clean

.gitattributes

@@ -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

README.md

@@ -0,0 +1,12 @@
+---
+title: Argilla Progress
+emoji: 🚀
+colorFrom: purple
+colorTo: purple
+sdk: gradio
+sdk_version: 4.42.0
+app_file: app.py
+pinned: false
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,193 @@
+import os
+import datetime
+import pandas as pd
+import gradio as gr
+import argilla as rg
+import plotly.graph_objects as go
+import plotly.colors as colors
+
+client = rg.Argilla(
+    api_url=os.getenv("ARGILLA_API_URL"), api_key=os.getenv("ARGILLA_API_KEY")
+)
+
+
+def fetch_data(dataset_name: str, workspace: str):
+    return client.datasets(dataset_name, workspace=workspace)
+
+
+def get_progress(dataset) -> dict:
+    records = list(dataset.records)
+    total_records = len(records)
+    annotated_records = len(
+        [record.status for record in records if record.status == "completed"]
+    )
+    progress = (annotated_records / total_records) * 100 if total_records > 0 else 0
+    return {
+        "total": total_records,
+        "annotated": annotated_records,
+        "progress": progress,
+    }
+
+
+def get_leaderboard(dataset) -> dict:
+    user_annotations = {}
+    for record in dataset.records:
+        for response in record.responses:
+            user = response.user_id
+            retrieved_user = client.users(id=user)
+            user = retrieved_user.username
+            if user not in user_annotations:
+                user_annotations[user] = 0
+            user_annotations[user] += 1
+    print(user_annotations)
+    return user_annotations
+
+
+def create_gauge_chart(progress):
+    fig = go.Figure(
+        go.Indicator(
+            mode="gauge+number+delta",
+            value=progress["progress"],
+            title={"text": "Dataset Annotation Progress", "font": {"size": 24}},
+            delta={"reference": 100, "increasing": {"color": "RebeccaPurple"}},
+            number={"font": {"size": 40}, "valueformat": ".1f", "suffix": "%"},
+            gauge={
+                "axis": {"range": [None, 100], "tickwidth": 1, "tickcolor": "darkblue"},
+                "bar": {"color": "deepskyblue"},
+                "bgcolor": "white",
+                "borderwidth": 2,
+                "bordercolor": "gray",
+                "steps": [
+                    {"range": [0, progress["progress"]], "color": "royalblue"},
+                    {"range": [progress["progress"], 100], "color": "lightgray"},
+                ],
+                "threshold": {
+                    "line": {"color": "red", "width": 4},
+                    "thickness": 0.75,
+                    "value": 100,
+                },
+            },
+        )
+    )
+
+    fig.update_layout(
+        annotations=[
+            dict(
+                text=(
+                    f"Total records: {progress['total']}<br>"
+                    f"Annotated: {progress['annotated']} ({progress['progress']:.1f}%)<br>"
+                    f"Remaining: {progress['total'] - progress['annotated']} ({100 - progress['progress']:.1f}%)"
+                ),
+                # x=0.5,
+                # y=-0.2,
+                showarrow=False,
+                xref="paper",
+                yref="paper",
