python_学习曲线_观察不同规模训练集对指标的影响

学习曲线
观察不同规模训练集对指标的影响

# 라이브러리를 임포트합니다.
import numpy as np
import matplotlib.pyplot as plt
from sklearn.ensemble import RandomForestClassifier
from sklearn.datasets import load_digits
from sklearn.model_selection import learning_curve

# 加载数据
digits = load_digits()

# 创建特征矩阵和目标向量
features, target = digits.data, digits.target

# 为不同规模训练集进行交叉验证，计算训练和测试得分
train_sizes, train_scores, test_scores = learning_curve(# 分类器
                                                        RandomForestClassifier(),
                                                        # 特征矩阵
                                                        features,
                                                        # 目标向量
                                                        target,
                                                        # 折数
                                                        cv=10,
                                                        # 性能指标
                                                        scoring='accuracy',
                                                        # 使用所有CPU
                                                        n_jobs=-1,
                                                        # 50个训练集的规模
                                                       train_sizes=np.linspace(
                                                       0.01,
                                                       1.0,
                                                       50))

# 计算训练集得分平均值和标准差
train_mean = np.mean(train_scores, axis=1)
train_std = np.std(train_scores, axis=1)

# 计算测试集得分平均值和标准差
test_mean = np.mean(test_scores, axis=1)
test_std = np.std(test_scores, axis=1)

# 划线
plt.plot(train_sizes, train_mean, '--', color="#111111",  label="Training score")
plt.plot(train_sizes, test_mean, color="#111111", label="Cross-validation score")

# 画带状图
# fill_between 填充两个函数之间的区域
# 填充
# 两个函数之间的区域用黄色填充
plt.fill_between(train_sizes, train_mean - train_std,
                 train_mean + train_std, color="#DDDDDD")
plt.fill_between(train_sizes, test_mean - test_std,
                 test_mean + test_std, color="#DDDDDD")

# 创建图
plt.title("Learning Curve")
plt.xlabel("Training Set Size"), plt.ylabel("Accuracy Score"),
plt.legend(loc="best")
plt.tight_layout()
plt.show()