pushing the application

.gitignore

@@ -0,0 +1,160 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

README.md

@@ -1,10 +1,10 @@
 ---
-title: Benchmark Annotation Argilla Dashboard
-emoji: 🏢
-colorFrom: gray
-colorTo: green
+title: SomosNLPDashboard
+emoji: 🌖
+colorFrom: purple
+colorTo: yellow
 sdk: gradio
-sdk_version: 4.20.0
+sdk_version: 4.19.2
 app_file: app.py
 pinned: false
 license: apache-2.0

app.py

@@ -0,0 +1,594 @@
+"""
+Dashboard to visualize the progress of the SomosNLP project.
+by Argilla.
+
+This dashboard shows the progress of the SomosNLP project, including the number of annotated and pending records, the top annotators, and the remaining records to be annotated.
+The data is fetched from the source datasets and updated every 5 minutes.
+Due to Gradio's limitation on what can be passed as input to their graph methods, the data is fetched outside of the graph methods and stored in global variables. Therefore,
+a function for each graph-dataset tuple is needed. Moreover, to also avoid circular imports, all the functions must be
+in the same Python file. This behavior is not ideal, and could be improved knowing how to pass input parameter to graph functions in Gradio.
+"""
+
+import datetime
+import os
+from typing import Dict, List, Tuple
+from uuid import UUID
+
+import altair as alt
+from apscheduler.schedulers.background import BackgroundScheduler
+import argilla as rg
+from argilla.feedback import FeedbackDataset
+from argilla.client.feedback.dataset.remote.dataset import RemoteFeedbackDataset
+import gradio as gr
+import pandas as pd
+
+
+def get_source_datasets() -> Tuple[
+    FeedbackDataset | RemoteFeedbackDataset,
+    FeedbackDataset | RemoteFeedbackDataset,
+    FeedbackDataset | RemoteFeedbackDataset,
+]:
+    """
+    This function returns the source datasets to be showed in the visualization. The datasets names
+    and the workspace name is obtained from the environment variables.
+
+    Returns:
+        A tuple with the three source datasets
+    """
+
+    return (
+        rg.FeedbackDataset.from_argilla(
+            os.getenv("SOURCE_DATASET_1"), workspace=os.getenv("SOURCE_WORKSPACE")
+        ),
+        rg.FeedbackDataset.from_argilla(
+            os.getenv("SOURCE_DATASET_2"), workspace=os.getenv("SOURCE_WORKSPACE")
+        ),
+        rg.FeedbackDataset.from_argilla(
+            os.getenv("SOURCE_DATASET_3"), workspace=os.getenv("SOURCE_WORKSPACE")
+        ),
+    )
+
+
+def get_user_annotations_dictionary(
+    datasets: List[FeedbackDataset | RemoteFeedbackDataset],
+) -> Dict[str, int]:
+    """
+    This function returns a dictionary with the username as the key and the number of annotations as the value.
+    All annotationsfrom all datasets are introduced in the same dictionary.
+
+    Args:
+        datasets: A list with the datasets to be used to obtain the annotations and the annotators.
+    Returns:
+        A dictionary with the username as the key and the number of annotations as the value.
+    """
+    output = {}
+    for dataset in datasets:
+        for record in dataset:
+            for response in record.responses:
+                if str(response.user_id) not in output.keys():
+                    output[str(response.user_id)] = 1
+                else:
+                    output[str(response.user_id)] += 1
+
+    # Changing the name of the keys, from the id to the username
+    for key in list(output.keys()):
+        output[rg.User.from_id(UUID(key)).username] = output.pop(key)
+
+    return output
+
+
+def donut_chart_1() -> alt.Chart:
+    """
+    This function returns a donut chart with the number of annotated and pending records, for the first dataset
+
+    Returns:
+        An altair chart with the donut chart.
