Skip to content

Increase training and inference performance for GAK kernel #77

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

Open
wants to merge 7 commits into
base: main
Choose a base branch
from
Open

Increase training and inference performance for GAK kernel #77

Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
48587e3
initial implementation of sparse sim matrix using support vectors
Oct 21, 2018
c86fef3
dataset2 should be set to None to trigger self_similarity
Oct 21, 2018
67b8bb3
remove comments
Oct 21, 2018
6ea1847
modified comment
Oct 21, 2018
bb75442
Made statement more compact
Oct 21, 2018
e8ca156
Changed to more logical order
Oct 21, 2018
0f2a5b0
Ommit introduction of new variable
Oct 22, 2018
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
31 changes: 28 additions & 3 deletions tslearn/svm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,6 +32,29 @@ def _kernel_func_gak(sz, d, gamma):
gamma = 1.
return lambda x, y: cdist_gak(x.reshape((-1, sz, d)), y.reshape((-1, sz, d)), sigma=numpy.sqrt(gamma / 2.))

def _sparse_kernel_func_gak(sz, d, gamma, slice_support_vectors=None):
if gamma == "auto":
gamma = 1.

def sparse_gak(X, X_fit):

if X_fit is X:
return cdist_gak(X.reshape((-1, sz, d)), None, sigma=numpy.sqrt(gamma / 2.))

if slice_support_vectors is not None:
# slice out support vectors
sliced_X_fit = X_fit[slice_support_vectors]
gak_sim_dense = cdist_gak(X.reshape((-1, sz, d)), sliced_X_fit.reshape((-1, sz, d)), sigma=numpy.sqrt(gamma / 2.))

# act like nothing has happend ...
gak_sim = numpy.empty((len(X), len(X_fit)))
gak_sim[:, slice_support_vectors] = gak_sim_dense

return gak_sim

return cdist_gak(X.reshape((-1, sz, d)), X_fit.reshape((-1, sz, d)), sigma=numpy.sqrt(gamma / 2.))

return sparse_gak

class TimeSeriesSVC(BaseSVC):
"""Time-series specific Support Vector Classifier.
Expand Down Expand Up @@ -148,7 +171,7 @@ def __init__(self, sz, d, C=1.0, kernel="gak", degree=3, gamma="auto", coef0=0.0
self.sz = sz
self.d = d
if kernel == "gak":
kernel = _kernel_func_gak(sz=sz, d=d, gamma=gamma)
kernel = _sparse_kernel_func_gak(sz=sz, d=d, gamma=gamma)
super(TimeSeriesSVC, self).__init__(C=C, kernel=kernel, degree=degree, gamma=gamma, coef0=coef0,
shrinking=shrinking, probability=probability, tol=tol,
cache_size=cache_size, class_weight=class_weight, verbose=verbose,
Expand All @@ -169,8 +192,10 @@ def fit(self, X, y, sample_weight=None):
sklearn_X = _prepare_ts_datasets_sklearn(X)
if self.kernel == "gak" and self.gamma == "auto":
self.gamma = gamma_soft_dtw(to_time_series_dataset(X))
self.kernel = _kernel_func_gak(sz=self.sz, d=self.d, gamma=self.gamma)
return super(TimeSeriesSVC, self).fit(sklearn_X, y, sample_weight=sample_weight)
self.kernel = _sparse_kernel_func_gak(sz=self.sz, d=self.d, gamma=self.gamma)
super(TimeSeriesSVC, self).fit(sklearn_X, y, sample_weight=sample_weight)
self.kernel = _sparse_kernel_func_gak(sz=self.sz, d=self.d, gamma=self.gamma, slice_support_vectors=self.support_)
return self

def predict(self, X):
sklearn_X = _prepare_ts_datasets_sklearn(X)
Expand Down