app.py

import streamlit as st
import tensorflow as tf
from transformers import pipeline
from textblob import TextBlob
from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch
import torch.nn.functional as F
from transformers import BertForMaskedLM

model = BertForMaskedLM.from_pretrained("remi/bertabs-finetuned-extractive-abstractive-summarization")

textIn = st.text_input("Input Text Here:", "I really like the color of your car!")

option = st.selectbox('Which pre-trained model would you like for your sentiment analysis?',('MILESTONE 3', 'Pipeline', 'TextBlob'))

st.write('You selected:', option)

if option == 'MILESTONE 3':

    st.write('test1')

    model_name_0 = "Rathgeberj/milestone3_1"
    # model_0 = AutoModelForSequenceClassification.from_pretrained(model_name_0)
    model_0 = BertForMaskedLM.from_pretrained("Rathgeberj/milestone3_0")
    tokenizer_0 = AutoTokenizer.from_pretrained(model_name_0)
    classifier_0 = pipeline(task="sentiment-analysis", model=model_0, tokenizer=tokenizer_0)

    # model_name_1 = "Rathgeberj/milestone3_1"
    # model_1 = AutoModelForSequenceClassification.from_pretrained(model_name_1)
    # tokenizer_1 = AutoTokenizer.from_pretrained(model_name_1)
    # classifier_1 = pipeline(task="sentiment-analysis", model=model_1, tokenizer=tokenizer_1)

    # model_name_2 = "Rathgeberj/milestone3_2"
    # model_2 = AutoModelForSequenceClassification.from_pretrained(model_name_2)
    # tokenizer_2 = AutoTokenizer.from_pretrained(model_name_2)
    # classifier_2 = pipeline(task="sentiment-analysis", model=model_2, tokenizer=tokenizer_2)

    # model_name_3 = "Rathgeberj/milestone3_3"
    # model_3 = AutoModelForSequenceClassification.from_pretrained(model_name_3)
    # tokenizer_3 = AutoTokenizer.from_pretrained(model_name_3)
    # classifier_3 = pipeline(task="sentiment-analysis", model=model_3, tokenizer=tokenizer_3)

    # model_name_4 = "Rathgeberj/milestone3_4"
    # model_4 = AutoModelForSequenceClassification.from_pretrained(model_name_4)
    # tokenizer_4 = AutoTokenizer.from_pretrained(model_name_4)
    # classifier_4 = pipeline(task="sentiment-analysis", model=model_4, tokenizer=tokenizer_4)

    # model_name_5 = "Rathgeberj/milestone3_5"
    # model_5 = AutoModelForSequenceClassification.from_pretrained(model_name_5)
    # tokenizer_5 = AutoTokenizer.from_pretrained(model_name_5)
    # classifier_5 = pipeline(task="sentiment-analysis", model=model_5, tokenizer=tokenizer_5)

    # models = [model_0, model_1, model_2, model_3, model_4, model_5]
    # tokenizers = [tokenizer_0, tokenizer_1, tokenizer_2, tokenizer_3, tokenizer_4, tokenizer_5]
    # classifiers = [classifier_0, classifier_1, classifier_2, classifier_3, classifier_4, classifier_5]

    # X_train = [textIn]
    # batch = tokenizer(X_train, padding=True, truncation=True, max_length=512, return_tensors="pt")
    st.write('test2')

if option == 'Pipeline':

    model_name = "distilbert-base-uncased-finetuned-sst-2-english"
    model = AutoModelForSequenceClassification.from_pretrained(model_name)
    tokenizer = AutoTokenizer.from_pretrained(model_name)
    classifier = pipeline(task="sentiment-analysis", model=model, tokenizer=tokenizer)
    preds = classifier(textIn)
    preds = [{"score": round(pred["score"], 4), "label": pred["label"]} for pred in preds]
    st.write('According to Pipeline, input text is ', preds[0]['label'], ' with a confidence of ', preds[0]['score'])

if option == 'TextBlob':
    polarity = TextBlob(textIn).sentiment.polarity
    subjectivity = TextBlob(textIn).sentiment.subjectivity
    sentiment = ''
    if polarity < 0:
        sentiment = 'Negative'
    elif polarity == 0:
        sentiment = 'Neutral'
    else:
        sentiment = 'Positive'
    st.write('According to TextBlob, input text is ', sentiment, ' and a subjectivity score (from 0 being objective to 1 being subjective) of ', subjectivity)


#------------------------------------------------------------------------

# tokens = tokenizer.tokenize(textIn)
# token_ids = tokenizer.convert_tokens_to_ids(tokens)
# input_ids = tokenizer(textIn)


# X_train = [textIn]

# batch = tokenizer(X_train, padding=True, truncation=True, max_length=512, return_tensors="pt")
# # batch = torch.tensor(batchbatch["input_ids"])

# with torch.no_grad():
#     outputs = model(**batch, labels=torch.tensor([1, 0]))
#     predictions = F.softmax(outputs.logits, dim=1)
#     labels = torch.argmax(predictions, dim=1)
#     labels = [model.config.id2label[label_id] for label_id in labels.tolist()]

# # save_directory = "saved"
# tokenizer.save_pretrained(save_directory)
# model.save_pretrained(save_directory)

# tokenizer = AutoTokenizer.from_pretrained(save_directory)
# model = AutoModelForSequenceClassification.from_pretrained(save_directory)

#------------------------------------------------------------------------