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

Fixed NaN probability scores in BernoulliNB converter when alpha=0 #238

Merged
merged 3 commits into from
Aug 28, 2019
Merged

Fixed NaN probability scores in BernoulliNB converter when alpha=0 #238

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
b555320
Fixed NaN probability scores in BernoulliNB converter when alpha=0
Aug 27, 2019
0be03b7
Merge branch 'master' into prroy/bernoullinb
Aug 27, 2019
d864b1d
Merge branch 'master' into prroy/bernoullinb
Aug 28, 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
5 changes: 3 additions & 2 deletions skl2onnx/operator_converters/naive_bayes.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -237,8 +237,9 @@ def convert_sklearn_naive_bayes(scope, operator, container):
dot_prod_name = scope.get_unique_variable_name('dot_prod')
partial_sum_result_name = scope.get_unique_variable_name(
'partial_sum_result')

container.add_initializer(constant_name, proto_type, [], [1.0])
# Define constant slightly greater than 1 to avoid log 0
# scenarios when calculating log (1 - x) and x=1 in line 273
container.add_initializer(constant_name, proto_type, [], [1.000000001])
xadupre marked this conversation as resolved.
Show resolved Hide resolved

if nb.binarize is not None:
threshold_name = scope.get_unique_variable_name('threshold')
Expand Down