main.py

import pandas as pd
from huggingface_hub import HfApi, login
from transformers import BertTokenizer, BertForSequenceClassification, Trainer, TrainingArguments
from datasets import Dataset

# Log in to Hugging Face
login()  # Pastikan kamu sudah login ke akun Hugging Face

# Load dataset
data = {
    'text': ["I love programming!", "I hate bugs.", "Python is great.", "I dislike syntax errors."],
    'label': [1, 0, 1, 0]  # 1 untuk sentimen positif, 0 untuk sentimen negatif
}
df = pd.DataFrame(data)

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

# Split the dataset into training and evaluation sets
train_test_split = dataset.train_test_split(test_size=0.2)  # 80% train, 20% eval
train_dataset = train_test_split['train']
eval_dataset = train_test_split['test']

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

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

# Tokenisasi data training dan evaluasi
tokenized_train = train_dataset.map(tokenize_function, batched=True)
tokenized_eval = eval_dataset.map(tokenize_function, batched=True)

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

# Set training arguments
training_args = TrainingArguments(
    output_dir='./results',
    evaluation_strategy="epoch",
    learning_rate=2e-5,
    per_device_train_batch_size=2,
    num_train_epochs=3,
    weight_decay=0.01,
)

# Train the model
trainer = Trainer(
    model=model,
    args=training_args,
    train_dataset=tokenized_train,
    eval_dataset=tokenized_eval,  # Menyediakan dataset evaluasi di sini
)

trainer.train()

# Save the model
model.save_pretrained('./mytest-model')
tokenizer.save_pretrained('./mytest-model')

# Define model ID
model_id = "aslan-asilon3/mytest-model"
api = HfApi()

# Create a new repo on Hugging Face if it doesn't already exist
try:
    api.create_repo(repo_id=model_id)
except Exception as e:
    print(f"Repo mungkin sudah ada: {e}")

# Upload model dan tokenizer
model.push_to_hub(model_id)
tokenizer.push_to_hub(model_id)

print(f"Model berhasil diunggah ke Hugging Face: {model_id}")