+    """
+
+    annotated_records = len(dataset1.filter_by(response_status=["submitted"]))
+    pending_records = len(dataset1) - annotated_records
+
+    source = pd.DataFrame(
+        {
+            "values": [annotated_records, pending_records],
+            "category": ["Annotated", "Pending"],  # Add a new column for categories
+        }
+    )
+
+    base = alt.Chart(source).encode(
+        theta=alt.Theta("values:Q", stack=True),
+        radius=alt.Radius(
+            "values", scale=alt.Scale(type="sqrt", zero=True, rangeMin=20)
+        ),
+        color=alt.Color("category:N", legend=alt.Legend(title="Category")),
+    )
+
+    c1 = base.mark_arc(innerRadius=20, stroke="#fff")
+
+    c2 = base.mark_text(radiusOffset=10).encode(text="values:Q")
+
+    chart = c1 + c2
+
+    return chart
+
+
+def donut_chart_2() -> alt.Chart:
+    """
+    This function returns a donut chart with the number of annotated and pending records, for the second dataset.
+
+    Returns:
+        An altair chart with the donut chart.
+    """
+
+    annotated_records = len(dataset2.filter_by(response_status=["submitted"]))
+    pending_records = len(dataset2) - annotated_records
+
+    source = pd.DataFrame(
+        {
+            "values": [annotated_records, pending_records],
+            "category": ["Annotated", "Pending"],  # Add a new column for categories
+        }
+    )
+
+    base = alt.Chart(source).encode(
+        theta=alt.Theta("values:Q", stack=True),
+        radius=alt.Radius(
+            "values", scale=alt.Scale(type="sqrt", zero=True, rangeMin=20)
+        ),
+        color=alt.Color("category:N", legend=alt.Legend(title="Category")),
+    )
+
+    c1 = base.mark_arc(innerRadius=20, stroke="#fff")
+
+    c2 = base.mark_text(radiusOffset=10).encode(text="values:Q")
+
+    chart = c1 + c2
+
+    return chart
+
+
+def donut_chart_3() -> alt.Chart:
+    """
+    This function returns a donut chart with the number of annotated and pending records, for the third dataset.
+
+    Returns:
+        An altair chart with the donut chart.
+    """
+
+    annotated_records = len(dataset3.filter_by(response_status=["submitted"]))
+    pending_records = len(dataset3) - annotated_records
+
+    source = pd.DataFrame(
+        {
+            "values": [annotated_records, pending_records],
+            "category": ["Annotated", "Pending"],  # Add a new column for categories
+        }
+    )
+
+    base = alt.Chart(source).encode(
+        theta=alt.Theta("values:Q", stack=True),
+        radius=alt.Radius(
+            "values", scale=alt.Scale(type="sqrt", zero=True, rangeMin=20)
+        ),
+        color=alt.Color("category:N", legend=alt.Legend(title="Category")),
+    )
+
+    c1 = base.mark_arc(innerRadius=20, stroke="#fff")
+
+    c2 = base.mark_text(radiusOffset=10).encode(text="values:Q")
+
+    chart = c1 + c2
+
+    return chart
+
+
+def kpi_chart_submitted_1() -> alt.Chart:
+    """
+    This function returns a KPI chart with the total amount of records that have been annotated, for the first dataset.
+
+    Returns:
+        An altair chart with the KPI chart.
+    """
+
+    total = len(dataset1.filter_by(response_status=["submitted"]))
+
+    # Assuming you have a DataFrame with user data, create a sample DataFrame
+    data = pd.DataFrame({"Category": ["Total completed"], "Value": [total]})
+
+    # Create Altair chart
+    chart = (
+        alt.Chart(data)
+        .mark_text(fontSize=100, align="center", baseline="middle", color="steelblue")
+        .encode(text="Value:N")
+        .properties(title="Total completed", width=250, height=200)
+    )
+
+    return chart
+
+
+def kpi_chart_submitted_2() -> alt.Chart:
+    """
+    This function returns a KPI chart with the total amount of records that have been annotated, for the second dataset.
+
+    Returns:
+        An altair chart with the KPI chart.
+    """
+
+    total = len(dataset2.filter_by(response_status=["submitted"]))
+
+    # Assuming you have a DataFrame with user data, create a sample DataFrame
+    data = pd.DataFrame({"Category": ["Total completed"], "Value": [total]})
+
+    # Create Altair chart
+    chart = (
+        alt.Chart(data)
+        .mark_text(fontSize=100, align="center", baseline="middle", color="steelblue")
+        .encode(text="Value:N")
+        .properties(title="Total completed", width=250, height=200)
+    )
+
+    return chart
+
+
+def kpi_chart_submitted_3() -> alt.Chart:
+    """
+    This function returns a KPI chart with the total amount of records that have been annotated, for the third dataset.
+
+    Returns:
+        An altair chart with the KPI chart.
