Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,40 +1,252 @@
-import altair as alt
-import numpy as np
-import pandas as pd
 import streamlit as st
+import pandas as pd
+import numpy as np
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import StandardScaler
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.metrics import accuracy_score
+import time
+
+# -------------------------- Page Config --------------------------
+st.set_page_config(
+    page_title="Vinum Divinum • Wine Oracle",
+    page_icon="🍷",
+    layout="centered",
+    initial_sidebar_state="collapsed"
+)
+
+# -------------------------- Luxurious Custom CSS with Animations --------------------------
+st.markdown("""
+<style>
+    @import url('https://fonts.googleapis.com/css2?family=Cormorant+Garamond:wght@400;600;700&family=Playfair+Display:wght@700&display=swap');
+
+    .main {
+        background: linear-gradient(180deg, #0a001f, #001a00);
+        color: #e6e6e6;
+        font-family: 'Cormorant Garamond', serif;
+    }
+    
+    .stApp {
+        background: url('https://images.unsplash.com/photo-1510812431401-41d2bd2722f3?q=80&w=2832&auto=format&fit=crop') no-repeat center center fixed;
+        background-size: cover;
+    }
+    
+    .glass-card {
+        background: rgba(10, 25, 10, 0.65);
+        backdrop-filter: blur(12px);
+        border-radius: 20px;
+        padding: 2rem;
+        border: 1px solid rgba(100, 200, 100, 0.3);
+        box-shadow: 0 8px 32px rgba(0, 0, 0, 0.6);
+        margin: 1rem 0;
+        animation: fadeIn 1.5s ease-out;
+    }
+    
+    @keyframes fadeIn {
+        from {opacity: 0; transform: translateY(30px);}
+        to {opacity: 1; transform: translateY(0);}
+    }
+    
+    @keyframes glow {
+        0%, 100% {box-shadow: 0 0 20px #64c864;}
+        50% {box-shadow: 0 0 0 40px #00ff88;}
+    }
+    
+    .title-glow {
+        font-family: 'Playfair Display', serif;
+        font-size: 4.5rem;
+        background: linear-gradient(90deg, #ffd700, #00ff88, #ff00aa);
+        -webkit-background-clip: text;
+        -webkit-text-fill-color: transparent;
+        text-align: center;
+        animation: glow 4s infinite;
+        margin-bottom: 0;
+    }
+    
+    .subtitle {
+        font-size: 1.6rem;
+        text-align: center;
+        color: #b0ffb0;
+        font-style: italic;
+        margin-top: 0;
+    }
+    
+    .metric-card {
+        background: rgba(20, 40, 20, 0.7);
+        padding: 1rem;
+        border-radius: 15px;
+        border: 1px solid #00ff88;
+        text-align: center;
+        color: #e0ffe0;
+    }
+    
+    .stButton>button {
+        background: linear-gradient(45deg, #1e4d1e, #2e8b57);
+        color: gold;
+        font-weight: bold;
+        border: none;
+        border-radius: 50px;
+        padding: 0.8rem 2rem;
+        font-size: 1.3rem;
+        transition: all 0.4s;
+        box-shadow: 0 4px 15px rgba(0, 255, 100, 0.4);
+    }
+    
+    .stButton>button:hover {
+        transform: translateY(-5px);
+        box-shadow: 0 10px 25px rgba(0, 255, 100, 0.7);
+        background: linear-gradient(45deg, #2e8b57, #00ff88);
+    }
+    
+    .good-wine {
+        font-size: 4rem;
+        text-align: center;
+        color: #00ff88;
+        text-shadow: 0 0 30px #00ff88, 0 0 60px #00ff00;
+        animation: glow 2s infinite alternate;
+    }
+    
+    .bad-wine {
+        font-size: 3rem;
+        text-align: center;
+        color: #ff3366;
+        text-shadow: 0 0 20px #ff0066;
