def pca_transform_daal(pca_result,
X,
n_components,
fit_n_samples,
eigenvalues,
eigenvectors,
whiten=False,
scale_eigenvalues=False):
fptype = getFPType(X)
tr_data = {}
tr_data['mean'] = pca_result.dataForTransform['mean']
if whiten:
if scale_eigenvalues:
tr_data['eigenvalue'] = (fit_n_samples - 1) \
* pca_result.eigenvalues
else:
tr_data['eigenvalue'] = pca_result.eigenvalues
elif scale_eigenvalues:
tr_data['eigenvalue'] = np.full((1, pca_result.eigenvalues.size),
fit_n_samples - 1,
dtype=X.dtype)
transform_algorithm = pca_transform(fptype=fptype,
nComponents=n_components)
transform_result = transform_algorithm.compute(X, pca_result.eigenvectors,
tr_data)
return transform_result.transformedData
def _transform_daal4py(self, X, whiten=False, scale_eigenvalues=True, check_X=True):
check_is_fitted(self)
X = check_array(X, dtype=[np.float64, np.float32], force_all_finite=check_X)
fpType = getFPType(X)
tr_data = dict()
if self.mean_ is not None:
tr_data['mean'] = self.mean_.reshape((1, -1))
if whiten:
if scale_eigenvalues:
tr_data['eigenvalue'] = (self.n_samples_ - 1) * self.explained_variance_.reshape((1, -1))
else:
tr_data['eigenvalue'] = self.explained_variance_.reshape((1, -1))
elif scale_eigenvalues:
tr_data['eigenvalue'] = np.full(
(1, self.explained_variance_.shape[0]),
self.n_samples_ - 1.0, dtype=X.dtype)
if X.shape[1] != self.n_features_:
raise ValueError("The number of features of the input data, {}, is not "
"equal to the number of features of the training data, {}".format(
X.shape[1], self.n_features_))
tr_res = daal4py.pca_transform(
fptype=fpType
).compute(X, self.components_, tr_data)
return tr_res.transformedData
def compute(data, nComponents):
# configure a PCA object and perform PCA
pca_algo = d4p.pca(isDeterministic=True, resultsToCompute="mean|variance|eigenvalue")
pca_res = pca_algo.compute(data)
# Apply transform with whitening because means and eigenvalues are provided
pcatrans_algo = d4p.pca_transform(nComponents=nComponents)
return pcatrans_algo.compute(data, pca_res.eigenvectors, pca_res.dataForTransform)
def main(readcsv=read_csv, method='svdDense'):
dataFileName = "data/batch/pca_transform.csv"
nComponents = 2
# read data
data = readcsv(dataFileName, range(3))
# configure a PCA object and perform PCA
pca_algo = d4p.pca(isDeterministic=True, resultsToCompute="mean|variance|eigenvalue")
pca_res = pca_algo.compute(data)
# Apply transform with whitening because means and eigenvalues are provided
pcatrans_algo = d4p.pca_transform(nComponents=nComponents)
pcatrans_res = pcatrans_algo.compute(data, pca_res.eigenvectors,
pca_res.dataForTransform)
# pca_transform_result objects provides transformedData
return (pca_res, pcatrans_res)
def run_pca_daal4py_corr(X, Y):
algo = d4p.pca(resultsToCompute="mean|variance|eigenvalue",
isDeterministic=True,
method="correlationDense")
result1 = algo.compute(X)
pcatrans_algo = d4p.pca_transform(nComponents=X.shape[1] // 2)
transform = pcatrans_algo.compute(X, result1.eigenvectors,
result1.dataForTransform).transformedData
res = [
transform, result1.eigenvalues, result1.eigenvectors, result1.means,
result1.variances
]
name = [
"transform", "result1.eigenvalues", "result1.eigenvectors",
"result1.means", "result1.variances"
]
return res, name
def _transform_daal4py(self,
X,
whiten=False,
scale_eigenvalues=True,
check_X=True):
if sklearn_check_version('0.22'):
check_is_fitted(self)
else:
check_is_fitted(self, ['mean_', 'components_'], all_or_any=all)
if sklearn_check_version("1.0"):
self._check_feature_names(X, reset=False)
X = check_array(X,
dtype=[np.float64, np.float32],
force_all_finite=check_X)
fpType = getFPType(X)
tr_data = dict()
if self.mean_ is not None:
tr_data['mean'] = self.mean_.reshape((1, -1))
if whiten:
if scale_eigenvalues:
tr_data['eigenvalue'] = \
(self.n_samples_ - 1) * self.explained_variance_.reshape((1, -1))
else:
tr_data['eigenvalue'] = self.explained_variance_.reshape(
(1, -1))
elif scale_eigenvalues:
tr_data['eigenvalue'] = np.full(
(1, self.explained_variance_.shape[0]),
self.n_samples_ - 1.0,
dtype=X.dtype)
if X.shape[1] != self.n_features_:
raise ValueError(
(f'X has {X.shape[1]} features, '
f'but PCA is expecting {self.n_features_} features as input'))
tr_res = daal4py.pca_transform(fptype=fpType).compute(
X, self.components_, tr_data)
return tr_res.transformedData