In [1]:

    

import matplotlib.pyplot as plt
import matplotlib.patches as mpatches
from matplotlib import rc
%matplotlib auto
import numpy as np
from sklearn.neighbors import KernelDensity
from scipy.stats import gaussian_kde

rc('font', **{'family': 'serif'})
rc('text', usetex=True)
rc('text.latex', unicode=True)
rc('text.latex', preamble='\\usepackage[utf8]{inputenc}')
rc('text.latex', preamble='\\usepackage[russian]{babel}')


    

    




Using matplotlib backend: TkAgg

In [2]:

    

def plot_kernels():
    fig, ax = plt.subplots(figsize=(8, 6))
#     fig, ax = plt.plot()
    ax.grid(color='white', linestyle='-', linewidth=10)
    X_src = np.zeros((1, 1))
    x_grid = np.linspace(-3, 3, 1000)

    for kernel in ['gaussian', 'tophat', 'epanechnikov',
                   'linear', 'cosine']:
        log_dens = KernelDensity(kernel=kernel).fit(X_src).score_samples(x_grid[:, None])
        ax.plot(x_grid, np.exp(log_dens), lw=3, alpha=0.5)
    ax.set_ylim(0, 1.05)
    ax.set_xlim(-2.9, 2.9)
    ax.legend([u"гаусове", u"пряме", u"оптимальне", u"трикутне", u"квадратичне"])
    plt.show()


    

In [5]:

    

plot_kernels()