/usr/lib/python3/dist-packages/seaborn/utils.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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 | """Small plotting-related utility functions."""
from __future__ import print_function, division
import colorsys
import warnings
import os
import numpy as np
from scipy import stats
import pandas as pd
import matplotlib.colors as mplcol
import matplotlib.pyplot as plt
from distutils.version import LooseVersion
pandas_has_categoricals = LooseVersion(pd.__version__) >= "0.15"
from .external.six.moves.urllib.request import urlopen, urlretrieve
def ci_to_errsize(cis, heights):
"""Convert intervals to error arguments relative to plot heights.
Parameters
----------
cis: 2 x n sequence
sequence of confidence interval limits
heights : n sequence
sequence of plot heights
Returns
-------
errsize : 2 x n array
sequence of error size relative to height values in correct
format as argument for plt.bar
"""
cis = np.atleast_2d(cis).reshape(2, -1)
heights = np.atleast_1d(heights)
errsize = []
for i, (low, high) in enumerate(np.transpose(cis)):
h = heights[i]
elow = h - low
ehigh = high - h
errsize.append([elow, ehigh])
errsize = np.asarray(errsize).T
return errsize
def pmf_hist(a, bins=10):
"""Return arguments to plt.bar for pmf-like histogram of an array.
Parameters
----------
a: array-like
array to make histogram of
bins: int
number of bins
Returns
-------
x: array
left x position of bars
h: array
height of bars
w: float
width of bars
"""
n, x = np.histogram(a, bins)
h = n / n.sum()
w = x[1] - x[0]
return x[:-1], h, w
def desaturate(color, prop):
"""Decrease the saturation channel of a color by some percent.
Parameters
----------
color : matplotlib color
hex, rgb-tuple, or html color name
prop : float
saturation channel of color will be multiplied by this value
Returns
-------
new_color : rgb tuple
desaturated color code in RGB tuple representation
"""
# Check inputs
if not 0 <= prop <= 1:
raise ValueError("prop must be between 0 and 1")
# Get rgb tuple rep
rgb = mplcol.colorConverter.to_rgb(color)
# Convert to hls
h, l, s = colorsys.rgb_to_hls(*rgb)
# Desaturate the saturation channel
s *= prop
# Convert back to rgb
new_color = colorsys.hls_to_rgb(h, l, s)
return new_color
def saturate(color):
"""Return a fully saturated color with the same hue.
Parameters
----------
color : matplotlib color
hex, rgb-tuple, or html color name
Returns
-------
new_color : rgb tuple
saturated color code in RGB tuple representation
"""
return set_hls_values(color, s=1)
def set_hls_values(color, h=None, l=None, s=None):
"""Independently manipulate the h, l, or s channels of a color.
Parameters
----------
color : matplotlib color
hex, rgb-tuple, or html color name
h, l, s : floats between 0 and 1, or None
new values for each channel in hls space
Returns
-------
new_color : rgb tuple
new color code in RGB tuple representation
"""
# Get rgb tuple representation
rgb = mplcol.colorConverter.to_rgb(color)
vals = list(colorsys.rgb_to_hls(*rgb))
for i, val in enumerate([h, l, s]):
if val is not None:
vals[i] = val
rgb = colorsys.hls_to_rgb(*vals)
return rgb
def axlabel(xlabel, ylabel, **kwargs):
"""Grab current axis and label it."""
ax = plt.gca()
ax.set_xlabel(xlabel, **kwargs)
ax.set_ylabel(ylabel, **kwargs)
def despine(fig=None, ax=None, top=True, right=True, left=False,
bottom=False, offset=None, trim=False):
"""Remove the top and right spines from plot(s).
fig : matplotlib figure, optional
Figure to despine all axes of, default uses current figure.
ax : matplotlib axes, optional
Specific axes object to despine.
top, right, left, bottom : boolean, optional
If True, remove that spine.
offset : int or None (default), optional
Absolute distance, in points, spines should be moved away
from the axes (negative values move spines inward).
trim : bool, optional
If true, limit spines to the smallest and largest major tick
on each non-despined axis.
