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

Fix symmetrical case for hellinger distance. Fix #1854 #1860

Merged
merged 3 commits into from
Jan 30, 2018
Merged

Fix symmetrical case for hellinger distance. Fix #1854 #1860

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
1277067
fix: fix bugs in hellinger distance computing
caiyulun Jan 26, 2018
d4ae548
rename variable + fix union indices error in python3
caiyulun Jan 29, 2018
7ae1532
fix and add tests for hellinger distance
caiyulun Jan 29, 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
5 changes: 2 additions & 3 deletions gensim/matutils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -897,10 +897,9 @@ def hellinger(vec1, vec2):
if isbow(vec1) and isbow(vec2):
# if it is a BoW format, instead of converting to dense we use dictionaries to calculate appropriate distance
vec1, vec2 = dict(vec1), dict(vec2)
if len(vec2) < len(vec1):
vec1, vec2 = vec2, vec1 # swap references so that we iterate over the shorter vector
indices = set(list(vec1.keys()) + list(vec2.keys()))
sim = np.sqrt(
0.5 * sum((np.sqrt(value) - np.sqrt(vec2.get(index, 0.0)))**2 for index, value in iteritems(vec1))
0.5 * sum((np.sqrt(vec1.get(index, 0.0)) - np.sqrt(vec2.get(index, 0.0)))**2 for index in indices)
)
return sim
else:
Expand Down
13 changes: 11 additions & 2 deletions gensim/test/test_similarity_metrics.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -105,12 +105,21 @@ def test_inputs(self):

def test_distributions(self):

# checking bag of words as inputs
# checking different length bag of words as inputs
vec_1 = [(2, 0.1), (3, 0.4), (4, 0.1), (5, 0.1), (1, 0.1), (7, 0.2)]
vec_2 = [(1, 0.1), (3, 0.8), (4, 0.1)]
result = matutils.hellinger(vec_1, vec_2)
expected = 0.185241936534
expected = 0.484060507634
self.assertAlmostEqual(expected, result)

# checking symmetrical bag of words inputs return same distance
vec_1 = [(2, 0.1), (3, 0.4), (4, 0.1), (5, 0.1), (1, 0.1), (7, 0.2)]
vec_2 = [(1, 0.1), (3, 0.8), (4, 0.1), (8, 0.1), (10, 0.8), (9, 0.1)]
result = matutils.hellinger(vec_1, vec_2)
result_symmetric = matutils.hellinger(vec_2, vec_1)
expected = 0.856921568786
self.assertAlmostEqual(expected, result)
self.assertAlmostEqual(expected, result_symmetric)

# checking ndarray, csr_matrix as inputs
vec_1 = np.array([[1, 0.3], [0, 0.4], [2, 0.3]])
Expand Down