model.py

import pandas as pd
import torch
from sklearn.model_selection import train_test_split
from transformers import BertTokenizer, BertForSequenceClassification, TrainingArguments, Trainer

# Read the dataset
df = pd.read_csv('Training_Essay_Data.csv')  # Make sure the file name is correct

# Splitting the dataset
train_df, eval_df = train_test_split(df, test_size=0.1)

# Tokenizer
tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')


# Tokenize function
def tokenize_function(examples):
    return tokenizer(examples["text"], padding="max_length", truncation=True, max_length=512)


# Tokenize the dataset
train_encodings = tokenize_function(train_df)
eval_encodings = tokenize_function(eval_df)


# Essay dataset class
class EssayDataset(torch.utils.data.Dataset):
    def __init__(self, encodings, labels):
        self.encodings = encodings
        self.labels = labels

    def __getitem__(self, idx):
        item = {key: torch.tensor(val[idx]) for key, val in self.encodings.items()}
        item['labels'] = torch.tensor(int(self.labels[idx]))
        return item

    def __len__(self):
        return len(self.labels)


# Dataset preparation
train_dataset = EssayDataset(train_encodings, train_df['label'].tolist())
eval_dataset = EssayDataset(eval_encodings, eval_df['label'].tolist())

# Model
model = BertForSequenceClassification.from_pretrained('bert-base-uncased', num_labels=2)

# Training arguments
training_args = TrainingArguments(
    output_dir='./results',
    num_train_epochs=3,
    per_device_train_batch_size=16,
    per_device_eval_batch_size=64,
    warmup_steps=500,
    weight_decay=0.01,
    logging_dir='./logs',
    evaluation_strategy="epoch"
)

# Trainer
trainer = Trainer(
    model=model,
    args=training_args,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset
)

# Train the model
trainer.train()

# Save the model
model.save_pretrained("./saved_model")

# Load the model for prediction
model = BertForSequenceClassification.from_pretrained("./saved_model")


# Predicting
def predict(text):
    inputs = tokenizer(text, padding=True, truncation=True, return_tensors="pt")
    outputs = model(**inputs)
    predictions = torch.argmax(outputs.logits, dim=-1)
    return "AI-generated" if predictions.item() == 1 else "Human-written"


# Get user input and predict
user_input = input("Enter the text you want to classify: ")
print("Classified as:", predict(user_input))