Create app.py

app.py

@@ -0,0 +1,115 @@
+import gradio as gr
+import pandas as pd
+import torch
+from transformers import AutoTokenizer, AutoModelForSequenceClassification, Trainer, TrainingArguments
+from sklearn.preprocessing import LabelEncoder
+from sklearn.model_selection import train_test_split
+from datasets import Dataset
+from underthesea import word_tokenize
+import os
+import pickle
+
+# ---- Load PhoBERT ----
+MODEL_NAME = "vinai/phobert-base"
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME, use_fast=False)
+
+# ---- Label Encoder (sẽ lưu sau khi train) ----
+label_encoder = None
+
+# ---- Tokenization ----
+def preprocess_function(example):
+    # word_tokenize tiếng Việt đúng cách cho PhoBERT
+    tokens = word_tokenize(example["comment"], format="text")
+    return tokenizer(tokens, truncation=True)
+
+# ---- Train function ----
+def train_model(file):
+    df = pd.read_csv(file.name)
+
+    global label_encoder
+    label_encoder = LabelEncoder()
+    df["label"] = label_encoder.fit_transform(df["label"])
+
+    # Save encoder
+    with open("label_encoder.pkl", "wb") as f:
+        pickle.dump(label_encoder, f)
+
+    # Chuyển Hugging Face Dataset
+    dataset = Dataset.from_pandas(df[["comment", "label"]])
+    tokenized_dataset = dataset.map(preprocess_function)
+
+    # Split
+    tokenized_dataset = tokenized_dataset.train_test_split(test_size=0.2)
+
+    # Load model
+    model = AutoModelForSequenceClassification.from_pretrained(MODEL_NAME, num_labels=len(set(df["label"])))
+
+    # Training
+    args = TrainingArguments(
+        output_dir="./results",
+        evaluation_strategy="epoch",
+        per_device_train_batch_size=8,
+        per_device_eval_batch_size=8,
+        num_train_epochs=3,
+        save_strategy="no",
+        logging_steps=10
+    )
+
+    trainer = Trainer(
+        model=model,
+        args=args,
+        train_dataset=tokenized_dataset["train"],
+        eval_dataset=tokenized_dataset["test"],
+        tokenizer=tokenizer,
+    )
+
+    trainer.train()
+
+    # Save model
+    model.save_pretrained("finetuned_phobert")
+    tokenizer.save_pretrained("finetuned_phobert")
+
+    return "✅ Huấn luyện thành công!"
+
+# ---- Dự đoán ----
+def predict_sentiment(text):
+    if not os.path.exists("finetuned_phobert"):
+        return "❌ Chưa có mô hình được huấn luyện."
+
+    model = AutoModelForSequenceClassification.from_pretrained("finetuned_phobert")
+    tokenizer = AutoTokenizer.from_pretrained("finetuned_phobert", use_fast=False)
+
+    global label_encoder
+    if label_encoder is None:
+        with open("label_encoder.pkl", "rb") as f:
+            label_encoder = pickle.load(f)
+
+    tokens = word_tokenize(text, format="text")
+    inputs = tokenizer(tokens, return_tensors="pt", truncation=True)
+
+    with torch.no_grad():
+        outputs = model(**inputs)
+        probs = torch.nn.functional.softmax(outputs.logits, dim=-1)
+        pred = torch.argmax(probs, dim=1).item()
+
+    return f"🔎 Dự đoán: {label_encoder.inverse_transform([pred])[0]} (xác suất: {probs[0][pred]:.2f})"
+
+# ---- Giao diện Gradio ----
+with gr.Blocks() as demo:
+    gr.Markdown("# 🔥 Fine-tune cảm xúc tiếng Việt với PhoBERT")
+
+    with gr.Tab("1️⃣ Huấn luyện"):
+        file_input = gr.File(label="Tải lên file CSV")
+        train_button = gr.Button("Huấn luyện mô hình")
+        train_output = gr.Textbox(label="Kết quả")
+
+        train_button.click(fn=train_model, inputs=file_input, outputs=train_output)
+
+    with gr.Tab("2️⃣ Dự đoán"):
+        text_input = gr.Textbox(label="Nhập câu đánh giá")
+        predict_button = gr.Button("Dự đoán")
+        predict_output = gr.Textbox(label="Kết quả")
+
+        predict_button.click(fn=predict_sentiment, inputs=text_input, outputs=predict_output)
+
+demo.launch()