Python 中的模型诊断技术：从学习曲线到残差分析

from sklearn.datasets import load_boston
from sklearn.tree import DecisionTreeRegressor
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error
import matplotlib.pyplot as plt

data = load_boston()
X_train, X_test, y_train, y_test = train_test_split(data.data, data.target)

train_errors, test_errors = [], []
for i in range(1, len(X_train)):
    model = DecisionTreeRegressor(max_depth=i)
    model.fit(X_train[:i], y_train[:i])
    y_train_pred = model.predict(X_train[:i])
    y_test_pred = model.predict(X_test)
    train_errors.append(mean_squared_error(y_train[:i], y_train_pred))
    test_errors.append(mean_squared_error(y_test, y_test_pred))

plt.plot(range(1, len(X_train)), train_errors, label='Train')
plt.plot(range(1, len(X_train)), test_errors, label='Test')
plt.xlabel('Training set size')
plt.ylabel(' MSE')
plt.legend()
plt.show()

from sklearn.datasets import load_boston
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split
import matplotlib.pyplot as plt

data = load_boston()
X_train, X_test, y_train, y_test = train_test_split(data.data, data.target)

model = LinearRegression()
model.fit(X_train, y_train)
y_train_pred = model.predict(X_train)
y_test_pred = model.predict(X_test)
train_residuals = y_train - y_train_pred
test_residuals = y_test - y_test_pred

plt.scatter(y_train_pred, train_residuals, c='blue', marker='o', label='Training data')
plt.scatter(y_test_pred, test_residuals, c='lightgreen', marker='s', label='Testing data')
plt.xlabel('Predicted values')
plt.ylabel('Residuals')
plt.legend()
plt.title('Linear regression residuals')
plt.show()