Decision Tree (Classifier)

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36

import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets import make_classification
from sklearn.tree import DecisionTreeClassifier, plot_tree

n_classes = 2
X, y = make_classification(
    n_samples=100,
    n_features=2,
    n_redundant=0,
    n_informative=2,
    random_state=2,
    n_classes=n_classes,
    n_clusters_per_class=1,
)

clf = DecisionTreeClassifier(criterion="gini", random_state=0).fit(X, y)

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.arange(x_min, x_max, 0.1),
    np.arange(y_min, y_max, 0.1),
)
Z = clf.predict(np.c_[xx.ravel(), yy.ravel()]).reshape(xx.shape)

plt.figure(figsize=(8, 8))
plt.contourf(xx, yy, Z, cmap=plt.cm.Pastel1, alpha=0.6)
plt.xlabel("x1")
plt.ylabel("x2")
for i, color, label_name in zip(range(n_classes), ["r", "b"], ["A", "B"]):
    idx = np.where(y == i)
    plt.scatter(X[idx, 0], X[idx, 1], c=color, label=label_name, edgecolor="k")
plt.legend()
plt.title("Decision regions created by a tree")
plt.show()

1
2
3

plt.figure(figsize=(12, 12))
plot_tree(clf, filled=True, feature_names=["x1", "x2"], class_names=["A", "B"])
plt.show()