:Decision Tree classifier

Create a DecisionTreeClassifier instance with depth of 2:

clf = DecisionTreeClassifier(criterion='entropy',max_depth=2)

clf = clf.fit(X_train,y_train)

Confusion_matrix : (by using the builtin scikit-learn class)

cm = confusion_matrix(y, tr_pred)

#normalised confusion matrix

cm_normalised = cm/cm.sum(axis=1)[:, np.newaxis]

Visualise the normalised confusion matrix with heatmap:

def plot_confusion_matrix(cm, classes=None, title='Confusion matrix'):
    """Plots a confusion matrix."""
    if classes is not None:
        sns.heatmap(cm, xticklabels=classes, yticklabels=classes, vmin=0., vmax=1., annot=True)
    else:
        sns.heatmap(cm, vmin=0., vmax=1.)
    plt.title(title)
    plt.ylabel('True label')
    plt.xlabel('Predicted label')

plt.figure()
plot_confusion_matrix(cm_norm, classes=clf.classes_)

 Random decision forest

rdf_clf = RandomForestClassifier(criterion='entropy',n_estimators=100)
rdf_clf.fit(X_train,y_train)