import pandas as pd
import numpy as np
from matplotlib import pyplot as plt
%matplotlib inline

from sklearn.datasets import load_boston
from sklearn.utils import shuffle

dataset = load_boston()
df = shuffle(pd.DataFrame(dataset.data))
y = dataset.target

from sklearn import preprocessing
min_max_scaler = preprocessing.MinMaxScaler()
x_scaled = min_max_scaler.fit_transform(df.values)
df = pd.DataFrame(x_scaled)

from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(df, y, test_size=0.1, random_state=0)

from sklearn.linear_model import Ridge
from sklearn.metrics import mean_squared_error as MSE

alphas = np.linspace(0, 1, 100)
mses = list()

for alpha in alphas:
    model = Ridge(alpha=alpha)
    model.fit(X_train, y_train)
    mse = MSE(y_test, model.predict(X_test))
    mses.append(mse)

plt.figure()
plt.plot(alphas, mses)