/usr/lib/python3/dist-packages/seaborn/tests/test_distributions.py is in python3-seaborn 0.6.0-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 | import numpy as np
import pandas as pd
import matplotlib as mpl
import matplotlib.pyplot as plt
import nose.tools as nt
import numpy.testing as npt
from numpy.testing.decorators import skipif
from .. import distributions as dist
try:
import statsmodels.nonparametric.api
assert statsmodels.nonparametric.api
_no_statsmodels = False
except ImportError:
_no_statsmodels = True
class TestKDE(object):
rs = np.random.RandomState(0)
x = rs.randn(50)
y = rs.randn(50)
kernel = "gau"
bw = "scott"
gridsize = 128
clip = (-np.inf, np.inf)
cut = 3
def test_scipy_univariate_kde(self):
"""Test the univariate KDE estimation with scipy."""
grid, y = dist._scipy_univariate_kde(self.x, self.bw, self.gridsize,
self.cut, self.clip)
nt.assert_equal(len(grid), self.gridsize)
nt.assert_equal(len(y), self.gridsize)
for bw in ["silverman", .2]:
dist._scipy_univariate_kde(self.x, bw, self.gridsize,
self.cut, self.clip)
@skipif(_no_statsmodels)
def test_statsmodels_univariate_kde(self):
"""Test the univariate KDE estimation with statsmodels."""
grid, y = dist._statsmodels_univariate_kde(self.x, self.kernel,
self.bw, self.gridsize,
self.cut, self.clip)
nt.assert_equal(len(grid), self.gridsize)
nt.assert_equal(len(y), self.gridsize)
for bw in ["silverman", .2]:
dist._statsmodels_univariate_kde(self.x, self.kernel, bw,
self.gridsize, self.cut,
self.clip)
def test_scipy_bivariate_kde(self):
"""Test the bivariate KDE estimation with scipy."""
clip = [self.clip, self.clip]
x, y, z = dist._scipy_bivariate_kde(self.x, self.y, self.bw,
self.gridsize, self.cut, clip)
nt.assert_equal(x.shape, (self.gridsize, self.gridsize))
nt.assert_equal(y.shape, (self.gridsize, self.gridsize))
nt.assert_equal(len(z), self.gridsize)
# Test a specific bandwidth
clip = [self.clip, self.clip]
x, y, z = dist._scipy_bivariate_kde(self.x, self.y, 1,
self.gridsize, self.cut, clip)
# Test that we get an error with an invalid bandwidth
with nt.assert_raises(ValueError):
dist._scipy_bivariate_kde(self.x, self.y, (1, 2),
self.gridsize, self.cut, clip)
@skipif(_no_statsmodels)
def test_statsmodels_bivariate_kde(self):
"""Test the bivariate KDE estimation with statsmodels."""
clip = [self.clip, self.clip]
x, y, z = dist._statsmodels_bivariate_kde(self.x, self.y, self.bw,
self.gridsize,
self.cut, clip)
nt.assert_equal(x.shape, (self.gridsize, self.gridsize))
nt.assert_equal(y.shape, (self.gridsize, self.gridsize))
nt.assert_equal(len(z), self.gridsize)
@skipif(_no_statsmodels)
def test_statsmodels_kde_cumulative(self):
"""Test computation of cumulative KDE."""
grid, y = dist._statsmodels_univariate_kde(self.x, self.kernel,
self.bw, self.gridsize,
self.cut, self.clip,
cumulative=True)
nt.assert_equal(len(grid), self.gridsize)
nt.assert_equal(len(y), self.gridsize)
# make sure y is monotonically increasing
npt.assert_((np.diff(y) > 0).all())
def test_kde_cummulative_2d(self):
"""Check error if args indicate bivariate KDE and cumulative."""