+    }
+</style>
+""", unsafe_allow_html=True)
+
+# -------------------------- Load Data (Same Logic) --------------------------
+@st.cache_data
+def load_wine_data():
+    red = pd.read_csv("https://archive.ics.uci.edu/ml/machine-learning-databases/wine-quality/winequality-red.csv", sep=";")
+    red["type"] = "Red"
+    white = pd.read_csv("https://archive.ics.uci.edu/ml/machine-learning-databases/wine-quality/winequality-white.csv", sep=";")
+    white["type"] = "White"
+    df = pd.concat([red, white], ignore_index=True)
+    df["is_good"] = (df["quality"] >= 6).astype(int)
+    return df
+
+df = load_wine_data()
+
+# -------------------------- Hero Title with Animation --------------------------
+st.markdown("<h1 class='title-glow'>Vinum Divinum</h1>", unsafe_allow_html=True)
+st.markdown("<p class='subtitle'>The Ancient Oracle of Wine Quality</p>", unsafe_allow_html=True)
+
+st.markdown("<br>", unsafe_allow_html=True)
+
+# -------------------------- Stats in Glass Cards --------------------------
+with st.container():
+    st.markdown("<div class='glass-card'>", unsafe_allow_html=True)
+    c1, c2, c3, c4 = st.columns(4)
+    with c1:
+        st.markdown("<div class='metric-card'>", unsafe_allow_html=True)
+        st.metric("Total Vintages", f"{len(df):,}")
+        st.markdown("</div>", unsafe_allow_html=True)
+    with c2:
+        st.markdown("<div class='metric-card'>", unsafe_allow_html=True)
+        st.metric("Red Wines", f"{len(df[df['type']=='Red']):,}")
+        st.markdown("</div>", unsafe_allow_html=True)
+    with c3:
+        st.markdown("<div class='metric-card'>", unsafe_allow_html=True)
+        st.metric("White Wines", f"{len(df[df['type']=='White']):,}")
+        st.markdown("</div>", unsafe_allow_html=True)
+    with c4:
+        st.markdown("<div class='metric-card'>", unsafe_allow_html=True)
+        good_pct = df['is_good'].mean() * 100
+        st.metric("Deemed Worthy", f"{good_pct:.1f}%")
+        st.markdown("</div>", unsafe_allow_html=True)
+    st.markdown("</div>", unsafe_allow_html=True)
+
+# -------------------------- Model Training (Same Powerful Model) --------------------------
+X = df.drop(columns=["quality", "is_good"])
+y = df["is_good"]
+X = pd.get_dummies(X, columns=["type"])
+numerical_cols = [c for c in X.columns if c not in ["type_Red", "type_White"]]
+
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42, stratify=y)
+
+scaler = StandardScaler()
+X_train_scaled = scaler.fit_transform(X_train[numerical_cols])
+X_train_final = np.hstack([X_train_scaled, X_train[["type_Red", "type_White"]].values])
+
+X_test_scaled = scaler.transform(X_test[numerical_cols])
+X_test_final = np.hstack([X_test_scaled, X_test[["type_Red", "type_White"]].values])
+
+@st.cache_resource
+def train_oracle():
+    model = RandomForestClassifier(
+        n_estimators=1200,
+        max_depth=18,
+        min_samples_split=5,
+        class_weight="balanced",
+        random_state=42,
+        n_jobs=-1
+    )
+    model.fit(X_train_final, y_train)
+    return model, scaler
+
+model, scaler = train_oracle()
+
+# Accuracy
+accuracy = accuracy_score(y_test, model.predict(X_test_final))
+
+st.markdown(f"<div class='glass-card' style='text-align:center;'><h3>Oracle Accuracy: <span style='color:#00ff88'>{accuracy:.4f}</span> ({accuracy*100:.2f}%)</h3></div>", unsafe_allow_html=True)
+
+# -------------------------- Interactive Oracle Prediction --------------------------
+st.markdown("<div class='glass-card'>", unsafe_allow_html=True)
+st.markdown("<h2 style='text-align:center; color:#ffd700;'>Consult the Wine Oracle</h2>", unsafe_allow_html=True)
+
+wine_type = st.select_slider("Select Thy Wine", options=["Red", "White"], value="Red")
+
+col1, col2 = st.columns(2)
+input_dict = {"type_Red": 1 if wine_type == "Red" else 0, "type_White": 1 if wine_type == "White" else 0}
+
+for i, feat in enumerate(numerical_cols):
+    col = col1 if i % 2 == 0 else col2
+    with col:
+        min_val, max_val, avg_val = df[feat].min(), df[feat].max(), df[feat].mean()
+        value = st.slider(
+            feat.replace("_", " ").title(),
+            min_value=float(min_val),
+            max_value=float(max_val),
+            value=float(avg_val),
+            step=0.1,
+            format="%.2f",
+            key=feat
+        )
+        input_dict[feat] = value
+
+if st.button("✨ Reveal Destiny ✨", use_container_width=True):
+    with st.spinner("The Oracle is tasting..."):
+        time.sleep(2)
+    
+    # Prepare input
+    input_num = np.array([[input_dict[f] for f in numerical_cols]])
+    input_scaled = scaler.transform(input_num)
+    input_final = np.hstack([input_scaled, [[input_dict["type_Red"], input_dict["type_White"]]]])
+    
+    pred = model.predict(input_final)[0]
+    prob = model.predict_proba(input_final)[0]
+    
+    st.markdown("<br>", unsafe_allow_html=True)
+    
+    if pred == 1:
+        st.balloons()
+        st.markdown(f"<h1 class='good-wine'>DIVINE VINTAGE!</h1>", unsafe_allow_html=True)
+        st.markdown(f"<h3 style='text-align:center; color:#b0ffb0;'>A {wine_type} wine blessed by Dionysus himself!</h3>", unsafe_allow_html=True)
+        st.success(f"Confidence of Glory: *{prob[1]:.1%}*")
+        st.markdown("### Raise your glass — this is nectar of the gods!")
+    else:
+        st.markdown(f"<h2 class='bad-wine'>Alas, Not This Time...</h2>", unsafe_allow_html=True)
+        st.error(f"Confidence of Mediocrity: *{prob[0]:.1%}*")
+        st.info("Perhaps offer it to the earth... or use it to clean copper?")
+
+st.markdown("</div>", unsafe_allow_html=True)
 
-"""
-# Welcome to Streamlit!
-
-Edit `/streamlit_app.py` to customize this app to your heart's desire :heart:.
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
-
-In the meantime, below is an example of what you can do with just a few lines of code:
-"""
-
-num_points = st.slider("Number of points in spiral", 1, 10000, 1100)
-num_turns = st.slider("Number of turns in spiral", 1, 300, 31)
-
-indices = np.linspace(0, 1, num_points)
-theta = 2 * np.pi * num_turns * indices
-radius = indices
-
-x = radius * np.cos(theta)
-y = radius * np.sin(theta)
-
-df = pd.DataFrame({
-    "x": x,
-    "y": y,
-    "idx": indices,
-    "rand": np.random.randn(num_points),
-})
-
-st.altair_chart(alt.Chart(df, height=700, width=700)
-    .mark_point(filled=True)
-    .encode(
-        x=alt.X("x", axis=None),
-        y=alt.Y("y", axis=None),
-        color=alt.Color("idx", legend=None, scale=alt.Scale()),
-        size=alt.Size("rand", legend=None, scale=alt.Scale(range=[1, 150])),
-    ))
+# -------------------------- Footer --------------------------
+st.markdown("""
+    <div style='text-align:center; margin-top: 4rem; color: #666;'>
+        <p>© 2025 Vinum Divinum • Powered by Ancient Wisdom & Random Forests</p>
+        <p style='font-size:0.9rem; opacity:0.7;'>Dataset: UCI Wine Quality • Model trained on 6,497 sacred bottles</p>
+    </div>
+""", unsafe_allow_html=True)