Upload 5 files

README.md

@@ -1,12 +1,11 @@
 ---
-title: Dashboard
-emoji: 🐢
-colorFrom: pink
-colorTo: pink
+title: Template for Dashboards - Multilingual Prompt Evaluation Project
+emoji: 📊
+colorFrom: indigo
+colorTo: indigo
 sdk: gradio
-sdk_version: 4.25.0
+sdk_version: 4.21.0
 app_file: app.py
 pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+license: apache-2.0
+---

app.py

@@ -0,0 +1,373 @@
+from apscheduler.schedulers.background import BackgroundScheduler
+import datetime
+import os
+from typing import Dict, Tuple
+from uuid import UUID
+
+import altair as alt
+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
+
+"""
+This is the main file for the dashboard application. It contains the main function and the functions to obtain the data and create the charts.
+It's designed as a template to recreate the dashboard for the prompt translation project of any language. 
+
+To create a new dashboard, you need several environment variables, that you can easily set in the HuggingFace Space that you are using to host the dashboard:
+
+- SOURCE_DATASET: The dataset id of the source dataset
+- SOURCE_WORKSPACE: The workspace id of the source dataset
+- TARGET_RECORDS: The number of records that you have as a target to annotate. We usually set this to 500.
+- ARGILLA_API_URL: Link to the Huggingface Space where the annotation effort is being hosted. For example, the Spanish one is https://somosnlp-dibt-prompt-translation-for-es.hf.space/
+- ARGILLA_API_KEY: The API key to access the Huggingface Space. Please, write this as a secret in the Huggingface Space configuration.
+"""
+
+# Translation of legends and titles
+ANNOTATED = 'Anotované'
+NUMBER_ANNOTATED = 'Celkový počet anotácií'
+PENDING = 'Zostáva anotovať'
+
+NUMBER_ANNOTATORS = "Počet anotátorov"
+NAME = 'Užívateľ'
+NUMBER_ANNOTATIONS = 'Počet anotácií'
+
+CATEGORY = 'Kategória'
+
+
+def obtain_source_target_datasets() -> (
+    Tuple[
+        FeedbackDataset | RemoteFeedbackDataset, FeedbackDataset | RemoteFeedbackDataset
+    ]
+):
+    """
+    This function returns the source and target datasets to be used in the application.
+
+    Returns:
+        A tuple with the source and target datasets. The source dataset is filtered by the response status 'pending'.
+
+    """
+
+    # Obtain the public dataset and see how many pending records are there
+    source_dataset = rg.FeedbackDataset.from_argilla(
+        os.getenv("SOURCE_DATASET"), workspace=os.getenv("SOURCE_WORKSPACE")
+    )
+    filtered_source_dataset = source_dataset.filter_by(
+        response_status=["pending"])
+
+    # Obtain a list of users from the private workspace
+    # target_dataset = rg.FeedbackDataset.from_argilla(
+    #    os.getenv("RESULTS_DATASET"), workspace=os.getenv("RESULTS_WORKSPACE")
+    # )
+
+    target_dataset = source_dataset.filter_by(response_status=["submitted"])
+
+    return filtered_source_dataset, target_dataset
+
+
+def get_user_annotations_dictionary(
+    dataset: FeedbackDataset | RemoteFeedbackDataset,
+) -> Dict[str, int]:
+    """
+    This function returns a dictionary with the username as the key and the number of annotations as the value.
+
+    Args:
+        dataset: The dataset to be analyzed.
+    Returns:
+        A dictionary with the username as the key and the number of annotations as the value.
+    """
+    output = {}
+    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_total() -> alt.Chart:
+    """
+    This function returns a donut chart with the progress of the total annotations.
+    Counts each record that has been annotated at least once.
+
+    Returns:
+        An altair chart with the donut chart.
+    """
+
+    # Load your data
+    annotated_records = len(target_dataset)
+    pending_records = int(os.getenv("TARGET_RECORDS")) - annotated_records
+
+    # Prepare data for the donut chart
+    source = pd.DataFrame(
+        {
+            "values": [annotated_records, pending_records],
+            "category": [ANNOTATED, PENDING],
+            # Blue for Completed, Orange for Remaining
+            "colors": ["#4682b4", "#e68c39"],
+        }
+    )
+
+    domain = source['category'].tolist()
+    range_ = source['colors'].tolist()
+
+    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(field="category", type="nominal", scale=alt.Scale(
+            domain=domain, range=range_), legend=alt.Legend(title=CATEGORY)),
+    )
+
+    c1 = base.mark_arc(innerRadius=20, stroke="#fff")
+
+    c2 = base.mark_text(radiusOffset=20).encode(text="values:Q")
+
+    chart = c1 + c2
+
+    return chart
+
+
+def kpi_chart_remaining() -> alt.Chart:
+    """
+    This function returns a KPI chart with the remaining amount of records to be annotated.
+    Returns:
+        An altair chart with the KPI chart.
+    """
+
+    pending_records = int(os.getenv("TARGET_RECORDS")) - len(target_dataset)
+    # Assuming you have a DataFrame with user data, create a sample DataFrame
+    data = pd.DataFrame({"Category": [PENDING], "Value": [pending_records]})
+
+    # Create Altair chart
+    chart = (
+        alt.Chart(data)
+        .mark_text(fontSize=100, align="center", baseline="middle", color="#e68b39")
+        .encode(text="Value:N")
+        .properties(title=PENDING, width=250, height=200)
+    )
+
+    return chart
+
+
+def kpi_chart_submitted() -> alt.Chart:
+    """
+    This function returns a KPI chart with the total amount of records that have been annotated.
+    Returns:
+        An altair chart with the KPI chart.
+    """
+
+    total = len(target_dataset)
+
+    # Assuming you have a DataFrame with user data, create a sample DataFrame
