def get_correl_coef(sample_density, sample_elastic):
import lab1
n = lab1.selection_size
sample_2D = list(zip(sample_density, sample_elastic))
borders_1, buckets_1 = lab1.get_interval_sample(sample_density)
borders_2, buckets_2 = lab1.get_interval_sample(sample_elastic)
freqs_1 = [len(array) for array in buckets_1]
freqs_2 = [len(array) for array in buckets_2]
mid_borders_1 = [(border[0] + border[1]) / 2 for border in borders_1]
mid_borders_2 = [(border[0] + border[1]) / 2 for border in borders_2]
step_size_1 = borders_1[0][1] - borders_1[0][0]
step_size_2 = borders_2[0][1] - borders_2[0][0]
C_1 = 472 # из прошлых работ
C_2 = 122
# СКО для условных вариант
v = [(elem - C_1) / step_size_1 for elem in mid_borders_1]
u = [(elem - C_2) / step_size_2 for elem in mid_borders_2]
mean_v = sum([x[0] * x[1] for x in zip(v, freqs_1)]) / n
mean_u = sum([x[0] * x[1] for x in zip(u, freqs_2)]) / n
S_v = sqrt(sum([x[0]**2 * x[1] for x in zip(v, freqs_1)]) / n - mean_v**2)
S_u = sqrt(sum([x[0]**2 * x[1] for x in zip(u, freqs_2)]) / n - mean_u**2)
table = build_corr_table(sample_2D, borders_1, borders_2)
sum_from_table = countSum(table, v, u)
r = (sum_from_table + n * mean_v * mean_u) / (n * S_v * S_u)
return r
def build_table(sample_density):
borders, buckets = lab1.get_interval_sample(sample_density)
mid_borders = [round((border[0] + border[1]) / 2) for border in borders]
build_table.C = mid_borders[max([(len(bucket), i)
for i, bucket in enumerate(buckets)])[1]]
build_table.h = int(
(mid_borders[-1] - mid_borders[0]) / (len(mid_borders) - 1))
table = [[0 for i in range(8)] for i in range(len(mid_borders) + 1)]
for i, bucket in enumerate(buckets):
xi = mid_borders[i]
n = len(buckets[i])
ui = (xi - build_table.C) / build_table.h
table[i][0] = xi
table[-1][0] += xi
table[i][1] = n
table[-1][1] += n
table[i][2] = ui
table[-1][2] += ui
table[i][3] = ui * n
table[-1][3] += ui * n
table[i][4] = ui**2 * n
table[-1][4] += ui**2 * n
table[i][5] = ui**3 * n
table[-1][5] += ui**3 * n
table[i][6] = ui**4 * n
table[-1][6] += ui**4 * n
table[i][7] = (ui + 1)**4 * n
table[-1][7] += (ui + 1)**4 * n
return table
a_left = X - t_igrek * S / sqrt(N)
a_right = X + t_igrek * S / sqrt(N)
print("Доверительный интервал для математического ожидания: ", end="")
print("({0:.4f}; {1:.4f})\n".format(a_left, a_right))
gamma = 0.95
q = 0.147
sd_left = S*(1-q)
sd_right = S*(1+q)
print("Доверительный интервал для среднеквадратического отклонения: ", end="")
print("({0:.4f}; {1:.4f})\n".format(sd_left, sd_right))
borders, buckets = lab1.get_interval_sample(sample_density)
# print(borders, buckets)
vals = [len(bucket) for bucket in buckets]
# print(borders)
# print(buckets)
print("Частоты в интервалах:")
print(vals)
print()
# Объединяем последние интервалы
borders[-2] = (borders[-2][0], borders[-1][1])
del borders[-1]
buckets[-2] += buckets[-1]
del buckets[-1]
vals = [len(bucket) for bucket in buckets]
# print(borders)
S_u = sqrt(sum([x[0]**2 * x[1] for x in zip(u, freqs_2)]) / n - mean_u**2)
table = build_corr_table(sample_2D, borders_1, borders_2)
sum_from_table = countSum(table, v, u)
r = (sum_from_table + n * mean_v * mean_u) / (n * S_v * S_u)
return r
if __name__ == "__main__":
n = lab1.selection_size
general_population = lab1.read_data(filename=lab1.data_file_name)
sample_density = lab1.get_sample_first(general_population, n)
sample_elastic = lab1.get_sample_second(general_population, n)
borders_1, buckets_1 = lab1.get_interval_sample(sample_density)
borders_2, buckets_2 = lab1.get_interval_sample(sample_elastic)
freqs_1 = [len(array) for array in buckets_1]
freqs_2 = [len(array) for array in buckets_2]
# Расчёты прогоняем, меняя источник данных в лабе 2
# Часть 2
sample_2D = list(zip(sample_density, sample_elastic))
print("Двумерная выборка:")
print_beauty(sample_2D, size=6)
print(end="\n")
table = build_corr_table(sample_2D, borders_1, borders_2)
print("Данные для таблицы:")
for row in table:
print(row)
# y_maxval = mean_y + coef_y_x*(max_val - mean_x)
# ax.plot([min_val, max_val], [y_minval, y_maxval], "-r", label="$y_x$ = 0.31x - 12.33") # yx
# min_val, max_val = min(sample_elastic), max(sample_elastic)
# print(min_val, max_val)
# x_minval = mean_x + coef_x_y*(min_val - mean_y)
# x_maxval = mean_x + coef_x_y*(max_val - mean_y)
# ax.plot([x_minval, x_maxval], [min_val, max_val], "-b", label="$x_y$ = 1.91y + 212.58") # xy
# ax.legend()
# # ax.set_xlabel('Варианты')
# # ax.set_ylabel('Абсолютная частота')
# ax.set_title('Прямые среднеквадратической регрессии')
# # fig.tight_layout()
# plt.show()
borders_x, buckets_x = lab1.get_interval_sample(sample_density)
borders_y, buckets_y = lab1.get_interval_sample(sample_elastic)
freqs_x = [len(array) for array in buckets_x]
freqs_y = [len(array) for array in buckets_y]
mid_borders_x = [(border[0] + border[1]) / 2 for border in borders_x]
mid_borders_y = [(border[0] + border[1]) / 2 for border in borders_y]
for elem in mid_borders_x:
print("{0:.2f}".format(elem), end=" ")
print()
# print(freqs_x)
for elem in mid_borders_y:
print("{0:.2f}".format(elem), end=" ")
print()
# print(freqs_y)
As = m3 / pow(sigma, 3)
E = (m4 / pow(sigma, 4)) - 3
return X_cherta, S
if __name__ == "__main__":
general_population = lab1.read_data(filename=lab1.data_file_name)
# sample = lab1.get_sample(general_population, lab1.selection_size)
sample_density = lab1.get_sample_first(general_population,
lab1.selection_size)
sample_elastic = lab1.get_sample_second(general_population,
lab1.selection_size)
curr_sample = sample_elastic
borders, buckets = lab1.get_interval_sample(curr_sample)
lab1.print_beautiful_interval_freq(buckets, borders)
mid_borders = [round((border[0] + border[1]) / 2) for border in borders]
C = mid_borders[max([(len(bucket), i)
for i, bucket in enumerate(buckets)])[1]]
# h = mid_borders[1] - mid_borders[0]
h = int((mid_borders[-1] - mid_borders[0]) /
(len(mid_borders) -
1)) # вроде работает, на за счёт округление может быть шляпа
table = build_table(curr_sample)
for row in table:
for number in row:
print("{0:.2f}".format(number), end=" ")
print(end="\n")