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 weight in interpolation #58

Merged
merged 5 commits into from
Nov 21, 2021
Merged

fix weight in interpolation #58

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
abfe968
fix weight in interpolation
kunigami Nov 20, 2021
fd848e0
fix weight in interpolation
kunigami Nov 20, 2021
9a12482
Merge branch 'fix_weight' of github.com:kunigami/tdigest into fix_weight
kunigami Nov 20, 2021
9be574a
rm print
kunigami Nov 20, 2021
fdabf3f
Merge remote-tracking branch 'origin/fix_weight' into fix_weight
kunigami Nov 20, 2021
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
6 changes: 2 additions & 4 deletions tdigest/tdigest.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -179,12 +179,10 @@ def percentile(self, p):

else:
k = (c_i_plus_one.count + c_i.count) / 2.
if p < t + k:
if p <= t + k:
z1 = p - t
z2 = t + k - p
return (c_i.mean * z1 + c_i_plus_one.mean * z2) / (z1 + z2)
if p == t + k:
return c_i_plus_one.mean
return (c_i.mean * z2 + c_i_plus_one.mean * z1) / k
c_i = c_i_plus_one
t += k

Expand Down
11 changes: 8 additions & 3 deletions tests/test_tdigest.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -142,7 +142,6 @@ def test_negative_extreme_percentile_is_still_positive(self, empty_tdigest):
# Test https://github.com/CamDavidsonPilon/tdigest/issues/16
t = TDigest()
t.batch_update([62.0, 202.0, 1415.0, 1433.0])
print(t.percentile(26))
Copy link
Owner

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

🔥

assert t.percentile(26) > 0

def test_percentile_at_border_returns_an_intermediate_value(self, empty_tdigest):
Expand All @@ -151,7 +150,13 @@ def test_percentile_at_border_returns_an_intermediate_value(self, empty_tdigest)
t.batch_update(data)
assert t.percentile(25) == 132.0

def test_adding_centroid_with_exisiting_key_does_not_break_synchronicity(self, empty_tdigest, example_centroids):
def test_percentile_weighted_interpolation(self, empty_tdigest):
data = [1, 10, 10, 10, 10, 100, 100, 100, 100, 1000]
t = TDigest()
t.batch_update(data)
assert t.percentile(40) == 32.5

def test_adding_centroid_with_existing_key_does_not_break_synchronicity(self, empty_tdigest, example_centroids):
td = empty_tdigest
td.C = example_centroids
assert -1.1 in td.C
Expand Down Expand Up @@ -220,7 +225,7 @@ def test_ints(self):
t = TDigest()
t.batch_update([1, 1, 2, 2, 3, 4, 4, 4, 5, 5])
assert t.percentile(30) == 2
assert t.percentile(40)*3 == 7
assert t.percentile(40)*3 == 8
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

eh, sorry I didn't realize I would have to update this test again >.<


@pytest.mark.parametrize("percentile_range", [[0, 7], [27, 47], [39, 66], [81, 99], [77, 100], [0, 100]])
@pytest.mark.parametrize("data_size", [100, 1000, 5000])
Expand Down