Add task selector

app.py

@@ -33,6 +33,16 @@ DEFAULT_HTML_TABLE = """
 </table>
 """
 
+TASKS = {
+    "leaderboard_arc_challenge": ("ARC", "leaderboard_arc_challenge"),
+    "leaderboard_bbh": ("BBH", "leaderboard_bbh"),
+    "leaderboard_gpqa": ("GPQA", "leaderboard_gpqa"),
+    "leaderboard_ifeval": ("IFEval", "leaderboard_ifeval"),
+    "leaderboard_math_hard": ("MATH", "leaderboard_math"),
+    "leaderboard_mmlu": ("MMLU", "leaderboard_mmlu"),
+    "leaderboard_mmlu_pro": ("MMLU-Pro", "leaderboard_mmlu_pro"),
+    "leaderboard_musr": ("MuSR", "leaderboard_musr"),
+}
 
 fs = HfFileSystem()
 
@@ -113,6 +123,11 @@ def concat_result_1(result_1, results):
         pd.concat([result_1, results.iloc[:, [0, 2]].set_index("Parameters")], axis=1)
         .reset_index()
     )
+    return df
+
+
+def display_dataframe(df):
+    # style = Styler(df, uuid_len=0, cell_ids=False)
     return (
         df.style
         .format(na_rep="")
@@ -127,22 +142,28 @@ def concat_result_2(result_2, results):
         pd.concat([results.iloc[:, [0, 1]].set_index("Parameters"), result_2], axis=1)
         .reset_index()
     )
-    return (
-        df.style
-        .format(na_rep="")
-        .hide(axis="index")
-        .to_html()
-    )
+    return df
 
 
-def render_result_1(model_id, *results):
+def render_result_1(model_id, task, *results):
     result = load_result(model_id)
-    return [concat_result_1(*result_args) for result_args in zip(result, results)]
+    concat_results = [concat_result_1(*result_args) for result_args in zip(result, results)]
+    if task:
+        concat_results = [df[df["Parameters"].str.startswith(task[len("leaderboard_"):])] for df in concat_results]
+    return [display_dataframe(df) for df in concat_results]
 
 
-def render_result_2(model_id, *results):
+def render_result_2(model_id, task, *results):
     result = load_result(model_id)
-    return [concat_result_2(*result_args) for result_args in zip(result, results)]
+    concat_results = [concat_result_2(*result_args) for result_args in zip(result, results)]
+    if task:
+        concat_results = [df[df["Parameters"].str.startswith(task[len("leaderboard_"):])] for df in concat_results]
+    return [display_dataframe(df) for df in concat_results]
+
+
+def render_results(model_id_1, model_id_2, task, *results):
+    results = render_result_1(model_id_1, task, *results)
+    return render_result_2(model_id_2, task, *results)
 
 
 # if __name__ == "__main__":
@@ -159,6 +180,13 @@ with gr.Blocks(fill_height=True) as demo:
         with gr.Column():
             model_id_2 = gr.Dropdown(choices=list(latest_result_path_per_model.keys()), label="Results")
             load_btn_2 = gr.Button("Load")
+    with gr.Row():
+        task = gr.Radio(
+            ["All"] + list(TASKS.values()),
+            label="Tasks",
+            info="Evaluation tasks to be displayed",
+            value="All",
+        )
 
     results = []
     with gr.Row():
@@ -192,12 +220,17 @@ with gr.Blocks(fill_height=True) as demo:
 
     load_btn_1.click(
         fn=render_result_1,
-        inputs=[model_id_1, *results],
+        inputs=[model_id_1, task, *results],
         outputs=[*results],
     )
     load_btn_2.click(
         fn=render_result_2,
-        inputs=[model_id_2, *results],
+        inputs=[model_id_2, task, *results],
+        outputs=[*results],
+    )
+    task.change(
+        fn=render_results,
+        inputs=[model_id_1, model_id_2, task, *results],
         outputs=[*results],
     )