def test_predict(X, training_result, params):
fptype = getFPType(X)
kf = daal_kernel(params.kernel, fptype, gamma=params.gamma)
svm_predict = svm_prediction(fptype=fptype,
method='defaultDense',
kernel=kf)
if params.n_classes == 2:
prdct = svm_predict
else:
prdct = multi_class_classifier_prediction(nClasses=params.n_classes,
fptype=fptype,
maxIterations=params.maxiter,
accuracyThreshold=params.tol,
pmethod='voteBased',
tmethod='oneAgainstOne',
prediction=svm_predict)
res = prdct.compute(X, training_result.model)
if params.n_classes == 2:
y_predict = np.greater(res.prediction.ravel(), 0)
else:
y_predict = res.prediction.ravel()
return y_predict
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 df_regr_fit(X,
y,
n_trees=100,
seed=12345,
n_features_per_node=0,
max_depth=0,
min_impurity=0,
bootstrap=True):
fptype = getFPType(X)
features_per_node = X.shape[1]
if n_features_per_node > 0 and n_features_per_node <= features_per_node:
features_per_node = n_features_per_node
engine = engines_mt2203(seed=seed, fptype=fptype)
algorithm = decision_forest_regression_training(
fptype=fptype,
method='defaultDense',
nTrees=n_trees,
observationsPerTreeFraction=1.,
featuresPerNode=features_per_node,
maxTreeDepth=max_depth,
minObservationsInLeafNode=1,
engine=engine,
impurityThreshold=min_impurity,
varImportance='MDI',
resultsToCompute='',
memorySavingMode=False,
bootstrap=bootstrap)
df_regr_result = algorithm.compute(X, y)
return df_regr_result
def test_predict(X, X_init):
algorithm = kmeans(fptype=getFPType(X),
nClusters=params.n_clusters,
maxIterations=0,
assignFlag=True,
accuracyThreshold=0.0)
return algorithm.compute(X, X_init)
def __init__(self, X, y, beta, hess=False, fit_intercept=True):
self.compute_hess = hess
self.n = X.shape[0]
self.fptype = getFPType(X)
self.fit_intercept = fit_intercept
self.X = make2d(X)
self.y = make2d(y)
self.last_beta = beta.copy()
self.func = None
self.grad = None
self.hess = None
def test_fit(X, y, params):
fptype = getFPType(X)
kf = daal_kernel(params.kernel, fptype, gamma=params.gamma)
if params.n_classes == 2:
y[y == 0] = -1
else:
y[y == -1] = 0
svm_train = svm_training(fptype=fptype,
C=params.C,
maxIterations=params.maxiter,
tau=params.tau,
cacheSize=params.cache_size_bytes,
accuracyThreshold=params.tol,
doShrinking=params.shrinking,
kernel=kf)
if params.n_classes == 2:
clf = svm_train
else:
clf = multi_class_classifier_training(fptype=fptype,
nClasses=params.n_classes,
accuracyThreshold=params.tol,
method='oneAgainstOne',
maxIterations=params.maxiter,
training=svm_train)
training_result = clf.compute(X, y)
support = construct_dual_coefs(training_result.model, params.n_classes, X,
y)
indices = y.take(support, axis=0)
if params.n_classes == 2:
n_support_ = np.array([np.sum(indices == -1),
np.sum(indices == 1)],
dtype=np.int32)
else:
n_support_ = np.array([
np.sum(indices == c)
for c in [-1] + list(range(1, params.n_classes))
],
dtype=np.int32)
return training_result, support, indices, n_support_
def test_predict(X, beta, intercept=0, multi_class='ovr'):
fptype = getFPType(X)
scores = np.dot(X, beta.T) + intercept
if multi_class == 'ovr':
# use binary logistic regressions and normalize
logistic = math_logistic(fptype=fptype, method='defaultDense')
prob = logistic.compute(scores).value
if prob.shape[1] == 1:
return np.c_[1 - prob, prob]
else:
return prob / prob.sum(axis=1)[:, np.newaxis]
else:
# use softmax of exponentiated scores
if scores.shape[1] == 1:
scores = np.c_[-scores, scores]
softmax = math_softmax(fptype=fptype, method='defaultDense')
return softmax.compute(scores).value
def pca_fit_daal(X, n_components, method):
if n_components < 1:
n_components = min(X.shape)
fptype = getFPType(X)
centering_algo = normalization_zscore(fptype=fptype, doScale=False)
pca_algorithm = pca(fptype=fptype,
method=method,
normalization=centering_algo,
resultsToCompute='mean|variance|eigenvalue',
isDeterministic=True,
nComponents=n_components)
pca_result = pca_algorithm.compute(X)
eigenvectors = pca_result.eigenvectors
eigenvalues = pca_result.eigenvalues.ravel()
singular_values = np.sqrt((X.shape[0] - 1) * eigenvalues)
return pca_result, eigenvalues, eigenvectors, singular_values
def compute_distances(pairwise_distances, X):
algorithm = pairwise_distances(fptype=getFPType(X))
return algorithm.compute(X)
def test_dbscan(X):
algorithm = dbscan(fptype=getFPType(X),
epsilon=params.eps,
minObservations=params.min_samples,
resultsToCompute='computeCoreIndices')
return algorithm.compute(X)
def test_predict(Xp, model):
regr_predict = linear_regression_prediction(fptype=getFPType(Xp))
return regr_predict.compute(Xp, model)
def test_fit(X, y):
regr_train = linear_regression_training(fptype=getFPType(X),
method=params.method,
interceptFlag=params.fit_intercept)
return regr_train.compute(X, y)
def test_fit(X, y):
regr_train = ridge_regression_training(fptype=getFPType(X),
ridgeParameters=np.array(
[[params.alpha]]),
interceptFlag=params.fit_intercept)
return regr_train.compute(X, y)