Optimize data loading and filter in display

app.py

@@ -12,26 +12,13 @@ EXCLUDED_KEYS =  {
     "chat_template",
     "group_subtasks",
 }
-EXCLUDED_RESULTS_KEYS = {
-    "leaderboard",
-}
-EXCLUDED_RESULTS_LEADERBOARDS_KEYS = {
-    "alias",
-}
+# EXCLUDED_RESULTS_KEYS = {
+#     "leaderboard",
+# }
+# EXCLUDED_RESULTS_LEADERBOARDS_KEYS = {
+#     "alias",
+# }
 
-DEFAULT_HTML_TABLE = """
-<table>
-  <thead>
-    <tr>
-      <th>Parameters</th>
-      <th>Model-1</th>
-      <th>Model-2</th>
-    </tr>
-  </thead>
-  <tbody>
-  </tbody>
-</table>
-"""
 
 TASKS = {
     "leaderboard_arc_challenge": ("ARC", "leaderboard_arc_challenge"),
@@ -71,98 +58,64 @@ def load_data(result_path) -> pd.DataFrame:
     return data
 
 
-def load_result(model_id):
+def load_result_dataframe(model_id):
     result_path = get_result_path_from_model(model_id, latest_result_path_per_model)
     data = load_data(result_path)
-    df = to_dataframe(data)
-    result = [
-        # to_vertical(df),
-        to_vertical(filter_results(df)),
-        to_vertical(filter_configs(df)),
-    ]
-    return result
-
-
-def to_vertical(df):
-    df = df.T.rename_axis("Parameters")
-    df.index = df.index.str.join(".")
-    return df
-
-
-def to_dataframe(data):
+    model_name = data.get("model_name", "Model")
     df = pd.json_normalize([{key: value for key, value in data.items() if key not in EXCLUDED_KEYS}])
     # df.columns = df.columns.str.split(".")  # .split return a list instead of a tuple
-    df.columns = list(map(lambda x: tuple(x.split(".")), df.columns))
-    df.index = [data.get("model_name", "Model")]
-    return df
-
-
-def filter_results(df):
-    df = df.loc[:, df.columns.str[0] == "results"]
-    df = df.loc[:, ~df.columns.str[1].isin(EXCLUDED_RESULTS_KEYS)]
-    # df.columns.str[1].str = df.columns.str[1].str.removeprefix("leaderboard_")
-    df = df.loc[:, ~df.columns.str[2].isin(EXCLUDED_RESULTS_LEADERBOARDS_KEYS)]
-    df.columns = df.columns.str[1:]
-    df.columns = map(lambda x: (x[0].removeprefix("leaderboard_"), *x[1:]), df.columns)
-    return df
-
-
-def filter_configs(df):
-    df = df.loc[:, df.columns.str[0] == "configs"]
-    # df = df.loc[:, ~df.columns.str[1].isin(EXCLUDED_RESULTS_KEYS)]
-    # df = df.loc[:, ~df.columns.str[2].isin(EXCLUDED_RESULTS_LEADERBOARDS_KEYS)]
-    df.columns = df.columns.str[1:]
-    df.columns = map(lambda x: (x[0].removeprefix("leaderboard_"), *x[1:]), df.columns)
-    return df
-
-
-def concat_result_1(result_1, results):
-    results = pd.read_html(io.StringIO(results))[0]
-    df = (
-        pd.concat([result_1, results.iloc[:, [0, 2]].set_index("Parameters")], axis=1)
-        .reset_index()
+    return df.set_index(pd.Index([model_name])).reset_index()
+
+
+def display_results(df_1, df_2, task):
+    df = pd.concat([df.set_index("index") for df in [df_1, df_2] if "index" in df.columns])
+    df = df.T.rename_axis(columns=None)  # index="Parameters",  # .reset_index()
+    # return display_dataframe(df)
+    # d = df.set_index(df.index.str.split("."))  # .split return a list instead of a tuple
+    # results = d.loc[d.index.str[0] == "results"]
+    # results.index = results.index.str.join(".")
+    # configs = d.loc[d.index.str[0] == "configs"]
+    # configs.index = configs.index.str.join(".")
+    # return display_dataframe(results), display_dataframe(configs)
+    return display_results_tab(df, task), display_configs_tab(df, task)
+
+
+def display_results_tab(df, task):
+    df = df.style.format(na_rep="")
+    df.hide(
+        [
+            row
+            for row in df.index
+            if (
+                not row.startswith("results.")
+                or row.startswith("results.leaderboard.")
+                or row.endswith(".alias")
+                or (not row.startswith(f"results.{task}") if task != "All" else False)
+            )
+        ],
+        axis="index",
     )
-    return df
-
-
-def display_dataframe(df):
-    # style = Styler(df, uuid_len=0, cell_ids=False)
-    return (
-        df.style
-        .format(na_rep="")
-        .hide(axis="index")
-        .to_html()
+    df.format_index(lambda idx: idx[len("results.leaderboard_"):].removesuffix(",none"), axis="index")
+    return df.to_html()
+
+
+def display_configs_tab(df, task):
+    df = df.style.format(na_rep="")
+    df.hide(
+        [
+            row
+            for row in df.index
+            if (
+                not row.startswith("configs.")
+                or row.startswith("configs.leaderboard.")
+                or row.endswith(".alias")
+                or (not row.startswith(f"configs.{task}") if task != "All" else False)
+            )
+        ],
+        axis="index",
     )
-
-
-def concat_result_2(result_2, results):
-    results = pd.read_html(io.StringIO(results))[0]
-    df = (
-        pd.concat([results.iloc[:, [0, 1]].set_index("Parameters"), result_2], axis=1)
-        .reset_index()
-    )
-    return df
-
-
-def render_result_1(model_id, task, *results):
-    result = load_result(model_id)
-    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, task, *results):
-    result = load_result(model_id)
-    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)
+    df.format_index(lambda idx: idx[len("configs.leaderboard_"):], axis="index")
+    return df.to_html()
 
