app.py

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

# Convert PDF to DataFrame (assuming it's already loaded as df in CSV or DataFrame format)
df = pd.read_csv('diabetes_data.csv')  # Replace with the path to your CSV
df['label'] = (df['target_column'] > threshold_value).astype(int)  # Adjust target column for binary classification

# Split the dataset
train_df, test_df = train_test_split(df, test_size=0.2)
train_df.to_csv("train.csv", index=False)
test_df.to_csv("test.csv", index=False)

# Load dataset with Hugging Face Datasets
dataset = load_dataset('csv', data_files={'train': 'train.csv', 'test': 'test.csv'})

# Load tokenizer and model
tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased')
model = AutoModelForSequenceClassification.from_pretrained('bert-base-uncased', num_labels=2)

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

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

# Set 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 Trainer
trainer = Trainer(
    model=model,
    args=training_args,
    train_dataset=tokenized_dataset['train'],
    eval_dataset=tokenized_dataset['test'],
)

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