app.py

import pandas as pd
from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch
from datasets import load_dataset

# Check if GPU is available
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

# Load the Enron dataset
dataset = load_dataset("Hellisotherpeople/enron_emails_parsed")
enron_data = pd.DataFrame(dataset['train'])

# Load the model and tokenizer
model_name = "modelSamLowe/roberta-base-go_emotions"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name).to(device)

# Define the emotion labels (based on the GoEmotions dataset)
emotion_labels = ["admiration", "amusement", "anger", "annoyance", "approval",
                  "caring", "confusion", "curiosity", "desire", "disappointment",
                  "disapproval", "disgust", "embarrassment", "excitement", "fear",
                  "gratitude", "grief", "joy", "love", "nervousness", "optimism",
                  "pride", "realization", "relief", "remorse", "sadness", "surprise",
                  "neutral"]

# Function to classify emotions in batches
def classify_emotions_in_batches(texts, batch_size=32):
    results = []
    for i in range(0, len(texts), batch_size):
        batch = texts[i:i+batch_size]
        inputs = tokenizer(batch, return_tensors="pt", truncation=True, padding=True).to(device)
        with torch.no_grad():
            outputs = model(**inputs)
            logits = outputs.logits
            predicted_class_ids = torch.argmax(logits, dim=-1).tolist()
            results.extend(predicted_class_ids)
    return results

# Apply emotion classification to the email content in batches
email_texts = enron_data['body'].tolist()
enron_data['emotion'] = classify_emotions_in_batches(email_texts, batch_size=32)

# Save the results to a CSV file
enron_data.to_csv("enron_emails_with_emotions.csv", index=False)