def scale(data_matrix):
num_rows, num_cols = shape(data_matrix)
means = [mean(get_column(data_matrix, j)) for j in range(num_cols)]
stdevs = [
standard_deviation(get_column(data_matrix, j)) for j in range(num_cols)
]
return means, stdevs
def least_squares_fit(x, y):
"""given training values for x and y,
find the least-squares values of alpha and beta"""
beta = correlation(x, y) * standard_deviation(y) / standard_deviation(x)
alpha = mean(y) - beta * mean(x)
return alpha, beta
[200 + random.random() for _ in range(50)])
print "bootstrap_statistic(close_to_100, median, 100):"
print bootstrap_statistic(close_to_100, median, 100)
print "bootstrap_statistic(far_from_100, median, 100):"
print bootstrap_statistic(far_from_100, median, 100)
print
random.seed(0) # so that you get the same results as me
bootstrap_betas = bootstrap_statistic(zip(x, daily_minutes_good),
estimate_sample_beta,
100)
bootstrap_standard_errors = [
standard_deviation([beta[i] for beta in bootstrap_betas])
for i in range(4)]
print "bootstrap standard errors", bootstrap_standard_errors
print
print "p_value(30.6143, 1.174)", p_value(30.63, 1.174)
print "p_value(0.972, 0.079)", p_value(0.972, 0.079)
print "p_value(-1.868, 0.131)", p_value(-1.868, 0.131)
print "p_value(0.911, 0.990)", p_value(0.911, 0.990)
print
print "regularization"
random.seed(0)
for alpha in [0.0, 0.01, 0.1, 1, 10]: