/usr/lib/python3/dist-packages/seaborn/distributions.py is in python3-seaborn 0.4.0-3.
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 | """Plottng functions for visualizing distributions."""
from __future__ import division
import colorsys
import numpy as np
from scipy import stats
import pandas as pd
import matplotlib as mpl
import matplotlib.pyplot as plt
import warnings
try:
import statsmodels
import statsmodels.api as sm
_has_statsmodels = True
from distutils.version import LooseVersion as LV
_has_statsmodels_ge_0_6 = LV(statsmodels.__version__) >= LV("0.6")
def needs_statsmodels_0_6():
if not _has_statsmodels_ge_0_6:
raise RuntimeError("This functionality requires statsmodels 0.6"
" or later. You have %s" % statsmodels.__version__)
except ImportError:
_has_statsmodels = False
from .external.six.moves import range
from .utils import set_hls_values, desaturate, percentiles, iqr, _kde_support
from .palettes import color_palette, husl_palette, blend_palette
from .axisgrid import JointGrid
def _box_reshape(vals, groupby, names, order):
"""Reshape the box/violinplot input options and find plot labels."""
# Set up default label outputs
xlabel, ylabel = None, None
# If order is provided, make sure it was used correctly
if order is not None:
# Assure that order is the same length as names, if provided
if names is not None:
if len(order) != len(names):
raise ValueError("`order` must have same length as `names`")
# Assure that order is only used with the right inputs
is_pd = isinstance(vals, pd.Series) or isinstance(vals, pd.DataFrame)
if not is_pd:
raise ValueError("`vals` must be a Pandas object to use `order`.")
# Handle case where data is a wide DataFrame
if isinstance(vals, pd.DataFrame):
if order is not None:
vals = vals[order]
if names is None:
names = vals.columns.tolist()
if vals.columns.name is not None:
xlabel = vals.columns.name
vals = vals.values.T
# Handle case where data is a long Series and there is a grouping object
elif isinstance(vals, pd.Series) and groupby is not None:
groups = pd.groupby(vals, groupby).groups
order = sorted(groups) if order is None else order
if hasattr(groupby, "name"):
if groupby.name is not None:
xlabel = groupby.name
if vals.name is not None:
ylabel = vals.name
vals = [vals.reindex(groups[name]) for name in order]
if names is None:
names = order
else:
# Handle case where the input data is an array or there was no groupby
if hasattr(vals, 'shape'):
if len(vals.shape) == 1:
if np.isscalar(vals[0]):
vals = [vals]
else:
vals = list(vals)
elif len(vals.shape) == 2:
nr, nc = vals.shape
if nr == 1:
vals = [vals]
elif nc == 1:
vals = [vals.ravel()]
else:
vals = [vals[:, i] for i in range(nc)]
else:
error = "Input `vals` can have no more than 2 dimensions"
raise ValueError(error)
# This should catch things like flat lists
elif np.isscalar(vals[0]):
vals = [vals]
# By default, just use the plot positions as names
if names is None:
names = list(range(1, len(vals) + 1))
elif hasattr(names, "name"):
if names.name is not None:
xlabel = names.name
# Now convert vals to a common representation
# The plotting functions will work with a list of arrays
# The list allows each array to possibly be of a different length
vals = [np.asarray(a, np.float) for a in vals]
return vals, xlabel, ylabel, names
def _box_colors(vals, color, sat):
"""Find colors to use for boxplots or violinplots."""
if color is None:
# Default uses either the current palette or husl
current_palette = mpl.rcParams["axes.color_cycle"]
if len(vals) <= len(current_palette):
colors = color_palette(n_colors=len(vals))
else:
colors = husl_palette(len(vals), l=.7)
else:
try:
color = mpl.colors.colorConverter.to_rgb(color)
colors = [color for _ in vals]
except ValueError:
colors = color_palette(color, len(vals))
# Desaturate a bit because these are patches
colors = [mpl.colors.colorConverter.to_rgb(c) for c in colors]
colors = [desaturate(c, sat) for c in colors]
# Determine the gray color for the lines
light_vals = [colorsys.rgb_to_hls(*c)[1] for c in colors]
l = min(light_vals) * .6
gray = (l, l, l)
return colors, gray
def boxplot(vals, groupby=None, names=None, join_rm=False, order=None,
color=None, alpha=None, fliersize=3, linewidth=1.5, widths=.8,
saturation=.7, label=None, ax=None, **kwargs):
"""Wrapper for matplotlib boxplot with better aesthetics and functionality.
