app.py

import subprocess

subprocess.run(["pip", "install", "-q", "transformers", "datasets", "streamlit"])


from transformers import AutoModelForSequenceClassification
from transformers import TFAutoModelForSequenceClassification
from transformers import AutoTokenizer, AutoConfig
import numpy as np
from scipy.special import softmax


tokenizer = AutoTokenizer.from_pretrained('bert-base-cased')

model_path = f"avichr/heBERT_sentiment_analysis"
config = AutoConfig.from_pretrained(model_path)
model = AutoModelForSequenceClassification.from_pretrained(model_path)

# 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)

# Input preprocessing
text = "Covid cases are increasing fast!"
text = preprocess(text)

# PyTorch-based models
encoded_input = tokenizer(text, return_tensors='pt')
output = model(**encoded_input)
scores = output[0][0].detach().numpy()
scores = softmax(scores)

# TensorFlow-based models
# model = TFAutoModelForSequenceClassification.from_pretrained(model_path)
# model.save_pretrained(model_path)
# text = "Covid cases are increasing fast!"
# encoded_input = tokenizer(text, return_tensors='tf')
# output = model(encoded_input)
# scores = output[0][0].numpy()
# scores = softmax(scores)

config.id2label = {0: 'NEGATIVE', 1: 'NEUTRAL', 2: 'POSITIVE'}

# Print labels and scores
ranking = np.argsort(scores)
ranking = ranking[::-1]
print(f"Classified text: {text}")
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)}")

from transformers import AutoModelForSequenceClassification
from transformers import TFAutoModelForSequenceClassification
from transformers import AutoTokenizer, AutoConfig
from scipy.special import softmax
import streamlit as st


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)


def sentiment_analysis(text):
    text = preprocess(text)

    # Load the model
    model_path = f"avichr/heBERT_sentiment_analysis"
    tokenizer = AutoTokenizer.from_pretrained('bert-base-cased')
    config = AutoConfig.from_pretrained(model_path)
    model = AutoModelForSequenceClassification.from_pretrained(model_path)

    # Encode text input
    encoded_input = tokenizer(text, return_tensors='pt')
    output = model(**encoded_input)
    scores_ = output[0][0].detach().numpy()

    # Calculate softmax probabilities
    scores_ = softmax(scores_)

    # Format output dict of scores
    labels = ['Negative', 'Neutral', 'Positive']
    scores = {l:float(s) for (l,s) in zip(labels, scores_) }

    return scores


import streamlit as st

st.title("Sentiment Analysis for Covid Feelings")

# User input field
text = st.text_input(label="Enter your text:")

# Perform sentiment analysis
if text:
    scores = sentiment_analysis(text)

    # Display sentiment scores
    st.subheader("Sentiment Scores")
    for label in scores:
        score = scores[label]
        st.write(f"{label}: {score:.2f}")