app.py

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
from src.utils import norm_sNavie, pivot_df
import ipdb


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)
# df = pd.read_csv('LOTSAv2_EvalBenchmark(Long).csv')
# # Step 2: Pivot the DataFrame
# LEADERBOARD_DF = df.pivot_table(index='model',
#                              columns='dataset',
#                              values='eval_metrics/MAE[0.5]',
#                              aggfunc='first')
# LEADERBOARD_DF.drop(columns=['ALL'], inplace=True)
#
# # Reset the index if you want the model column to be part of the DataFrame
# LEADERBOARD_DF.reset_index(inplace=True)
# # Step 3: noramlize the values
# # ipdb.set_trace()
# LEADERBOARD_DF = norm_sNavie(LEADERBOARD_DF)
#
# # LEADERBOARD_DF['Average'] = LEADERBOARD_DF.mean(axis=1)
# # LEADERBOARD_DF.insert(1, 'Average', LEADERBOARD_DF.pop('Average'))
# # LEADERBOARD_DF = LEADERBOARD_DF.sort_values(by=['Average'], ascending=True)
# print(f"The leaderboard is {LEADERBOARD_DF}")
# print(f'Columns: ', LEADERBOARD_DF.columns)

# LEADERBOARD_DF = pd.read_csv('pivoted_df.csv')
domain_df = pivot_df('results/grouped_results_by_domain.csv', tab_name='domain')
print(f'Domain dataframe is {domain_df}')
freq_df = pivot_df('results/grouped_results_by_frequency.csv', tab_name='frequency')
print(f'Freq dataframe is {freq_df}')
term_length_df = pivot_df('results/grouped_results_by_term_length.csv', tab_name='term_length')
print(f'Term length dataframe is {term_length_df}')
variate_type_df = pivot_df('results/grouped_results_by_univariate.csv', tab_name='univariate')
print(f'Variate type dataframe is {variate_type_df}')

(
    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 and c.name not in ['params', 'available_on_hub', 'hub', 'Model sha','Hub License']],
            default_selection=list(dataframe.columns),
            cant_deselect=['model'],
            label="Select Datasets to Display:",
        ),

        search_columns=['model'],
        # 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=500,
        #         label="Select the number of parameters (B)",
        #     ),
        #     ColumnFilter(
        #         AutoEvalColumn.still_on_hub.name, type="boolean", label="Deleted/incomplete", default=False
        #     ),
        # ],
        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("🏅 By Domain", elem_id="llm-benchmark-tab-table", id=0):
            leaderboard = init_leaderboard(domain_df)
            print(f"FINAL Domain LEADERBOARD 1 {domain_df}")

        with gr.TabItem("🏅 By Frequency", elem_id="llm-benchmark-tab-table", id=1):
            leaderboard = init_leaderboard(freq_df)
            print(f"FINAL Frequency LEADERBOARD 1 {freq_df}")

        with gr.TabItem("🏅 By term length", elem_id="llm-benchmark-tab-table", id=2):
            leaderboard = init_leaderboard(term_length_df)
            print(f"FINAL term length LEADERBOARD 1 {term_length_df}")

        with gr.TabItem("🏅 By variate type", elem_id="llm-benchmark-tab-table", id=3):
            leaderboard = init_leaderboard(variate_type_df)
            print(f"FINAL LEADERBOARD 1 {variate_type_df}")
        with gr.TabItem("📝 About", elem_id="llm-benchmark-tab-table", id=4):
            gr.Markdown(LLM_BENCHMARKS_TEXT, elem_classes="markdown-text")

        with gr.TabItem("🚀 Submit here! ", elem_id="llm-benchmark-tab-table", id=5):
            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,
                            )

                    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 outputs !", elem_classes="markdown-text")
                gr.Markdown(
                    "Send your model outputs for all the models using the ContextualBench code and email them to us at xnguyen@salesforce.com ",
                    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,
            #         )

            #     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()