Upload folder using huggingface_hub

app.py

@@ -1,4 +1,4 @@
-import streamlit as st
+import gradio as gr
 import numpy as np
 import joblib
 
@@ -8,80 +8,51 @@ import joblib
 model = joblib.load("model.joblib")
 
 # =========================
-# Page config
+# Prediction function
 # =========================
-st.set_page_config(
-    page_title="EV Performance Prediction",
-    page_icon="🔋",
-    layout="centered"
-)
-
-# =========================
-# Header
-# =========================
-st.markdown(
-    """
-    <h1 style='text-align: center;'>🔋 Electric Vehicle Performance Prediction</h1>
-    <p style='text-align: center; font-size:18px;'>
-        Dự báo hiệu suất kỹ thuật xe điện (Electric Range)
-    </p>
-    <hr>
-    """,
-    unsafe_allow_html=True
-)
-
-# =========================
-# Sidebar (thầy cô rất thích)
-# =========================
-st.sidebar.header("📌 Thông tin mô hình")
-st.sidebar.markdown(
-    """
-    - **Bài toán**: Hồi quy (Regression)  
-    - **Thuật toán**: XGBoost  
-    - **Đầu ra**: Electric Range  
-    - **Triển khai**: Hugging Face  
-    """
-)
+def predict_ev(year, make, model_code, ev_type, cafv, utility):
+    X = np.array([[year, make, model_code, ev_type, cafv, utility]])
+    prediction = model.predict(X)
+    return f"🔍 Electric Range dự đoán: {prediction[0]:.2f} km"
 
 # =========================
-# Input section
+# Gradio Interface
 # =========================
-st.subheader("📥 Nhập thông tin xe")
+with gr.Blocks(title="EV Performance Prediction") as demo:
+    gr.Markdown(
+        """
+        # 🔋 Electric Vehicle Performance Prediction
+        **Dự báo hiệu suất kỹ thuật xe điện (Electric Range)**  
+        ---
+        """
+    )
 
-col1, col2 = st.columns(2)
+    gr.Markdown("### 📥 Nhập thông tin xe")
 
-with col1:
-    year = st.number_input("Model Year", 1990, 2035, 2020)
-    make = st.number_input("Make (encoded)", value=10)
-    model_code = st.number_input("Model (encoded)", value=20)
+    with gr.Row():
+        year = gr.Number(label="Model Year", value=2020)
+        make = gr.Number(label="Make (encoded)", value=10)
+        model_code = gr.Number(label="Model (encoded)", value=20)
 
-with col2:
-    ev_type = st.number_input("EV Type (encoded)", value=1)
-    cafv = st.number_input("CAFV Eligibility (encoded)", value=0)
-    utility = st.number_input("Electric Utility (encoded)", value=60)
+    with gr.Row():
+        ev_type = gr.Number(label="EV Type (encoded)", value=1)
+        cafv = gr.Number(label="CAFV Eligibility (encoded)", value=0)
+        utility = gr.Number(label="Electric Utility (encoded)", value=60)
 
-# =========================
-# Predict button
-# =========================
-st.markdown("<br>", unsafe_allow_html=True)
+    predict_btn = gr.Button("🚀 Dự báo hiệu suất")
+    output = gr.Textbox(label="Kết quả dự báo")
 
-if st.button("🚀 Dự báo hiệu suất"):
-    X = np.array([[year, make, model_code, ev_type, cafv, utility]])
-    prediction = model.predict(X)
+    predict_btn.click(
+        fn=predict_ev,
+        inputs=[year, make, model_code, ev_type, cafv, utility],
+        outputs=output
+    )
 
-    st.success(
-        f"🔍 **Electric Range dự đoán:** `{prediction[0]:.2f}` km"
+    gr.Markdown(
+        """
+        ---
+        *Student Research Project – Academic Year 2024–2025*
+        """
     )
 
-# =========================
-# Footer
-# =========================
-st.markdown(
-    """
-    <hr>
-    <p style='text-align: center; font-size:14px;'>
-        Student Research Project – Academic Year 2024–2025
-    </p>
-    """,
-    unsafe_allow_html=True
-)
+demo.launch()

requirements.txt

@@ -2,4 +2,4 @@ scikit-learn
 xgboost
 joblib
 numpy
-streamlit
+gardio