+    """
+
+    total = len(dataset3.filter_by(response_status=["submitted"]))
+
+    # Assuming you have a DataFrame with user data, create a sample DataFrame
+    data = pd.DataFrame({"Category": ["Total completed"], "Value": [total]})
+
+    # Create Altair chart
+    chart = (
+        alt.Chart(data)
+        .mark_text(fontSize=100, align="center", baseline="middle", color="steelblue")
+        .encode(text="Value:N")
+        .properties(title="Total completed", width=250, height=200)
+    )
+
+    return chart
+
+
+def kpi_chart_remaining_1() -> alt.Chart:
+    """
+    This function returns a KPI chart with the remaining amount of records to be annotated, for the first dataset.
+
+    Returns:
+        An altair chart with the KPI chart.
+    """
+
+    annotated_records = len(dataset1.filter_by(response_status=["submitted"]))
+    pending_records = len(dataset1) - annotated_records
+
+    # Assuming you have a DataFrame with user data, create a sample DataFrame
+    data = pd.DataFrame({"Category": ["Total remaining"], "Value": [pending_records]})
+
+    # Create Altair chart
+    chart = (
+        alt.Chart(data)
+        .mark_text(fontSize=100, align="center", baseline="middle", color="steelblue")
+        .encode(text="Value:N")
+        .properties(title="Total remaining", width=250, height=200)
+    )
+
+    return chart
+
+
+def kpi_chart_remaining_2() -> alt.Chart:
+    """
+    This function returns a KPI chart with the remaining amount of records to be annotated, for the second dataset.
+    Returns:
+        An altair chart with the KPI chart.
+    """
+
+    annotated_records = len(dataset2.filter_by(response_status=["submitted"]))
+    pending_records = len(dataset2) - annotated_records
+
+    # Assuming you have a DataFrame with user data, create a sample DataFrame
+    data = pd.DataFrame({"Category": ["Total remaining"], "Value": [pending_records]})
+
+    # Create Altair chart
+    chart = (
+        alt.Chart(data)
+        .mark_text(fontSize=100, align="center", baseline="middle", color="steelblue")
+        .encode(text="Value:N")
+        .properties(title="Total remaining", width=250, height=200)
+    )
+
+    return chart
+
+
+def kpi_chart_remaining_3() -> alt.Chart:
+    """
+    This function returns a KPI chart with the remaining amount of records to be annotated, for the third dataset.
+
+    Returns:
+        An altair chart with the KPI chart.
+    """
+
+    annotated_records = len(dataset3.filter_by(response_status=["submitted"]))
+    pending_records = len(dataset3) - annotated_records
+
+    # Assuming you have a DataFrame with user data, create a sample DataFrame
+    data = pd.DataFrame({"Category": ["Total remaining"], "Value": [pending_records]})
+
+    # Create Altair chart
+    chart = (
+        alt.Chart(data)
+        .mark_text(fontSize=100, align="center", baseline="middle", color="steelblue")
+        .encode(text="Value:N")
+        .properties(title="Total remaining", width=250, height=200)
+    )
+
+    return chart
+
+
+def render_hub_user_link(hub_id: str) -> str:
+    """
+    This function formats the username with a link to the user's profile in the Hugging Face Hub.
+
+    Args:
+        hub_id: The user's id in the Hugging Face Hub.
+    Returns:
+        A string with the username formatted as a link to the user's profile in the Hugging Face Hub.
+    """
+    link = f"https://huggingface.co/{hub_id}"
+    return f'<a target="_blank" href="{link}" style="color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;">{hub_id}</a>'
+
+
+def kpi_chart_annotators() -> alt.Chart:
+    """
+    This function returns a KPI chart with the total amount of annotators.
+
+    Returns:
+        An altair chart with the KPI chart.
+    """
+
+    # Obtain the total amount of annotators
+    total_annotators = len(user_ids_annotations)
+
+    # Assuming you have a DataFrame with user data, create a sample DataFrame
+    data = pd.DataFrame(
+        {"Category": ["Total Contributors"], "Value": [total_annotators]}
+    )
+
+    # Create Altair chart
+    chart = (
+        alt.Chart(data)
+        .mark_text(fontSize=100, align="center", baseline="middle", color="steelblue")
+        .encode(text="Value:N")
+        .properties(title="Number of Contributors", width=250, height=200)
+    )
+
+    return chart
+
+
+def obtain_top_users(user_ids_annotations: Dict[str, int]) -> pd.DataFrame:
+    """
+    This function returns the top 50 users with the most annotations. The usernames are formatted as links to the user's profile in the Hugging Face Hub.
+
+    Args:
+        user_ids_annotations: A dictionary with the user ids as the key and the number of annotations as the value.
+    Returns:
+        A pandas dataframe with the top 5 users with the most annotations.
+    """
+
+    dataframe = pd.DataFrame(
+        user_ids_annotations.items(), columns=["Name", "Submitted Responses"]
+    )
+    dataframe["Name"] = dataframe["Name"].apply(render_hub_user_link)
+    dataframe = dataframe.sort_values(by="Submitted Responses", ascending=False)
+    return dataframe.head(50)
+
+
+def get_top() -> pd.DataFrame:
+    """
+    This function returns the top users with the most annotations. The usernames are formatted as links to the user's profile in the Hugging Face Hub.
+
+    Returns:
+        A pandas dataframe with the top users with the most annotations.
+    """
+    return obtain_top_users(user_ids_annotations)
+
+
+def fetch_data() -> None:
+    """
+    This function fetches the data from the source datasets and updates the global variables.
+    """
+
+    print(f"Starting to fetch data: {datetime.datetime.now()}")
+
+    # Load the dataset as global variable to be able to use it in all Gradio graph methods,
+    # as they usually do not allow arguments.
+    global dataset1, dataset2, dataset3, user_ids_annotations
+    dataset1, dataset2, dataset3 = get_source_datasets()
+    user_ids_annotations = get_user_annotations_dictionary(
+        [dataset1, dataset2, dataset3]
+    )
+
+    # Print the current date and time
+    print(f"Data fetched: {datetime.datetime.now()}")
+
+
+def main() -> None:
+
+    # Set the update interval
+    update_interval = 300  # seconds
+    update_interval_charts = 30  # seconds
+
+    # Connect to the space with rg.init()
+    rg.init(
+        api_url=os.getenv("ARGILLA_API_URL"),
+        api_key=os.getenv("ARGILLA_API_KEY"),
+        extra_headers={"Authorization": f"Bearer {os.getenv('HF_TOKEN')}"},
+    )
+
+    # Initial data fetching
+    fetch_data()
+
+    scheduler = BackgroundScheduler()
+    scheduler.add_job(
+        func=fetch_data, trigger="interval", seconds=update_interval, max_instances=1
+    )
+    scheduler.start()
+
+    # To avoid the orange border for the Gradio elements that are in constant loading
+    css = """
+    .generating {
+        border: none;
+    }
+    """
+
+    with gr.Blocks(css=css, title="LLM Benchmark en Español Dashboard") as demo:
+
+        # JSS code to force light theme
+        demo.load(
+            None,
+            None,
+            js="""
+                () => {
+                const params = new URLSearchParams(window.location.search);
+                if (!params.has('__theme')) {
+                    params.set('__theme', 'light');
+                    window.location.search = params.toString();
+                }
+                }""",
+        )
+
+        gr.Markdown(
+            """
+            # 🗣️ SomosNLP Progress Dashboard
+            """
+        )
+
+        gr.Markdown(
+            f"""
+            ## 🚀 Progress in dataset {os.getenv("SOURCE_DATASET_1")}
+            """
+        )
+        with gr.Row():
+
+            plot = gr.Plot(label="Plot")
+            demo.load(
+                kpi_chart_submitted_1,
+                inputs=[],
+                outputs=[plot],
+                every=update_interval_charts,
+            )
+
+            plot = gr.Plot(label="Plot")
+            demo.load(
+                kpi_chart_remaining_1,
+                inputs=[],
+                outputs=[plot],
+                every=update_interval_charts,
+            )
+
+            # donut_chart_plotted_1 = gr.Plot(label="Plot")
+            # demo.load(
+            #     donut_chart_1,
+            #     inputs=[],
+            #     outputs=[donut_chart_plotted_1],
+            # )
+
+        gr.Markdown(
+            f"""
+            ## 🚀 Progress in dataset {os.getenv("SOURCE_DATASET_2")}
+            """
+        )
+        with gr.Row():
+
+            plot = gr.Plot(label="Plot")
+            demo.load(
+                kpi_chart_submitted_2,
+                inputs=[],
+                outputs=[plot],
+                every=update_interval_charts,
+            )
+
+            plot = gr.Plot(label="Plot")
+            demo.load(
+                kpi_chart_remaining_2,
+                inputs=[],
+                outputs=[plot],
+                every=update_interval_charts,
+            )
+
+            # donut_chart_plotted_2 = gr.Plot(label="Plot")
+            # demo.load(
+            #     donut_chart_2,
+            #     inputs=[],
+            #     outputs=[donut_chart_plotted_2],
+            # )
+
+        gr.Markdown(
+            f"""
+            ## 🚀 Progress in dataset {os.getenv("SOURCE_DATASET_3")}
+            """
+        )
+        with gr.Row():
+
+            plot = gr.Plot(label="Plot")
+            demo.load(
+                kpi_chart_submitted_3,
+                inputs=[],
+                outputs=[plot],
+                every=update_interval_charts,
+            )
+
+            plot = gr.Plot(label="Plot")
+            demo.load(
+                kpi_chart_remaining_3,
+                inputs=[],
+                outputs=[plot],
+                every=update_interval_charts,
+            )
+
+            # donut_chart_plotted_3 = gr.Plot(label="Plot")
+            # demo.load(
+            #     donut_chart_3,
+            #     inputs=[],
+            #     outputs=[donut_chart_plotted_3],
+            # )
+
+        gr.Markdown(
+            """
+            ## 👾 Contributors Hall of Fame
+            The number of all contributors and the top contributors:
+            """
+        )
+
+        with gr.Row():
+
+            plot2 = gr.Plot(label="Plot")
+            demo.load(
+                kpi_chart_annotators,
+                inputs=[],
+                outputs=[plot2],
+                every=update_interval_charts,
+            )
+
+            top_df_plot = gr.Dataframe(
+                headers=["Name", "Submitted Responses"],
+                datatype=[
+                    "markdown",
+                    "number",
+                ],
+                row_count=50,
+                col_count=(2, "fixed"),
+                interactive=False,
+            )
+
+            demo.load(get_top, None, [top_df_plot], every=update_interval_charts)
+
+    # Launch the Gradio interface
+    demo.launch(share=True, debug=True)
+
+
+if __name__ == "__main__":
+    main()

requirements.txt

@@ -0,0 +1,72 @@
+aiofiles==23.2.1
+altair==5.2.0
+annotated-types==0.6.0
+anyio==4.2.0
+apscheduler==3.10.4
+argilla==1.23.0
+attrs==23.2.0
+backoff==2.2.1
+certifi==2024.2.2
+charset-normalizer==3.3.2
+click==8.1.7
+colorama==0.4.6
+contourpy==1.2.0
+cycler==0.12.1
+Deprecated==1.2.14
+exceptiongroup==1.2.0
+fastapi==0.109.2
+ffmpy==0.3.1
+filelock==3.13.1
+fonttools==4.48.1
+fsspec==2024.2.0
+gradio==4.17.0
+gradio_client==0.9.0
+h11==0.14.0
+httpcore==1.0.2
+httpx==0.26.0
+huggingface-hub==0.20.3
+idna==3.6
+importlib-resources==6.1.1
+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==3.8.2
+mdurl==0.1.2
+monotonic==1.6
+numpy==1.23.5
+orjson==3.9.13
+packaging==23.2
+pandas==1.5.3
+pillow==10.2.0
+pydantic==2.6.1
+pydantic_core==2.16.2
+pydub==0.25.1
+Pygments==2.17.2
+pyparsing==3.1.1
+python-dateutil==2.8.2
+python-multipart==0.0.7
+pytz==2024.1
+PyYAML==6.0.1
+referencing==0.33.0
+requests==2.31.0
+rich==13.7.0
+rpds-py==0.17.1
+ruff==0.2.1
+semantic-version==2.10.0
+shellingham==1.5.4
+six==1.16.0
+sniffio==1.3.0
+starlette==0.36.3
+tomlkit==0.12.0
+toolz==0.12.1
+tqdm==4.66.1
+typer==0.9.0
+typing_extensions==4.9.0
+urllib3==2.2.0
+uvicorn==0.27.0.post1
+vega-datasets==0.9.0
+websockets==11.0.3
+wrapt==1.14.1