[Add, Ref] matplotlib test, random test value for sim

app.py

@@ -1,7 +1,38 @@
 import gradio as gr
+import matplotlib.pyplot as plt
+import numpy as np
+from io import BytesIO
+from PIL import Image
+
 from src.dataloading import get_leaderboard_models_cached, get_leaderboard_datasets
 from src.similarity import compute_similarity
 
+# Set the backend to 'Agg' for non-GUI environments (optional)
+import matplotlib
+matplotlib.use('Agg')
+
+
+def generate_plot():
+    # Generate data
+    x = np.linspace(0, 10, 100)
+    y = np.sin(x)
+    
+    # Create figure
+    fig, ax = plt.subplots()
+    ax.plot(x, y)
+    ax.set_title("Sine Wave")
+    
+    # Save figure to a BytesIO buffer
+    buf = BytesIO()
+    fig.savefig(buf, format="png", bbox_inches="tight", facecolor="white", dpi=100)
+    plt.close(fig)  # Close the figure to free memory
+    
+    # Convert buffer to PIL Image
+    buf.seek(0)
+    img = Image.open(buf).convert("RGB")
+    return img
+
+
 def validate_inputs(selected_model_a, selected_model_b, selected_dataset):
     if not selected_model_a:
         raise gr.Error("Please select Model A!")
@@ -66,5 +97,10 @@ with gr.Blocks(title="LLM Similarity Analyzer") as demo:
         outputs=[model_a_dropdown, model_b_dropdown, dataset_dropdown, similarity_output]
     )
 
+    gr.Markdown("## Matplotlib Plot in Gradio")
+    plot_button = gr.Button("Generate Plot")
+    plot_output = gr.Image(label="Sine Wave Plot")
+    plot_button.click(fn=generate_plot, outputs=plot_output)
+
 if __name__ == "__main__":
     demo.launch()

src/similarity.py

@@ -1,8 +1,10 @@
 from src.dataloading import load_run_data
 from lmsim.metrics import Kappa_p
+import random
 
 
 def compute_similarity(selected_model_a, selected_model_b, selected_dataset):
+    """
     probs_a, gt_a = load_run_data(selected_model_a, selected_dataset)
     probs_b, gt_b = load_run_data(selected_model_b, selected_dataset)
 
@@ -21,5 +23,8 @@ def compute_similarity(selected_model_a, selected_model_b, selected_dataset):
     # Placeholder similarity value
     kappa_p = Kappa_p()
     similarity = kappa_p.compute_k(output_a, output_b, gt)
+    """
+    
+    similarity = random.random()
     
     return similarity