Upload 3 files

README.md

@@ -1,8 +1,8 @@
 ---
 title: Foqa Validation
-emoji: 📚
-colorFrom: red
-colorTo: red
+emoji: ⚡
+colorFrom: yellow
+colorTo: gray
 sdk: gradio
 sdk_version: 4.28.3
 app_file: app.py

app.py

@@ -0,0 +1,149 @@
+"""Gradio app to validate examples of the FoQA dataset."""
+
+from functools import partial
+import os
+from typing import Generator
+import gradio as gr
+from datasets import Dataset, load_dataset
+import logging
+import pandas as pd
+import os
+from dotenv import load_dotenv
+
+load_dotenv()
+
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger("foqa")
+
+
+# Load the FoQA dataset in the global scope, as it is used in multiple functions
+foqa = load_dataset(
+    "alexandrainst/foqa", split="train", token=os.getenv("HF_HUB_TOKEN")
+)
+assert isinstance(foqa, Dataset)
+df = foqa.to_pandas()
+assert isinstance(df, pd.DataFrame)
+
+
+def main():
+    def non_validated_samples() -> Generator[tuple[str, str, str], None, None]:
+        """Iterate over non-validated samples in the FoQA dataset.
+
+        Yields:
+            A tuple (idx, question, answer) of a non-validated sample.
+        """
+        for idx, sample in df.iterrows():
+            if sample.validation is None:
+                yield str(idx), sample.question, sample.answers["text"][0]
+
+    itr = non_validated_samples()
+    idx, question, answer = next(itr)
+
+    with gr.Blocks(theme="monochrome", title="FoQA validation") as demo:
+        gr.Markdown("""
+            # FoQA Validation
+
+            This app automatically fetches examples from the Faroese Question Answering
+            dataset (FoQA), allowing you to annotate whether the question and answer
+            are correct Faroese or not.
+        """)
+        with gr.Row():
+            with gr.Column():
+                gr.Markdown("### Sample ID")
+                idx_box = gr.Markdown(value=idx)
+                gr.Markdown("### Question")
+                question_box = gr.Markdown(value=question)
+                gr.Markdown("### Answer")
+                answer_box = gr.Markdown(value=answer)
+            with gr.Column():
+                correct_btn = gr.Button(value="Correct")
+                incorrect_btn = gr.Button(value="Incorrect")
+                save_results_btn = gr.Button(value="Save results")
+
+        correct_btn.click(
+            fn=partial(assign_correct, itr=itr),
+            inputs=[idx_box, question_box, answer_box],
+            outputs=[idx_box, question_box, answer_box],
+        )
+        incorrect_btn.click(
+            fn=partial(assign_incorrect, itr=itr),
+            inputs=[idx_box, question_box, answer_box],
+            outputs=[idx_box, question_box, answer_box],
+        )
+        save_results_btn.click(fn=partial(save_results))
+
+    auth = [
+        ("annika", os.environ["ANNIKA_PASSWORD"]),
+        ("admin", os.environ["ADMIN_PASSWORD"]),
+    ]
+
+    demo.launch(share=True, auth=auth)
+
+
+def save_results() -> None:
+    """Update the FoQA dataset with the validation status of a sample."""
+    logger.info("Saving results...")
+    gr.Info(message="Saving results...")
+    Dataset.from_pandas(df, preserve_index=False).push_to_hub(
+        repo_id="alexandrainst/foqa", token=os.getenv("HF_HUB_TOKEN")
+    )
+    gr.Info(message="Saved results!")
+    logger.info("Saved results.")
+
+
+def assign_correct(
+    idx: str, question: str, answer: str, itr: Generator
+) -> tuple[gr.Markdown, gr.Markdown, gr.Markdown]:
+    """Assign the question and answer as correct.
+
+    Args:
+        idx:
+            The index of the sample to be assigned as correct.
+        question:
+            The question to be assigned as correct.
+        answer:
+            The answer to be assigned as correct.
+        itr:
+            The iterator over non-validated samples.
+
+    Returns:
+        The updated textboxes.
+    """
+    gr.Info(message="Assigned sample as correct")
+    logger.info(f"Assigned sample as correct: {question} - {answer}")
+    df.iloc[int(idx)].validation = "correct"
+    idx, question, answer = next(itr)
+    return (
+        gr.Markdown(value=idx), gr.Markdown(value=question), gr.Markdown(value=answer)
+    )
+
+
+def assign_incorrect(
+    idx: str, question: str, answer: str, itr: Generator
+) -> tuple[gr.Markdown, gr.Markdown, gr.Markdown]:
+    """Assign the question and answer as incorrect.
+
+    Args:
+        idx:
+            The index of the sample to be assigned as incorrect.
+        question:
+            The question to be assigned as incorrect.
+        answer:
+            The answer to be assigned as incorrect.
+        itr:
+            The iterator over non-validated samples.
+
+    Returns:
+        The updated textboxes.
+    """
+    gr.Info(message="Assigned sample as incorrect")
+    logger.info(f"Assigned sample as incorrect: {question} - {answer}")
+    df.iloc[int(idx)].validation = "incorrect"
+    idx, question, answer = next(itr)
+    return (
+        gr.Markdown(value=idx), gr.Markdown(value=question), gr.Markdown(value=answer)
+    )
+
+
+if __name__ == "__main__":
+    main()

requirements.txt

@@ -0,0 +1,78 @@
+aiofiles==23.2.1
+aiohttp==3.9.5
+aiosignal==1.3.1
+altair==5.3.0
+annotated-types==0.6.0
+anyio==4.3.0
+async-timeout==4.0.3
+attrs==23.2.0
+certifi==2024.2.2
+charset-normalizer==3.3.2
+click==8.1.7
+contourpy==1.2.1
+cycler==0.12.1
+datasets==2.19.0
+dill==0.3.8
+exceptiongroup==1.2.1
+fastapi==0.110.2
+ffmpy==0.3.2
+filelock==3.13.4
+fonttools==4.51.0
+frozenlist==1.4.1
+fsspec==2024.3.1
+gradio==4.28.3
+gradio_client==0.16.0
+h11==0.14.0
+httpcore==1.0.5
+httpx==0.27.0
+huggingface-hub==0.22.2
+idna==3.7
+importlib_resources==6.4.0
+Jinja2==3.1.3
+jsonschema==4.21.1
+jsonschema-specifications==2023.12.1
+kiwisolver==1.4.5
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+matplotlib==3.8.4
+mdurl==0.1.2
+multidict==6.0.5
+multiprocess==0.70.16
+numpy==1.26.4
+orjson==3.10.1
+packaging==24.0
+pandas==2.2.2
+pillow==10.3.0
+pyarrow==16.0.0
+pyarrow-hotfix==0.6
+pydantic==2.7.1
+pydantic_core==2.18.2
+pydub==0.25.1
+Pygments==2.17.2
+pyparsing==3.1.2
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+python-multipart==0.0.9
+pytz==2024.1
+PyYAML==6.0.1
+referencing==0.35.0
+requests==2.31.0
+rich==13.7.1
+rpds-py==0.18.0
+ruff==0.4.2
+semantic-version==2.10.0
+shellingham==1.5.4
+six==1.16.0
+sniffio==1.3.1
+starlette==0.37.2
+tomlkit==0.12.0
+toolz==0.12.1
+tqdm==4.66.2
+typer==0.12.3
+typing_extensions==4.11.0
+tzdata==2024.1
+urllib3==2.2.1
+uvicorn==0.29.0
+websockets==11.0.3
+xxhash==3.4.1
+yarl==1.9.4