Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,40 +1,241 @@
-import altair as alt
-import numpy as np
-import pandas as pd
+Hugging Face's logo
+Hugging Face
+Models
+Datasets
+Spaces
+Community
+Docs
+Pricing
+
+
+Spaces:
+Man0707
+/
+Wine_Quality
+
+private
+
+App
+Files
+Community
+Settings
+Wine_Quality
+/
+src
+/
+streamlit_app.py
+
+Man0707's picture
+Man0707
+Update src/streamlit_app.py
+efc0150
+verified
+about 3 hours ago
+raw
+
+Copy download link
+history
+blame
+edit
+delete
+
+7.46 kB
 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
+
+# -------------------------- Page Config --------------------------
+st.set_page_config(
+    page_title="Wine Quality Master 🍷",
+    page_icon="🍇",
+    layout="centered",
+    initial_sidebar_state="expanded"
+)
+
+# -------------------------- Custom CSS - Dark Purple Magic --------------------------
+st.markdown("""
+<style>
+    .main {background: #0f001a; color: #e6e6fa;}
+    .stApp {background: linear-gradient(135deg, #2a0052, #000000);}
+    .glass-card {
+        background: rgba(138, 43, 226, 0.15);
+        backdrop-filter: blur(12px);
+        border-radius: 20px;
+        border: 1px solid rgba(138, 43, 226, 0.3);
+        padding: 2rem;
+        box-shadow: 0 8px 32px rgba(138, 43, 226, 0.2);
+        margin: 1.5rem 0;
+    }
+    h1, h2 {background: linear-gradient(90deg, #9b59b6, #e91e63, #ff9800); 
+             -webkit-background-clip: text; -webkit-text-fill-color: transparent;}
+    .wine-red {color: #c0392b;}
+    .wine-white {color: #f1c40f;}
+    .prediction-good {font-size: 2.5rem; font-weight: bold; text-align: center; 
+                      color: #8e44ad; text-shadow: 0 0 20px #9b59b6;}
+</style>
+""", unsafe_allow_html=True)
+
+# -------------------------- Load Full Wine Quality Dataset (Red + White) --------------------------
+@st.cache_data
+def load_wine_data():
+    # Red wine
+    red = pd.read_csv("https://archive.ics.uci.edu/ml/machine-learning-databases/wine-quality/winequality-red.csv", sep=";")
+    red["type"] = "Red"
+    
+    # White wine
+    white = pd.read_csv("https://archive.ics.uci.edu/ml/machine-learning-databases/wine-quality/winequality-white.csv", sep=";")
+    white["type"] = "White"
+    
+    # Combine
+    df = pd.concat([red, white], ignore_index=True)
+    
+    # Binary classification: Good (>=6), Bad (<6)
+    df["is_good"] = (df["quality"] >= 6).astype(int)
+    
+    return df
+
+df = load_wine_data()
+
+# -------------------------- Hero Section --------------------------
+col1, col2, col3 = st.columns([1,3,1])
+with col2:
+    st.markdown("<h1 style='text-align:center;'>Wine Quality Master</h1>", unsafe_allow_html=True)
+    st.markdown("<p style='text-align:center; font-size:1.4rem; opacity:0.9;'>Red or White – Will it be divine... or declined?</p>", unsafe_allow_html=True)
+
+st.markdown("---")
+
+# -------------------------- Dataset Info --------------------------
+with st.container():
+    st.markdown("<div class='glass-card'>", unsafe_allow_html=True)
+    col1, col2, col3, col4 = st.columns(4)
+    with col1:
+        st.metric("Total Wines", f"{len(df):,}")
+    with col2:
+        st.metric("Red Wines", f"{len(df[df['type']=='Red']):,}", "Red Wine")
+    with col3:
+        st.metric("White Wines", f"{len(df[df['type']=='White']):,}", "White Wine")
+    with col4:
+        st.metric("Good Wines (≥6)", f"{df['is_good'].sum():,}")
+    
+    st.markdown("<br>", unsafe_allow_html=True)
+    st.dataframe(df.head(), use_container_width=True)
+    st.markdown("</div>", unsafe_allow_html=True)
+
+# -------------------------- Prepare Features --------------------------
+X = df.drop(columns=["quality", "is_good"])
+y = df["is_good"]
+
+# One-hot encode wine type (ensures consistent column order)
+X = pd.get_dummies(X, columns=["type"], drop_first=False)
+
+# Train-test split
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42, stratify=y)