+                font=dict(size=16),
+            )
+        ],
+    )
+
+    fig.add_annotation(
+        text=(
+            f"Current Progress: {progress['progress']:.1f}% complete<br>"
+            f"({progress['annotated']} out of {progress['total']} records annotated)"
+        ),
+        xref="paper",
+        yref="paper",
+        x=0.5,
+        y=1.1,
+        showarrow=False,
+        font=dict(size=18),
+        align="center",
+    )
+
+    return fig
+
+
+def create_treemap(user_annotations, total_records):
+    sorted_users = sorted(user_annotations.items(), key=lambda x: x[1], reverse=True)
+    color_scale = colors.qualitative.Pastel + colors.qualitative.Set3
+
+    labels, parents, values, text, user_colors = [], [], [], [], []
+
+    for i, (user, contribution) in enumerate(sorted_users):
+        percentage = (contribution / total_records) * 100
+        labels.append(user)
+        parents.append("Annotations")
+        values.append(contribution)
+        text.append(f"{contribution} annotations<br>{percentage:.2f}%")
+        user_colors.append(color_scale[i % len(color_scale)])
+
+    labels.append("Annotations")
+    parents.append("")
+    values.append(total_records)
+    text.append(f"Total: {total_records} annotations")
+    user_colors.append("#FFFFFF")
+
+    fig = go.Figure(
+        go.Treemap(
+            labels=labels,
+            parents=parents,
+            values=values,
+            text=text,
+            textinfo="label+text",
+            hoverinfo="label+text+value",
+            marker=dict(colors=user_colors, line=dict(width=2)),
+        )
+    )
+
+    fig.update_layout(
+        title_text="User contributions to the total end dataset",
+        height=500,
+        margin=dict(l=10, r=10, t=50, b=10),
+        paper_bgcolor="#F0F0F0",  # Light gray background
+        plot_bgcolor="#F0F0F0",  # Light gray background
+    )
+
+    return fig
+
+
+def update_dashboard():
+    dataset = fetch_data(os.getenv("DATASET_NAME"), os.getenv("WORKSPACE"))
+    progress = get_progress(dataset)
+    user_annotations = get_leaderboard(dataset)
+
+    gauge_chart = create_gauge_chart(progress)
+    treemap = create_treemap(user_annotations, progress["total"])
+
+    leaderboard_df = pd.DataFrame(
+        list(user_annotations.items()), columns=["User", "Annotations"]
+    )
+    leaderboard_df = leaderboard_df.sort_values(
+        "Annotations", ascending=False
+    ).reset_index(drop=True)
+
+    return gauge_chart, treemap, leaderboard_df
+
+
+with gr.Blocks() as demo:
+    gr.Markdown("# Argilla Dataset Dashboard")
+
+    with gr.Row():
+        gauge_output = gr.Plot(label="Overall Progress")
+        treemap_output = gr.Plot(label="User contributions")
+
+    with gr.Row():
+        leaderboard_output = gr.Dataframe(
+            label="Leaderboard", headers=["User", "Annotations"]
+        )
+
+    demo.load(
+        update_dashboard,
+        inputs=None,
+        outputs=[gauge_output, treemap_output, leaderboard_output],
+    )
+    gr.Button("Refresh").click(
+        update_dashboard,
+        inputs=None,
+        outputs=[gauge_output, treemap_output, leaderboard_output],
+    )
+
+if __name__ == "__main__":
+    demo.launch()

