pip install transformers
pip install googletrans==4.0.0-rc1
import streamlit as st
from transformers import pipeline
from googletrans import Translator

# Initialize translation and classification pipelines
translator = Translator()
emotion_classifier = pipeline("text-classification", model="arpanghoshal/EmoRoBERTa")


def classify_emotion(text, src_lang="auto", target_lang="en"):
    """
    Classifies emotion in text after translating to English (if needed).

    Args:
        text: Input text sentence in any language.
        src_lang: Source language of the text (default: "auto").
        target_lang: Target language for translation (default: "en").

    Returns:
        A dictionary containing the predicted emotion and its probability.
    """
    # Translate to English if necessary
    if src_lang != target_lang:
        translated_text = translator.translate(text, dest=target_lang).text
    else:
        translated_text = text

    # Classify emotion using EmoRoBERTa
    predictions = emotion_classifier(translated_text)
    return predictions[0]


def split_sentences_with_conjunctions(paragraph):
    """
    Splits a paragraph into sentences considering conjunctions and punctuation.

    Args:
        paragraph: The input paragraph as a string.

    Returns:
        A list of individual sentences.
    """
    sentences = []
    current_sentence = ""
    conjunctions = ["and", "but", "or", "for", "nor", "so", "yet"]  # Common conjunctions

    for word in paragraph.split():
        current_sentence += word + " "
        if word.lower() in conjunctions or word.endswith(".") or word.endswith("?"):
            sentences.append(current_sentence.strip())
            current_sentence = ""

    # Add any remaining sentence fragment
    if current_sentence.strip():
        sentences.append(current_sentence.strip())

    return sentences
paragraph = st.text_area("Enter your input: ")

# Split paragraph into sentences considering conjunctions
sentences = split_sentences_with_conjunctions(paragraph)

# Classify emotion for each sentence
emotion_results = []
for sentence in sentences:
    if sentence.strip():  # Check if sentence is not empty after stripping
        emotion_result = classify_emotion(sentence)
        emotion_results.append(emotion_result)

# Print emotions for each sentence
for sentence, emotion_result in zip(sentences, emotion_results):
    print(f"Sentence: {sentence} | Emotion: {emotion_result['label']} ({emotion_result['score']:.2f})")