def _statsmodels_bivariate_kde(x, y, bw, gridsize, cut, clip):
"""Compute a bivariate kde using statsmodels."""
# statsmodels 0.8 fails on int type data
x = x.astype(np.float64)
y = y.astype(np.float64)
if isinstance(bw, str):
bw_func = getattr(smnp.bandwidths, "bw_" + bw)
x_bw = bw_func(x)
y_bw = bw_func(y)
bw = [x_bw, y_bw]
elif np.isscalar(bw):
bw = [bw, bw]
if isinstance(x, pd.Series):
x = x.values
if isinstance(y, pd.Series):
y = y.values
kde = smnp.KDEMultivariate([x, y], "cc", bw)
x_support = _kde_support(x, kde.bw[0], gridsize, cut, clip[0])
y_support = _kde_support(y, kde.bw[1], gridsize, cut, clip[1])
xx, yy = np.meshgrid(x_support, y_support)
z = kde.pdf([xx.ravel(), yy.ravel()]).reshape(xx.shape)
return xx, yy, z
def _statsmodels_bivariate_kde(x,
y,
bw='scott',
gridsize=100,
cut=3,
clip=[(-np.inf, np.inf), (-np.inf, np.inf)]):
"""Compute a bivariate kde using statsmodels."""
if isinstance(bw, string_types):
bw_func = getattr(smnp.bandwidths, "bw_" + bw)
x_bw = bw_func(x)
y_bw = bw_func(y)
bw = [x_bw, y_bw]
elif np.isscalar(bw):
bw = [bw, bw]
if isinstance(x, pd.Series):
x = x.values
if isinstance(y, pd.Series):
y = y.values
kde = smnp.KDEMultivariate([x, y], "cc", bw)
x_support = _kde_support(x, kde.bw[0], gridsize, cut, clip[0])
y_support = _kde_support(y, kde.bw[1], gridsize, cut, clip[1])
xx, yy = np.meshgrid(x_support, y_support)
z = kde.pdf([xx.ravel(), yy.ravel()]).reshape(xx.shape)
return xx, yy, z
def hacked_statsmodels_bivariate_kde(x, y, bw, gridsize, cut, clip):
"""Compute a bivariate kde using statsmodels. Modified to give the exponentiated values on the y axis"""
import statsmodels.nonparametric.api as smnp
from seaborn.utils import _kde_support
if isinstance(bw, str):
bw_func = getattr(smnp.bandwidths, "bw_" + bw)
x_bw = bw_func(x)
y_bw = bw_func(y)
bw = [x_bw, y_bw]
elif np.isscalar(bw):
bw = [bw, bw]
if isinstance(x, pd.Series):
x = x.values
if isinstance(y, pd.Series):
y = y.values
kde = smnp.KDEMultivariate([x, y], "cc", bw)
x_support = _kde_support(x, kde.bw[0], gridsize, cut, clip[0])
y_support = _kde_support(y, kde.bw[1], gridsize, cut, clip[1])
xx, yy = np.meshgrid(x_support, y_support)
z = kde.pdf([xx.ravel(), yy.ravel()]).reshape(xx.shape)
# exponentiate y values
return xx, np.exp(yy), z
def _bivariate_kdeplot(x,
y,
xscale=None,
yscale=None,
shade=False,
kernel="gau",
bw="scott",
gridsize=100,
cut=3,
clip=None,
legend=True,
**kwargs):
ax = plt.gca()
# Determine the clipping
clip = [(-np.inf, np.inf), (-np.inf, np.inf)]
x = xscale(x)
y = yscale(y)
# Compute a bivariate kde using statsmodels.
if isinstance(bw, string_types):
bw_func = getattr(smnp.bandwidths, "bw_" + bw)
x_bw = bw_func(x)
y_bw = bw_func(y)
bw = [x_bw, y_bw]
elif np.isscalar(bw):
bw = [bw, bw]
kde = smnp.KDEMultivariate([x, y], "cc", bw)
x_support = _kde_support(x, kde.bw[0], gridsize, cut, clip[0])
y_support = _kde_support(y, kde.bw[1], gridsize, cut, clip[1])
xx, yy = np.meshgrid(x_support, y_support)
z = kde.pdf([xx.ravel(), yy.ravel()]).values.reshape(xx.shape)
n_levels = kwargs.pop("n_levels", 10)
color = kwargs.pop("color")
kwargs['colors'] = (color, )
x_support = xscale.inverse(x_support)
y_support = yscale.inverse(y_support)
xx, yy = np.meshgrid(x_support, y_support)
contour_func = ax.contourf if shade else ax.contour
cset = contour_func(xx, yy, z, n_levels, **kwargs)
num_collections = len(cset.collections)
min_alpha = kwargs.pop("min_alpha", 0.2)
if shade:
min_alpha = 0
max_alpha = kwargs.pop("max_alpha", 0.9)
alpha = np.linspace(min_alpha, max_alpha, num=num_collections)
for el in range(num_collections):
cset.collections[el].set_alpha(alpha[el])
# Label the axes
if hasattr(x, "name") and legend:
ax.set_xlabel(x.name)
if hasattr(y, "name") and legend:
ax.set_ylabel(y.name)
return ax