機器學習——CART迴歸樹

一. 迴歸樹

注意：CART做分類時代價函數是基尼指數，做迴歸時代價函數時均方差函數

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

# Data set
x = np.array(list(range(1, 11))).reshape(-1, 1)
y = np.array([5.56, 5.70, 5.91, 6.40, 6.80, 7.05, 8.90, 8.70, 9.00, 9.05]).ravel()

# Fit regression model
model1 = DecisionTreeRegressor(max_depth=1)
model2 = DecisionTreeRegressor(max_depth=3)
model3 = linear_model.LinearRegression()
model1.fit(x, y)
model2.fit(x, y)
model3.fit(x, y)

# Predict
X_test = np.arange(0.0, 10.0, 0.01)[:, np.newaxis]
y_1 = model1.predict(X_test)
y_2 = model2.predict(X_test)
y_3 = model3.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=1", linewidth=2)
plt.plot(X_test, y_2, color="yellowgreen", label="max_depth=3", linewidth=2)
plt.plot(X_test, y_3, color='red', label='liner regression', linewidth=2)
plt.xlabel("data")
plt.ylabel("target")
plt.title("Decision Tree Regression")
plt.legend()
plt.show()