Лабораторная 2 / Вариант 3 / Lab2

import matplotlib.pyplot as plt
import numpy as np


class BigFrogRandom:
    def __init__(self, r, M, seed=1):
        self.r = r
        self.M = M
        self.mod = 2 ** r
        self.A = seed % self.mod

    def next(self):
        self.A = (self.A * self.M) % self.mod

        return self.A / self.mod


class RandomValue:
    def __init__(self, xj, pj):
        self.Pj = [sum(pj[:i+1]) for i in range(len(pj))]
        self.xj = xj
        self.pj = pj
        self.z = BigFrogRandom(32, 3**12)

    def next(self):
        z = self.z.next()
        for p in range(len(self.Pj)):
            if z <= self.Pj[p]:
                return self.xj[p]


x = np.array([-93.3, -73.2, -70.2, -55.6, -20.3, 38.8, 49.8])
p = [0.099, 0.061, 0.160, 0.159, 0.171, 0.176, 0.174]
rv = RandomValue(x, p)
RV = []
N = 500
for i in range(N):
    RV.append(rv.next())
print("Первые 30 значений:")
for i in range(30):
    print(RV[i])


M = sum(RV) / N
D = sum([x ** 2 for x in RV]) / N - M ** 2
print(f"Эмпирические: M = {M:.5f}, D = {D:.5f}")

M_exp = sum([p[j] * x[j] for j in range(len(p))])
D_exp = sum([p[j] * x[j] ** 2 for j in range(len(p))]) - M_exp ** 2
print(f"Теоретические: M = {M_exp:.5f}, D = {D_exp:.5f}")


edges = (x[:-1] + x[1:]) / 2
bins = np.concatenate(
    ([x[0] - (edges[0] - x[0])], edges, [x[-1] + (x[-1] - edges[-1])]))
plt.hist([RV, x], bins=14,
         weights=[np.ones_like(RV) / len(RV), np.ones_like(x) * p],
         label=['Эмпирическое', 'Теоретическое'])

plt.legend(loc='upper left')
plt.savefig("Veronika/ms2.mono.svg")
plt.show()