def eliminate2(n):
u2 = 50 * random(x0, z, n)
u1 = random(1.7231 * x0, z - 2, n)
list = []
for i in range(len(u2)):
if u2[i] <= fin2(u1[i]):
list.append(u1[i])
return list
def eliminateCauchy(n):
u2 = 0.35 * random(0.1423123, 13, n)
u1 = 4 * random(0.1221321, 11, n) - 8
list = []
for i in range(len(u2)):
if u2[i] <= finCauchy(u1[i]):
list.append(u1[i])
return list
def eliminate1(n):
u2 = random(x0, z, n)
u1 = 2 * random(1.7231 * x0, z - 2, n) - 1
list = []
for i in range(len(u2)):
if u2[i] <= fin1(u1[i]):
list.append(u1[i])
return list
def eliminate_cauchy_upgraded(n):
tmplist = []
num_of_elements = 0
i = 0
u2 = 0.35 * random(0.1231231213, 11, 5 * n)
u1 = 10 * random(0.1221321, 11, 5 * n) - 5
while (num_of_elements < n):
if u2[i] <= finCauchy(u1[i]):
tmplist.append(u1[i])
num_of_elements += 1
i += 1
return tmplist
def eliminate41(n):
tmplist = []
d = 2
num_of_elements = 0
i = 0
u2 = d * random(0.1231231213, 11, 3 * n)
u1 = random(0.14421322321, 15, 3 * n)
while (num_of_elements < n):
if u2[i] <= function41(u1[i]):
tmplist.append(u1[i])
num_of_elements += 1
i += 1
return tmplist
def eliminate4(n, x00):
c = sqrt(2 * np.e / np.pi)
V = f4(n)
U = random(x00, z, n)
list = []
for i in range(len(V)):
if np.fabs(V[i]) <= sqrt(-2 * np.log(U[i])) + 1:
list.append(V[i])
return list
import numpy as np
import matplotlib.pyplot as plt
from labgotowe import random
from lab5 import rectangular_kernel, epanechnikov_kernel, boscar_kernel
A = 1
N = 500
Z = np.random.normal(0, 1, N)
X = 4 * random(0.14123216, 15, N) - 2
x_sorted = sorted(X)
Q = 100
def m_function(a, x):
return np.arctan(a * x)
def m_function_all(a, tab):
output = []
for i in range(len(tab)):
output.append(m_function(a, tab[i]))
return output
def system_output(x_tab, z_tab):
output = []
for x in range(len(x_tab)):
output.append(m_function(A, x_tab[x]) + z_tab[x])
return output
def valid(kernel_type, x_tab, y_tab, hv):
if __name__ == "__main__":
N = 200
h = 1
M = 100
L = 10
normal_tab = normal_generator(N)
random_tab = random(0.13213421, 13, N)
print(normal_generator(10))
fig1, ax1 = plt.subplots(3)
x1, y1 = kernel_estimator("rectangular", normal_tab, 0.4, N)
ax1[0].plot(x1, y1)
ax1[0].set_title('h = 0.4')
x2, y2 = kernel_estimator("rectangular", normal_tab, 1, N)
ax1[1].plot(x2, y2)
ax1[1].set_title('h = 1')
x3, y3 = kernel_estimator("rectangular", normal_tab, 4, N)
ax1[2].plot(x3, y3)
ax1[2].set_title('h = 4')
fig2, ax2 = plt.subplots(3)
x4, y4 = kernel_estimator("rectangular", normal_tab, h, N)
ax2[0].plot(x4, y4)
ax2[0].set_title('Rozkład normalny - jądro prostokątne')
import numpy as np
import matplotlib.pyplot as plt
from labgotowe import random
from lab5 import rectangular_kernel, epanechnikov_kernel, boscar_kernel
A = 1
N = 250
L = 15
Q = 100
x_tab = 2 * np.pi * random(0.14123141, 15, N) - np.pi
x_sorted = sorted(x_tab)
z_tab = np.random.normal(0, 1, 500)
def m7_function(a, x):
if 0 <= abs(x) < 1:
tmp = a * pow(x, 2)
elif 1 <= abs(x) < 2:
tmp = 1
else:
tmp = 0
return tmp
def m7_for_tab(a, tab):
output = []
for i in range(len(tab)):
output.append(m7_function(a, tab[i]))
return output