Python의 pdf_multivariate_gauss() 함수

Question

IPython에서 pdf_multivariate_gauss() 함수를 실행하는 데 필요한 모듈은 무엇입니까?

아래 코드를 실행하려고하지만 "가져 오기 오류"및 "이름 오류"와 같은 오류가 발생합니다.

코드 : (이미 지적했듯이)

import numpy as np 
from matplotlib import pyplot as plt 
from matplotlib.mlab import bivariate_normal 
import parzen_window_est 
import pdf_multivariate_gauss ######## ImportError ######## 
import operator 


from mpl_toolkits.mplot3d import Axes3D 

############################################## 
### Predicted bivariate Gaussian densities ### 
############################################## 


mu_vec = np.array([0,0]) 
cov_mat = np.array([[1,0],[0,1]]) 
x_2Dgauss = np.random.multivariate_normal(mu_vec, cov_mat, 10000) 
# generate a range of 400 window widths between 0 < h < 1 
h_range = np.linspace(0.001, 1, 400) 

# calculate the actual density at the center [0, 0] 
mu = np.array([[0],[0]]) 
cov = np.eye(2) 
actual_pdf_val = pdf_multivariate_gauss.pdf_multivariate_gauss(np.array([[0],[0]]), mu, cov) 
######## NameError ######### 

# get a list of the differnces (|estimate-actual|) for different window widths 
parzen_estimates = [np.abs(parzen_window_est.parzen_window_est(x_2Dgauss, h=1, center=[0, 0])) for i in h_range] 

# get the window width for which |estimate-actual| is closest to 0 
min_index, min_value = min(enumerate(parzen_estimates), key=operator.itemgetter(1)) 

IPython output

Answer 1

는 지금까지 내가 말할 수있는, pdf_multivariate_gauss 같은 것은이 없습니다. 이것의 파이썬 구현하지만, scipy에있다 : 당신이 난만큼 지금까지이 pdf_multivariate_gaus` 파이썬에서 이러한 모듈 (`와 혼동 생각

from scipy.stats import multivariate_normal 
mvn = multivariate_normal(mu,cov) #create a multivariate Gaussian object with specified mean and covariance matrix 
p = mvn.pdf(x) #evaluate the probability density at x