困扰ing.qaq
代码如下： 求帮助
predictions = data.values[:, 5]
features = data.values[:, 0:5]
from sklearn.model_selection import train_test_split #清洗分割数据
x_train, x_test, y_train, y_test = train_test_split(features, predictions, test_size=0.2, random_state=50)
import matplotlib.pyplot as plt
from sklearn.model_selection import ShuffleSplit, learning_curve
from sklearn.tree import DecisionTreeRegressor
def ModelLearningGraphMetrics(x, y):
cv = ShuffleSplit(n_splits=10, test_size=0.2, random_state=0)
train_sizes = np.rint(np.linspace(1, x.shape[0]*0.8-1, 18)).astype(int) # 返回数据
fig = plt.figure(figsize=(10, 7))
for k, depth in enumerate([1, 2, 6, 10]):
regressor = DecisionTreeRegressor(max_depth=depth)
sizes, train_scores, test_scores = learning_curve(regressor, x, y,
train_sizes =train_sizes, cv=cv, scoring=None)
train_std = np.std(train_scores, axis=1)
test_std = np.std(test_scores, axis=1)
train_mean = np.mean(train_scores, axis=1)
test_mean = np.mean(test_scores, axis=1)
ax = fig.add_subplot(2, 2, k+1)
ax.plot(sizes, train_mean, 'o-', color='r', label='Training Score')
ax.plot(sizes, test_mean, 'o-', color='g', label='Testing Score')
ax.fill_between(sizes, train_mean-train_std, train_mean+train_std, alpha=0.15, color='r')
ax.fill_between(sizes, test_mean - test_std, test_mean + test_std, alpha=0.3, color='g')
ax.set_title('max_depth={}'.format(depth))
ax.set_xlabel('Number of training points')
ax.set_ylabel('score')
ax.set_xlim([0, x.shape[0]*0.5])
ax.set_ylim([-0.05, 1.05])
ax.legend(bbox_to_anchor=(1.05, 2.05), loc='upper center', borderaxespad=0.)
fig.suptitle('performance', fontsize=16, y=1.03)
fig.tight_layout()
fig.show()
ModelLearningGraphMetrics(features, predictions)
```