Update app.py

app.py

@@ -1,204 +1,207 @@
 import gradio as gr
-from gradio_leaderboard import Leaderboard, ColumnFilter, SelectColumns
+import json
 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)
-
-(
-    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,
-    )
-
-
-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():
+from urllib.request import urlopen
+from urllib.error import URLError
+import re
+from datetime import datetime
+
+# Constants
+CITATION_BUTTON_TEXT = r"""@misc{2023opencompass,
+    title={OpenCompass: A Universal Evaluation Platform for Foundation Models},
+    author={OpenCompass Contributors},
+    howpublished = {\url{https://github.com/open-compass/opencompass}},
+    year={2023}
+}"""
+CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results"
+# 开发环境
+# DATA_URL_BASE = "http://opencompass.oss-cn-shanghai.aliyuncs.com/dev-assets/research-rank/research-data.REALTIME."
+# DATA_URL_BASE = "./s1test"
+# 生产环境
+DATA_URL_BASE = "http://opencompass.oss-cn-shanghai.aliyuncs.com/assets/research-rank/research-data.REALTIME."
+
+
+def find_latest_data_url():
+    """Find the latest available data URL by trying different dates."""
+    today = datetime.now()
+    for i in range(365):
+        date = today.replace(day=today.day - i)
+        date_str = date.strftime("%Y%m%d")
+        url = f"{DATA_URL_BASE}{date_str}.json"
+        try:
+            urlopen(url)
+            return url, date_str
+        except URLError:
+            continue
+    breakpoint()
+    return None, None
+
+
+def get_latest_data():
+    """Get latest data URL and update time"""
+    data_url, update_time = find_latest_data_url()
+    if not data_url:
+        raise Exception("Could not find valid data URL")
+    formatted_update_time = datetime.strptime(update_time, "%Y%m%d").strftime("%Y-%m-%d")
+    return data_url, formatted_update_time
+
+
+def get_leaderboard_title(update_time):
+    return f"# Supported Datasets List (Last Updated: {update_time})"
+
+
+MAIN_DESCRIPTION = """## The List of Datasets Supported by OpenCompass
+Testing line.
+- All configurations and datsets can be found in [**OpenCompass**: A Toolkit for Evaluation of LLMs](https://github.com/open-compass/opencompass)🏆.
+"""
+
+
+
+
+def load_data(data_url):
+    response = urlopen(data_url)
+
+    with open('s1.json','r',encoding='utf8') as f:
+        data = json.load(f)
+
+    return data
+
+
+def build_main_table(data):
+    df = pd.DataFrame(data).transpose()
+    columns = {
+        'name': 'Name', 'category': 'Category', 'article': 'Article Address',
+    }
+    df = df[list(columns.keys())].rename(columns=columns)
+    return df
+
+
+DATA_CATEGORY = ['med', 'law', 'code']
+
+def filter_table1(df, data_category):
+    filtered_df = df.copy()
+    if data_category:
+        mask = pd.Series(False, index=filtered_df.index)
+        for category in data_category:
+            mask |= filtered_df['Category'] == category
+        filtered_df = filtered_df[mask]
+
+    return filtered_df
+
+
+def calculate_column_widths(df):
+    column_widths = []
+    for column in df.columns:
+        header_length = len(str(column))
+        max_content_length = df[column].astype(str).map(len).max()
+        width = max(header_length * 10, max_content_length * 8) + 20
+        width = max(160, min(400, width))
+        column_widths.append(width)
+    return column_widths
+
+
+class DataState:
+    def __init__(self):
+        self.current_df = None
+
+
+data_state = DataState()
+
+
+def create_interface():
+    empty_df = pd.DataFrame(columns=[
+        'Name', 'Category', 'Article Address'
+    ])
+
+    def load_initial_data():
+        try:
+            data_url, update_time = get_latest_data()
+            data = load_data(data_url)
+            new_df = build_main_table(data)
+            data_state.current_df = new_df
+            filtered_df = filter_table1(new_df, DATA_CATEGORY)
+            return get_leaderboard_title(update_time), filtered_df.sort_values("Name", ascending=True)
+        except Exception as e:
+            print(f"Error loading initial data: {e}")
+            return "# Supported Datasets List (Error loading data)", empty_df
+
+    def refresh_data():
+        try:
+            data_url, update_time = get_latest_data()
+            data = load_data(data_url)
+            new_df = build_main_table(data)
+            data_state.current_df = new_df
+            filtered_df = filter_table1(new_df, DATA_CATEGORY)
+            return get_leaderboard_title(update_time), filtered_df.sort_values("Name", ascending=True)
+        except Exception as e:
+            print(f"Error refreshing data: {e}")
+            return None, None
+
+    def update_table(category):
+        if data_state.current_df is None:
+            return empty_df
+        filtered_df = filter_table1(data_state.current_df, category)
+        return filtered_df.sort_values("Name", ascending=True)
+
+    initial_title, initial_data = load_initial_data()
+
+    with gr.Blocks() as demo:
+        title_comp = gr.Markdown(initial_title)
+
+        with gr.Tabs() as tabs:
+            with gr.TabItem("Dataset List", elem_id='main'):
+                gr.Markdown(MAIN_DESCRIPTION)
+
                 with gr.Row():
-                    gr.Markdown(EVALUATION_QUEUE_TEXT, elem_classes="markdown-text")
+                    with gr.Column():
+                        category_filter = gr.CheckboxGroup(
+                            choices=DATA_CATEGORY,
+                            value=DATA_CATEGORY,
+                            label='Category',
+                            interactive=True,
+                        )
 
                 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,
-                            )
-
-                    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")
-
-            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,
+                    table = gr.DataFrame(
+                        value=initial_data,
+                        interactive=False,
+                        wrap=False,
+                        column_widths=calculate_column_widths(initial_data),
                     )
 
-                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)")
-
-            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.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()
+                refresh_button = gr.Button("Refresh Data")
+
+                def refresh_and_update():
+                    title, data = refresh_data()
+                    return title, data
+
+                refresh_button.click(
+                    fn=refresh_and_update,
+                    outputs=[title_comp, table],
+                )
+
+                category_filter.change(
+                    fn=update_table,
+                    inputs=[category_filter],
+                    outputs=table,
+                )
+
+
+        with gr.Row():
+            with gr.Accordion("Citation", open=False):
+                citation_button = gr.Textbox(
+                    value=CITATION_BUTTON_TEXT,
+                    label=CITATION_BUTTON_LABEL,
+                    elem_id='citation-button',
+                    lines=6,  # 增加行数
+                    max_lines=8,  # 设置最大行数
+                    show_copy_button=True  # 添加复制按钮使其更方便使用
+                )
+
+    return demo
+
+
+if __name__ == '__main__':
+    demo = create_interface()
+    demo.queue()
+    demo.launch(server_name='0.0.0.0')