requirements.in

@@ -0,0 +1,3 @@
+gradio
+argilla
+plotly

requirements.txt

@@ -0,0 +1,224 @@
+# This file was autogenerated by uv via the following command:
+#    uv pip compile requirements.in -o requirements.txt
+aiofiles==23.2.1
+    # via gradio
+aiohappyeyeballs==2.4.0
+    # via aiohttp
+aiohttp==3.10.5
+    # via
+    #   datasets
+    #   fsspec
+aiosignal==1.3.1
+    # via aiohttp
+annotated-types==0.7.0
+    # via pydantic
+anyio==4.4.0
+    # via
+    #   gradio
+    #   httpx
+    #   starlette
+argilla==2.0.1
+    # via -r requirements.in
+attrs==24.2.0
+    # via aiohttp
+certifi==2024.7.4
+    # via
+    #   httpcore
+    #   httpx
+    #   requests
+charset-normalizer==3.3.2
+    # via requests
+click==8.1.7
+    # via
+    #   typer
+    #   uvicorn
+contourpy==1.3.0
+    # via matplotlib
+cycler==0.12.1
+    # via matplotlib
+datasets==2.21.0
+    # via argilla
+dill==0.3.8
+    # via
+    #   datasets
+    #   multiprocess
+fastapi==0.112.2
+    # via gradio
+ffmpy==0.4.0
+    # via gradio
+filelock==3.15.4
+    # via
+    #   datasets
+    #   huggingface-hub
+fonttools==4.53.1
+    # via matplotlib
+frozenlist==1.4.1
+    # via
+    #   aiohttp
+    #   aiosignal
+fsspec==2024.6.1
+    # via
+    #   datasets
+    #   gradio-client
+    #   huggingface-hub
+gradio==4.42.0
+    # via -r requirements.in
+gradio-client==1.3.0
+    # via gradio
+h11==0.14.0
+    # via
+    #   httpcore
+    #   uvicorn
+httpcore==1.0.5
+    # via httpx
+httpx==0.27.2
+    # via
+    #   argilla
+    #   gradio
+    #   gradio-client
+huggingface-hub==0.24.6
+    # via
+    #   argilla
+    #   datasets
+    #   gradio
+    #   gradio-client
+idna==3.8
+    # via
+    #   anyio
+    #   httpx
+    #   requests
+    #   yarl
+importlib-resources==6.4.4
+    # via gradio
+jinja2==3.1.4
+    # via gradio
+kiwisolver==1.4.5
+    # via matplotlib
+markdown-it-py==3.0.0
+    # via rich
+markupsafe==2.1.5
+    # via
+    #   gradio
+    #   jinja2
+matplotlib==3.9.2
+    # via gradio
+mdurl==0.1.2
+    # via markdown-it-py
+multidict==6.0.5
+    # via
+    #   aiohttp
+    #   yarl
+multiprocess==0.70.16
+    # via datasets
+numpy==2.1.0
+    # via
+    #   contourpy
+    #   datasets
+    #   gradio
+    #   matplotlib
+    #   pandas
+    #   pyarrow
+orjson==3.10.7
+    # via gradio
+packaging==24.1
+    # via
+    #   datasets
+    #   gradio
+    #   gradio-client
+    #   huggingface-hub
+    #   matplotlib
+    #   plotly
+pandas==2.2.2
+    # via
+    #   datasets
+    #   gradio
+pillow==10.4.0
+    # via
+    #   gradio
+    #   matplotlib
+plotly==5.23.0
+    # via -r requirements.in
+pyarrow==17.0.0
+    # via datasets
+pydantic==2.8.2
+    # via
+    #   argilla
+    #   fastapi
+    #   gradio
+pydantic-core==2.20.1
+    # via pydantic
+pydub==0.25.1
+    # via gradio
+pygments==2.18.0
+    # via rich
+pyparsing==3.1.4
+    # via matplotlib
+python-dateutil==2.9.0.post0
+    # via
+    #   matplotlib
+    #   pandas
+python-multipart==0.0.9
+    # via gradio
+pytz==2024.1
+    # via pandas
+pyyaml==6.0.2
+    # via
+    #   datasets
+    #   gradio
+    #   huggingface-hub
+requests==2.32.3
+    # via
+    #   datasets
+    #   huggingface-hub
+rich==13.8.0
+    # via
+    #   argilla
+    #   typer
+ruff==0.6.3
+    # via gradio
+semantic-version==2.10.0
+    # via gradio
+shellingham==1.5.4
+    # via typer
+six==1.16.0
+    # via python-dateutil
+sniffio==1.3.1
+    # via
+    #   anyio
+    #   httpx
+starlette==0.38.2
+    # via fastapi
+tenacity==9.0.0
+    # via plotly
+tomlkit==0.12.0
+    # via gradio
+tqdm==4.66.5
+    # via
+    #   argilla
+    #   datasets
+    #   huggingface-hub
+typer==0.12.5
+    # via gradio
+typing-extensions==4.12.2
+    # via
+    #   fastapi
+    #   gradio
+    #   gradio-client
+    #   huggingface-hub
+    #   pydantic
+    #   pydantic-core
+    #   typer
+tzdata==2024.1
+    # via pandas
+urllib3==2.2.2
+    # via
+    #   gradio
+    #   requests
+uvicorn==0.30.6
+    # via gradio
+websockets==12.0
+    # via gradio-client
+xxhash==3.5.0
+    # via datasets
+yarl==1.9.4
+    # via aiohttp