机器学习算法22 决策树到集成学习思想(07 决策树算法实列：代码回归树，决策树深度探索 )

import numpy as np
from sklearn.tree import DecisionTreeRegressor
import matplotlib.pyplot as plt


N = 100
x = np.random.rand(N) * 6 - 3
y = np.sin(x) + np.random.rand(N) * 0.05
print(y)

x = x.reshape(-1, 1)
print(x)


dt_reg = DecisionTreeRegressor(criterion='mse', max_depth=3)
dt_reg.fit(x, y)

x_test = np.linspace(-3, 3, 50).reshape(-1, 1)
y_hat = dt_reg.predict(x_test)

plt.plot(x, y, "y*", label="actual")
plt.plot(x_test, y_hat, "b-", linewidth=2, label="predict")
plt.legend(loc="upper left")
plt.grid()
plt.show()
# plt.savefig("./temp_decision_tree_regressor")


# 比较不同深度的决策树
depth = [2, 4, 6, 8, 10]
color = 'rgbmy'
dt_reg = DecisionTreeRegressor()
plt.plot(x, y, "ko", label="actual")
x_test = np.linspace(-3, 3, 50).reshape(-1, 1)
for d, c in zip(depth, color):
    dt_reg.set_params(max_depth=d)
    dt_reg.fit(x, y)
    y_hat = dt_reg.predict(x_test)
    plt.plot(x_test, y_hat, '-', color=c, linewidth=2, label="depth=%d" % d)
plt.legend(loc="upper left")
plt.grid(b=True)
plt.show()
# plt.savefig("./temp_compare_decision_tree_depth")

举例2：

决策树用于拟合带有噪声观察的正弦曲线。结果，它学习了近似正弦曲线的局部线性回归。

我们可以看到，如果树的最大深度（由 max_depth参数控制）设置得太高，决策树会学习到训练数据的过细细节并从噪声中学习，即它们过拟合。

# Import the necessary modules and libraries
import numpy as np
from sklearn.tree import DecisionTreeRegressor
import matplotlib.pyplot as plt

# Create a random dataset
rng = np.random.RandomState(1)
X = np.sort(5 * rng.rand(80, 1), axis=0)
y = np.sin(X).ravel()
y[::5] += 3 * (0.5 - rng.rand(16))

# Fit regression model
regr_1 = DecisionTreeRegressor(max_depth=2)
regr_2 = DecisionTreeRegressor(max_depth=5)
regr_1.fit(X, y)
regr_2.fit(X, y)

# Predict
X_test = np.arange(0.0, 5.0, 0.01)[:, np.newaxis]
y_1 = regr_1.predict(X_test)
y_2 = regr_2.predict(X_test)

# Plot the results
plt.figure()
plt.scatter(X, y, s=20, edgecolor="black", c="darkorange", label="data")
plt.plot(X_test, y_1, color="cornflowerblue", label="max_depth=2", linewidth=2)
plt.plot(X_test, y_2, color="yellowgreen", label="max_depth=5", linewidth=2)
plt.xlabel("data")
plt.ylabel("target")
plt.title("Decision Tree Regression")
plt.legend()
plt.show()