# import sklearn
from os import O_ACCMODE
import gradio as gr
import joblib
from transformers import pipeline
import requests.exceptions
from huggingface_hub import HfApi, hf_hub_download
from huggingface_hub.repocard import metadata_load


app = gr.Blocks()

model_id_1 = "nlptown/bert-base-multilingual-uncased-sentiment"
model_id_2 = "microsoft/deberta-base"
model_id_3 = "distilbert-base-uncased-finetuned-sst-2-english"
model_id_4 = "lordtt13/emo-mobilebert"
model_id_5 = "juliensimon/reviews-sentiment-analysis"


def get_prediction(model_id):

    classifier = pipeline("text-classification", model=model_id, return_all_scores=True)
             
    def predict(review):
            prediction = classifier(review)
            print(prediction)
            return prediction
    return predict


with app:
    gr.Markdown(
    """
    # Compare Sentiment Analysis Models 
    
    Type text to predict sentiment.
    """)   
    with gr.Row():
        inp_1= gr.Textbox(label="Type text here.",placeholder="The customer service was satisfactory.")

    gr.Markdown(
    """
    **Model Predictions**
    """)
    with gr.Row():
        with gr.Column():
            text1 = gr.Textbox(label="Model 1 = nlptown/bert-base-multilingual-uncased-sentiment")
            btn1 = gr.Button("Predict - Model 1")
            text2 = gr.Textbox(label="Model 2 = microsoft/deberta-base")
            btn2 = gr.Button("Predict - Model 2")
        with gr.Column():
            out_1 = gr.Textbox(label="Predictions for Model 1")
            out_2 = gr.Textbox(label="Predictions for Model 2")     
        btn1.click(fn=get_prediction(model_id_1), inputs=inp_1, outputs=out_1)
        btn2.click(fn=get_prediction(model_id_2), inputs=inp_1, outputs=out_2)
    
   
app.launch()