Update app.py

app.py

@@ -1,30 +1,29 @@
 import gradio as gr
-import torch
-from transformers import AutoModelForSequenceClassification, AutoTokenizer, TrainingArguments, Trainer
-from datasets import load_dataset
-import os
+from model.model import fine_tune
+from data.preprocess import load_data, preprocess_data, save_processed_data
 
-# Function to fine-tune model
-def fine_tune(model_name, dataset_url, file, epochs, batch_size, learning_rate):
-    try:
-        # Load dataset
-        if dataset_url:
-            dataset = load_dataset(dataset_url)
-        elif file:
-            dataset = load_dataset("csv", data_files={"train": file.name})
-        else:
-            return "Please provide a dataset URL or upload a file."
+def prepare_and_train(model_name, dataset_path, epochs, batch_size, learning_rate):
+    # Load and preprocess the dataset
+    data = load_data(dataset_path)
+    cleaned_data = preprocess_data(data)
+    processed_data_path = 'data/processed/processed_dataset.csv'
+    save_processed_data(cleaned_data, processed_data_path)
 
-        # Load model & tokenizer
-        model = AutoModelForSequenceClassification.from_pretrained(model_name, num_labels=2)
-        tokenizer = AutoTokenizer.from_pretrained(model_name)
+    # Proceed with model fine-tuning
+    return fine_tune(model_name, dataset_url=None, file=processed_data_path, epochs=epochs, batch_size=batch_size, learning_rate=learning_rate)
 
-        def tokenize_function(examples):
-            return tokenizer(examples["text"], padding="max_length", truncation=True)
+iface = gr.Interface(
+    fn=prepare_and_train,
+    inputs=[
+        gr.Textbox(label="Model Name", placeholder="e.g., bert-base-uncased"),
+        gr.File(label="Upload Dataset"),
+        gr.Number(label="Epochs", value=3),
+        gr.Number(label="Batch Size", value=8),
+        gr.Number(label="Learning Rate", value=5e-5),
+    ],
+    outputs="text",
+    live=True,
+)
 
-        dataset = dataset.map(tokenize_function, batched=True)
-
-        # Define training arguments
-        training_args = TrainingArguments(
-            output_dir="./results",
-            evaluation_strategy="epoch
+if __name__ == "__main__":
+    iface.launch()