45 lines
2.2 KiB
Python
45 lines
2.2 KiB
Python
import numpy as np
|
|
from matplotlib import pyplot as plt
|
|
from matplotlib.colors import ListedColormap
|
|
from sklearn.model_selection import train_test_split
|
|
from sklearn.pipeline import make_pipeline
|
|
from sklearn.preprocessing import PolynomialFeatures
|
|
from sklearn.datasets import make_circles
|
|
from sklearn.linear_model import LinearRegression, Ridge
|
|
|
|
rs = np.random.RandomState(50)
|
|
X, y = make_circles(noise=0.2, factor=0.5, random_state=rs) # генерация данных
|
|
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.4, random_state=42)
|
|
|
|
# создание моделей
|
|
linear_regression = LinearRegression()
|
|
polynomial_regression = make_pipeline(PolynomialFeatures(degree=5), LinearRegression())
|
|
ridge_polynomial_regression = make_pipeline(PolynomialFeatures(degree=5), Ridge(alpha=1.0))
|
|
models = [("Линейная регрессия", linear_regression),
|
|
("Полиномиальная регрессия", polynomial_regression),
|
|
("Гребневая полиномиальная регрессия", ridge_polynomial_regression)]
|
|
|
|
# тренируем модель
|
|
for name, model in models:
|
|
model.fit(X_train, y_train) # обучение модели
|
|
y_predict = model.predict(X_test) # предсказание
|
|
score = model.score(X_train, y_train) # оценка качества
|
|
print(name + ': качество модели = ' + str(score))
|
|
|
|
# построение графиков
|
|
cm = plt.cm.RdBu
|
|
cm_bright = ListedColormap(['#FF0000', '#0000FF'])
|
|
for i, (name, model) in enumerate(models):
|
|
current_subplot = plt.subplot(1, 3, i + 1)
|
|
h = .02 # шаг регулярной сетки
|
|
x0_min, x0_max = X[:, 0].min() - .5, X[:, 0].max() + .5
|
|
x1_min, x1_max = X[:, 1].min() - .5, X[:, 1].max() + .5
|
|
xx0, xx1 = np.meshgrid(np.arange(x0_min, x0_max, h), np.arange(x1_min, x1_max, h))
|
|
Z = model.predict(np.c_[xx0.ravel(), xx1.ravel()])
|
|
Z = Z.reshape(xx0.shape)
|
|
current_subplot.contourf(xx0, xx1, Z, cmap=cm, alpha=.8)
|
|
current_subplot.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap=cm_bright)
|
|
current_subplot.scatter(X_test[:, 0], X_test[:, 1], c=y_test, cmap=cm_bright, alpha=0.4)
|
|
plt.title(name)
|
|
|
|
plt.show() |