Parameters
----------
vals : DataFrame, Series, 2D array, list of vectors, or vector.
Data for plot. DataFrames and 2D arrays are assumed to be "wide" with
each column mapping to a box. Lists of data are assumed to have one
element per box. Can also provide one long Series in conjunction with
a grouping element as the `groupy` parameter to reshape the data into
several boxes. Otherwise 1D data will produce a single box.
groupby : grouping object
If `vals` is a Series, this is used to group into boxes by calling
pd.groupby(vals, groupby).
names : list of strings, optional
Names to plot on x axis; otherwise plots numbers. This will override
names inferred from Pandas inputs.
order : list of strings, optional
If vals is a Pandas object with name information, you can control the
order of the boxes by providing the box names in your preferred order.
join_rm : boolean, optional
If True, positions in the input arrays are treated as repeated
measures and are joined with a line plot.
color : mpl color, sequence of colors, or seaborn palette name
Inner box color.
alpha : float
Transparancy of the inner box color.
fliersize : float, optional
Markersize for the fliers.
linewidth : float, optional
Width for the box outlines and whiskers.
saturation : float, 0-1
Saturation relative to the fully-saturated color. Large patches tend
to look better at lower saturations, so this dims the palette colors
a bit by default.
ax : matplotlib axis, optional
Existing axis to plot into, otherwise grab current axis.
kwargs : additional keyword arguments to boxplot
Returns
-------
ax : matplotlib axis
Axis where boxplot is plotted.
"""
if ax is None:
ax = plt.gca()
# Reshape and find labels for the plot
vals, xlabel, ylabel, names = _box_reshape(vals, groupby, names, order)
# Draw the boxplot using matplotlib
boxes = ax.boxplot(vals, patch_artist=True, widths=widths, **kwargs)
# Find plot colors
colors, gray = _box_colors(vals, color, saturation)
# Set the new aesthetics
for i, box in enumerate(boxes["boxes"]):
box.set_color(colors[i])
if alpha is not None:
box.set_alpha(alpha)
box.set_edgecolor(gray)
box.set_linewidth(linewidth)
for i, whisk in enumerate(boxes["whiskers"]):
whisk.set_color(gray)
whisk.set_linewidth(linewidth)
whisk.set_linestyle("-")
for i, cap in enumerate(boxes["caps"]):
cap.set_color(gray)
cap.set_linewidth(linewidth)
for i, med in enumerate(boxes["medians"]):
med.set_color(gray)
med.set_linewidth(linewidth)
for i, fly in enumerate(boxes["fliers"]):
fly.set_color(gray)
fly.set_marker("d")
fly.set_markeredgecolor(gray)
fly.set_markersize(fliersize)
# This is a hack to get labels to work
# It's unclear whether this is actually broken in matplotlib or just not
# implemented, either way it's annoying.
if label is not None:
pos = kwargs.get("positions", [1])[0]
med = np.median(vals[0])
color = colors[0]
ax.add_patch(plt.Rectangle([pos, med], 0, 0, color=color, label=label))
# Is this a vertical plot?
vertical = kwargs.get("vert", True)
# Draw the joined repeated measures
if join_rm:
x, y = np.arange(1, len(vals) + 1), vals
if not vertical:
x, y = y, x
ax.plot(x, y, color=gray, alpha=2. / 3)
# Label the axes and ticks
if vertical:
ax.set_xticklabels(list(names))
else:
ax.set_yticklabels(list(names))
xlabel, ylabel = ylabel, xlabel
if xlabel is not None:
ax.set_xlabel(xlabel)
if ylabel is not None:
ax.set_ylabel(ylabel)
# Turn off the grid parallel to the boxes
if vertical:
ax.xaxis.grid(False)
else:
ax.yaxis.grid(False)
return ax
def violinplot(vals, groupby=None, inner="box", color=None, positions=None,
names=None, order=None, bw="scott", widths=.8, alpha=None,
saturation=.7, join_rm=False, gridsize=100, cut=3,
inner_kws=None, ax=None, vert=True, **kwargs):
"""Create a violin plot (a combination of boxplot and kernel density plot).
