add files

.gitignore

@@ -0,0 +1,10 @@
+# Python-generated files
+__pycache__/
+*.py[oc]
+build/
+dist/
+wheels/
+*.egg-info
+
+# Virtual environments
+.venv

README.md

@@ -1,14 +1,17 @@
----
-title: TabArena
-emoji: 🦀
-colorFrom: gray
-colorTo: red
-sdk: gradio
-sdk_version: 5.30.0
-app_file: app.py
-pinned: false
-license: apache-2.0
-short_description: TabArena leaderboard for tabular methods
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# TabArena Leaderboard code
+
+This repository contains the frontend code to display TabArena leaderboard. The leaderboard is hosted on a 
+HuggingFace space.
+
+Reference:
+* website: tabarena.ai
+* paper: TODO
+* codebase to compute the leaderboard: https://github.com/autogluon/tabrepo/tree/tabarena
+
+TODOS:
+* add regression/classif/multiclassif
+
+DONE:
+* readme title and information
+* pull data from leaderboard
+* update columns

constants.py

@@ -0,0 +1,19 @@
+class MethodTypes:
+    col_name: str = "method_type"
+    automl: str = "AutoML"
+    tree: str = "Tree-based"
+    foundational: str = "Foundational"
+    finetuned: str = "Neural-network"
+    baseline: str = "Baseline"
+    other: str = "Other"
+
+
+
+model_type_emoji = {
+    MethodTypes.tree: "🌴",
+    MethodTypes.foundational: "🧠",
+    MethodTypes.finetuned: "🌐",
+    MethodTypes.automl: "🤖",
+    MethodTypes.baseline: "📏",
+    MethodTypes.other: "❓",
+}

data/leaderboard-all.csv.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9e301dfeeb8cc7092301268aad4e4c9922517b6288101a588b5a15f5a0aaca9
+size 4679

data/leaderboard-classification.csv.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9e301dfeeb8cc7092301268aad4e4c9922517b6288101a588b5a15f5a0aaca9
+size 4679

data/leaderboard-regression.csv.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9e301dfeeb8cc7092301268aad4e4c9922517b6288101a588b5a15f5a0aaca9
+size 4679

main.py

@@ -0,0 +1,118 @@
+from pathlib import Path
+
+from apscheduler.schedulers.background import BackgroundScheduler
+import pandas as pd
+import gradio as gr
+from gradio_leaderboard import Leaderboard, ColumnFilter
+
+from constants import MethodTypes, model_type_emoji
+
+
+TITLE = """<h1 align="center" id="space-title">TabArena: Public leaderboard for Tabular methods</h1>"""
+
+INTRODUCTION_TEXT = ("TabArena Leaderboard measures the performance of tabular models on a collection of tabular "
+                     "datasets manually curated. The datasets are collected to make sure they are tabular, with "
+                     "permissive license without ethical issues and so on, we refer to the paper XXX for a "
+                     "description of our approach.")
+
+ABOUT_TEXT = f"""
+## How It Works.
+
+To evaluate the leaderboard, follow install instructions in 
+`https://github.com/autogluon/tabrepo/tree/tabarena` and run 
+`https://github.com/autogluon/tabrepo/blob/tabarena/examples/tabarena/run_tabarena_eval.py`.
+
+
+This will generate a leaderboard. You can add your own method and contact the authors if you want it to be added
+to the leaderboard. We require method to have public code available to be considered in the leaderboard. 
+"""
+
+CITATION_BUTTON_LABEL = "If you use this leaderboard in your research please cite the following:"
+CITATION_BUTTON_TEXT = r"""
+@article{
+TODO update when arxiv version is ready,
+}
+"""
+
+
+def get_model_family(model_name: str) -> str:
+    prefixes_mapping = {
+        MethodTypes.automl: ["AutoGluon"],
+        MethodTypes.finetuned: ["REALMLP", "TabM", "FASTAI", "MNCA", "NN_TORCH"],
+        MethodTypes.tree: ["GBM", "CAT", "EBM", "XGB"],
+        MethodTypes.foundational: ["TABDPT", "TABICL", "TABPFN"],
+        MethodTypes.baseline: ["KNN", "LR"]
+    }
+    for method_type, prefixes in prefixes_mapping.items():
+        for prefix in prefixes:
+            if prefix.lower() in model_name.lower():
+                return method_type
+    return MethodTypes.other
+
+
+def load_data(filename: str):
+    df_leaderboard = pd.read_csv(Path(__file__).parent / "data" / f"{filename}.csv.zip")
+    print(f"Loaded dataframe with {len(df_leaderboard)} rows and columns {df_leaderboard.columns}")
+    df_leaderboard["family"] = df_leaderboard.loc[:, "method"].apply(get_model_family)
+    df_leaderboard["family"] = df_leaderboard.loc[:, "family"].apply(lambda s: s + " " + model_type_emoji[s])
+    df_leaderboard = df_leaderboard.loc[:, ["method", "family", "time_train_s", "time_infer_s", "rank", "elo"]]
+    df_leaderboard = df_leaderboard.round(1)
+    df_leaderboard.rename(columns={
+        "time_train_s": "training time (s)",
+        "time_infer_s": "inference time (s)",
+    }, inplace=True)
+    return df_leaderboard
+
+
+def make_leaderboard(df_leaderboard: pd.DataFrame) -> Leaderboard:
+    return Leaderboard(
+        value=df_leaderboard,
+        search_columns=["method"],
+        filter_columns=[
+            # "method",
+            ColumnFilter("family", type="dropdown", label="Filter by family"),
+        ]
+    )
+
+
+def main():
+
+    demo = gr.Blocks()
+    with demo:
+        gr.HTML(TITLE)
+        gr.Markdown(INTRODUCTION_TEXT, elem_classes="markdown-text")
+
+        with gr.Tabs(elem_classes="tab-buttons") as tabs:
+            with gr.TabItem('🏅 Overall', elem_id="llm-benchmark-tab-table", id=2):
+                df_leaderboard = load_data("leaderboard-all")
+                leaderboard = make_leaderboard(df_leaderboard)
+
+            with gr.TabItem('🏅 Regression', elem_id="llm-benchmark-tab-table", id=0):
+                df_leaderboard = load_data("leaderboard-regression")
+                leaderboard = make_leaderboard(df_leaderboard)
+
+            with gr.TabItem('🏅 Classification', elem_id="llm-benchmark-tab-table", id=1):
+                df_leaderboard = load_data("leaderboard-classification")
+                leaderboard = make_leaderboard(df_leaderboard)
+
+            with gr.TabItem("📝 About", elem_id="llm-benchmark-tab-table", id=4):
+                gr.Markdown(ABOUT_TEXT, elem_classes="markdown-text")
+        with gr.Row():
+            with gr.Accordion("📙 Citation", open=False):
+                citation_button = gr.Textbox(
+                    value=CITATION_BUTTON_TEXT,
+                    label=CITATION_BUTTON_LABEL,
+                    lines=20,
+                    elem_id="citation-button",
+                    show_copy_button=True,
+                )
+
+    scheduler = BackgroundScheduler()
+    # scheduler.add_job(restart_space, "interval", seconds=1800)
+    scheduler.start()
+    demo.queue(default_concurrency_limit=40).launch()
+    demo.launch()
+
+
+if __name__ == "__main__":
+    main()

pyproject.toml

@@ -0,0 +1,13 @@
+[project]
+name = "tabarenaleaderboard"
+version = "0.1.0"
+description = "Add your description here"
+readme = "README.md"
+requires-python = ">=3.12"
+dependencies = [
+    "apscheduler>=3.11.0",
+    "gradio-client>=1.3.0",
+    "gradio-leaderboard==0.0.9",
+    "gradio[oauth]==4.44.0",
+    "pandas>=2.2.3",
+]