参考：作者的Jupyter Notebook
Chapter 6 – Decision Trees
- 保存图片
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21from __future__ import division, print_function, unicode_literals
import numpy as np
import matplotlib as mpl
import matplotlib.pyplot as plt
import os
np.random.seed(42)
mpl.rc('axes', labelsize=14)
mpl.rc('xtick', labelsize=12)
mpl.rc('ytick', labelsize=12)
# Where to save the figures
PROJECT_ROOT_DIR = "images"
CHAPTER_ID = "decision_trees"
def save_fig(fig_id, tight_layout=True):
path = os.path.join(PROJECT_ROOT_DIR, CHAPTER_ID, fig_id + ".png")
print("Saving figure", fig_id)
if tight_layout:
plt.tight_layout()
plt.savefig(path, format='png', dpi=600)
决策树训练和可视化
要了解决策树，让我们先构建一个决策树，看看它是如何做出预测的。下面的代码在鸢尾花数据集（见第4章）上训练了一个DecisionTreeClassifier：
1
2
3
4
5
6
7
8
9
10from sklearn.datasets import load_iris
from sklearn.tree import DecisionTreeClassifier
iris = load_iris()
X = iris.data[:, 2:] # petal length and width
y = iris.target
tree_clf = DecisionTreeClassifier(max_depth=2, random_state=42)
tree_clf.fit(X, y)
#print(tree_clf.fit(X, y))要将决策树可视化，首先，使用export_graphviz（）方法输出一个图形定义文件，命名为iris_tree.dot：
1
2
3
4
5
6
7
8
9
10
11
12from sklearn.tree import export_graphviz
export_graphviz(
tree_clf,
out_file=image_path("iris_tree.dot"),
feature_names=iris.feature_names[2:],
class_names=iris.target_names,
rounded=True,
filled=True
)
#下面这行命令将.dot文件转换为.png图像文件：
#$ dot -Tpng iris_tree.dot -o iris_tree.png
做出预测
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
37
38
39
from matplotlib.colors import ListedColormap
def plot_decision_boundary(clf, X, y, axes=[0, 7.5, 0, 3], iris=True, legend=False, plot_training=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 not iris:
custom_cmap2 = ListedColormap(['#7d7d58','#4c4c7f','#507d50'])
plt.contour(x1, x2, y_pred, cmap=custom_cmap2, alpha=0.8)
if plot_training:
plt.plot(X[:, 0][y==0], X[:, 1][y==0], "yo", label="Iris-Setosa")
plt.plot(X[:, 0][y==1], X[:, 1][y==1], "bs", label="Iris-Versicolor")
plt.plot(X[:, 0][y==2], X[:, 1][y==2], "g^", label="Iris-Virginica")
plt.axis(axes)
if iris:
plt.xlabel("Petal length", fontsize=14)
plt.ylabel("Petal width", fontsize=14)
else:
plt.xlabel(r"$x_1$", fontsize=18)
plt.ylabel(r"$x_2$", fontsize=18, rotation=0)
if legend:
plt.legend(loc="lower right", fontsize=14)
plt.figure(figsize=(8, 4))
plot_decision_boundary(tree_clf, X, y)
plt.plot([2.45, 2.45], [0, 3], "k-", linewidth=2)
plt.plot([2.45, 7.5], [1.75, 1.75], "k--", linewidth=2)
plt.plot([4.95, 4.95], [0, 1.75], "k:", linewidth=2)
plt.plot([4.85, 4.85], [1.75, 3], "k:", linewidth=2)
plt.text(1.40, 1.0, "Depth=0", fontsize=15)
plt.text(3.2, 1.80, "Depth=1", fontsize=13)
plt.text(4.05, 0.5, "(Depth=2)", fontsize=11)
save_fig("decision_tree_decision_boundaries_plot")
plt.show()
估算类别概率
- 决策树同样可以估算某个实例属于特定类别k的概率
1
2#print(tree_clf.predict_proba([[5, 1.5]]))
#print(tree_clf.predict([[5, 1.5]]))0
CART训练算法
Scikit-Learn使用的是分类与回归树（Classification And Regression Tree，简称CART）算法来训练决策树（也叫作“生长”树）。
计算复杂度
基尼不纯度还是信息熵
正则化超参数
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
from sklearn.datasets import make_moons
Xm, ym = make_moons(n_samples=100, noise=0.25, random_state=53)
deep_tree_clf1 = DecisionTreeClassifier(random_state=42)
deep_tree_clf2 = DecisionTreeClassifier(min_samples_leaf=4, random_state=42)
deep_tree_clf1.fit(Xm, ym)
deep_tree_clf2.fit(Xm, ym)
plt.figure(figsize=(11, 4))
plt.subplot(121)
plot_decision_boundary(deep_tree_clf1, Xm, ym, axes=[-1.5, 2.5, -1, 1.5], iris=False)
plt.title("No restrictions", fontsize=16)
plt.subplot(122)
plot_decision_boundary(deep_tree_clf2, Xm, ym, axes=[-1.5, 2.5, -1, 1.5], iris=False)
