| import streamlit as st |
| import pickle |
| import numpy as np |
| import os |
|
|
| |
| model_path = "random_forest_pipeline.pkl" |
|
|
| |
| st.set_page_config(page_title="Wine Quality Prediction 🍷🔬", layout="centered") |
|
|
| |
| st.markdown( |
| """ |
| <style> |
| .stApp { background-color: #003366; color: white; } |
| .title { font-size: 36px; font-weight: bold; color: white; text-align: center; } |
| .subtitle { font-size: 24px; font-weight: bold; color: #ffcc00; } |
| .stSelectbox label, .stNumberInput label, .stSlider label { font-size: 18px; font-weight: bold; color: white; } |
| .stButton>button { background-color: #ffcc00; color: #003366; font-size: 18px; font-weight: bold; border-radius: 10px; } |
| .stButton>button:hover { background-color: #ff9900; color: white; } |
| .prediction { font-size: 26px; font-weight: bold; color: #32CD32; text-align: center; } |
| </style> |
| """, |
| unsafe_allow_html=True, |
| ) |
|
|
| st.markdown('<h1 class="title">Wine Quality Prediction 🍷🔬</h1>', unsafe_allow_html=True) |
| st.write("Predicting Wine Quality based on wine parameters.") |
|
|
| |
| if os.path.exists(model_path): |
| with open(model_path, "rb") as f: |
| model = pickle.load(f) |
| st.success("✅ Model loaded successfully!") |
| model_loaded = True |
| else: |
| st.error(f"❌ Model file '{model_path}' not found! Please upload or train the model first.") |
| model_loaded = False |
|
|
| |
| fixed_acidity = st.number_input("Fixed Acidity", min_value=4.6, max_value=15.9, value=7.6) |
| volatile_acidity = st.number_input("Volatile Acidity", min_value=0.12, max_value=1.58, value=1.2) |
| citric_acid = st.number_input("Citric Acid", min_value=0.0, max_value=1.66, value=0.5) |
| residual_sugar = st.number_input("Residual Sugar", min_value=0.9, max_value=15.5, value=5.8) |
| chlorides = st.number_input("Chlorides", min_value=0.012, max_value=0.611, value=0.044) |
| free_sulfur_dioxide = st.slider("Free Sulfur Dioxide", 1, 72, 15) |
| total_sulfur_dioxide = st.slider("Total Sulfur Dioxide", 6, 289, 100) |
| density = st.number_input("Density", min_value=0.99007, max_value=1.00369, value=1.00111) |
| pH = st.number_input("pH", min_value=2.74, max_value=4.01, value=3.12) |
| sulphates = st.number_input("Sulphates", min_value=0.33, max_value=2.00, value=0.9) |
| alcohol = st.number_input("Alcohol", min_value=8.4, max_value=14.9, value=10.2) |
|
|
| |
| input_data = np.array([[fixed_acidity, volatile_acidity, citric_acid, residual_sugar, chlorides, |
| free_sulfur_dioxide, total_sulfur_dioxide, density, pH, sulphates, alcohol]]) |
|
|
| |
| if st.button("Predict Wine Quality"): |
| if model_loaded: |
| prediction = model.predict(input_data) |
| st.markdown(f'<p class="prediction">Predicted Wine Quality: {prediction[0]}</p>', unsafe_allow_html=True) |
| else: |
| st.error(f"❌ Model file '{model_path}' not found. Please train the model and try again.") |
|
|
|
|
|
|
