import numpy as np
import pandas as pd
import pickle
import datasets
from datasets import Dataset, DatasetDict
from six import BytesIO
import gradio as gr
from huggingface_hub import snapshot_download
import os 
from matplotlib import pyplot as plt
import seaborn as sns
import torch
from neuralforecast import NeuralForecast
from neuralforecast.models import NBEATS

#PATH_TO_LABELS = 'label_map.pbtxt'   
#category_index = label_map_util.create_category_index_from_labelmap(PATH_TO_LABELS, use_display_name=True)


    
#def load_image_into_numpy_array(path):
                                    
#    image = None
#    image_data = tf.io.gfile.GFile(path, 'rb').read()
#    image = Image.open(BytesIO(image_data))
#    return pil_image_as_numpy_array(image)            

def load_model():
    download_dir = snapshot_download(REPO_ID)
    saved_model_dir = os.path.join(download_dir, "saved_model")
    futr_df = Dataset.from_pandas(futr_df)
    prediction_model = NeuralForecast.load(saved_model_dir)

    return prediction_model



# samples_folder = 'test_samples
# image_path = 'test_samples/sample_balloon.jpeg
# 

#def predict(pilimg):

 #   image_np = pil_image_as_numpy_array(pilimg)
  #  return predict2(image_np)

#def predict2(image_np):

#    results = detection_model(image_np)

    # different object detection models have additional results
#    result = {key:value.numpy() for key,value in results.items()}
    
 #   label_id_offset = 0
  #  image_np_with_detections = image_np.copy()

   # viz_utils.visualize_boxes_and_labels_on_image_array(
#        image_np_with_detections[0],
#        result['detection_boxes'][0],
#        (result['detection_classes'][0] + label_id_offset).astype(int),
#        result['detection_scores'][0],
#        category_index,
#        use_normalized_coordinates=True,
#        max_boxes_to_draw=200,
#        min_score_thresh=.60,
#        agnostic_mode=False,
#        line_thickness=2)

   # result_pil_img = tf.keras.utils.array_to_img(image_np_with_detections[0])
    
   # return result_pil_img


REPO_ID = "magcheong/ITI110_Energy_Prediction"
prediction_model = load_model()



title = "testing"
description = "This is an app to detect burger and fries."
css_code = ".gradio-container {background: rgb(250, 250, 210)}"

# css_code='body{background-size: 25% 25%; background-repeat: no-repeat; background-image:url("https://static.vecteezy.com/system/resources/previews/022/787/250/original/illustration-of-french-fries-transparent-background-generative-ai-png.png");}'

gr.Interface(fn=predict,
             title = title,
             description = description,
             css=css_code,
             #inputs=gr.Image(type="pil", height=309),
             #outputs=gr.Image(type="pil", height=350)
             ).launch(share=True)