In [63]:

    

from scipy.stats import multivariate_normal


    

In [64]:

    

# covariance matrix
cov = [[1, 0],[0,1]]
# mean vector
mu = np.array([0,0])


    

In [65]:

    

# define the grid
x = y = linspace(-4, 4, 200)
X, Y = np.meshgrid(x,y)
pos = np.dstack((X,Y))


    

In [66]:

    

z = multivariate_normal(mean = mu,cov= cov)
z.pdf([0,0])


    

    
Out[66]:





0.15915494309189535

In [67]:

    

from mpl_toolkits.mplot3d import Axes3D
fig = plt.figure()
ax = fig.add_subplot(111, projection='3d')
ax.plot_surface(X, Y, z.pdf(pos), shade=1, alpha=1, cmap='BuGn')


    

    
Out[67]:





<mpl_toolkits.mplot3d.art3d.Poly3DCollection at 0x57778d0>






    

In [68]:

    

# covariance matrix
cov = [[.7, 0.0],[0.0,.7]]
# mean vector
mu = np.array([0,0])


    

In [69]:

    

z = multivariate_normal(mean = mu,cov= cov)
z.pdf([0,0])


    

    
Out[69]:





0.2273642044169934

In [70]:

    

from mpl_toolkits.mplot3d import Axes3D
fig = plt.figure()
ax = fig.add_subplot(111, projection='3d')
ax.plot_surface(X, Y, z.pdf(pos), shade=1, alpha=1, cmap='BuGn')


    

    
Out[70]:





<mpl_toolkits.mplot3d.art3d.Poly3DCollection at 0x576a510>






    

In [ ]: