# Import necessary libraries
import pandas as pd
from datasets import Dataset
from transformers import AutoTokenizer, AutoModelForSequenceClassification, Trainer, TrainingArguments
from sklearn.model_selection import train_test_split

# Load the dataset
df = pd.read_csv('diabetes_prediction_dataset.csv')  # Ensure this file is uploaded to the root directory

# Define the target column (e.g., 'hypertension') and create binary labels
# Replace 'hypertension' with your actual target column if needed
threshold_value = 0
df['label'] = (df['hypertension'] > threshold_value).astype(int)

# Split the dataset into train and test sets
train_df, test_df = train_test_split(df, test_size=0.2, random_state=42)
train_dataset = Dataset.from_pandas(train_df)
test_dataset = Dataset.from_pandas(test_df)

# Load the tokenizer and model from Hugging Face
model_name = "bert-base-uncased"  # You can replace this with another compatible model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name, num_labels=2)

# Define a tokenization function
def preprocess_function(examples):
    # Convert each feature to a string and concatenate them
    inputs = [f"{age} {bmi} {hba1c}" for age, bmi, hba1c in zip(examples["age"], examples["bmi"], examples["HbA1c_level"])]
    return tokenizer(inputs, padding="max_length", truncation=True, max_length=32)

# Apply the tokenization function to the datasets
tokenized_train = train_dataset.map(preprocess_function, batched=True)
tokenized_test = test_dataset.map(preprocess_function, batched=True)

# Set up training arguments
training_args = TrainingArguments(
    output_dir="./results",
    evaluation_strategy="epoch",
    per_device_train_batch_size=16,
    per_device_eval_batch_size=16,
    num_train_epochs=3,
    weight_decay=0.01,
)

# Initialize the Trainer
trainer = Trainer(
    model=model,
    args=training_args,
    train_dataset=tokenized_train,
    eval_dataset=tokenized_test,
)

# Train and evaluate the model
trainer.train()
trainer.evaluate()