plt.title("min_samples_leaf = {}".format(deep_tree_clf2.min_samples_leaf), fontsize=14)
save_fig("min_samples_leaf_plot正则化超参数")
plt.show()
左图使用默认参数（即无约束）来训练决策树，右图的决策树应用min_samples_leaf=4进行训练。很明显，左图模型过度拟合，右图的泛化效果更佳。
回归
决策树也可以执行回归任务。我们用Scikit_Learn的DecisionTreeRegressor来构建一个回归树，在一个带噪声的二次数据集上进行训练，其中max_depth=2：
1
2
3
4
5
6
7
8
9
10
11np.random.seed(42)
m = 200
X = np.random.rand(m, 1)
y = 4 * (X - 0.5) ** 2
y = y + np.random.randn(m, 1) / 10
from sklearn.tree import DecisionTreeRegressor
tree_reg = DecisionTreeRegressor(max_depth=2, random_state=42)
tree_reg.fit(X, y)
#print(tree_reg.fit(X, y))两个决策树回归模型的预测对比
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
37
38
39from sklearn.tree import DecisionTreeRegressor
tree_reg1 = DecisionTreeRegressor(random_state=42, max_depth=2)
tree_reg2 = DecisionTreeRegressor(random_state=42, max_depth=3)
tree_reg1.fit(X, y)
tree_reg2.fit(X, y)
def plot_regression_predictions(tree_reg, X, y, axes=[0, 1, -0.2, 1], ylabel="$y$"):
x1 = np.linspace(axes[0], axes[1], 500).reshape(-1, 1)
y_pred = tree_reg.predict(x1)
plt.axis(axes)
plt.xlabel("$x_1$", fontsize=18)
if ylabel:
plt.ylabel(ylabel, fontsize=18, rotation=0)
plt.plot(X, y, "b.")
plt.plot(x1, y_pred, "r.-", linewidth=2, label=r"$\hat{y}$")
plt.figure(figsize=(11, 4))
plt.subplot(121)
plot_regression_predictions(tree_reg1, X, y)
for split, style in ((0.1973, "k-"), (0.0917, "k--"), (0.7718, "k--")):
plt.plot([split, split], [-0.2, 1], style, linewidth=2)
plt.text(0.21, 0.65, "Depth=0", fontsize=15)
plt.text(0.01, 0.2, "Depth=1", fontsize=13)
plt.text(0.65, 0.8, "Depth=1", fontsize=13)
plt.legend(loc="upper center", fontsize=18)
plt.title("max_depth=2", fontsize=14)
plt.subplot(122)
plot_regression_predictions(tree_reg2, X, y, ylabel=None)
for split, style in ((0.1973, "k-"), (0.0917, "k--"), (0.7718, "k--")):
plt.plot([split, split], [-0.2, 1], style, linewidth=2)
for split in (0.0458, 0.1298, 0.2873, 0.9040):
plt.plot([split, split], [-0.2, 1], "k:", linewidth=1)
plt.text(0.3, 0.5, "Depth=2", fontsize=13)
plt.title("max_depth=3", fontsize=14)
save_fig("tree_regression_plot两个决策树回归模型的预测对比")
plt.show()
不稳定性
对数据旋转敏感
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21np.random.seed(6)
Xs = np.random.rand(100, 2) - 0.5
ys = (Xs[:, 0] > 0).astype(np.float32) * 2
angle = np.pi / 4
rotation_matrix = np.array([[np.cos(angle), -np.sin(angle)], [np.sin(angle), np.cos(angle)]])
Xsr = Xs.dot(rotation_matrix)
tree_clf_s = DecisionTreeClassifier(random_state=42)
tree_clf_s.fit(Xs, ys)
tree_clf_sr = DecisionTreeClassifier(random_state=42)
tree_clf_sr.fit(Xsr, ys)
plt.figure(figsize=(11, 4))
plt.subplot(121)
plot_decision_boundary(tree_clf_s, Xs, ys, axes=[-0.7, 0.7, -0.7, 0.7], iris=False)
plt.subplot(122)
plot_decision_boundary(tree_clf_sr, Xsr, ys, axes=[-0.7, 0.7, -0.7, 0.7], iris=False)
save_fig("sensitivity_to_rotation_plot对数据旋转敏感")
plt.show()对训练集细节敏感
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18X[(X[:, 1]==X[:, 1][y==1].max()) & (y==1)] # widest Iris-Versicolor flower
not_widest_versicolor = (X[:, 1]!=1.8) | (y==2)
X_tweaked = X[not_widest_versicolor]
y_tweaked = y[not_widest_versicolor]
tree_clf_tweaked = DecisionTreeClassifier(max_depth=2, random_state=40)
tree_clf_tweaked.fit(X_tweaked, y_tweaked)
plt.figure(figsize=(8, 4))
plot_decision_boundary(tree_clf_tweaked, X_tweaked, y_tweaked, legend=False)
plt.plot([0, 7.5], [0.8, 0.8], "k-", linewidth=2)
plt.plot([0, 7.5], [1.75, 1.75], "k--", linewidth=2)
plt.text(1.0, 0.9, "Depth=0", fontsize=15)
plt.text(1.0, 1.80, "Depth=1", fontsize=13)
save_fig("decision_tree_inst ability_plot对训练集细节敏感")
plt.show()