+
+# Scale numerical features (preserve exact column order)
+scaler = StandardScaler()
+numerical_cols = [col for col in X.columns if col not in ["type_Red", "type_White"]]
+X_train_num_scaled = scaler.fit_transform(X_train[numerical_cols])
+X_train = pd.concat([
+    pd.DataFrame(X_train_num_scaled, columns=numerical_cols, index=X_train.index),
+    X_train[["type_Red", "type_White"]]
+], axis=1)
+
+X_test_num_scaled = scaler.transform(X_test[numerical_cols])
+X_test = pd.concat([
+    pd.DataFrame(X_test_num_scaled, columns=numerical_cols, index=X_test.index),
+    X_test[["type_Red", "type_White"]]
+], axis=1)
+
+# Train model
+@st.cache_resource
+def train_model():
+    model = RandomForestClassifier(
+        n_estimators=1000,
+        max_depth=15,
+        random_state=42,
+        n_jobs=-1,
+        class_weight="balanced"
+    )
+    model.fit(X_train, y_train)
+    return model
+
+model = train_model()
+
+# Accuracy
+y_pred = model.predict(X_test)
+accuracy = accuracy_score(y_test, y_pred)
+
+with st.container():
+    st.markdown("<div class='glass-card'>", unsafe_allow_html=True)
+    st.success(f"Model Accuracy on Test Set: *{accuracy:.4f}* ({accuracy*100:.2f}%)")
+    st.markdown("</div>", unsafe_allow_html=True)
+
+# -------------------------- Interactive Prediction --------------------------
+st.markdown("<div class='glass-card'>", unsafe_allow_html=True)
+st.header("Predict Your Wine's Destiny")
+
+# Wine type selector
+wine_type = st.selectbox("Choose Wine Type", options=["Red", "White"], index=0)
+
+col1, col2 = st.columns(2)
+input_data = {"type_Red": 0, "type_White": 0}
+input_data[f"type_{wine_type}"] = 1
+
+features = [col for col in X.columns if col not in ["type_Red", "type_White"]]
+
+for i, feature in enumerate(features):
+    col = col1 if i % 2 == 0 else col2
+    with col:
+        min_v, max_v = float(df[feature].min()), float(df[feature].max())
+        mean_v = float(df[feature].mean())
+        val = st.slider(
+            feature.replace("_", " ").title(),
+            min_value=min_v,
+            max_value=max_v,
+            value=mean_v,
+            step=0.1,
+            format="%.2f"
+        )
+        input_data[feature] = val
+
+if st.button("Reveal the Quality!", use_container_width=True, type="primary"):
+    input_df = pd.DataFrame([input_data])
+    
+    # Scale numerical columns (FIX: Reconstruct to match exact column order)
+    input_num_scaled = scaler.transform(input_df[numerical_cols])
+    input_scaled = pd.concat([
+        pd.DataFrame(input_num_scaled, columns=numerical_cols, index=input_df.index),
+        input_df[["type_Red", "type_White"]]
+    ], axis=1)
+    
+    # Debug: Check column order (remove after testing)
+    with st.expander("Debug: Column Check (Remove in Production)"):
+        st.write("Input scaled columns:", list(input_scaled.columns))
+        st.write("Training columns:", list(X_train.columns))
+        st.write("Match?", list(input_scaled.columns) == list(X_train.columns))
+    
+    pred = model.predict(input_scaled)[0]
+    prob = model.predict_proba(input_scaled)[0]
+    
+    st.markdown("<br>", unsafe_allow_html=True)
+    
+    if pred == 1:
+        st.balloons()
+        st.markdown(f"<h2 class='prediction-good'>OUTSTANDING WINE! {wine_type} Wine</h2>", unsafe_allow_html=True)
+        st.success(f"Confidence: *{prob[1]:.1%}* – This belongs in a museum... or your glass right now!")
+    else:
+        st.error(f"Not quite a masterpiece... {wine_type} Wine")
+        st.warning(f"Confidence: *{prob[0]:.1%}* – Maybe use it for cooking?")
+    
+    # Feature importance hint
+    st.info(f"Pro tip: For {wine_type.lower()} wines, alcohol, sulphates, and volatile acidity matter most!")
+
+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("---")
+st.caption("Made with passion | Dataset: UCI Wine Quality (Red + White) | Model: Random Forest")