from transformers import AutoModelForSequenceClassification
from transformers import TFAutoModelForSequenceClassification
from transformers import AutoTokenizer, AutoConfig
import numpy as np
from scipy.special import softmax
import streamlit as st
st.title("Tho Tran - Milestone2")
# Preprocess text (username and link placeholders)
def preprocess(text):
    new_text = []
    for t in text.split(" "):
        t = '@user' if t.startswith('@') and len(t) > 1 else t
        t = 'http' if t.startswith('http') else t
        new_text.append(t)
    return " ".join(new_text)

MODEL = f"cardiffnlp/twitter-xlm-roberta-base-sentiment"

tokenizer = AutoTokenizer.from_pretrained(MODEL)
config = AutoConfig.from_pretrained(MODEL)

# PT
model = AutoModelForSequenceClassification.from_pretrained(MODEL)
model.save_pretrained(MODEL)
tokenizer.save_pretrained(MODEL)

text = st.text_input("Enter text here:","I love you")
text = preprocess(text)
encoded_input = tokenizer(text, return_tensors='pt')
output = model(**encoded_input)
scores = output[0][0].detach().numpy()
scores = softmax(scores)


# Print labels and scores
ranking = np.argsort(scores)
ranking = ranking[::-1]
for i in range(scores.shape[0]):
    l = config.id2label[ranking[i]]
    s = scores[ranking[i]]
    # print(f"{i+1}) {l} {np.round(float(s), 4)}")
    st.write(l,np.round(float(s),4))

st.write("choosen model is https://huggingface.co/cardiffnlp/twitter-xlm-roberta-base-sentiment?text=T%27estimo%21")