with npt.assert_raises(TypeError):
dist.kdeplot(self.x, data2=self.y, cumulative=True)
def test_bivariate_kde_series(self):
df = pd.DataFrame({'x': self.x, 'y': self.y})
ax_series = dist.kdeplot(df.x, df.y)
ax_values = dist.kdeplot(df.x.values, df.y.values)
nt.assert_equal(len(ax_series.collections),
len(ax_values.collections))
nt.assert_equal(ax_series.collections[0].get_paths(),
ax_values.collections[0].get_paths())
plt.close("all")
class TestJointPlot(object):
rs = np.random.RandomState(sum(map(ord, "jointplot")))
x = rs.randn(100)
y = rs.randn(100)
data = pd.DataFrame(dict(x=x, y=y))
def test_scatter(self):
g = dist.jointplot("x", "y", self.data)
nt.assert_equal(len(g.ax_joint.collections), 1)
x, y = g.ax_joint.collections[0].get_offsets().T
npt.assert_array_equal(self.x, x)
npt.assert_array_equal(self.y, y)
x_bins = dist._freedman_diaconis_bins(self.x)
nt.assert_equal(len(g.ax_marg_x.patches), x_bins)
y_bins = dist._freedman_diaconis_bins(self.y)
nt.assert_equal(len(g.ax_marg_y.patches), y_bins)
plt.close("all")
def test_reg(self):
g = dist.jointplot("x", "y", self.data, kind="reg")
nt.assert_equal(len(g.ax_joint.collections), 2)
x, y = g.ax_joint.collections[0].get_offsets().T
npt.assert_array_equal(self.x, x)
npt.assert_array_equal(self.y, y)
x_bins = dist._freedman_diaconis_bins(self.x)
nt.assert_equal(len(g.ax_marg_x.patches), x_bins)
y_bins = dist._freedman_diaconis_bins(self.y)
nt.assert_equal(len(g.ax_marg_y.patches), y_bins)
nt.assert_equal(len(g.ax_joint.lines), 1)
nt.assert_equal(len(g.ax_marg_x.lines), 1)
nt.assert_equal(len(g.ax_marg_y.lines), 1)
plt.close("all")
def test_resid(self):
g = dist.jointplot("x", "y", self.data, kind="resid")
nt.assert_equal(len(g.ax_joint.collections), 1)
nt.assert_equal(len(g.ax_joint.lines), 1)
nt.assert_equal(len(g.ax_marg_x.lines), 0)
nt.assert_equal(len(g.ax_marg_y.lines), 1)
plt.close("all")
def test_hex(self):
g = dist.jointplot("x", "y", self.data, kind="hex")
nt.assert_equal(len(g.ax_joint.collections), 1)
x_bins = dist._freedman_diaconis_bins(self.x)
nt.assert_equal(len(g.ax_marg_x.patches), x_bins)
y_bins = dist._freedman_diaconis_bins(self.y)
nt.assert_equal(len(g.ax_marg_y.patches), y_bins)
plt.close("all")
def test_kde(self):
g = dist.jointplot("x", "y", self.data, kind="kde")
nt.assert_true(len(g.ax_joint.collections) > 0)
nt.assert_equal(len(g.ax_marg_x.collections), 1)
nt.assert_equal(len(g.ax_marg_y.collections), 1)
nt.assert_equal(len(g.ax_marg_x.lines), 1)
nt.assert_equal(len(g.ax_marg_y.lines), 1)
plt.close("all")
def test_color(self):
g = dist.jointplot("x", "y", self.data, color="purple")
purple = mpl.colors.colorConverter.to_rgb("purple")
scatter_color = g.ax_joint.collections[0].get_facecolor()[0, :3]
nt.assert_equal(tuple(scatter_color), purple)
hist_color = g.ax_marg_x.patches[0].get_facecolor()[:3]
nt.assert_equal(hist_color, purple)
plt.close("all")
def test_annotation(self):
g = dist.jointplot("x", "y", self.data)
nt.assert_equal(len(g.ax_joint.legend_.get_texts()), 1)
g = dist.jointplot("x", "y", self.data, stat_func=None)
nt.assert_is(g.ax_joint.legend_, None)
plt.close("all")
def test_hex_customise(self):
# test that default gridsize can be overridden
g = dist.jointplot("x", "y", self.data, kind="hex",
joint_kws=dict(gridsize=5))
nt.assert_equal(len(g.ax_joint.collections), 1)
a = g.ax_joint.collections[0].get_array()
nt.assert_equal(28, a.shape[0]) # 28 hexagons expected for gridsize 5
plt.close("all")
def test_bad_kind(self):
with nt.assert_raises(ValueError):
dist.jointplot("x", "y", self.data, kind="not_a_kind")
@classmethod
def teardown_class(cls):
"""Ensure that all figures are closed on exit."""
plt.close("all")
|