import sklearn.datasets
import sklearn.linear_model
import sklearn.model_selection
import matplotlib.pyplot as plt
import pandas as pd
diabetes = sklearn.datasets.load_diabetes()
df = pd.DataFrame(diabetes.data, columns=diabetes.feature_names)
df
diabetes.target
x = diabetes.data
y = diabetes.target
x_train, x_test, y_train, y_test = sklearn.model_selection.train_test_split(x, y, test_size=0.2)
lr = sklearn.linear_model.LinearRegression()
lr.fit(x_train, y_train)
lr.score(x_test, y_test)
predicted = lr.predict(x)
fig, ax = plt.subplots()
ax.scatter(y, predicted, edgecolors=(0, 0, 0))
ax.plot([y.min(), y.max()], [y.min(), y.max()], “k–“, lw=4)
ax.set_xlabel(“Measured”)
ax.set_ylabel(“Predicted”)
plt.show()