+    data = pd.DataFrame({"Category": [NUMBER_ANNOTATED], "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=NUMBER_ANNOTATED, width=250, height=200)
+    )
+
+    return chart
+
+
+def kpi_chart_total_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": [NUMBER_ANNOTATORS], "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_ANNOTATORS, width=250, height=200)
+    )
+
+    return chart
+
+
+def render_hub_user_link(hub_id: str) -> str:
+    """
+    This function returns a link to the user's profile on Hugging Face.
+
+    Args:
+        hub_id: The user's id on Hugging Face.
+
+    Returns:    
+        A string with the link to the user's profile on Hugging Face.
+    """
+    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 obtain_top_users(user_ids_annotations: Dict[str, int], N: int = 50) -> pd.DataFrame:
+    """
+    This function returns the top N users with the most annotations.
+
+    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 N users with the most annotations.
+    """
+
+    dataframe = pd.DataFrame(
+        user_ids_annotations.items(), columns=[NAME, NUMBER_ANNOTATIONS]
+    )
+    dataframe[NAME] = dataframe[NAME].apply(render_hub_user_link)
+    dataframe = dataframe.sort_values(by=NUMBER_ANNOTATIONS, ascending=False)
+    return dataframe.head(N)
+
+
+def fetch_data() -> None:
+    """
+    This function fetches the data from the source and target datasets and updates the global variables.
+    """
+
+    print(f"Starting to fetch data: {datetime.datetime.now()}")
+
+    global source_dataset, target_dataset, user_ids_annotations, annotated, remaining, percentage_completed, top_dataframe
+    source_dataset, target_dataset = obtain_source_target_datasets()
+    user_ids_annotations = get_user_annotations_dictionary(target_dataset)
+
+    annotated = len(target_dataset)
+    remaining = int(os.getenv("TARGET_RECORDS")) - annotated
+    percentage_completed = round(
+        (annotated / int(os.getenv("TARGET_RECORDS"))) * 100, 1
+    )
+
+    # Print the current date and time
+    print(f"Data fetched: {datetime.datetime.now()}")
+
+
+def get_top(N=50) -> pd.DataFrame:
+    """
+    This function returns the top N users with the most annotations.
+
+    Args:
+        N: The number of users to be returned. 50 by default
+
+    Returns:
+        A pandas dataframe with the top N users with the most annotations.
+    """
+
+    return obtain_top_users(user_ids_annotations, N=N)
+
+
+def main() -> None:
+
+    # Connect to the space with rg.init()
+    rg.init(
+        api_url=os.getenv("ARGILLA_API_URL"),
+        api_key=os.getenv("ARGILLA_API_KEY"),
+    )
+
+    # Fetch the data initially
+    fetch_data()
+
+    # To avoid the orange border for the Gradio elements that are in constant loading
+    css = """
+    .generating {
+        border: none;
+    }
+    """
+
+    with gr.Blocks(css=css) as demo:
+        gr.Markdown(
+            """
+            # 🌍 Slovak - Multilingual Prompt Evaluation Project
+
+            Hugging Face a @argilla vyvíjajú projekt [Multilingual Prompt Evaluation Project](https://github.com/huggingface/data-is-better-together/tree/main/prompt_translation). Ide o verejný multilinguálny benchmark pre vyhodnocovanie jazykových modelov.
+
+            ## Cieľom je preložiť 500 promptov
+            K evaluácií avšak potrebujeme dáta! Komunita vybrala 500 najlepších promptov, ktoré budú tvoriť benchmark, ktoré sú ale v angličtine.
+            **Preto potrebujeme vašu pomoc**: ak preložíme všetkých 500 promptov, môžeme pridať slovenčinu do evaluácie jazykových modelov.
+
+            ## Ako sa zapojiť
+            Navštívte [anotačné prostredie](https://dibt-slovak-prompt-translation-for-slovak.hf.space/), prihláste sa pomocou existujúceho Hugging Face účtu alebo si môžete vytvoriť nové Hugging Face konto. Po prihlásení môžete začať prekladať.
+            Vďaka za vašu pomoc! Aby sme vám trochu pomohli, využili sme SeamlessM4T model pre vytvorenie návrhov v slovenčine. Tieto návrhy je možné schváliť, upraviť alebo prepísať celé nanovo.
+            """
+        )
+
+        gr.Markdown(
+            f"""
+            ## 🚀 Aktuálny progres
+            """
+        )
+        with gr.Row():
+
+            kpi_submitted_plot = gr.Plot(label="Plot")
+            demo.load(
+                kpi_chart_submitted,
+                inputs=[],
+                outputs=[kpi_submitted_plot],
+            )
+
+            kpi_remaining_plot = gr.Plot(label="Plot")
+            demo.load(
+                kpi_chart_remaining,
+                inputs=[],
+                outputs=[kpi_remaining_plot],
+            )
+
+            donut_total_plot = gr.Plot(label="Plot")
+            demo.load(
+                donut_chart_total,
+                inputs=[],
+                outputs=[donut_total_plot],
+            )
+
+        gr.Markdown(
+            """
+            ## 👾 Sieň slávy
+            Tu môžete vidieť najaktívnejších prispievateľov a počet anotácií, ktoré urobili.
+            """
+        )
+
+        with gr.Row():
+
+            kpi_hall_plot = gr.Plot(label="Plot")
+            demo.load(
+                kpi_chart_total_annotators, inputs=[], outputs=[kpi_hall_plot]
+            )
+
+            top_df_plot = gr.Dataframe(
+                headers=[NAME, NUMBER_ANNOTATIONS],
+                datatype=[
+                    "markdown",
+                    "number",
+                ],
+                row_count=50,
+                col_count=(2, "fixed"),
+                interactive=False,
+            )
+            demo.load(get_top, None, [top_df_plot])
+
+    # Launch the Gradio interface
+    demo.launch()
+
+
+if __name__ == "__main__":
+    main()

