Prompt

import pandas as pd from sklearn.feature_extraction.text import TfidfVectorizer from sklearn.model_selection import train_test_split from sklearn.svm import SVC from sklearn.metrics import accuracy_score, confusion_matrix import seaborn as sns import matplotlib.pyplot as plt from transformers import pipeline, AutoTokenizer from joblib import dump # Load the data data = pd.read_excel(r"/content/alldata.xlsx", sheet_name="Sheet1", usecols=["clean", "label"]) # Define the GPT-2 model and tokenize