Adding Model... let's test it

model.py

@@ -0,0 +1,64 @@
+import pandas as pd
+import torch
+from sklearn.model_selection import train_test_split
+from transformers import BertTokenizer, BertForSequenceClassification, TrainingArguments, Trainer
+
+df = pd.read_csv('Training_Essay_Data 1.csv.csv')
+
+train_df, eval_df = train_test_split(df, test_size=0.1)  # Here 10% for validation
+
+tokenizer = BertTokenizer.from_pretrained('bert-baseuncased')
+
+
+def tokenize_function(examples):
+    return tokenizer(examples['text'], padding='max_length', truncation=True, max_length=512)
+
+
+train_encodings = tokenize_function(train_df)
+eval_encodings = tokenize_function(eval_df)
+
+
+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]))  # Convert labels to tensor
+        return item
+
+    def __len__(self):
+        return len(self.labels)
+
+
+train_dataset = EssayDataset(train_encodings, train_df['label'].tolist())
+eval_dataset = EssayDataset(eval_encodings, eval_df['label'].tolist())
+
+model = BertForSequenceClassification.from_pretrained('bertbase-uncased', num_labels=2)
+
+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',
+)
+
+trainer = Trainer(
+    model=model,
+    args=training_args,
+    train_dataset=train_dataset,
+    eval_dataset=eval_dataset
+)
+
+trainer.train()
+
+user_input = input("Enter the text you want to classify: ")
+inputs = tokenizer(user_input, padding=True, truncation=True,
+                   return_tensors="pt")
+outputs = model(**inputs)
+predictions = torch.argmax(outputs.logits, dim=-1)
+print("Classified as:", "AI-generated" if predictions.item() == 1 else "Human-written")