Parameters
----------
vals : DataFrame, Series, 2D array, or list of vectors.
Data for plot. DataFrames and 2D arrays are assumed to be "wide" with
each column mapping to a box. Lists of data are assumed to have one
element per box. Can also provide one long Series in conjunction with
a grouping element as the `groupy` parameter to reshape the data into
several violins. Otherwise 1D data will produce a single violins.
groupby : grouping object
If `vals` is a Series, this is used to group into boxes by calling
pd.groupby(vals, groupby).
inner : {'box' | 'stick' | 'points'}
Plot quartiles or individual sample values inside violin.
color : mpl color, sequence of colors, or seaborn palette name
Inner violin colors
positions : number or sequence of numbers
Position of first violin or positions of each violin.
names : list of strings, optional
Names to plot on x axis; otherwise plots numbers. This will override
names inferred from Pandas inputs.
order : list of strings, optional
If vals is a Pandas object with name information, you can control the
order of the plot by providing the violin names in your preferred
order.
bw : {'scott' | 'silverman' | scalar}
Name of reference method to determine kernel size, or size as a
scalar.
widths : float
Width of each violin at maximum density.
alpha : float, optional
Transparancy of violin fill.
saturation : float, 0-1
Saturation relative to the fully-saturated color. Large patches tend
to look better at lower saturations, so this dims the palette colors
a bit by default.
join_rm : boolean, optional
If True, positions in the input arrays are treated as repeated
measures and are joined with a line plot.
gridsize : int
Number of discrete gridpoints to evaluate the density on.
cut : scalar
Draw the estimate to cut * bw from the extreme data points.
inner_kws : dict, optional
Keyword arugments for inner plot.
ax : matplotlib axis, optional
Axis to plot on, otherwise grab current axis.
vert : boolean, optional
If true (default), draw vertical plots; otherwise, draw horizontal
ones.
kwargs : additional parameters to fill_betweenx
Returns
-------
ax : matplotlib axis
Axis with violin plot.
"""
if ax is None:
ax = plt.gca()
# Reshape and find labels for the plot
vals, xlabel, ylabel, names = _box_reshape(vals, groupby, names, order)
# Sort out the plot colors
colors, gray = _box_colors(vals, color, saturation)
# Initialize the kwarg dict for the inner plot
if inner_kws is None:
inner_kws = {}
inner_kws.setdefault("alpha", .6 if inner == "points" else 1)
inner_kws["alpha"] *= 1 if alpha is None else alpha
inner_kws.setdefault("color", gray)
inner_kws.setdefault("marker", "." if inner == "points" else "")
lw = inner_kws.pop("lw", 1.5 if inner == "box" else .8)
inner_kws.setdefault("linewidth", lw)
# Find where the violins are going
if positions is None:
positions = np.arange(1, len(vals) + 1)
elif not hasattr(positions, "__iter__"):
positions = np.arange(positions, len(vals) + positions)
# Set the default linewidth if not provided in kwargs
try:
lw = kwargs[({"lw", "linewidth"} & set(kwargs)).pop()]
except KeyError:
lw = 1.5
# Iterate over the variables
for i, a in enumerate(vals):
x = positions[i]
# If we only have a single value, plot a horizontal line
if len(a) == 1:
y = a[0]
if vert:
ax.plot([x - widths / 2, x + widths / 2], [y, y], **inner_kws)
else:
ax.plot([y, y], [x - widths / 2, x + widths / 2], **inner_kws)
continue
# Fit the KDE
try:
kde = stats.gaussian_kde(a, bw)
except TypeError:
kde = stats.gaussian_kde(a)
if bw != "scott": # scipy default
msg = ("Ignoring bandwidth choice, "
"please upgrade scipy to use a different bandwidth.")
