refactor: reorganize data source into categorized groups with toggles

app.py

@@ -344,37 +344,127 @@ if __name__ == "__main__":
                         model_selector = gr.CheckboxGroup(label="Model Size", choices=model_size_list, value=model_size_list)
                         size_range_slider = RangeSlider(minimum=0, maximum=40, value=[0, 40], step=0.1, label="Model Size Range")
                         metric_selector = gr.Dropdown(label="Metric", choices=metric_list, value=initial_metric)
-                    with gr.Column():
                         midpoint_slider = gr.Slider(minimum=0.1, maximum=0.9, value=0.5, step=0.01, label="Color Gradient Midpoint")
                         color_selector = gr.CheckboxGroup(label="Colored Columns", choices=["Average", "Individual Tests"], value=initial_colors)
-                        colfilter = gr.CheckboxGroup(label="Data Source", choices=initial_columns, value=initial_columns)
+                    with gr.Column():
+                        # Data Source 分组定义
+                        code_cols = ["github cpp", "github python", "github javascript"]
+                        research_cols = ["arxiv physics", "arxiv cs", "arxiv math"]
+                        writing_cols = ["ao3 english", "github markdown"]
+                        knowledge_cols = ["bbc news", "wikipedia english"]
+
+                        initial_code = [c for c in code_cols if c in initial_columns]
+                        initial_research = [c for c in research_cols if c in initial_columns]
+                        initial_writing = [c for c in writing_cols if c in initial_columns]
+                        initial_knowledge = [c for c in knowledge_cols if c in initial_columns]
+
+                        gr.Markdown("**Data Source**")
+
+                        # 代码 (Code)
+                        with gr.Row():
+                            toggle_code = gr.Checkbox(label="💻 Code", value=True, scale=0, min_width=150)
+                            colfilter_code = gr.CheckboxGroup(choices=initial_code, value=initial_code, show_label=False, scale=3)
+
+                        # 科研 (Research)
+                        with gr.Row():
+                            toggle_research = gr.Checkbox(label="🔬 Research", value=True, scale=0, min_width=150)
+                            colfilter_research = gr.CheckboxGroup(choices=initial_research, value=initial_research, show_label=False, scale=3)
+
+                        # 写作 (Writing)
+                        with gr.Row():
+                            toggle_writing = gr.Checkbox(label="✍️ Writing", value=True, scale=0, min_width=150)
+                            colfilter_writing = gr.CheckboxGroup(choices=initial_writing, value=initial_writing, show_label=False, scale=3)
+
+                        # 世界知识 (World Knowledge)
+                        with gr.Row():
+                            toggle_knowledge = gr.Checkbox(label="🌍 Knowledge", value=True, scale=0, min_width=150)
+                            colfilter_knowledge = gr.CheckboxGroup(choices=initial_knowledge, value=initial_knowledge, show_label=False, scale=3)
+
+                        # 多语言 (Multilingual) - Coming Soon
+                        with gr.Row():
+                            gr.Checkbox(label="🌐 Multilingual (Coming Soon)", value=False, interactive=False, scale=0, min_width=250)
+
                 table = gr.HTML(initial_data)
 
-                def update_table_wrapper(period, models_size, metric, visible_columns, color_columns, size_range, midpoint):
+                def update_table_wrapper(
+                    period, models_size, metric, code_sel, research_sel, writing_sel, knowledge_sel, color_columns, size_range, midpoint
+                ):
+                    visible_columns = code_sel + research_sel + writing_sel + knowledge_sel
                     return update_table(data_manager, period, models_size, metric, visible_columns, color_columns, size_range, midpoint)
 
-                def update_column_choices(period, current_selected):
+                def update_column_choices(period, cur_code, cur_research, cur_writing, cur_knowledge):
                     if not period:
-                        return gr.update(choices=[], value=[])
+                        empty = gr.update(choices=[], value=[])
+                        return empty, empty, empty, empty
                     columns = data_manager.get_available_columns(period)
-                    # 只保留在新 choices 中存在的已选择值
-                    if current_selected:
-                        valid_selected = [col for col in current_selected if col in columns]
-                        # 如果过滤后为空，默认选择所有列（保持默认行为）
-                        if not valid_selected:
-                            valid_selected = columns
-                    else:
-                        # 如果没有当前选择，默认选择所有列（保持默认行为）
-                        valid_selected = columns
-                    return gr.update(choices=columns, value=valid_selected)
 
-                shared_inputs = [period_selector, model_selector, metric_selector, colfilter, color_selector, size_range_slider, midpoint_slider]
+                    new_code = [c for c in code_cols if c in columns]
+                    new_research = [c for c in research_cols if c in columns]
+                    new_writing = [c for c in writing_cols if c in columns]
+                    new_knowledge = [c for c in knowledge_cols if c in columns]
+
+                    sel_code = [c for c in cur_code if c in new_code] if cur_code else new_code
+                    sel_research = [c for c in cur_research if c in new_research] if cur_research else new_research
+                    sel_writing = [c for c in cur_writing if c in new_writing] if cur_writing else new_writing
+                    sel_knowledge = [c for c in cur_knowledge if c in new_knowledge] if cur_knowledge else new_knowledge
+
+                    if not sel_code:
+                        sel_code = new_code
+                    if not sel_research:
+                        sel_research = new_research
+                    if not sel_writing:
+                        sel_writing = new_writing
+                    if not sel_knowledge:
+                        sel_knowledge = new_knowledge
+
+                    return (
+                        gr.update(choices=new_code, value=sel_code),
+                        gr.update(choices=new_research, value=sel_research),
+                        gr.update(choices=new_writing, value=sel_writing),
+                        gr.update(choices=new_knowledge, value=sel_knowledge),
+                    )
+
+                # 总开关功能
+                def toggle_group(enabled, group_cols, available_cols):
+                    valid_cols = [c for c in group_cols if c in available_cols]
+                    return valid_cols if enabled else []
+
+                toggle_code.change(lambda enabled: toggle_group(enabled, code_cols, initial_columns), inputs=[toggle_code], outputs=[colfilter_code])
+                toggle_research.change(
+                    lambda enabled: toggle_group(enabled, research_cols, initial_columns), inputs=[toggle_research], outputs=[colfilter_research]
+                )
+                toggle_writing.change(
+                    lambda enabled: toggle_group(enabled, writing_cols, initial_columns), inputs=[toggle_writing], outputs=[colfilter_writing]
+                )
+                toggle_knowledge.change(
+                    lambda enabled: toggle_group(enabled, knowledge_cols, initial_columns), inputs=[toggle_knowledge], outputs=[colfilter_knowledge]
+                )
 
-                period_selector.change(update_column_choices, inputs=[period_selector, colfilter], outputs=colfilter)
+                shared_inputs = [
+                    period_selector,
+                    model_selector,
+                    metric_selector,
+                    colfilter_code,
+                    colfilter_research,
+                    colfilter_writing,
+                    colfilter_knowledge,
+                    color_selector,
+                    size_range_slider,
+                    midpoint_slider,
+                ]
+
+                period_selector.change(
+                    update_column_choices,
+                    inputs=[period_selector, colfilter_code, colfilter_research, colfilter_writing, colfilter_knowledge],
+                    outputs=[colfilter_code, colfilter_research, colfilter_writing, colfilter_knowledge],
+                )
                 period_selector.change(update_table_wrapper, inputs=shared_inputs, outputs=table)
                 model_selector.change(update_table_wrapper, inputs=shared_inputs, outputs=table)
                 metric_selector.change(update_table_wrapper, inputs=shared_inputs, outputs=table)
-                colfilter.change(update_table_wrapper, inputs=shared_inputs, outputs=table)
+                colfilter_code.change(update_table_wrapper, inputs=shared_inputs, outputs=table)
+                colfilter_research.change(update_table_wrapper, inputs=shared_inputs, outputs=table)
+                colfilter_writing.change(update_table_wrapper, inputs=shared_inputs, outputs=table)
+                colfilter_knowledge.change(update_table_wrapper, inputs=shared_inputs, outputs=table)
                 color_selector.change(update_table_wrapper, inputs=shared_inputs, outputs=table)
                 size_range_slider.change(update_table_wrapper, inputs=shared_inputs, outputs=table)
                 midpoint_slider.change(update_table_wrapper, inputs=shared_inputs, outputs=table)

data_manager.py

@@ -242,16 +242,20 @@ class DataManager:
 
         fixed_cols = ["Name", "Params (B)", "Average (lower=better)"]
         column_priority = [
-            "ao3 english",
-            "bbc news",
-            "wikipedia english",
-            "github markdown",
-            "arxiv physics",
-            "arxiv cs",
-            "arxiv math",
+            # 代码 (Code)
             "github cpp",
             "github python",
             "github javascript",
+            # 科研 (Research)
+            "arxiv physics",
+            "arxiv cs",
+            "arxiv math",
+            # 写作 (Writing)
+            "ao3 english",
+            "github markdown",
+            # 世界知识 (World Knowledge)
+            "bbc news",
+            "wikipedia english",
         ]
         existing_cols = filtered_df.columns.tolist()
         ordered_cols = []