Returns
-------
None
"""
# Get references to the axes we want
if fig is None and ax is None:
axes = plt.gcf().axes
elif fig is not None:
axes = fig.axes
elif ax is not None:
axes = [ax]
for ax_i in axes:
for side in ["top", "right", "left", "bottom"]:
# Toggle the spine objects
is_visible = not locals()[side]
ax_i.spines[side].set_visible(is_visible)
if offset is not None and is_visible:
_set_spine_position(ax_i.spines[side], ('outward', offset))
# Set the ticks appropriately
if bottom:
ax_i.xaxis.tick_top()
if top:
ax_i.xaxis.tick_bottom()
if left:
ax_i.yaxis.tick_right()
if right:
ax_i.yaxis.tick_left()
if trim:
# clip off the parts of the spines that extend past major ticks
xticks = ax_i.get_xticks()
if xticks.size:
firsttick = np.compress(xticks >= min(ax_i.get_xlim()),
xticks)[0]
lasttick = np.compress(xticks <= max(ax_i.get_xlim()),
xticks)[-1]
ax_i.spines['bottom'].set_bounds(firsttick, lasttick)
ax_i.spines['top'].set_bounds(firsttick, lasttick)
newticks = xticks.compress(xticks <= lasttick)
newticks = newticks.compress(newticks >= firsttick)
ax_i.set_xticks(newticks)
yticks = ax_i.get_yticks()
if yticks.size:
firsttick = np.compress(yticks >= min(ax_i.get_ylim()),
yticks)[0]
lasttick = np.compress(yticks <= max(ax_i.get_ylim()),
yticks)[-1]
ax_i.spines['left'].set_bounds(firsttick, lasttick)
ax_i.spines['right'].set_bounds(firsttick, lasttick)
newticks = yticks.compress(yticks <= lasttick)
newticks = newticks.compress(newticks >= firsttick)
ax_i.set_yticks(newticks)
def offset_spines(offset=10, fig=None, ax=None):
"""Simple function to offset spines away from axes.
Use this immediately after creating figure and axes objects.
Offsetting spines after plotting or manipulating the axes
objects may result in loss of labels, ticks, and formatting.
Parameters
----------
offset : int, optional
Absolute distance, in points, spines should be moved away
from the axes (negative values move spines inward).
fig : matplotlib figure, optional
Figure to despine all axes of, default uses current figure.
ax : matplotlib axes, optional
Specific axes object to despine
Returns
-------
None
"""
warn_msg = "`offset_spines` is deprecated and will be removed in v0.5"
warnings.warn(warn_msg, UserWarning)
# Get references to the axes we want
if fig is None and ax is None:
axes = plt.gcf().axes
elif fig is not None:
axes = fig.axes
elif ax is not None:
axes = [ax]
for ax_i in axes:
for spine in ax_i.spines.values():
_set_spine_position(spine, ('outward', offset))
def _set_spine_position(spine, position):
"""
Set the spine's position without resetting an associated axis.
As of matplotlib v. 1.0.0, if a spine has an associated axis, then
spine.set_position() calls axis.cla(), which resets locators, formatters,
etc. We temporarily replace that call with axis.reset_ticks(), which is
sufficient for our purposes.
"""
axis = spine.axis
if axis is not None:
cla = axis.cla
axis.cla = axis.reset_ticks
spine.set_position(position)
if axis is not None:
axis.cla = cla
def _kde_support(data, bw, gridsize, cut, clip):
"""Establish support for a kernel density estimate."""
support_min = max(data.min() - bw * cut, clip[0])
support_max = min(data.max() + bw * cut, clip[1])
return np.linspace(support_min, support_max, gridsize)
def percentiles(a, pcts, axis=None):
"""Like scoreatpercentile but can take and return array of percentiles.
Parameters
----------
a : array
data
pcts : sequence of percentile values
percentile or percentiles to find score at
axis : int or None
if not None, computes scores over this axis
Returns
-------
scores: array
array of scores at requested percentiles
first dimension is length of object passed to ``pcts``
"""
scores = []
try:
n = len(pcts)
except TypeError:
pcts = [pcts]
n = 0
for i, p in enumerate(pcts):
if axis is None:
score = stats.scoreatpercentile(a.ravel(), p)
else:
score = np.apply_along_axis(stats.scoreatpercentile, axis, a, p)
scores.append(score)
scores = np.asarray(scores)
if not n:
scores = scores.squeeze()
return scores
def ci(a, which=95, axis=None):
"""Return a percentile range from an array of values."""
p = 50 - which / 2, 50 + which / 2
return percentiles(a, p, axis)
def sig_stars(p):
"""Return a R-style significance string corresponding to p values."""
if p < 0.001:
return "***"
elif p < 0.01:
return "**"
elif p < 0.05:
return "*"
elif p < 0.1:
return "."
return ""
def iqr(a):
"""Calculate the IQR for an array of numbers."""
a = np.asarray(a)
q1 = stats.scoreatpercentile(a, 25)
q3 = stats.scoreatpercentile(a, 75)
return q3 - q1
def get_dataset_names():
"""Report available example datasets, useful for reporting issues."""
