nmf', 'sparse_pca',
'mini_batch_sparse_pca'):
loadings_ = np.dot(dc[:,signal_mask] - mean, factors)
else:
loadings_ = sk.transform(dc[:,signal_mask])
target.loadings = loadings_
if reproject in ('signal', 'both'):
if algorithm not in ('nmf', 'sparse_pca',
'mini_batch_sparse_pca'):
factors = np.dot(np.linalg.pinv(loadings),
dc[navigation_mask,:] - mean).T
target.factors = factors
else:
messages.information("Reprojecting the signal is not yet "
"supported for this algorithm")
if reproject == 'both':
reproject = 'signal'
else:
reproject = None
# Rescale the results if the noise was normalized
if normalize_poissonian_noise is True:
target.factors[:] *= self._root_bH.T
target.loadings[:] *= self._root_aG
# Set the pixels that were not processed to nan
if not isinstance(signal_mask, slice):
# Store the (inverted, as inputed) signal mask
target.signal_mask = ~signal_mask.reshape(
self.axes_manager._signal_shape_in_array)
if reproject not in ('both', 'signal'):
factors = np.zeros((dc.shape[-1], target.factors.shape[1]))
factors[signal_mask == True,:] = target.factors
factors[signal_mask == False,:] = np.nan
target.factors = factors
if not isinstance(navigation_mask, slice):
# Store the (inverted, as inputed) navigation mask
target.navigation_mask = ~navigation_mask.reshape(
self.axes_manager._navigation_shape_in_array)
if reproject not in ('both', 'navigation'):
loadings = np.zeros((dc.shape[0], target.loadings.shape[1]))
loadings[navigation_mask == True,:] = target.loadings
loadings[navigation_mask == False,:] = np.nan
target.loadings = loadings
finally:
#undo any pre-treatments
self.undo_treatments()
if self._unfolded4decomposition is True:
self.fold()
self._unfolded4decomposition is False
def test_centre_error(self):
with pytest.raises(ValueError, match="'centre' must be one of"):
_ = svd_pca(self.X, centre="random")
def test_arpack_error(self):
with pytest.raises(ValueError,
match="requires output_dimension to be strictly"):
_ = svd_pca(self.X,
output_dimension=min(self.X.shape) + 1,
svd_solver="arpack")
