Skip to content

Commit

Permalink
cranfield fix (#276)
Browse files Browse the repository at this point in the history
* fixes cranfield query_ids

* updated cranfield tests

---------

Co-authored-by: Djoerd Hiemstra <[email protected]>
  • Loading branch information
seanmacavaney and djoerd authored Nov 11, 2024
1 parent b9ae1f2 commit b6da232
Show file tree
Hide file tree
Showing 2 changed files with 5 additions and 3 deletions.
4 changes: 3 additions & 1 deletion ir_datasets/datasets/cranfield.py
Original file line number Diff line number Diff line change
Expand Up @@ -109,6 +109,7 @@ def queries_path(self):
def queries_iter(self):
with self.queries_dlc.stream() as stream:
stream = io.TextIOWrapper(stream)
query_id = 1
for lines in prefix_sentinel_splitter(stream, sentinel='.I '):
record = {'query_id': '', 'text': ''}
field = 'query_id'
Expand All @@ -118,7 +119,8 @@ def queries_iter(self):
else:
record[field] += line
record = {k: v.strip() for k, v in record.items()}
record['query_id'] = record['query_id'].lstrip('0') # remove leading 0s to match qrels
record['query_id'] = str(query_id) # overwrite query_id to match qrels
query_id += 1
yield GenericQuery(**record)

def queries_cls(self):
Expand Down
4 changes: 2 additions & 2 deletions test/integration/cranfield.py
Original file line number Diff line number Diff line change
Expand Up @@ -16,8 +16,8 @@ def test_docs(self):
def test_queries(self):
self._test_queries('cranfield', count=225, items={
0: GenericQuery('1', 'what similarity laws must be obeyed when constructing aeroelastic models\nof heated high speed aircraft .'),
9: GenericQuery('18', 'are real-gas transport properties for air available over a wide range of\nenthalpies and densities .'),
224: GenericQuery('365', 'what design factors can be used to control lift-drag ratios at mach\nnumbers above 5 .'),
9: GenericQuery('10', 'are real-gas transport properties for air available over a wide range of\nenthalpies and densities .'),
224: GenericQuery('225', 'what design factors can be used to control lift-drag ratios at mach\nnumbers above 5 .'),
})

def test_qrels(self):
Expand Down

0 comments on commit b6da232

Please sign in to comment.