Update app.py

app.py

@@ -3,23 +3,45 @@ __all__ = ['block', 'make_clickable_model', 'make_clickable_user', 'get_submissi
 import gradio as gr
 import pandas as pd
 import re
-import pandas as pd
 import os
 import json
 import yaml
+import matplotlib.pyplot as plt
 
 from src.about import *
 from src.bin.PROBE import run_probe
 
 global data_component, filter_component
 
-
 def get_baseline_df():
     df = pd.read_csv(CSV_RESULT_PATH)
     present_columns = ["Method"] + checkbox_group.value
     df = df[present_columns]
     return df
 
+# Function to create the plot
+def create_plot(methods_selected, x_metric, y_metric):
+    df = pd.read_csv(CSV_RESULT_PATH)
+    filtered_df = df[df['Method'].isin(methods_selected)]
+    
+    # Create the plot
+    plt.figure(figsize=(8, 6))
+    for method in methods_selected:
+        method_data = filtered_df[filtered_df['Method'] == method]
+        plt.plot(method_data[x_metric], method_data[y_metric], label=method, marker='o')
+    
+    plt.xlabel(x_metric)
+    plt.ylabel(y_metric)
+    plt.title(f'{y_metric} vs {x_metric} for selected methods')
+    plt.legend()
+    plt.grid(True)
+    
+    # Save the plot to display it in Gradio
+    plot_path = "plot.png"
+    plt.savefig(plot_path)
+    plt.close()
+    
+    return plot_path
 
 def add_new_eval(
     human_file,
@@ -33,31 +55,43 @@ def add_new_eval(
     family_prediction_dataset,
 ):
     representation_name = model_name_textbox if revision_name_textbox == '' else revision_name_textbox
-
     results = run_probe(benchmark_type, representation_name, human_file, skempi_file, similarity_tasks, function_prediction_aspect, function_prediction_dataset, family_prediction_dataset)
-
     return None
 
 block = gr.Blocks()
 
 with block:
-    gr.Markdown(
-        LEADERBOARD_INTRODUCTION
-    )
+    gr.Markdown(LEADERBOARD_INTRODUCTION)
+    
     with gr.Tabs(elem_classes="tab-buttons") as tabs:
         # table jmmmu bench
         with gr.TabItem("🏅 PROBE Benchmark", elem_id="probe-benchmark-tab-table", id=1):
-            # selection for column part:
+            
+            # Add the visualizer components (Dropdown, Checkbox, Button, Image)
+            with gr.Row():
+                method_names = pd.read_csv(CSV_RESULT_PATH)['Method'].unique().tolist()
+                metric_names = pd.read_csv(CSV_RESULT_PATH).columns.tolist()
+                metric_names.remove('Method')  # Remove Method from the metric options
+                
+                method_selector = gr.CheckboxGroup(choices=method_names, label="Select Methods", interactive=True)
+                x_metric_selector = gr.Dropdown(choices=metric_names, label="Select X-axis Metric", interactive=True)
+                y_metric_selector = gr.Dropdown(choices=metric_names, label="Select Y-axis Metric", interactive=True)
+                plot_button = gr.Button("Plot")
+                output_plot = gr.Image(label="Plot")
+                
+                plot_button.click(create_plot, inputs=[method_selector, x_metric_selector, y_metric_selector], outputs=output_plot)
+            
+            # Now the rest of the UI elements as they were before
             checkbox_group = gr.CheckboxGroup(
                 choices=TASK_INFO,
                 label="Benchmark Type",
                 interactive=True,
-            ) # user can select the evaluation dimension
-
+            )  # User can select the evaluation dimension
+            
             baseline_value = get_baseline_df()
             baseline_header = ["Method"] + checkbox_group.value
             baseline_datatype = ['markdown'] + ['number'] * len(checkbox_group.value)
-
+            
             data_component = gr.components.Dataframe(
                 value=baseline_value,
                 headers=baseline_header,
@@ -65,7 +99,7 @@ with block:
                 datatype=baseline_datatype,
                 interactive=False,
                 visible=True,
-                )
+            )
 
         # table 5
         with gr.TabItem("📝 About", elem_id="probe-benchmark-tab-table", id=2):
@@ -83,11 +117,11 @@ with block:
                 with gr.Column():
                     model_name_textbox = gr.Textbox(
                         label="Model name",
-                        )
+                    )
                     revision_name_textbox = gr.Textbox(
                         label="Revision Model Name",
                     )
-                    # Selection for benchmark type from (similartiy, family, function, affinity) to eval the representations (chekbox)
+                    
                     benchmark_type = gr.CheckboxGroup(
                         choices=TASK_INFO,
                         label="Benchmark Type",
@@ -99,21 +133,18 @@ with block:
                         interactive=True,
                     )
                 
-                    # Dropdown for function prediction aspect
                     function_prediction_aspect = gr.Radio(
                         choices=function_prediction_aspect_options,
                         label="Select Function Prediction Aspect",
                         interactive=True,
                     )
                 
-                    # Dropdown for function prediction dataset
                     function_prediction_dataset = gr.Radio(
                         choices=function_prediction_dataset_options,
                         label="Select Function Prediction Dataset",
                         interactive=True,
                     )
                 
-                    # Checkbox for family prediction dataset
                     family_prediction_dataset = gr.CheckboxGroup(
                         choices=family_prediction_dataset_options,
                         label="Select Family Prediction Dataset",
@@ -128,7 +159,7 @@ with block:
                 submission_result = gr.Markdown()
                 submit_button.click(
                     add_new_eval,
-                    inputs = [
+                    inputs=[
                         human_file,
                         skempi_file,
                         model_name_textbox,
@@ -143,14 +174,11 @@ with block:
 
     def refresh_data():
         value = get_baseline_df()
-
         return value
 
     with gr.Row():
         data_run = gr.Button("Refresh")
-        data_run.click(
-            refresh_data, outputs=[data_component]
-        )
+        data_run.click(refresh_data, outputs=[data_component])
 
     with gr.Accordion("Citation", open=False):
         citation_button = gr.Textbox(