Skip to content

Add robust similarity metrics and normalization to compare.text #1144

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

Merged
ebhills merged 4 commits into from
Aug 26, 2026
Merged

Add robust similarity metrics and normalization to compare.text #1144

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
352a633
Add robust similarity metrics and normalization to compare.text
mborodii-prog Aug 25, 2026
6306882
fix tests
mborodii-prog Aug 25, 2026
418e8b2
Update test_recipes.py
mborodii-prog Aug 26, 2026
2f2b069
Restore case_sensitive toggle, split overlap ratio output, add per-me…
mborodii-prog Aug 26, 2026
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
3 changes: 3 additions & 0 deletions requirements.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,6 +8,9 @@ numexpr
polars==1.33.0
pyarrow

# Fuzzy text similarity
rapidfuzz>=3.0,<4.0

# Recipe engine & templating
jinja2
lorem
Expand Down
14 changes: 7 additions & 7 deletions tests/recipes/test_recipes.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -131,7 +131,7 @@ def test_recipe_by_production_version():
"""
Test running a recipe using a model ID and production version
"""
df = wrangles.recipe.run("a6bac9e7-2388-4347")
df = wrangles.recipe.run("e954717c-fb9c-4c47")
assert (
len(df) == 20 and
list(df.columns) == ["header"]
Expand All @@ -154,10 +154,10 @@ def test_recipe_by_production_semantic_version(mocker):
return_value={"recipe": "{}"}
)

wrangles.recipe.run("a6bac9e7-2388-4347:production")
wrangles.recipe.run("e954717c-fb9c-4c47:production")

model_content.assert_called_once_with(
"a6bac9e7-2388-4347",
"e954717c-fb9c-4c47",
"production-version-id"
)

Expand All @@ -178,17 +178,17 @@ def test_recipe_by_production_semantic_version_falls_back_to_latest(
return_value={"recipe": "{}"}
)

wrangles.recipe.run("a6bac9e7-2388-4347:production")
wrangles.recipe.run("e954717c-fb9c-4c47:production")

model_content.assert_called_once_with("a6bac9e7-2388-4347", None)
model_content.assert_called_once_with("e954717c-fb9c-4c47", None)
assert "No production version exists, defaulting to latest version" in caplog.text


def test_recipe_by_version_latest():
"""
Test running a recipe using a model ID and latest version
"""
df = wrangles.recipe.run("a6bac9e7-2388-4347:latest")
df = wrangles.recipe.run("e954717c-fb9c-4c47:latest")
assert (
len(df) == 10 and
list(df.columns) == ["header"]
Expand All @@ -198,7 +198,7 @@ def test_recipe_by_latest_version():
"""
Test running a recipe using a model ID and latest version
"""
df = wrangles.recipe.run("02fc0c63-1294-415b")
df = wrangles.recipe.run("1b41d016-7129-4b66")
assert (
len(df) == 15 and
list(df.columns) == ["header"]
Expand Down
Loading