TechIA

import pandas as pd
from datasets import Dataset
from transformers import BertTokenizer, BertForSequenceClassification, Trainer, TrainingArguments
import torch

# Load your data from a CSV file
csv_file = "xenodm.log"
df = pd.read_csv(csv_file)

# Convert the DataFrame to a Hugging Face Dataset
dataset = Dataset.from_pandas(df)

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

# Tokenize the dataset
def tokenize_function(examples):
    return tokenizer(examples['text'], padding='max_length', truncation=True)

tokenized_dataset = dataset.map(tokenize_function, batched=True)

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

# Set up training arguments
training_args = TrainingArguments(
    output_dir='./results',
    num_train_epochs=3,
    per_device_train_batch_size=16,
    per_device_eval_batch_size=16,
    warmup_steps=500,
    weight_decay=0.01,
    logging_dir='./logs',
    logging_steps=10,
    evaluation_strategy="epoch",
)

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

# Fine-tune the model
trainer.train()

# Save the fine-tuned model
model.save_pretrained("fine_tuned_bert")
tokenizer.save_pretrained("fine_tuned_bert")