Bagging Ensembles Classifier In Machine Learning | Hire Machine Learning Expert

Bagging Ensembles

Another way to get a diverse set of classifiers is to use the same training algorithm for every predictor and train them on different random subsets of the training set. When sampling is performed with replacement, this method is called bagging (short for boot‐strap aggregating). When sampling is performed without replacement, it is called pasting.

More information about sampling with and without replacement can be found here.

The following code trains an ensemble of 500 Decision Tree classifiers. Each is trained on 100 training instances randomly sampled from the training set with replacement (therefore, this is an example of bagging, but if you want to use pasting instead, just set bootstrap=False).

from sklearn.model_selection import train_test_split
from sklearn.datasets import make_moons

X, y = make_moons(n_samples=500, noise=0.30, random_state=42)
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42)

from sklearn.ensemble import BaggingClassifier
from sklearn.tree import DecisionTreeClassifier

bag_clf = BaggingClassifier(DecisionTreeClassifier(random_state=42), n_estimators = 500,
                               max_samples = 100, bootstrap=True, random_state=42)
bag_clf.fit(X_train, y_train)

y_pred = bag_clf.predict(X_test)
y_pred

output:

array([0, 0, 0, 1, 1, 1, 0, 0, 0, 0, 1, 0, 1, 1, 1, 0, 0, 1, 1, 0, 0, 1,
       1, 0, 0, 0, 1, 0, 1, 0, 1, 1, 0, 0, 1, 0, 0, 1, 1, 1, 0, 1, 0, 0,
       0, 0, 1, 1, 1, 1, 1, 1, 0, 0, 1, 0, 1, 1, 0, 1, 0, 1, 1, 0, 1, 0,
       0, 0, 0, 1, 0, 0, 1, 1, 0, 0, 1, 1, 0, 0, 1, 1, 1, 0, 1, 1, 1, 0,
       1, 1, 1, 0, 0, 0, 0, 1, 0, 1, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, 1, 1,
       1, 0, 0, 1, 1, 0, 0, 0, 0, 1, 1, 1, 0, 0, 0], dtype=int64)

from sklearn.metrics import accuracy_score
print(accuracy_score(y_test, y_pred))

output:

0.904

Let's compare this to the accuracy of a single decision tree:

tree_clf = DecisionTreeClassifier(random_state=42)
tree_clf.fit(X_train, y_train)
y_pred_tree = tree_clf.predict(X_test)
print(accuracy_score(y_test, y_pred_tree))

output:

0.856

Let's compare the decision boundaries of the single decision tree and the ensemble of decision trees:

from matplotlib.colors import ListedColormap
def plot_decision_boundary(clf, X, y, axes=[-1.5, 2.45, -1, 1.5], alpha=0.5, contour=True):
    x1s = np.linspace(axes[0], axes[1], 100)
    x2s = np.linspace(axes[2], axes[3], 100)
    x1, x2 = np.meshgrid(x1s, x2s)
    X_new = np.c_[x1.ravel(), x2.ravel()]
    y_pred = clf.predict(X_new).reshape(x1.shape)
    custom_cmap = ListedColormap(['#fafab0','#9898ff','#a0faa0'])
    plt.contourf(x1, x2, y_pred, alpha=0.3, cmap=custom_cmap)
    if contour:
        custom_cmap2 = ListedColormap(['#7d7d58','#4c4c7f','#507d50'])
        plt.contour(x1, x2, y_pred, cmap=custom_cmap2, alpha=0.8)
    plt.plot(X[:, 0][y==0], X[:, 1][y==0], "yo", alpha=alpha)
    plt.plot(X[:, 0][y==1], X[:, 1][y==1], "bs", alpha=alpha)
    plt.axis(axes)
    plt.xlabel(r"$x_1$", fontsize=18)
    plt.ylabel(r"$x_2$", fontsize=18, rotation=0)

fix, axes = plt.subplots(ncols=2, figsize=(10,4), sharey=True)
plt.sca(axes[0])
plot_decision_boundary(tree_clf, X, y)
plt.title("Decision Tree", fontsize=14)
plt.sca(axes[1])
plot_decision_boundary(bag_clf, X, y)
plt.title("Decision Trees with Bagging", fontsize=14)
plt.ylabel("")
save_fig("decision_tree_without_and_with_bagging_plot")
plt.show()

output: