Skip to content

Add CategorizeText aggregation #1589

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
merged 1 commit into from
Apr 15, 2024
Merged

Add CategorizeText aggregation #1589

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
4 changes: 4 additions & 0 deletions elasticsearch_dsl/aggs.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -309,6 +309,10 @@ class MultiTerms(Bucket):
name = "multi_terms"


class CategorizeText(Bucket):
name = "categorize_text"


# metric aggregations
class TopHits(Agg):
name = "top_hits"
Expand Down
17 changes: 17 additions & 0 deletions tests/test_aggs.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -342,6 +342,23 @@ def test_multi_terms_aggregation():
} == a.to_dict()


def test_categorize_text_aggregation():
a = aggs.CategorizeText(
field="tags",
categorization_filters=["\\w+\\_\\d{3}"],
max_matched_tokens=2,
similarity_threshold=30,
)
assert {
"categorize_text": {
"field": "tags",
"categorization_filters": ["\\w+\\_\\d{3}"],
"max_matched_tokens": 2,
"similarity_threshold": 30,
}
} == a.to_dict()


def test_median_absolute_deviation_aggregation():
a = aggs.MedianAbsoluteDeviation(field="rating")

Expand Down