Closed
Description
Description
TSNE learning on digit dataset throws error for perplexity=8
Steps/Code to Reproduce
from sklearn import manifold, datasets
data = datasets.load_digits()
X = data['data']
n_components = 2
tsne = manifold.TSNE(n_components=n_components, init='pca', perplexity=8,
random_state=0, verbose=0)
Y = tsne.fit_transform(X)Expected Results
No error.
Actual Results
---------------------------------------------------------------------------
AssertionError Traceback (most recent call last)
<ipython-input-9-553b1868b3c8> in <module>()
11 tsne = manifold.TSNE(n_components=n_components, init='pca', perplexity=8,
12 random_state=0, verbose=0)
---> 13 Y = tsne.fit_transform(X)
/home/owner/py27_env/local/lib/python2.7/site-packages/sklearn/manifold/t_sne.pyc in fit_transform(self, X, y)
895 Embedding of the training data in low-dimensional space.
896 """
--> 897 embedding = self._fit(X)
898 self.embedding_ = embedding
899 return self.embedding_
/home/owner/py27_env/local/lib/python2.7/site-packages/sklearn/manifold/t_sne.pyc in _fit(self, X, skip_num_points)
792 X_embedded=X_embedded,
793 neighbors=neighbors_nn,
--> 794 skip_num_points=skip_num_points)
795
796 @property
/home/owner/py27_env/local/lib/python2.7/site-packages/sklearn/manifold/t_sne.pyc in _tsne(self, P, degrees_of_freedom, n_samples, random_state, X_embedded, neighbors, skip_num_points)
868 opt_args['it'] = it + 1
869 params, kl_divergence, it = _gradient_descent(obj_func, params,
--> 870 **opt_args)
871
872 if self.verbose:
/home/owner/py27_env/local/lib/python2.7/site-packages/sklearn/manifold/t_sne.pyc in _gradient_descent(objective, p0, it, n_iter, objective_error, n_iter_check, n_iter_without_progress, momentum, learning_rate, min_gain, min_grad_norm, min_error_diff, verbose, args, kwargs)
386
387 for i in range(it, n_iter):
--> 388 new_error, grad = objective(p, *args, **kwargs)
389 grad_norm = linalg.norm(grad)
390
/home/owner/py27_env/local/lib/python2.7/site-packages/sklearn/manifold/t_sne.pyc in _kl_divergence_bh(params, P, neighbors, degrees_of_freedom, n_samples, n_components, angle, skip_num_points, verbose)
289 error = _barnes_hut_tsne.gradient(sP, X_embedded, neighbors,
290 grad, angle, n_components, verbose,
--> 291 dof=degrees_of_freedom)
292 c = 2.0 * (degrees_of_freedom + 1.0) / degrees_of_freedom
293 grad = grad.ravel()
sklearn/manifold/_barnes_hut_tsne.pyx in sklearn.manifold._barnes_hut_tsne.gradient (sklearn/manifold/_barnes_hut_tsne.c:8155)()
AssertionError: Tree consistency failed: unexpected number of points=1796 at root node=1797
Versions
Linux-4.4.0-78-generic-x86_64-with-Ubuntu-16.04-xenial
('Python', '2.7.12 (default, Jul 1 2016, 15:12:24) \n[GCC 5.4.0 20160609]')
('NumPy', '1.12.1')
('SciPy', '0.18.1')
('Scikit-Learn', '0.19.dev0')
Note:
No error encountered for perplexity = 7 or 9, or any other values tried.