Skip to content

misc: lint main #1961

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
isaac-chung merged 3 commits into from
Feb 5, 2025
Merged

misc: lint main #1961

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
e71ecf8
lint main
isaac-chung Feb 5, 2025
829272c
try 3.10
isaac-chung Feb 5, 2025
cd2839d
make lint
isaac-chung Feb 5, 2025
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
2 changes: 1 addition & 1 deletion .github/workflows/lint.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@ jobs:

- uses: actions/setup-python@v4
with:
python-version: "3.9"
python-version: "3.10"
cache: "pip"

- name: Install dependencies
Expand Down
2 changes: 1 addition & 1 deletion mteb/abstasks/AbsTaskClassification.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -150,7 +150,7 @@ def _evaluate_subset(
) # we store idxs to make the shuffling reproducible
for i in range(self.n_experiments):
logger.info(
"=" * 10 + f" Experiment {i+1}/{self.n_experiments} " + "=" * 10
"=" * 10 + f" Experiment {i + 1}/{self.n_experiments} " + "=" * 10
)
# Bootstrap `self.samples_per_label` samples per label for each split
X_sampled, y_sampled, idxs = self._undersample_data(
Expand Down
2 changes: 1 addition & 1 deletion mteb/abstasks/AbsTaskMultilabelClassification.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -215,7 +215,7 @@ def _evaluate_subset(
for i_experiment, sample_indices in enumerate(train_samples):
logger.info(
"=" * 10
+ f" Experiment {i_experiment+1}/{self.n_experiments} "
+ f" Experiment {i_experiment + 1}/{self.n_experiments} "
+ "=" * 10
)
X_train = np.stack([unique_train_embeddings[idx] for idx in sample_indices])
Expand Down
2 changes: 1 addition & 1 deletion mteb/abstasks/AbsTaskSpeedTask.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -78,7 +78,7 @@ def get_system_info(self) -> dict[str, str]:
list_gpus.append(
{
"gpu_name": gpu.name,
"gpu_total_memory": f"{gpu.memoryTotal/1024.0} GB",
"gpu_total_memory": f"{gpu.memoryTotal / 1024.0} GB",
}
)
info["gpu_info"] = list_gpus
Expand Down
2 changes: 1 addition & 1 deletion mteb/abstasks/Image/AbsTaskImageClassification.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -133,7 +133,7 @@ def _evaluate_subset(
) # we store idxs to make the shuffling reproducible
for i in range(self.n_experiments):
logger.info(
"=" * 10 + f" Experiment {i+1}/{self.n_experiments} " + "=" * 10
"=" * 10 + f" Experiment {i + 1}/{self.n_experiments} " + "=" * 10
)
# Bootstrap `self.samples_per_label` samples per label for each split
undersampled_train, idxs = self._undersample_data(
Expand Down
2 changes: 1 addition & 1 deletion mteb/abstasks/Image/AbsTaskImageMultilabelClassification.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -183,7 +183,7 @@ def _evaluate_subset(
for i_experiment, sample_indices in enumerate(train_samples):
logger.info(
"=" * 10
+ f" Experiment {i_experiment+1}/{self.n_experiments} "
+ f" Experiment {i_experiment + 1}/{self.n_experiments} "
+ "=" * 10
)
X_train = np.stack([unique_train_embeddings[idx] for idx in sample_indices])
Expand Down
4 changes: 2 additions & 2 deletions mteb/tasks/Retrieval/eng/LitSearchRetrieval.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -52,7 +52,7 @@ def load_data(self, **kwargs):

self.queries["test"] = dict(
zip(
[f"q{x+1}" for x in range(len(query_ds["full"]))],
[f"q{x + 1}" for x in range(len(query_ds["full"]))],
query_ds["full"]["query"],
)
)
Expand All @@ -69,7 +69,7 @@ def load_data(self, **kwargs):
}

self.relevant_docs["test"] = {
f"q{e+1}": dict(zip([f"d{i}" for i in ids], range(1, len(ids) + 1)))
f"q{e + 1}": dict(zip([f"d{i}" for i in ids], range(1, len(ids) + 1)))
for e, ids in enumerate(query_ds["full"]["corpusids"])
}

Expand Down
6 changes: 3 additions & 3 deletions mteb/tasks/Retrieval/slk/SlovakSumRetrieval.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,12 +56,12 @@ def load_data(self, **kwargs):
dataset_path, split=f"{split}[:{n_sample}]"
)
# Transforming news summary into retrieval task
queries = {f"q{e+1}": x["sum"] for e, x in enumerate(split_ds)}
queries = {f"q{e + 1}": x["sum"] for e, x in enumerate(split_ds)}
corpus = {
f"d{e+1}": {"title": x["title"], "text": x["text"]}
f"d{e + 1}": {"title": x["title"], "text": x["text"]}
for e, x in enumerate(split_ds)
}
qrels = {f"q{i+1}": {f"d{i+1}": 1} for i in range(split_ds.shape[0])}
qrels = {f"q{i + 1}": {f"d{i + 1}": 1} for i in range(split_ds.shape[0])}
self.corpus[split], self.queries[split], self.relevant_docs[split] = (
corpus,
queries,
Expand Down
2 changes: 1 addition & 1 deletion scripts/task_selection/task_selection_eng_lite.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2551,7 +2551,7 @@
"for model, revision in mteb_results.items():\n",
" for rev, results in revision.items():\n",
" print(\n",
" f\"{model}: {sum(res.evaluation_time for res in results) / 3600 :.2f} hours\"\n",
" f\"{model}: {sum(res.evaluation_time for res in results) / 3600:.2f} hours\"\n",
" )"
]
},
Expand Down