def D_N(empiric_dist, space, ex=Lab1.Ex1()): d_n = [] for i in range(len(empiric_dist)): d_n.append(abs(empiric_dist[i] - ex.F(space[i]))) return max(d_n)
# F_real = [Lab1.Ex1().F(x) for x in space] # for nr_of_samples in n: # # F_empiric = empiric_distribution(randoms[0:nr_of_samples], space) # # D.append(D_N(F_empiric,space)) # # pyplot.plot(n,D,'r*') # # pyplot.xlabel('N') # pyplot.ylabel('D(N)') # pyplot.plot(space, F_real, 'o') # pyplot.plot(space, F_empiric, '*') nr_of_samples = 500 keys = [random.uniform(0, 1) for i in range(nr_of_samples)] randoms = Lab1.Generator.generate_random_numbers(keys, Lab1.Ex1()) F_empiric = empiric_distribution(randoms, space) fig = pyplot.figure() ax1 = fig.add_subplot(211) ax2 = fig.add_subplot(212) ax1.title.set_text(r'Dystrybuanta empiryczna') ax2.title.set_text(r'Estymator wariancji') pyplot.subplot(2, 1, 1) pyplot.plot(space, F_empiric) pyplot.subplot(2, 1, 2) pyplot.plot(space, empiric_variance(F_empiric, Lab1.Ex1().F, space)) pyplot.show()