Rebuild the project

app.py

@@ -1,204 +1,37 @@
 import gradio as gr
-from gradio_leaderboard import Leaderboard, ColumnFilter, SelectColumns
-import pandas as pd
-from apscheduler.schedulers.background import BackgroundScheduler
-from huggingface_hub import snapshot_download
 
-from src.about import (
-    CITATION_BUTTON_LABEL,
-    CITATION_BUTTON_TEXT,
-    EVALUATION_QUEUE_TEXT,
-    INTRODUCTION_TEXT,
-    LLM_BENCHMARKS_TEXT,
-    TITLE,
-)
-from src.display.css_html_js import custom_css
-from src.display.utils import (
-    BENCHMARK_COLS,
-    COLS,
-    EVAL_COLS,
-    EVAL_TYPES,
-    AutoEvalColumn,
-    ModelType,
-    fields,
-    WeightType,
-    Precision
-)
-from src.envs import API, EVAL_REQUESTS_PATH, EVAL_RESULTS_PATH, QUEUE_REPO, REPO_ID, RESULTS_REPO, TOKEN
-from src.populate import get_evaluation_queue_df, get_leaderboard_df
-from src.submission.submit import add_new_eval
-
-
-def restart_space():
-    API.restart_space(repo_id=REPO_ID)
-
-### Space initialisation
-try:
-    print(EVAL_REQUESTS_PATH)
-    snapshot_download(
-        repo_id=QUEUE_REPO, local_dir=EVAL_REQUESTS_PATH, repo_type="dataset", tqdm_class=None, etag_timeout=30, token=TOKEN
-    )
-except Exception:
-    restart_space()
-try:
-    print(EVAL_RESULTS_PATH)
-    snapshot_download(
-        repo_id=RESULTS_REPO, local_dir=EVAL_RESULTS_PATH, repo_type="dataset", tqdm_class=None, etag_timeout=30, token=TOKEN
-    )
-except Exception:
-    restart_space()
-
-
-LEADERBOARD_DF = get_leaderboard_df(EVAL_RESULTS_PATH, EVAL_REQUESTS_PATH, COLS, BENCHMARK_COLS)
+from leaderboard.dataset import load_or_initialize_leaderboard
+from leaderboard.submission import submit_model
 
-(
-    finished_eval_queue_df,
-    running_eval_queue_df,
-    pending_eval_queue_df,
-) = get_evaluation_queue_df(EVAL_REQUESTS_PATH, EVAL_COLS)
 
-def init_leaderboard(dataframe):
-    if dataframe is None or dataframe.empty:
-        raise ValueError("Leaderboard DataFrame is empty or None.")
-    return Leaderboard(
-        value=dataframe,
-        datatype=[c.type for c in fields(AutoEvalColumn)],
-        select_columns=SelectColumns(
-            default_selection=[c.name for c in fields(AutoEvalColumn) if c.displayed_by_default],
-            cant_deselect=[c.name for c in fields(AutoEvalColumn) if c.never_hidden],
-            label="Select Columns to Display:",
-        ),
-        search_columns=[AutoEvalColumn.model.name, AutoEvalColumn.license.name],
-        hide_columns=[c.name for c in fields(AutoEvalColumn) if c.hidden],
-        filter_columns=[
-            ColumnFilter(AutoEvalColumn.model_type.name, type="checkboxgroup", label="Model types"),
-            ColumnFilter(AutoEvalColumn.precision.name, type="checkboxgroup", label="Precision"),
-            ColumnFilter(
-                AutoEvalColumn.params.name,
-                type="slider",
-                min=0.01,
-                max=150,
-                label="Select the number of parameters (B)",
-            ),
-            ColumnFilter(
-                AutoEvalColumn.still_on_hub.name, type="boolean", label="Deleted/incomplete", default=True
-            ),
-        ],
-        bool_checkboxgroup_label="Hide models",
-        interactive=False,
-    )
+# リーダーボード表示
+def display_leaderboard():
+    dataset = load_or_initialize_leaderboard()
+    return dataset.to_pandas()
 
 
-demo = gr.Blocks(css=custom_css)
-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("🏅 LLM Benchmark", elem_id="llm-benchmark-tab-table", id=0):
-            leaderboard = init_leaderboard(LEADERBOARD_DF)
-
-        with gr.TabItem("📝 About", elem_id="llm-benchmark-tab-table", id=2):
-            gr.Markdown(LLM_BENCHMARKS_TEXT, elem_classes="markdown-text")
-
-        with gr.TabItem("🚀 Submit here! ", elem_id="llm-benchmark-tab-table", id=3):
-            with gr.Column():
-                with gr.Row():
-                    gr.Markdown(EVALUATION_QUEUE_TEXT, elem_classes="markdown-text")
-
-                with gr.Column():
-                    with gr.Accordion(
-                        f"✅ Finished Evaluations ({len(finished_eval_queue_df)})",
-                        open=False,
-                    ):
-                        with gr.Row():
-                            finished_eval_table = gr.components.Dataframe(
-                                value=finished_eval_queue_df,
-                                headers=EVAL_COLS,
-                                datatype=EVAL_TYPES,
-                                row_count=5,
-                            )
-                    with gr.Accordion(
-                        f"🔄 Running Evaluation Queue ({len(running_eval_queue_df)})",
-                        open=False,
-                    ):
-                        with gr.Row():
-                            running_eval_table = gr.components.Dataframe(
-                                value=running_eval_queue_df,
-                                headers=EVAL_COLS,
-                                datatype=EVAL_TYPES,
-                                row_count=5,
-                            )
+# Gradio のコンポーネント
+leaderboard_component = gr.DataFrame(
+    display_leaderboard, headers=["Model Name", "Score", "Rank"], interactive=False, label="Leaderboard"
+)
 
