How can I add a scatterplot and the line of best fit to my Linear Regression program using Matplotlib

from matplotlib import pyplot as plt

data = pd.read_csv("student-mat.csv", sep=";")

data = data[["G1", "G2", "G3", "studytime", "failures", "absences"]]

predict = "G3"

X = np.array(data.drop([predict], 1))
y = np.array(data[predict])

x_train, x_test, y_train, y_test = sklearn.model_selection.train_test_split(X, y, test_size = 0.1)

linear = linear_model.LinearRegression()

linear.fit(x_train, y_train)
accuracy = linear.score(x_test, y_test)
print(accuracy*100)

print(‘Coefficient: n’, linear.coef_)
print(‘Intercept: n’, linear.intercept_)

predictions = linear.predict(x_test)

for x in range(len(predictions)):
print(predictions[x], x_test[x], y_test[x])

Source: Python Questions

LEAVE A COMMENT