import gradio as gr
import os
from PIL import Image

# Paths to the images folder
RAW_PATH = os.path.join("images", "raw")
EMBEDDINGS_PATH = os.path.join("images", "embeddings")

# Specific values for percentage and complexity
percentage_values = [10, 30, 50, 70, 100]
complexity_values = [16, 32]

# Function to load and display images based on user selection
def display_images(percentage_idx, complexity_idx):
    # Map the slider index to the actual value
    percentage = percentage_values[percentage_idx]
    complexity = complexity_values[complexity_idx]
    
    # Generate the paths to the images
    raw_image_path = os.path.join(RAW_PATH, f"percentage_{percentage}_complexity_{complexity}.png")
    embeddings_image_path = os.path.join(EMBEDDINGS_PATH, f"percentage_{percentage}_complexity_{complexity}.png")
    
    # Load images using PIL
    raw_image = Image.open(raw_image_path)
    embeddings_image = Image.open(embeddings_image_path)
    
    # Return the loaded images
    return raw_image, embeddings_image

# Define the beam prediction function
def beam_prediction(input_data):
    # Add your beam prediction logic here
    return {"Prediction": "Beam X", "Confidence": "95%"}

# Define the LoS/NLoS classification function
def los_nlos_classification(input_data):
    # Add your LoS/NLoS classification logic here
    return {"Classification": "LoS", "Confidence": "98%"}

# Define the Gradio interface
with gr.Blocks(css="""
    .vertical-slider input[type=range] {
        writing-mode: bt-lr; /* IE */
        -webkit-appearance: slider-vertical; /* WebKit */
        width: 8px;
        height: 200px;
    }
    .slider-container {
        display: inline-block;
        margin-right: 50px;
        text-align: center;
    }
""") as demo:
    
    gr.Markdown("# Wireless Model Tasks")
    
    # Tabs for Beam Prediction and LoS/NLoS Classification
    with gr.Tab("Beam Prediction Task"):
        gr.Markdown("### Beam Prediction Task")
        beam_input = gr.Textbox(label="Enter Input Data for Beam Prediction", placeholder="Enter data here...")
        beam_button = gr.Button("Predict Beam")
        beam_output = gr.JSON(label="Beam Prediction Result")
        beam_button.click(beam_prediction, inputs=beam_input, outputs=beam_output)
    
    with gr.Tab("LoS/NLoS Classification Task"):
        gr.Markdown("### LoS/NLoS Classification Task")
        los_input = gr.Textbox(label="Enter Input Data for LoS/NLoS Classification", placeholder="Enter data here...")
        los_button = gr.Button("Classify")
        los_output = gr.JSON(label="LoS/NLoS Classification Result")
        los_button.click(los_nlos_classification, inputs=los_input, outputs=los_output)
    
    with gr.Tab("Raw vs. Embeddings Inference Results"):
        gr.Markdown("Use the sliders to adjust the percentage of data for training and task complexity.")

        # Layout for vertical side-by-side sliders (using CSS to rotate sliders)
        with gr.Row():
            # Column for percentage slider
            with gr.Column(elem_id="slider-container"):
                gr.Markdown("Percentage of Data for Training")
                percentage_slider = gr.Slider(minimum=0, maximum=4, step=1, value=0, interactive=True, elem_id="vertical-slider")

            # Column for complexity slider
            with gr.Column(elem_id="slider-container"):
                gr.Markdown("Task Complexity")
                complexity_slider = gr.Slider(minimum=0, maximum=1, step=1, value=0, interactive=True, elem_id="vertical-slider")

        # Outputs (display the images side by side and set a smaller size for the images)
        with gr.Row():
            raw_img = gr.Image(label="Raw Channels", type="pil", width=300, height=300, interactive=False)  # Smaller image size
            embeddings_img = gr.Image(label="Embeddings", type="pil", width=300, height=300, interactive=False)  # Smaller image size

        # Trigger image updates when sliders change
        percentage_slider.change(fn=display_images, inputs=[percentage_slider, complexity_slider], outputs=[raw_img, embeddings_img])
        complexity_slider.change(fn=display_images, inputs=[percentage_slider, complexity_slider], outputs=[raw_img, embeddings_img])

# Launch the app
if __name__ == "__main__":
    demo.launch()