Skip to content
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

Jump to bottom

Fix for AttributeError thrown when calling metrics.pairwise_distances with binary metrics and Y is None #13864

Merged
merged 6 commits into from May 13, 2019
Merged

Fix for AttributeError thrown when calling metrics.pairwise_distances with binary metrics and Y is None #13864

Changes from 2 commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
0813142
add fix for PAIRWISE_BOOLEAN_FUNCTIONS, issue 13853
rick2047 May 11, 2019
3be3059
fix flake8 issues
rick2047 May 11, 2019
77a8035
Update sklearn/metrics/pairwise.py
rick2047 May 12, 2019
fd75262
TEST add a non-regression test
ogrisel May 13, 2019
ea2ed88
DOC add a what's new entry
ogrisel May 13, 2019
aed6a40
Typos in version numbers
ogrisel May 13, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
14 changes: 7 additions & 7 deletions sklearn/metrics/pairwise.py
View file
Open in desktop
Expand Up @@ -306,7 +306,7 @@ def _euclidean_distances_upcast(X, XX=None, Y=None, YY=None):
maxmem = max(
((x_density * n_samples_X + y_density * n_samples_Y) * n_features
+ (x_density * n_samples_X * y_density * n_samples_Y)) / 10,
10 * 2**17)
10 * 2 ** 17)

# The increase amount of memory in 8-byte blocks is:
# - x_density * batch_size * n_features (copy of chunk of X)
Expand All @@ -315,7 +315,7 @@ def _euclidean_distances_upcast(X, XX=None, Y=None, YY=None):
# Hence x² + (xd+yd)kx = M, where x=batch_size, k=n_features, M=maxmem
# xd=x_density and yd=y_density
tmp = (x_density + y_density) * n_features
batch_size = (-tmp + np.sqrt(tmp**2 + 4 * maxmem)) / 2
batch_size = (-tmp + np.sqrt(tmp ** 2 + 4 * maxmem)) / 2
batch_size = max(int(batch_size), 1)

x_batches = gen_batches(X.shape[0], batch_size)
Expand Down Expand Up @@ -900,7 +900,7 @@ def sigmoid_kernel(X, Y=None, gamma=None, coef0=1):
K = safe_sparse_dot(X, Y.T, dense_output=True)
K *= gamma
K += coef0
np.tanh(K, K) # compute tanh in-place
np.tanh(K, K) # compute tanh in-place
return K


Expand Down Expand Up @@ -933,7 +933,7 @@ def rbf_kernel(X, Y=None, gamma=None):

K = euclidean_distances(X, Y, squared=True)
K *= -gamma
np.exp(K, K) # exponentiate K in-place
np.exp(K, K) # exponentiate K in-place
return K


Expand Down Expand Up @@ -967,7 +967,7 @@ def laplacian_kernel(X, Y=None, gamma=None):
gamma = 1.0 / X.shape[1]

K = -gamma * manhattan_distances(X, Y)
np.exp(K, K) # exponentiate K in-place
np.exp(K, K) # exponentiate K in-place
return K


Expand Down Expand Up @@ -1545,7 +1545,8 @@ def pairwise_distances(X, Y=None, metric="euclidean", n_jobs=None, **kwds):

dtype = bool if metric in PAIRWISE_BOOLEAN_FUNCTIONS else None

if dtype == bool and (X.dtype != bool or Y.dtype != bool):
if dtype == bool and \
(X.dtype != bool or not ((Y is None) or Y.dtype == bool)):
rick2047 marked this conversation as resolved.
Show resolved Hide resolved
msg = "Data was converted to boolean for metric %s" % metric
warnings.warn(msg, DataConversionWarning)

Expand Down Expand Up @@ -1576,7 +1577,6 @@ def pairwise_distances(X, Y=None, metric="euclidean", n_jobs=None, **kwds):
'yule',
]


# Helper functions - distance
PAIRWISE_KERNEL_FUNCTIONS = {
# If updating this dictionary, update the doc in both distance_metrics()
Expand Down