Update pages/11_Ensembling_Techniques.py

pages/11_Ensembling_Techniques.py

@@ -0,0 +1,74 @@
+import streamlit as st
+import matplotlib.pyplot as plt
+import numpy as np
+from sklearn.datasets import make_classification
+from sklearn.ensemble import VotingClassifier, BaggingClassifier, RandomForestClassifier
+from sklearn.linear_model import LogisticRegression
+from sklearn.tree import DecisionTreeClassifier
+from sklearn.neighbors import KNeighborsClassifier
+from sklearn.model_selection import train_test_split
+from sklearn.metrics import accuracy_score
+from matplotlib.colors import ListedColormap
+
+st.set_page_config(page_title="Ensemble Learning Visualized", page_icon="🧭", layout="wide")
+st.title("🗺️ Ensemble Learning Techniques")
+
+X, y = make_classification(n_samples=300, n_features=2, n_redundant=0,
+                           n_clusters_per_class=1, n_classes=2, random_state=42)
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)
+
+technique = st.radio("Choose Ensemble Technique:", ["Voting Classifier", "Bagging", "Random Forest"])
+
+cm = plt.cm.RdYlBu
+cm_bright = ListedColormap(["#FF4C60", "#1f78d1"])
+
+def plot_decision_boundary(clf, X, y, title):
+    x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
+    y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
+    xx, yy = np.meshgrid(np.linspace(x_min, x_max, 300), np.linspace(y_min, y_max, 300))
+    Z = clf.predict(np.c_[xx.ravel(), yy.ravel()])
+    Z = Z.reshape(xx.shape)
+    fig, ax = plt.subplots()
+    ax.contourf(xx, yy, Z, cmap=cm, alpha=0.6)
+    scatter = ax.scatter(X[:, 0], X[:, 1], c=y, cmap=cm_bright, edgecolors='k')
+    ax.set_title(title)
+    ax.set_xlabel("Feature 1")
+    ax.set_ylabel("Feature 2")
+    st.pyplot(fig)
+
+if technique == "Voting Classifier":
+    st.subheader("🗳️ Voting Classifier")
+    clf1 = LogisticRegression()
+    clf2 = KNeighborsClassifier(n_neighbors=5)
+    clf3 = DecisionTreeClassifier()
+    eclf = VotingClassifier(estimators=[('lr', clf1), ('knn', clf2), ('dt', clf3)], voting='hard')
+    eclf.fit(X_train, y_train)
+    y_pred = eclf.predict(X_test)
+    acc = accuracy_score(y_test, y_pred)
+    st.write(f"**Accuracy**: {acc:.2f}")
+    plot_decision_boundary(eclf, X_test, y_test, "Voting Classifier Decision Region")
+
+elif technique == "Bagging":
+    st.subheader("🧺 Bagging with Decision Trees")
+    base_model = DecisionTreeClassifier()
+    bagging = BaggingClassifier(base_model, n_estimators=10, random_state=42)
+    bagging.fit(X_train, y_train)
+    y_pred = bagging.predict(X_test)
+    acc = accuracy_score(y_test, y_pred)
+    st.write(f"**Accuracy**: {acc:.2f}")
+    plot_decision_boundary(bagging, X_test, y_test, "Bagging Decision Region")
+
+elif technique == "Random Forest":
+    st.subheader("🌲 Random Forest")
+    rf = RandomForestClassifier(n_estimators=100, random_state=42)
+    rf.fit(X_train, y_train)
+    y_pred = rf.predict(X_test)
+    acc = accuracy_score(y_test, y_pred)
+    st.write(f"**Accuracy**: {acc:.2f}")
+    plot_decision_boundary(rf, X_test, y_test, "Random Forest Decision Region")
+
+st.markdown("---")
+st.markdown("""
+This interactive app helps you understand **Ensemble Methods** using decision boundaries.
+Select from Voting, Bagging, and Random Forest and visualize how they classify data differently.
+""")