Overfitting और इसे कैसे पहचानें

import numpy as np
import matplotlib.pyplot as plt

rng = np.random.default_rng(3)
def truth(x):
    return np.sin(x)                         # the hidden pattern

x_train = np.sort(rng.uniform(0, 6, 12))
y_train = truth(x_train) + rng.normal(0, 0.25, 12)
x_new = rng.uniform(x_train.min(), x_train.max(), 100)   # new points inside the same range
y_new = truth(x_new) + rng.normal(0, 0.25, 100)

grid = np.linspace(0, 6, 200)
plt.scatter(x_train, y_train, color="black", label="training points")
for degree in [1, 3, 9]:
    coefs = np.polyfit(x_train, y_train, degree)
    train_err = np.mean(np.abs(np.polyval(coefs, x_train) - y_train))
    new_err = np.mean(np.abs(np.polyval(coefs, x_new) - y_new))
    print("degree", degree, " training error", round(train_err, 3), " new-data error", round(new_err, 3))
    plt.plot(grid, np.polyval(coefs, grid), label="degree " + str(degree))
plt.ylim(-2, 2); plt.legend()