import gradio as gr
import pandas as pd
import umap
import matplotlib.pyplot as plt
import os
import tempfile
import scanpy as sc
import argparse
import subprocess
import sys
from io import BytesIO
from huggingface_hub import hf_hub_download


def main(input_file_path, species):

    # Get the current working directory
    current_working_directory = os.getcwd()
    
    # Print the current working directory
    print("Current Working Directory:", current_working_directory)

    # clone and cd into UCE repo
    os.system('git clone https://github.com/minwoosun/UCE.git')
    os.chdir('/home/user/app/UCE')

    # Get the current working directory
    current_working_directory = os.getcwd()
    
    # Print the current working directory
    print("Current Working Directory:", current_working_directory)

    # Specify the path to the directory you want to add
    new_directory = "/home/user/app/UCE"
    
    # Add the directory to the Python path
    sys.path.append(new_directory)


    ##############
    #     UCE    #
    ##############
    from evaluate import AnndataProcessor
    from accelerate import Accelerator

    #  python eval_single_anndata.py --adata_path "./data/10k_pbmcs_proc.h5ad" --dir "./" --model_loc "minwoosun/uce-100m"
    script_name = "/home/user/app/eval_single_anndata.py"
    args = ["--adata_path", input_file_path, "--dir", "/home/user/app/UCE/", "--model_loc", "minwoosun/uce-100m"]
    command = ["python", script_name] + args
    
    try:
        result = subprocess.run(command, capture_output=True, text=True, check=True)
        print(result.stdout)
        print(result.stderr)
    except subprocess.CalledProcessError as e:
        print(f"Error executing command: {e}")


    ##############
    #    UMAP    #
    ##############
    UMAP = True

    if (UMAP):
        adata = sc.read_h5ad('/home/user/app/UCE/10k_pbmcs_proc_uce_adata.h5ad')

        labels = pd.Categorical(adata.obs["cell_type"])

        reducer = umap.UMAP(n_neighbors=15, min_dist=0.1, n_components=2, random_state=42)
        embedding = reducer.fit_transform(adata.obsm["X_uce"])

        plt.figure(figsize=(10, 8))

        # Create the scatter plot
        scatter = plt.scatter(embedding[:, 0], embedding[:, 1], c=labels.codes, cmap='Set1', s=50, alpha=0.6)

        # Create a legend
        handles = []
        for i, cell_type in enumerate(labels.categories):
            handles.append(plt.Line2D([0], [0], marker='o', color='w', label=cell_type,
                                      markerfacecolor=plt.cm.Set1(i / len(labels.categories)), markersize=10))

        plt.legend(handles=handles, title='Cell Type')
        plt.title('UMAP projection of the data')
        plt.xlabel('UMAP1')
        plt.ylabel('UMAP2')
        
        # Save plot to a BytesIO object
        buf = BytesIO()
        plt.savefig(buf, format='png')
        buf.seek(0)
        
        # Read the image from BytesIO object
        img = plt.imread(buf, format='png')
    else:
        img = None
        print("no image")

    # this need to be changed based on data file name
    output_file = '/home/user/app/UCE/10k_pbmcs_proc_uce_adata.h5ad'
    
    return img, output_file

    
if __name__ == "__main__":   

    # Define Gradio inputs and outputs
    file_input = gr.File(label="Upload a .h5ad single cell gene expression file")
    species_input = gr.Dropdown(choices=["human", "mouse"], label="Select species")
    image_output = gr.Image(type="numpy", label="UMAP of UCE Embeddings")
    file_output = gr.File(label="Download embeddings")

    # Create the Gradio interface
    demo = gr.Interface(
        fn=main,
        inputs=[file_input, species_input],
        outputs=[image_output, file_output],
        title="UCE 100M Demo",
        description="Upload a .h5ad single cell gene expression file, and get a UMAP scatter plot along with the UMAP coordinates in a CSV file."
    )

    demo.launch()