warnings.warn(msg, UserWarning)
# Determine the support region
if isinstance(bw, str):
bw_name = "scotts" if bw == "scott" else bw
_bw = getattr(kde, "%s_factor" % bw_name)() * a.std(ddof=1)
else:
_bw = bw
y = _kde_support(a, _bw, gridsize, cut, (-np.inf, np.inf))
dens = kde.evaluate(y)
scl = 1 / (dens.max() / (widths / 2))
dens *= scl
# Draw the violin. If vert (default), we will use ``ax.plot`` in the
# standard way; otherwise, we invert x,y.
# For this, define a simple wrapper ``ax_plot``
color = colors[i]
if vert:
ax.fill_betweenx(y, x - dens, x + dens, alpha=alpha, color=color)
def ax_plot(x, y, *args, **kwargs):
ax.plot(x, y, *args, **kwargs)
else:
ax.fill_between(y, x - dens, x + dens, alpha=alpha, color=color)
def ax_plot(x, y, *args, **kwargs):
ax.plot(y, x, *args, **kwargs)
if inner == "box":
for quant in percentiles(a, [25, 75]):
q_x = kde.evaluate(quant) * scl
q_x = [x - q_x, x + q_x]
ax_plot(q_x, [quant, quant], linestyle=":", **inner_kws)
med = np.median(a)
m_x = kde.evaluate(med) * scl
m_x = [x - m_x, x + m_x]
ax_plot(m_x, [med, med], linestyle="--", **inner_kws)
elif inner == "stick":
x_vals = kde.evaluate(a) * scl
x_vals = [x - x_vals, x + x_vals]
ax_plot(x_vals, [a, a], linestyle="-", **inner_kws)
elif inner == "points":
x_vals = [x for _ in a]
ax_plot(x_vals, a, mew=0, linestyle="", **inner_kws)
for side in [-1, 1]:
ax_plot((side * dens) + x, y, c=gray, lw=lw)
# Draw the repeated measure bridges
if join_rm:
ax.plot(range(1, len(vals) + 1), vals,
color=inner_kws["color"], alpha=2. / 3)
# Add in semantic labels
if names is not None:
if len(vals) != len(names):
raise ValueError("Length of names list must match nuber of bins")
names = list(names)
if vert:
# Add in semantic labels
ax.set_xticks(positions)
ax.set_xlim(positions[0] - .5, positions[-1] + .5)
ax.set_xticklabels(names)
if xlabel is not None:
ax.set_xlabel(xlabel)
if ylabel is not None:
ax.set_ylabel(ylabel)
else:
# Add in semantic labels
ax.set_yticks(positions)
ax.set_yticklabels(names)
ax.set_ylim(positions[0] - .5, positions[-1] + .5)
if ylabel is not None:
ax.set_ylabel(xlabel)
if xlabel is not None:
ax.set_xlabel(ylabel)
ax.xaxis.grid(False)
return ax
def _freedman_diaconis_bins(a):
"""Calculate number of hist bins using Freedman-Diaconis rule."""
# From http://stats.stackexchange.com/questions/798/
a = np.asarray(a)
h = 2 * iqr(a) / (len(a) ** (1 / 3))
return np.ceil((a.max() - a.min()) / h)
def distplot(a, bins=None, hist=True, kde=True, rug=False, fit=None,
hist_kws=None, kde_kws=None, rug_kws=None, fit_kws=None,
color=None, vertical=False, norm_hist=False, axlabel=None,
label=None, ax=None):
"""Flexibly plot a distribution of observations.
Parameters
----------
a : (squeezable to) 1d array
Observed data.
bins : argument for matplotlib hist(), or None, optional
Specification of hist bins, or None to use Freedman-Diaconis rule.
hist : bool, optional
Whether to plot a (normed) histogram.
kde : bool, optional
Whether to plot a gaussian kernel density estimate.
rug : bool, optional
Whether to draw a rugplot on the support axis.
fit : random variable object, optional
An object with `fit` method, returning a tuple that can be passed to a
`pdf` method a positional arguments following an grid of values to
evaluate the pdf on.
{hist, kde, rug, fit}_kws : dictionaries, optional
Keyword arguments for underlying plotting functions.
color : matplotlib color, optional
Color to plot everything but the fitted curve in.
vertical : bool, optional
If True, oberved values are on y-axis.
norm_hist : bool, otional
If True, the histogram height shows a density rather than a count.
