with gr.Blocks() as iface:
    gr.Markdown("""
    # Multimodal Behavioral Anomalies Detection

    This tool detects anomalies in facial expressions, body language, and voice over the timeline of a video.
    It extracts faces, postures, and voice from video frames, and analyzes them to identify anomalies using time series analysis and a variational autoencoder (VAE) approach.
    """)

    with gr.Row():
        video_input = gr.Video()

    anomaly_threshold = gr.Slider(minimum=1, maximum=5, step=0.1, value=3, label="Anomaly Detection Threshold (Standard deviation)")
    fps_slider = gr.Slider(minimum=5, maximum=20, step=1, value=10, label="Frames Per Second (FPS)")
    process_btn = gr.Button("Detect Anomalies")
    progress_bar = gr.Progress()
    execution_time = gr.Number(label="Execution Time (seconds)")

    with gr.Group(visible=False) as results_group:
        results_text = gr.TextArea(label="Anomaly Detection Results", lines=4)

        with gr.Tabs():
            with gr.TabItem("Facial Features"):
                mse_features_plot = gr.Plot(label="MSE: Facial Features")
                mse_features_hist = gr.Plot(label="MSE Distribution: Facial Features")
                mse_features_heatmap = gr.Plot(label="MSE Heatmap: Facial Features")
                anomaly_frames_features = gr.Gallery(label="Anomaly Frames (Facial Features)", columns=6, rows=2, height="auto")
                face_samples_most_frequent = gr.Gallery(label="Most Frequent Person Samples", columns=10, rows=2, height="auto")

            with gr.TabItem("Body Posture"):
                mse_posture_plot = gr.Plot(label="MSE: Body Posture")
                mse_posture_hist = gr.Plot(label="MSE Distribution: Body Posture")
                mse_posture_heatmap = gr.Plot(label="MSE Heatmap: Body Posture")
                anomaly_frames_posture = gr.Gallery(label="Anomaly Frames (Body Posture)", columns=6, rows=2, height="auto")

            with gr.TabItem("Voice"):
                mse_voice_plot = gr.Plot(label="MSE: Voice")
                mse_voice_hist = gr.Plot(label="MSE Distribution: Voice")
                mse_voice_heatmap = gr.Plot(label="MSE Heatmap: Voice")

            with gr.TabItem("Video with Heatmap"):
                heatmap_video = gr.Video(label="Video with Anomaly Heatmap")

    df_store = gr.State()
    mse_features_store = gr.State()
    mse_posture_store = gr.State()
    mse_voice_store = gr.State()
    aligned_faces_folder_store = gr.State()
    frames_folder_store = gr.State()
    mse_heatmap_embeddings_store = gr.State()
    mse_heatmap_posture_store = gr.State()
    mse_heatmap_voice_store = gr.State()

    def show_results(outputs):
        return gr.Group(visible=True)

    process_btn.click(
        process_and_show_completion,
        inputs=[video_input, anomaly_threshold, fps_slider],
        outputs=[
            execution_time, results_text, df_store,
            mse_features_store, mse_posture_store, mse_voice_store,
            mse_features_plot, mse_posture_plot, mse_voice_plot,
            mse_features_hist, mse_posture_hist, mse_voice_hist,
            mse_features_heatmap, mse_posture_heatmap, mse_voice_heatmap,
            anomaly_frames_features, anomaly_frames_posture,
            face_samples_most_frequent,
            aligned_faces_folder_store, frames_folder_store,
            mse_heatmap_embeddings_store, mse_heatmap_posture_store, mse_heatmap_voice_store,
            heatmap_video
        ]
    ).then(
        show_results,
        inputs=None,
        outputs=results_group
    )

if __name__ == "__main__":
    iface.launch()