RobertaGoEmotionClassifier.py

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

# 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)

# 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 emotion
def classify_emotion(text):
    inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True)
    outputs = model(**inputs)
    logits = outputs.logits
    predicted_class_id = torch.argmax(logits, dim=-1).item()
    return emotion_labels[predicted_class_id]

# Apply emotion classification to the email content
enron_data['emotion'] = enron_data['body'].apply(classify_emotion)

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