This is implied if a KDE or fitted density is plotted.
axlabel : string, False, or None, optional
Name for the support axis label. If None, will try to get it
from a.namel if False, do not set a label.
label : string, optional
Legend label for the relevent component of the plot
ax : matplotlib axis, optional
if provided, plot on this axis
Returns
-------
ax : matplotlib axis
"""
if ax is None:
ax = plt.gca()
# Intelligently label the support axis
label_ax = bool(axlabel)
if axlabel is None and hasattr(a, "name"):
axlabel = a.name
if axlabel is not None:
label_ax = True
# Make a a 1-d array
a = np.asarray(a).squeeze()
# Decide if the hist is normed
norm_hist = norm_hist or kde or (fit is not None)
# Handle dictionary defaults
if hist_kws is None:
hist_kws = dict()
if kde_kws is None:
kde_kws = dict()
if rug_kws is None:
rug_kws = dict()
if fit_kws is None:
fit_kws = dict()
# Get the color from the current color cycle
if color is None:
if vertical:
line, = ax.plot(0, a.mean())
else:
line, = ax.plot(a.mean(), 0)
color = line.get_color()
line.remove()
# Plug the label into the right kwarg dictionary
if label is not None:
if hist:
hist_kws["label"] = label
elif kde:
kde_kws["label"] = label
elif rug:
rug_kws["label"] = label
elif fit:
fit_kws["label"] = label
if hist:
if bins is None:
bins = _freedman_diaconis_bins(a)
hist_kws.setdefault("alpha", 0.4)
hist_kws.setdefault("normed", norm_hist)
orientation = "horizontal" if vertical else "vertical"
hist_color = hist_kws.pop("color", color)
ax.hist(a, bins, orientation=orientation,
color=hist_color, **hist_kws)
if hist_color != color:
hist_kws["color"] = hist_color
if kde:
kde_color = kde_kws.pop("color", color)
kdeplot(a, vertical=vertical, ax=ax, color=kde_color, **kde_kws)
if kde_color != color:
kde_kws["color"] = kde_color
if rug:
rug_color = rug_kws.pop("color", color)
axis = "y" if vertical else "x"
rugplot(a, axis=axis, ax=ax, color=rug_color, **rug_kws)
if rug_color != color:
rug_kws["color"] = rug_color
if fit is not None:
fit_color = fit_kws.pop("color", "#282828")
gridsize = fit_kws.pop("gridsize", 200)
cut = fit_kws.pop("cut", 3)
clip = fit_kws.pop("clip", (-np.inf, np.inf))
bw = stats.gaussian_kde(a).scotts_factor() * a.std(ddof=1)
x = _kde_support(a, bw, gridsize, cut, clip)
params = fit.fit(a)
pdf = lambda x: fit.pdf(x, *params)
y = pdf(x)
if vertical:
x, y = y, x
ax.plot(x, y, color=fit_color, **fit_kws)
if fit_color != "#282828":
fit_kws["color"] = fit_color
if label_ax:
if vertical:
ax.set_ylabel(axlabel)
else:
ax.set_xlabel(axlabel)
return ax
def _univariate_kdeplot(data, shade, vertical, kernel, bw, gridsize, cut,
clip, legend, ax, cumulative=False, **kwargs):
"""Plot a univariate kernel density estimate on one of the axes."""
# Sort out the clipping
if clip is None:
clip = (-np.inf, np.inf)
# Calculate the KDE
if _has_statsmodels:
# Prefer using statsmodels for kernel flexibility
x, y = _statsmodels_univariate_kde(data, kernel, bw,
gridsize, cut, clip,
cumulative=cumulative)
else:
# Fall back to scipy if missing statsmodels
if kernel != "gau":
kernel = "gau"
msg = "Kernel other than `gau` requires statsmodels."
warnings.warn(msg, UserWarning)
if cumulative:
raise ImportError("Cumulative distributions are currently"
"only implemented in statsmodels."