dumpy.py

@@ -0,0 +1,52 @@
+import json
+import logging
+import os
+
+import argilla as rg
+from huggingface_hub import HfApi
+
+logger = logging.getLogger(__name__)
+logger.setLevel(logging.INFO)
+
+if __name__ == "__main__":
+    logger.info("*** Initializing Argilla session ***")
+    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')}"},
+    )
+
+    logger.info("*** Fetching dataset from Argilla ***")
+    dataset = rg.FeedbackDataset.from_argilla(
+        os.getenv("SOURCE_DATASET"),
+        workspace=os.getenv("SOURCE_WORKSPACE"),
+    )
+    logger.info("*** Filtering records by `response_status` ***")
+    dataset = dataset.filter_by(response_status=["submitted"])  # type: ignore
+
+    logger.info("*** Calculating users and annotation count ***")
+    output = {}
+    for record in dataset.records:
+        for response in record.responses:
+            if response.user_id not in output:
+                output[response.user_id] = 0
+            output[response.user_id] += 1
+
+    for key in list(output.keys()):
+        output[rg.User.from_id(key).username] = output.pop(key)
+
+    logger.info("*** Users and annotation count successfully calculated! ***")
+
+    logger.info("*** Dumping Python dict into `stats.json` ***")
+    with open("stats.json", "w") as file:
+        json.dump(output, file, indent=4)
+
+    logger.info("*** Uploading `stats.json` to Hugging Face Hub ***")
+    api = HfApi(token=os.getenv("HF_TOKEN"))
+    api.upload_file(
+        path_or_fileobj="stats.json",
+        path_in_repo="stats.json",
+        repo_id="DIBT/prompt-collective-dashboard",
+        repo_type="space",
+    )
+    logger.info("*** `stats.json` successfully uploaded to Hugging Face Hub! ***")

gitattributes.txt

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

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