Skip to content

fix bugs when use custom_dataset without groundtruth file #511

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
XuanYang-cn merged 1 commit into from
Apr 30, 2025
+17 −8
Merged

fix bugs when use custom_dataset without groundtruth file #511

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
12 changes: 8 additions & 4 deletions vectordb_bench/backend/dataset.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -220,10 +220,12 @@ def prepare(
train_files = utils.compose_train_files(file_count, use_shuffled)
all_files = train_files

gt_file, test_file = None, None
test_file = "test.parquet"
all_files.extend([test_file])
gt_file = None
if self.data.with_gt:
gt_file, test_file = utils.compose_gt_file(filters), "test.parquet"
all_files.extend([gt_file, test_file])
gt_file = utils.compose_gt_file(filters)
all_files.extend([gt_file])

if not self.data.is_custom:
source.reader().read(
Expand All @@ -232,8 +234,10 @@ def prepare(
local_ds_root=self.data_dir,
)

if gt_file is not None and test_file is not None:
if test_file is not None:
self.test_data = self._read_file(test_file)

if gt_file is not None:
self.gt_data = self._read_file(gt_file)

prefix = "shuffle_train" if use_shuffled else "train"
Expand Down
13 changes: 9 additions & 4 deletions vectordb_bench/backend/runner/serial_runner.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -209,7 +209,8 @@ def search(self, args: tuple[list, pd.DataFrame]) -> tuple[float, float, float]:
ideal_dcg = get_ideal_dcg(self.k)

log.debug(f"test dataset size: {len(test_data)}")
log.debug(f"ground truth size: {ground_truth.columns}, shape: {ground_truth.shape}")
if ground_truth is not None:
log.debug(f"ground truth size: {ground_truth.columns}, shape: {ground_truth.shape}")

latencies, recalls, ndcgs = [], [], []
for idx, emb in enumerate(test_data):
Expand All @@ -228,9 +229,13 @@ def search(self, args: tuple[list, pd.DataFrame]) -> tuple[float, float, float]:

latencies.append(time.perf_counter() - s)

gt = ground_truth["neighbors_id"][idx]
recalls.append(calc_recall(self.k, gt[: self.k], results))
ndcgs.append(calc_ndcg(gt[: self.k], results, ideal_dcg))
if ground_truth is not None:
gt = ground_truth["neighbors_id"][idx]
recalls.append(calc_recall(self.k, gt[: self.k], results))
ndcgs.append(calc_ndcg(gt[: self.k], results, ideal_dcg))
else:
recalls.append(0)
ndcgs.append(0)

if len(latencies) % 100 == 0:
log.debug(
Expand Down