"Please install statsmodels.")
x, y = _scipy_univariate_kde(data, bw, gridsize, cut, clip)
# Make sure the density is nonnegative
y = np.amax(np.c_[np.zeros_like(y), y], axis=1)
# Flip the data if the plot should be on the y axis
if vertical:
x, y = y, x
# Check if a label was specified in the call
label = kwargs.pop("label", None)
# Otherwise check if the data object has a name
if label is None and hasattr(data, "name"):
label = data.name
# Decide if we're going to add a legend
legend = label is not None and legend
label = "_nolegend_" if label is None else label
# Use the active color cycle to find the plot color
line, = ax.plot(x, y, **kwargs)
color = line.get_color()
line.remove()
kwargs.pop("color", None)
# Draw the KDE plot and, optionally, shade
ax.plot(x, y, color=color, label=label, **kwargs)
alpha = kwargs.get("alpha", 0.25)
if shade:
if vertical:
ax.fill_betweenx(y, 1e-12, x, color=color, alpha=alpha)
else:
ax.fill_between(x, 1e-12, y, color=color, alpha=alpha)
# Draw the legend here
if legend:
ax.legend(loc="best")
return ax
def _statsmodels_univariate_kde(data, kernel, bw, gridsize, cut, clip,
cumulative=False):
"""Compute a univariate kernel density estimate using statsmodels."""
needs_statsmodels_0_6()
fft = kernel == "gau"
kde = sm.nonparametric.KDEUnivariate(data)
kde.fit(kernel, bw, fft, gridsize=gridsize, cut=cut, clip=clip)
if cumulative:
grid, y = kde.support, kde.cdf
else:
grid, y = kde.support, kde.density
return grid, y
def _scipy_univariate_kde(data, bw, gridsize, cut, clip):
"""Compute a univariate kernel density estimate using scipy."""
try:
kde = stats.gaussian_kde(data, bw_method=bw)
except TypeError:
kde = stats.gaussian_kde(data)
if bw != "scott": # scipy default
msg = ("Ignoring bandwidth choice, "
"please upgrade scipy to use a different bandwidth.")
warnings.warn(msg, UserWarning)
if isinstance(bw, str):
bw = "scotts" if bw == "scott" else bw
bw = getattr(kde, "%s_factor" % bw)()
grid = _kde_support(data, bw, gridsize, cut, clip)
y = kde(grid)
return grid, y
def _bivariate_kdeplot(x, y, filled, kernel, bw, gridsize, cut, clip, axlabel,
ax, **kwargs):
"""Plot a joint KDE estimate as a bivariate contour plot."""
# Determine the clipping
if clip is None:
clip = [(-np.inf, np.inf), (-np.inf, np.inf)]
elif np.ndim(clip) == 1:
clip = [clip, clip]
# Calculate the KDE
if _has_statsmodels:
xx, yy, z = _statsmodels_bivariate_kde(x, y, bw, gridsize, cut, clip)
else:
xx, yy, z = _scipy_bivariate_kde(x, y, bw, gridsize, cut, clip)
# Plot the contours
n_levels = kwargs.pop("n_levels", 10)
cmap = kwargs.get("cmap", "BuGn" if filled else "BuGn_d")
if isinstance(cmap, str):
if cmap.endswith("_d"):
pal = ["#333333"]
pal.extend(color_palette(cmap.replace("_d", "_r"), 2))
cmap = blend_palette(pal, as_cmap=True)
kwargs["cmap"] = cmap
contour_func = ax.contourf if filled else ax.contour
contour_func(xx, yy, z, n_levels, **kwargs)
kwargs["n_levels"] = n_levels
# Label the axes
if hasattr(x, "name") and axlabel:
ax.set_xlabel(x.name)
if hasattr(y, "name") and axlabel:
ax.set_ylabel(y.name)
return ax
def _statsmodels_bivariate_kde(x, y, bw, gridsize, cut, clip):
"""Compute a bivariate kde using statsmodels."""
needs_statsmodels_0_6()
if isinstance(bw, str):
bw_func = getattr(sm.nonparametric.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 = sm.nonparametric.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 _scipy_bivariate_kde(x, y, bw, gridsize, cut, clip):
"""Compute a bivariate kde using scipy."""
data = np.c_[x, y]
kde = stats.gaussian_kde(data.T)
data_std = data.std(axis=0, ddof=1)
if isinstance(bw, str):
bw = "scotts" if bw == "scott" else bw
bw_x = getattr(kde, "%s_factor" % bw)() * data_std[0]
bw_y = getattr(kde, "%s_factor" % bw)() * data_std[1]
x_support = _kde_support(data[:, 0], bw_x, gridsize, cut, clip[0])
y_support = _kde_support(data[:, 1], bw_y, gridsize, cut, clip[1])
xx, yy = np.meshgrid(x_support, y_support)
z = kde([xx.ravel(), yy.ravel()]).reshape(xx.shape)
return xx, yy, z
def kdeplot(data, data2=None, shade=False, vertical=False, kernel="gau",
bw="scott", gridsize=100, cut=3, clip=None, legend=True, ax=None,
cumulative=False, **kwargs):
"""Fit and plot a univariate or bivarate kernel density estimate.
