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()