#!/usr/bin/env python3
# Source: t1-learning-theory.html
import numpy as np

rng = np.random.default_rng(0)
f = lambda x: np.sin(2 * np.pi * x)          # true function
sigma, n, trials = 0.3, 30, 500
x_test = np.linspace(0.05, 0.95, 200)

for degree in [1, 3, 5, 7]:
    preds = np.empty((trials, x_test.size))
    for t in range(trials):
        x = rng.uniform(0, 1, n)
        y = f(x) + sigma * rng.standard_normal(n)
        coef = np.polyfit(x, y, degree)
        preds[t] = np.polyval(coef, x_test)
    mean_pred = preds.mean(axis=0)
    bias2 = np.mean((mean_pred - f(x_test)) ** 2)
    var = np.mean(preds.var(axis=0))
    print(f"degree {degree:2d}: bias^2={bias2:.3f}  var={var:.3f}  "
          f"expected test MSE={bias2 + var + sigma**2:.3f}")

# degree  1: bias^2=0.152  var=0.021  expected test MSE=0.263
# degree  3: bias^2=0.003  var=0.013  expected test MSE=0.106
# degree  5: bias^2=0.000  var=0.026  expected test MSE=0.117
# degree  7: bias^2=0.001  var=0.380  expected test MSE=0.471