Parameters
----------
data : 1d or 2d array-like
Input data. If two-dimensional, assumed to be shaped (n_unit x n_var),
and a bivariate contour plot will be drawn.
data2: 1d array-like
Second input data. If provided `data` must be one-dimensional, and
a bivariate plot is produced.
shade : bool, optional
If true, shade in the area under the KDE curve (or draw with filled
contours when data is bivariate).
vertical : bool
If True, density is on x-axis.
kernel : {'gau' | 'cos' | 'biw' | 'epa' | 'tri' | 'triw' }, optional
Code for shape of kernel to fit with. Bivariate KDE can only use
gaussian kernel.
bw : {'scott' | 'silverman' | scalar | pair of scalars }, optional
Name of reference method to determine kernel size, scalar factor,
or scalar for each dimension of the bivariate plot.
gridsize : int, optional
Number of discrete points in the evaluation grid.
cut : scalar, optional
Draw the estimate to cut * bw from the extreme data points.
clip : pair of scalars, or pair of pair of scalars, optional
Lower and upper bounds for datapoints used to fit KDE. Can provide
a pair of (low, high) bounds for bivariate plots.
legend : bool, optoinal
If True, add a legend or label the axes when possible.
ax : matplotlib axis, optional
Axis to plot on, otherwise uses current axis.
cumulative : bool
If draw, draw the cumulative distribution estimated by the kde.
kwargs : other keyword arguments for plot()
Returns
-------
ax : matplotlib axis
Axis with plot.
"""
if ax is None:
ax = plt.gca()
data = data.astype(np.float64)
if data2 is not None:
data2 = data2.astype(np.float64)
bivariate = False
if isinstance(data, np.ndarray) and np.ndim(data) > 1:
bivariate = True
x, y = data.T
elif isinstance(data, pd.DataFrame) and np.ndim(data) > 1:
bivariate = True
x = data.iloc[:, 0].values
y = data.iloc[:, 1].values
elif data2 is not None:
bivariate = True
x = data
y = data2
if bivariate and cumulative:
raise TypeError("Cumulative distribution plots are not"
"supported for bivariate distributions.")
if bivariate:
ax = _bivariate_kdeplot(x, y, shade, kernel, bw, gridsize,
cut, clip, legend, ax, **kwargs)
else:
ax = _univariate_kdeplot(data, shade, vertical, kernel, bw,
gridsize, cut, clip, legend, ax,
cumulative=cumulative, **kwargs)
return ax
def rugplot(a, height=None, axis="x", ax=None, **kwargs):
"""Plot datapoints in an array as sticks on an axis.
Parameters
----------
a : vector
1D array of datapoints.
height : scalar, optional
Height of ticks, if None draw at 5% of axis range.
axis : {'x' | 'y'}, optional
Axis to draw rugplot on.
ax : matplotlib axis
Axis to draw plot into; otherwise grabs current axis.
kwargs : other keyword arguments for plt.plot()
Returns
-------
ax : matplotlib axis
Axis with rugplot.
"""
if ax is None:
ax = plt.gca()
a = np.asarray(a)
vertical = kwargs.pop("vertical", None)
if vertical is not None:
axis = "y" if vertical else "x"
other_axis = dict(x="y", y="x")[axis]
min, max = getattr(ax, "get_%slim" % other_axis)()
if height is None:
range = max - min
height = range * .05
if axis == "x":
ax.plot([a, a], [min, min + height], **kwargs)
else:
ax.plot([min, min + height], [a, a], **kwargs)
return ax
def jointplot(x, y, data=None, kind="scatter", stat_func=stats.pearsonr,
color=None, size=6, ratio=5, space=.2,
dropna=True, xlim=None, ylim=None,
joint_kws=None, marginal_kws=None, annot_kws=None):
"""Draw a plot of two variables with bivariate and univariate graphs.