 
 # if __name__ == "__main__":
@@ -176,9 +129,11 @@ with gr.Blocks(fill_height=True) as demo:
         with gr.Column():
             model_id_1 = gr.Dropdown(choices=list(latest_result_path_per_model.keys()), label="Results")
             load_btn_1 = gr.Button("Load")
+            dataframe_1 = gr.Dataframe(visible=False)
         with gr.Column():
             model_id_2 = gr.Dropdown(choices=list(latest_result_path_per_model.keys()), label="Results")
             load_btn_2 = gr.Button("Load")
+            dataframe_2 = gr.Dataframe(visible=False)
     with gr.Row():
         task = gr.Radio(
             ["All"] + list(TASKS.values()),
@@ -187,50 +142,36 @@ with gr.Blocks(fill_height=True) as demo:
             value="All",
         )
 
-    results = []
     with gr.Row():
         # with gr.Tab("All"):
-        #     # results.append(gr.Dataframe(
-        #     #     label="Results",
-        #     #     headers=["Parameters", "Model-1", "Model-2"],
-        #     #     interactive=False,
-        #     #     column_widths=["30%", "30%", "30%"],
-        #     #     wrap=True,
-        #     # ))
-        #     results.append(gr.HTML(value=DEFAULT_HTML_TABLE))
+        #     pass
         with gr.Tab("Results"):
-            # results.append(gr.Dataframe(
-            #     label="Results",
-            #     headers=["Parameters", "Model-1", "Model-2"],
-            #     interactive=False,
-            #     column_widths=["30%", "30%", "30%"],
-            #     wrap=True,
-            # ))
-            results.append(gr.HTML(value=DEFAULT_HTML_TABLE))
+            results = gr.HTML()
         with gr.Tab("Configs"):
-            # results.append(gr.Dataframe(
-            #     label="Results",
-            #     headers=["Parameters", "Model-1", "Model-2"],
-            #     interactive=False,
-            #     column_widths=["30%", "30%", "30%"],
-            #     wrap=True,
-            # ))
-            results.append(gr.HTML(value=DEFAULT_HTML_TABLE))
+            configs = gr.HTML()
 
     load_btn_1.click(
-        fn=render_result_1,
-        inputs=[model_id_1, task, *results],
-        outputs=[*results],
+        fn=load_result_dataframe,
+        inputs=model_id_1,
+        outputs=dataframe_1,
+    ).then(
+        fn=display_results,
+        inputs=[dataframe_1, dataframe_2, task],
+        outputs=[results, configs],
     )
     load_btn_2.click(
-        fn=render_result_2,
-        inputs=[model_id_2, task, *results],
-        outputs=[*results],
+        fn=load_result_dataframe,
+        inputs=model_id_2,
+        outputs=dataframe_2,
+    ).then(
+        fn=display_results,
+        inputs=[dataframe_1, dataframe_2, task],
+        outputs=[results, configs],
     )
     task.change(
-        fn=render_results,
-        inputs=[model_id_1, model_id_2, task, *results],
-        outputs=[*results],
+        fn=display_results,
+        inputs=[dataframe_1, dataframe_2, task],
+        outputs=[results, configs],
     )
 
 demo.launch()

requirements.txt

@@ -1,2 +0,0 @@
-lxml
-