评估机器学习模型好坏的时候,常常需要观察学习曲线的变化,以及最后的分类结果(二分类)的效果。一个好的可视化结果可以加强对模型的理解程度。下面总结一下决策边界和学习曲线的绘制代码,以便加强印象,方便查看。

# 决策边界的绘制
import numpy as np import matplotlib.pyplot as plt import matplotlib as mpl
def plot_decision_boundary(clf, X, y, num_row = 100, num_col = 100): """
绘制决策边界的核心代码 :param clf: 分类器, 即使用的模型 :param X: 输入的数据X :param y: 真实的分类结果y :param
num_row: 绘制决策边界时,行数据生成的个数 :param num_col: 列数据生成的个数 """ clf.fit(X, y) sigma = 1
# 防止数据在图形的边上而加上的一个偏移量,设定一个较小的值即可 x1_min, x1_max = np.min(X[:, 0])-sigma,
np.max(X[:, 0])+sigma x2_min, x2_max = np.min(X[:, 1])-sigma, np.max(X[:,
1])+sigma t1 = np.linspace(x1_min, x1_max, num_row) t2 = np.linspace(x2_min,
x2_max, num_col) x1, x2 = np.meshgrid(t1, t2) x_test = np.stack((x1, x2),
axis=1) # 设置使用的颜色colors, 这里假设最后的结果是三个类别 cm_dark =
mpl.colors.ListedColormap(['#FFA0A0', '#A0FFA0', '#A0A0FF']) cm_light =
mpl.colors.ListedColormap(['r', 'g', 'b']) y_hat = clf.predict(x_test) y_hat =
y_hat.reshape(x1.shape) plt.pcolormesh(x1, x2, y_hat, cmap=cm_dark) # 绘制底色
plt.scatter(X[:, 0], X[:, 1], y, edgecolors='k', cmap=cm_light) # 绘制数据的颜色
plt.xlabel('x label') plt.ylabel('y label') plt.title('decision-boundary')
plt.xlim(x1_min, x1_max) plt.ylim(x2_min, x2_max) plt.grid() plt.show()
# 学习曲线的绘制
from sklearn.model_selection import learning_curve import numpy as np import
matplotlib.pyplot as plt def plot_learning_curve(estimator, X, y, n_jobs=1, cv
= 5, train_size = np.linspace(0.02, 1, 50), verbose=0): """
绘制学习曲线,评估训练和测试结果,方便对模型进行评估 :param estimator: 使用的模型 """ train_sizes,
train_scores, test_scores = learning_curve(estimator=estimator, X=X, y=y,
cv=cv, n_jobs=n_jobs, train_sizes=train_size, scoring='accuracy',
verbose=verbose) # 从
http://scikit-learn.org/stable/modules/model_evaluation.html#scoring-parameter
选择适合的scoring train_score_mean = train_scores.mean(axis=1) train_size_std =
train_scores.std(axis=1) test_score_mean = np.mean(test_scores, axis=1)
test_score_std = np.std(test_scores, axis=1) plt.figure()
plt.fill_between(train_sizes, train_score_mean+train_size_std,
train_score_mean-train_size_std, color='blue', alpha=0.1)
plt.fill_between(train_sizes, test_score_mean+test_score_std,
test_score_mean-test_score_std, color='red', alpha=0.1) plt.plot(train_sizes,
train_score_mean, 'o-', color='blue', label='training score')
plt.plot(train_sizes, test_score_mean, 'o-', color='red', label='testing
score') plt.xlabel('xlabel') plt.ylabel('ylabel') plt.title('learning_curve')
plt.legend(loc='best') plt.grid() plt.show()
# 说明:以上部分代码可能来自网络,如有侵权,请联系删除