Parameters
----------
x, y : strings or vectors
Data or names of variables in `data`.
data : DataFrame, optional
DataFrame when `x` and `y` are variable names.
kind : { "scatter" | "reg" | "resid" | "kde" | "hex" }, optional
Kind of plot to draw.
stat_func : callable or None
Function used to calculate a statistic about the relationship and
annotate the plot. Should map `x` and `y` either to a single value
or to a (value, p) tuple. Set to ``None`` if you don't want to
annotate the plot.
color : matplotlib color, optional
Color used for the plot elements.
size : numeric, optional
Size of the figure (it will be square).
ratio : numeric, optional
Ratio of joint axes size to marginal axes height.
space : numeric, optional
Space between the joint and marginal axes
dropna : bool, optional
If True, remove observations that are missing from `x` and `y`.
{x, y}lim : two-tuples, optional
Axis limits to set before plotting.
{joint, marginal, annot}_kws : dicts
Additional keyword arguments for the plot components.
Returns
-------
grid : JointGrid
JointGrid object with the plot on it.
See Also
--------
JointGrid : The Grid class used for drawing this plot. Use it directly if
you need more flexibility.
"""
# Set up empty default kwarg dicts
if joint_kws is None:
joint_kws = {}
if marginal_kws is None:
marginal_kws = {}
if annot_kws is None:
annot_kws = {}
# Make a colormap based off the plot color
if color is None:
color = color_palette()[0]
color_rgb = mpl.colors.colorConverter.to_rgb(color)
colors = [set_hls_values(color_rgb, l=l) for l in np.linspace(1, 0, 12)]
cmap = blend_palette(colors, as_cmap=True)
# Initialize the JointGrid object
grid = JointGrid(x, y, data, dropna=dropna,
size=size, ratio=ratio, space=space,
xlim=xlim, ylim=ylim)
# Plot the data using the grid
if kind == "scatter":
joint_kws.setdefault("color", color)
grid.plot_joint(plt.scatter, **joint_kws)
marginal_kws.setdefault("kde", False)
marginal_kws.setdefault("color", color)
grid.plot_marginals(distplot, **marginal_kws)
elif kind.startswith("hex"):
x_bins = _freedman_diaconis_bins(grid.x)
y_bins = _freedman_diaconis_bins(grid.y)
gridsize = int(np.mean([x_bins, y_bins]))
joint_kws.setdefault("gridsize", gridsize)
joint_kws.setdefault("cmap", cmap)
grid.plot_joint(plt.hexbin, **joint_kws)
marginal_kws.setdefault("kde", False)
marginal_kws.setdefault("color", color)
grid.plot_marginals(distplot, **marginal_kws)
elif kind.startswith("kde"):
joint_kws.setdefault("shade", True)
joint_kws.setdefault("cmap", cmap)
grid.plot_joint(kdeplot, **joint_kws)
marginal_kws.setdefault("shade", True)
marginal_kws.setdefault("color", color)
grid.plot_marginals(kdeplot, **marginal_kws)
elif kind.startswith("reg"):
from .linearmodels import regplot
marginal_kws.setdefault("color", color)
grid.plot_marginals(distplot, **marginal_kws)
joint_kws.setdefault("color", color)
grid.plot_joint(regplot, **joint_kws)
elif kind.startswith("resid"):
from .linearmodels import residplot
joint_kws.setdefault("color", color)
grid.plot_joint(residplot, **joint_kws)
x, y = grid.ax_joint.collections[0].get_offsets().T
marginal_kws.setdefault("color", color)
marginal_kws.setdefault("kde", False)
distplot(x, ax=grid.ax_marg_x, **marginal_kws)
distplot(y, vertical=True, fit=stats.norm, ax=grid.ax_marg_y,
**marginal_kws)
stat_func = None
else:
msg = "kind must be either 'scatter', 'reg', 'resid', 'kde', or 'hex'"
raise ValueError(msg)
if stat_func is not None:
grid.annotate(stat_func, **annot_kws)
return grid
|