import streamlit as st
import pandas as pd
import torch
from transformers import AutoTokenizer, AutoModelForSequenceClassification
import csv
import random as r

with open('train.csv','r') as f:
    read = csv.reader(f)
    data = [row for row in read]
df = pd.DataFrame(data[1:],columns=data[0])
tweet = df['comment_text'][r.randint(0,1000)]
tokenizer = AutoTokenizer.from_pretrained("APJ23/MultiHeaded_Sentiment_Analysis_Model")
model = AutoModelForSequenceClassification.from_pretrained("APJ23/MultiHeaded_Sentiment_Analysis_Model")

# Define the classes and their corresponding labels
classes = {
    0: 'Non-Toxic',
    1: 'Toxic',
    2: 'Severely Toxic',
    3: 'Obscene',
    4: 'Threat',
    5: 'Insult',
    6: 'Identity Hate'
}

# Create a function to generate the toxicity predictions
@st.cache(allow_output_mutation=True)

# Create a table to display the toxicity predictions
def create_table(predictions):
    data = {'Tweet': [], 'Highest Toxicity Class': [], 'Probability': []}
    for tweet, prediction in predictions.items():
        data['Tweet'].append(tweet)
        data['Highest Toxicity Class'].append(prediction[0])
        data['Probability'].append(prediction[1])
    df = pd.DataFrame(data)
    return df

st.title('Toxicity Prediction App')
tweet_input = st.text_input('Enter a tweet:')
if st.button('Predict'):
    predicted_class_label, predicted_prob = predict_toxicity(tweet_input, model, tokenizer)
    prediction_text = f'Prediction: {predicted_class_label} ({predicted_prob:.2f})'
    st.write(prediction_text)

    # Display the toxicity predictions in a table
    predictions = {tweet_input: (predicted_class_label, predicted_prob)}
    table = create_table(predictions)
    st.table(table)