-                    with gr.Accordion(
-                        f"⏳ Pending Evaluation Queue ({len(pending_eval_queue_df)})",
-                        open=False,
-                    ):
-                        with gr.Row():
-                            pending_eval_table = gr.components.Dataframe(
-                                value=pending_eval_queue_df,
-                                headers=EVAL_COLS,
-                                datatype=EVAL_TYPES,
-                                row_count=5,
-                            )
-            with gr.Row():
-                gr.Markdown("# ✉️✨ Submit your model here!", elem_classes="markdown-text")
+submit_form = gr.Interface(
+    submit_model,
+    inputs=[gr.Textbox(label="Model Name"), gr.File(label="Model File")],
+    outputs=gr.DataFrame(headers=["Model Name", "Score", "Rank"], interactive=False),
+)
 
-            with gr.Row():
-                with gr.Column():
-                    model_name_textbox = gr.Textbox(label="Model name")
-                    revision_name_textbox = gr.Textbox(label="Revision commit", placeholder="main")
-                    model_type = gr.Dropdown(
-                        choices=[t.to_str(" : ") for t in ModelType if t != ModelType.Unknown],
-                        label="Model type",
-                        multiselect=False,
-                        value=None,
-                        interactive=True,
-                    )
+# Gradio アプリケーション
+app = gr.Blocks()
 
-                with gr.Column():
-                    precision = gr.Dropdown(
-                        choices=[i.value.name for i in Precision if i != Precision.Unknown],
-                        label="Precision",
-                        multiselect=False,
-                        value="float16",
-                        interactive=True,
-                    )
-                    weight_type = gr.Dropdown(
-                        choices=[i.value.name for i in WeightType],
-                        label="Weights type",
-                        multiselect=False,
-                        value="Original",
-                        interactive=True,
-                    )
-                    base_model_name_textbox = gr.Textbox(label="Base model (for delta or adapter weights)")
+with app:
+    gr.Markdown("# human_methylation_bench_ver1")
 
-            submit_button = gr.Button("Submit Eval")
-            submission_result = gr.Markdown()
-            submit_button.click(
-                add_new_eval,
-                [
-                    model_name_textbox,
-                    base_model_name_textbox,
-                    revision_name_textbox,
-                    precision,
-                    weight_type,
-                    model_type,
-                ],
-                submission_result,
-            )
+    with gr.Tab("Leaderboard"):
+        leaderboard_component.render()
 
-    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,
-            )
+    with gr.Tab("Submit Model"):
+        submit_form.render()
 
-scheduler = BackgroundScheduler()
-scheduler.add_job(restart_space, "interval", seconds=1800)
-scheduler.start()
-demo.queue(default_concurrency_limit=40).launch()
+if __name__ == "__main__":
+    app.launch()

leaderboard/dataset.py

@@ -0,0 +1,25 @@
+from datasets import Dataset, load_dataset
+
+DATASET_PATH = "leaderboard_dataset"
+
+# 初期データ
+INITIAL_DATA = {
+    "Model Name": ["Baseline Model"],
+    "Score": [0.8],
+    "Rank": [1],
+}
+
+
+# データセットを初期化またはロード
+def load_or_initialize_leaderboard():
+    try:
+        dataset = Dataset.load_from_disk(DATASET_PATH)
+    except FileNotFoundError:
+        dataset = Dataset.from_dict(INITIAL_DATA)
+        dataset.save_to_disk(DATASET_PATH)
+    return dataset
+
+
+# データセットを保存
+def save_leaderboard(dataset):
+    dataset.save_to_disk(DATASET_PATH)

leaderboard/evaluation.py

@@ -0,0 +1,8 @@
+# ダミーの評価関数
+def evaluate_model(model_path):
+    """
+    提出モデルを評価してスコアを返す関数。
+    本番ではモデルをロードしてテストデータに基づくスコアを計算する。
+    """
+    # TODO: 実際の評価ロジックを実装する
+    return 0.75  # 仮のスコア

leaderboard/submission.py

@@ -0,0 +1,32 @@
+from datasets import Dataset
+
+from .dataset import load_or_initialize_leaderboard, save_leaderboard
+from .evaluation import evaluate_model
+
+
+def submit_model(model_name, model_file):
+    """
+    モデルの提出を処理する関数。
+    1. モデルを評価する。
+    2. リーダーボードにデータを追加。
+    3. ランクを計算して保存。
+    """
+    dataset = load_or_initialize_leaderboard()
+
+    # モデル評価
+    score = evaluate_model(model_file.name)
+
+    # データに新しいモデルを追加
+    new_entry = {"Model Name": model_name, "Score": score}
+    dataset = dataset.add_item(new_entry)
+
+    # ランク付け
+    df = dataset.to_pandas()
+    df = df.sort_values(by="Score", ascending=False).reset_index(drop=True)
+    df["Rank"] = range(1, len(df) + 1)
+
+    # データセットを更新・保存
+    updated_dataset = Dataset.from_pandas(df)
+    save_leaderboard(updated_dataset)
+
+    return df

pyproject.toml

@@ -1,3 +1,20 @@
+[tool.poetry]
+name = "human-methylation-bench-ver1"
+version = "0.1.0"
+description = ""
+authors = ["Your Name <you@example.com>"]
+readme = "README.md"
+
+[tool.poetry.dependencies]
+python = "^3.12"
+gradio = "^5.6.0"
+pandas = "^2.2.3"
+datasets = "^3.1.0"
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"
+
 [tool.ruff]
 # Enable pycodestyle (`E`) and Pyflakes (`F`) codes by default.
 select = ["E", "F"]
@@ -10,4 +27,4 @@ profile = "black"
 line_length = 119
 
 [tool.black]
-line-length = 119
+line-length = 119