Update app.py

app.py

@@ -1,204 +1,81 @@
 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
+import numpy as np
+from collections import defaultdict
+from gradio_leaderboard import Leaderboard, SelectColumns
 
-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
+# Load the DataFrame from the CSV file for detailed pass@k metrics
+df = pd.read_csv('results.csv')
 
+# Function to estimate pass@k
+def estimate_pass_at_k(num_samples, num_correct, k):
+    def estimator(n, c, k):
+        if n - c < k:
+            return 1.0
+        return 1.0 - np.prod(1.0 - k / np.arange(n - c + 1, n + 1))
 
-def restart_space():
-    API.restart_space(repo_id=REPO_ID)
+    return np.array([estimator(n, c, k) for n, c in zip(num_samples, num_correct)])
 
-### 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()
+# Function to calculate pass@k
+def calculate_pass_at_k(df, model, scenario, k_values=[1, 5, 10]):
+    filtered_df = df[(df['Model'] == model) & (df['Scenario'] == scenario)]
+    num_samples = filtered_df['Runs'].values
+    num_correct = filtered_df['Successes'].values
 
+    pass_at_k = {f"pass@{k}": estimate_pass_at_k(num_samples, num_correct, k).mean() for k in k_values}
+    return pass_at_k
 
-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)
+# Function to filter data and calculate pass@k
+def filter_data(model, scenario):
+    pass_at_k = calculate_pass_at_k(df, model, scenario)
+    return pd.DataFrame([pass_at_k])
 
+# Initialize the leaderboard
 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)],
+        datatype=["markdown", "number", "number", "number"],  # Specify the types of your columns
         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],
+            default_selection=["Model", "pass@1", "pass@5", "pass@10"],  # Columns to display by default
+            cant_deselect=[],  # Columns that cannot be deselected
             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
-            ),
-        ],
+        search_columns=["Model"],  # Columns that can be searched
+        hide_columns=[],  # Columns to hide
+        filter_columns=[],  # Filters for the columns
         bool_checkboxgroup_label="Hide models",
         interactive=False,
     )
 
+# Gradio interface
+models = df['Model'].unique()
+scenarios = df['Scenario'].unique()
 
-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")
+demo = gr.Blocks()
 
-                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,
-                    )
-
-                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()
+with demo:
+    gr.Markdown("# 🏆 WebApp1K Detailed Leaderboard")
+    
+    model_input = gr.Dropdown(choices=models, label="Select Model")
+    scenario_input = gr.Dropdown(choices=scenarios, label="Select Scenario")
+    output = gr.DataFrame(headers=["pass@1", "pass@5", "pass@10"])
+    
+    filter_button = gr.Button("Filter")
+    filter_button.click(filter_data, inputs=[model_input, scenario_input], outputs=output)
+    
+    output.render()
+
+    # Initialize leaderboard with the complete DataFrame
+    complete_pass_at_k = df.groupby('Model').apply(lambda x: pd.Series({
+        'pass@1': estimate_pass_at_k(x['Runs'].values, x['Successes'].values, 1).mean(),
+        'pass@5': estimate_pass_at_k(x['Runs'].values, x['Successes'].values, 5).mean(),
+        'pass@10': estimate_pass_at_k(x['Runs'].values, x['Successes'].values, 10).mean()
+    })).reset_index()
+
+    leaderboard = init_leaderboard(complete_pass_at_k)
+    leaderboard.render()
+
+# Launch the Gradio interface
+demo.launch()