import pandas as pd
from sklearn.datasets import load_boston

boston = load_boston()
df = pd.DataFrame(boston['data'], columns=boston['feature_names'])
df.head()

dfX = df[['RM', 'AGE', 'DIS', 'LSTAT']]
X = dfX.values
y = boston['target']



x = X[:, 0].reshape(-1, 1)

plt.plot(x, y, 'o')

import numpy as np
from sklearn.linear_model import LinearRegression

reg = LinearRegression()

reg.fit(x, y)

y_hat = reg.predict(x)

reg.coef_, reg.intercept_

model_x = np.arange(3, 10, 0.1).reshape(-1, 1)
model_y = reg.predict(model_x)

plt.plot(x, y, 'o')
plt.plot(model_x, model_y)

from sklearn.metrics import r2_score

r2_score(y, y_hat)