Update app.py

app.py

@@ -9,125 +9,112 @@ from sklearn.metrics import classification_report, accuracy_score
 import matplotlib.pyplot as plt
 import seaborn as sns
 
-# Streamlit Page Configuration
+# Page Configuration
 st.set_page_config(page_title="Explore Logistic Regression", layout="wide")
 st.title("Logistic Regression Classifier")
 
+# Cache data loading
+@st.cache_data
+def load_data():
+    wine = load_wine()
+    df = pd.DataFrame(wine.data, columns=wine.feature_names)
+    df["target"] = wine.target
+    return df, wine
+
+df, wine = load_data()
+
 # Introduction
 st.markdown("""
 ## 🧠 What is Logistic Regression?
+Logistic Regression models the probability of class membership, especially for categorical outputs.
 
-Logistic Regression is a widely used classification technique that models the probability of class membership.
-It’s particularly useful when the output is categorical (e.g., types of wines 🍇).
-
+## 📦 Dataset: Wine Classification 🍷
+We’ll use chemical analysis of wines from 3 cultivars.
 ---
-
-## 📦 Dataset: Wine Classification🍷
-
-We'll be using the Wine dataset, which contains chemical analysis of wines grown in the same region in Italy, but derived from three different cultivars.
 """)
 
-# Load and preview Wine dataset
-wine = load_wine()
-df = pd.DataFrame(wine.data, columns=wine.feature_names)
-df['target'] = wine.target
-
+# Show dataset
 st.markdown("### 📋 Data Preview")
 st.dataframe(df.head(), use_container_width=True)
 
-# Sidebar: Model Settings
+# Sidebar Settings
 st.sidebar.header("⚙️ Model Settings")
-penalty = st.sidebar.radio("Penalty Type (Regularization)", ["l1", "l2", "elasticnet"])
-C = st.sidebar.slider("Inverse Regularization Strength (C)", 0.01, 10.0, value=1.0)
+penalty = st.sidebar.radio("Penalty Type", ["l1", "l2", "elasticnet"])
+C = st.sidebar.slider("Inverse Regularization Strength (C)", 0.01, 10.0, 1.0)
 
-# Determine solver and extra params based on penalty
 l1_ratio = None
-
-if penalty == 'elasticnet':
-    solver = 'saga'
+if penalty == "elasticnet":
+    solver = "saga"
     l1_ratio = st.sidebar.slider("ElasticNet Mixing Ratio (l1_ratio)", 0.0, 1.0, 0.5)
-elif penalty == 'l1':
-    solver = 'liblinear'  # saga also works for l1
+elif penalty == "l1":
+    solver = "liblinear"
 else:
-    solver = 'lbfgs'
+    solver = "lbfgs"
 
-# Prepare features and target
+# Prepare data
 X = df.drop("target", axis=1)
 y = df["target"]
 
-# Feature scaling
 scaler = StandardScaler()
 X_scaled = scaler.fit_transform(X)
-
-# Train-test split
 X_train, X_test, y_train, y_test = train_test_split(X_scaled, y, test_size=0.2, random_state=42)
 
-# Train the Logistic Regression model
-model = LogisticRegression(
-    penalty=penalty,
-    C=C,
-    solver=solver,
-    multi_class='ovr',
-    max_iter=200,
-    l1_ratio=l1_ratio  # Ignored if not used
-)
-model.fit(X_train, y_train)
-y_pred = model.predict(X_test)
-
-# Accuracy and classification report
+# Train model
+with st.spinner("Training the model..."):
+    model = LogisticRegression(
+        penalty=penalty,
+        C=C,
+        solver=solver,
+        max_iter=100,
+        multi_class="ovr",
+        l1_ratio=l1_ratio
+    )
+    model.fit(X_train, y_train)
+    y_pred = model.predict(X_test)
+
+# Show metrics
 accuracy = accuracy_score(y_test, y_pred)
 st.success(f"✅ Model Accuracy: {accuracy * 100:.2f}%")
 
 st.markdown("### 📊 Classification Report")
 st.text(classification_report(y_test, y_pred, target_names=wine.target_names))
 
-# Visualization Section
+# Visualization
 st.markdown("## 🎨 Visualizing the Decision Boundary (2 Features Only)")
-
-feature_x = st.selectbox("Select X-axis Feature", df.columns[:-1], index=0)
-feature_y = st.selectbox("Select Y-axis Feature", df.columns[:-1], index=1)
+feature_x = st.selectbox("X-axis Feature", df.columns[:-1], index=0)
+feature_y = st.selectbox("Y-axis Feature", df.columns[:-1], index=1)
 
 X_vis = df[[feature_x, feature_y]]
 X_vis_scaled = scaler.fit_transform(X_vis)
-
 X_train_v, X_test_v, y_train_v, y_test_v = train_test_split(X_vis_scaled, y, test_size=0.2, random_state=42)
 
+# Visualization model (simplified)
 model_vis = LogisticRegression(
-    penalty=penalty,
-    C=C,
-    solver=solver,
-    multi_class='ovr',
-    max_iter=200,
-    l1_ratio=l1_ratio
+    penalty="l2", C=1.0, solver="lbfgs", max_iter=100, multi_class="ovr"
 )
 model_vis.fit(X_train_v, y_train_v)
 
-# Meshgrid for decision boundary
-h = .02
+# Plot decision boundary
+h = 0.05
 x_min, x_max = X_vis_scaled[:, 0].min() - 1, X_vis_scaled[:, 0].max() + 1
 y_min, y_max = X_vis_scaled[:, 1].min() - 1, X_vis_scaled[:, 1].max() + 1
 xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h))
-Z = model_vis.predict(np.c_[xx.ravel(), yy.ravel()])
-Z = Z.reshape(xx.shape)
+Z = model_vis.predict(np.c_[xx.ravel(), yy.ravel()]).reshape(xx.shape)
 
 fig, ax = plt.subplots(figsize=(8, 6))
 plt.contourf(xx, yy, Z, alpha=0.3)
-sns.scatterplot(x=X_vis_scaled[:, 0], y=X_vis_scaled[:, 1], hue=df['target'], palette='Set1', ax=ax)
+sns.scatterplot(x=X_vis_scaled[:, 0], y=X_vis_scaled[:, 1], hue=df["target"], palette="Set1", ax=ax)
 plt.xlabel(feature_x)
 plt.ylabel(feature_y)
-plt.title("Decision Boundaries using Logistic Regression")
+plt.title("Decision Boundary")
 st.pyplot(fig)
 
-# Closing Notes
+# Summary
 st.markdown("""
 ---
-
 ## ✅ Summary
-
-- **Logistic Regression** is great for interpretable, fast classification.
-- `l2` penalty works well for most tasks.
-- `l1` encourages sparsity (feature selection).
-- `elasticnet` balances both `l1` and `l2`.
-
-🎯 *Tip:* Try different penalties and mixing ratios to understand their effect on model performance and interpretability.
+- Logistic Regression is great for interpretable, fast classification.
+- `l2` is default; `l1` helps with feature selection.
+- `elasticnet` balances both.
+🎯 *Tip:* Try adjusting C and penalty type for deeper insights!
 """)