# delayed import to not demand bs4 unless this function is actually used
from bs4 import BeautifulSoup
http = urlopen('https://github.com/mwaskom/seaborn-data/')
gh_list = BeautifulSoup(http)
return [l.text.replace('.csv', '')
for l in gh_list.find_all("a", {"class": "js-directory-link"})
if l.text.endswith('.csv')]
def get_data_home(data_home=None):
"""Return the path of the seaborn data directory.
This is used by the ``load_dataset`` function.
If the ``data_home`` argument is not specified, the default location
is ``~/seaborn-data``.
Alternatively, a different default location can be specified using the
environment variable ``SEABORN_DATA``.
"""
if data_home is None:
data_home = os.environ.get('SEABORN_DATA',
os.path.join('~', 'seaborn-data'))
data_home = os.path.expanduser(data_home)
if not os.path.exists(data_home):
os.makedirs(data_home)
return data_home
def load_dataset(name, cache=True, data_home=None, **kws):
"""Load a dataset from the online repository (requires internet).
Parameters
----------
name : str
Name of the dataset (`name`.csv on
https://github.com/mwaskom/seaborn-data). You can obtain list of
available datasets using :func:`get_dataset_names`
cache : boolean, optional
If True, then cache data locally and use the cache on subsequent calls
data_home : string, optional
The directory in which to cache data. By default, uses ~/seaborn_data/
kws : dict, optional
Passed to pandas.read_csv
"""
path = "https://github.com/mwaskom/seaborn-data/raw/master/{0}.csv"
full_path = path.format(name)
if cache:
cache_path = os.path.join(get_data_home(data_home),
os.path.basename(full_path))
if not os.path.exists(cache_path):
urlretrieve(full_path, cache_path)
full_path = cache_path
df = pd.read_csv(full_path, **kws)
if df.iloc[-1].isnull().all():
df = df.iloc[:-1]
if not pandas_has_categoricals:
return df
# Set some columns as a categorical type with ordered levels
if name == "tips":
df["day"] = pd.Categorical(df["day"], ["Thur", "Fri", "Sat", "Sun"])
df["sex"] = pd.Categorical(df["sex"], ["Male", "Female"])
df["time"] = pd.Categorical(df["time"], ["Lunch", "Dinner"])
df["smoker"] = pd.Categorical(df["smoker"], ["Yes", "No"])
if name == "flights":
df["month"] = pd.Categorical(df["month"], df.month.unique())
if name == "exercise":
df["time"] = pd.Categorical(df["time"], ["1 min", "15 min", "30 min"])
df["kind"] = pd.Categorical(df["kind"], ["rest", "walking", "running"])
df["diet"] = pd.Categorical(df["diet"], ["no fat", "low fat"])
if name == "titanic":
df["class"] = pd.Categorical(df["class"], ["First", "Second", "Third"])
df["deck"] = pd.Categorical(df["deck"], list("ABCDEFG"))
return df
def axis_ticklabels_overlap(labels):
"""Return a boolean for whether the list of ticklabels have overlaps.
Parameters
----------
labels : list of ticklabels
Returns
-------
overlap : boolean
True if any of the labels overlap.
"""
if not labels:
return False
try:
bboxes = [l.get_window_extent() for l in labels]
overlaps = [b.count_overlaps(bboxes) for b in bboxes]
return max(overlaps) > 1
except RuntimeError:
# Issue on macosx backend rasies an error in the above code
return False
def axes_ticklabels_overlap(ax):
"""Return booleans for whether the x and y ticklabels on an Axes overlap.
Parameters
----------
ax : matplotlib Axes
Returns
-------
x_overlap, y_overlap : booleans
True when the labels on that axis overlap.
"""
return (axis_ticklabels_overlap(ax.get_xticklabels()),
axis_ticklabels_overlap(ax.get_yticklabels()))
def categorical_order(values, order=None):
"""Return a list of unique data values.
Determine an ordered list of levels in ``values``.
Parameters
----------
values : list, array, Categorical, or Series
Vector of "categorical" values
order : list-like, optional
Desired order of category levels to override the order determined
from the ``values`` object.
Returns
-------
order : list
Ordered list of category levels not including null values.
"""
if order is None:
if hasattr(values, "categories"):
order = values.categories
else:
try:
order = values.cat.categories
except (TypeError, AttributeError):
try:
order = values.unique()
except AttributeError:
order = pd.unique(values)
order = filter(pd.notnull, order)
return list(order)
|