Update app.py

app.py

@@ -0,0 +1,109 @@
+import streamlit as st
+import pandas as pd
+import numpy as np
+from sklearn.datasets import load_wine
+from sklearn.model_selection import train_test_split
+from sklearn.linear_model import LogisticRegression
+from sklearn.preprocessing import StandardScaler
+from sklearn.metrics import classification_report, accuracy_score
+import matplotlib.pyplot as plt
+import seaborn as sns
+
+# Streamlit Page Configuration
+st.set_page_config(page_title="Explore Logistic Regression", layout="wide")
+st.title("🍷 Logistic Regression Classifier on Wine Dataset")
+
+# Introduction
+st.markdown("""
+## 🧠 What is Logistic Regression?
+
+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 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
+
+st.markdown("### 📋 Data Preview")
+st.dataframe(df.head(), use_container_width=True)
+
+# User Input: Regularization settings
+st.sidebar.header("⚙️ Model Settings")
+penalty = st.sidebar.radio("Penalty Type (Regularization)", ["l2", "none"])
+C = st.sidebar.slider("Inverse Regularization Strength (C)", 0.01, 10.0, value=1.0)
+
+# Prepare features and target
+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, multi_class='ovr', solver='lbfgs', max_iter=200)
+model.fit(X_train, y_train)
+y_pred = model.predict(X_test)
+
+# Accuracy and classification report
+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
+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)
+
+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)
+
+model_vis = LogisticRegression(C=C, multi_class='ovr', solver='lbfgs', max_iter=200)
+model_vis.fit(X_train_v, y_train_v)
+
+# Meshgrid for decision boundary
+h = .02
+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)
+
+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)
+plt.xlabel(feature_x)
+plt.ylabel(feature_y)
+plt.title("Decision Boundaries using Logistic Regression")
+st.pyplot(fig)
+
+# Closing Notes
+st.markdown("""
+---
+
+## ✅ Summary
+
+- **Logistic Regression** is great for interpretable, fast classification.
+- It works well when your features are **linearly separable**.
+- The **Wine dataset** is a good example of multiclass classification.
+- Always **scale features** and **tune regularization** for best results.
+
+🎯 *Pro Tip:* Explore different feature combinations in the plot above to see how separation varies!
+""")