forked from geopandas/geopandas
/
plotting.py
724 lines (608 loc) · 23.2 KB
/
plotting.py
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
from __future__ import print_function
import warnings
import numpy as np
import pandas as pd
def _flatten_multi_geoms(geoms, colors=None):
"""
Returns Series like geoms and colors, except that any Multi geometries
are split into their components and colors are repeated for all component
in the same Multi geometry. Maintains 1:1 matching of geometry to color.
Passing `color` is optional, and when no `color` is passed a list of None
values is returned as `component_colors`.
"Colors" are treated opaquely and so can actually contain any values.
Returns
-------
components : list of geometry
component_colors : list of whatever type `colors` contains
"""
if colors is None:
colors = [None] * len(geoms)
components, component_colors = [], []
if not geoms.geom_type.str.startswith("Multi").any():
return geoms, colors
# precondition, so zip can't short-circuit
assert len(geoms) == len(colors)
for geom, color in zip(geoms, colors):
if geom.type.startswith("Multi"):
for poly in geom:
components.append(poly)
# repeat same color for all components
component_colors.append(color)
else:
components.append(geom)
component_colors.append(color)
return components, component_colors
def plot_polygon_collection(
ax, geoms, values=None, color=None, cmap=None, vmin=None, vmax=None, **kwargs
):
"""
Plots a collection of Polygon and MultiPolygon geometries to `ax`
Parameters
----------
ax : matplotlib.axes.Axes
where shapes will be plotted
geoms : a sequence of `N` Polygons and/or MultiPolygons (can be mixed)
values : a sequence of `N` values, optional
Values will be mapped to colors using vmin/vmax/cmap. They should
have 1:1 correspondence with the geometries (not their components).
Otherwise follows `color` / `facecolor` kwargs.
edgecolor : single color or sequence of `N` colors
Color for the edge of the polygons
facecolor : single color or sequence of `N` colors
Color to fill the polygons. Cannot be used together with `values`.
color : single color or sequence of `N` colors
Sets both `edgecolor` and `facecolor`
**kwargs
Additional keyword arguments passed to the collection
Returns
-------
collection : matplotlib.collections.Collection that was plotted
"""
try:
from descartes.patch import PolygonPatch
except ImportError:
raise ImportError(
"The descartes package is required for plotting polygons in geopandas."
)
from matplotlib.collections import PatchCollection
geoms, multiindex = _flatten_multi_geoms(geoms, range(len(geoms)))
if values is not None:
values = np.take(values, multiindex)
# PatchCollection does not accept some kwargs.
if "markersize" in kwargs:
del kwargs["markersize"]
if color is not None:
kwargs["color"] = color
if pd.api.types.is_list_like(color):
kwargs["color"] = np.take(color, multiindex)
else:
kwargs["color"] = color
else:
for att in ["facecolor", "edgecolor"]:
if att in kwargs:
if pd.api.types.is_list_like(kwargs[att]):
kwargs[att] = np.take(kwargs[att], multiindex)
collection = PatchCollection([PolygonPatch(poly) for poly in geoms], **kwargs)
if values is not None:
collection.set_array(np.asarray(values))
collection.set_cmap(cmap)
if "norm" not in kwargs:
collection.set_clim(vmin, vmax)
ax.add_collection(collection, autolim=True)
ax.autoscale_view()
return collection
def plot_linestring_collection(
ax, geoms, values=None, color=None, cmap=None, vmin=None, vmax=None, **kwargs
):
"""
Plots a collection of LineString and MultiLineString geometries to `ax`
Parameters
----------
ax : matplotlib.axes.Axes
where shapes will be plotted
geoms : a sequence of `N` LineStrings and/or MultiLineStrings (can be
mixed)
values : a sequence of `N` values, optional
Values will be mapped to colors using vmin/vmax/cmap. They should
have 1:1 correspondence with the geometries (not their components).
color : single color or sequence of `N` colors
Cannot be used together with `values`.
Returns
-------
collection : matplotlib.collections.Collection that was plotted
"""
from matplotlib.collections import LineCollection
geoms, multiindex = _flatten_multi_geoms(geoms, range(len(geoms)))
if values is not None:
values = np.take(values, multiindex)
# LineCollection does not accept some kwargs.
if "markersize" in kwargs:
del kwargs["markersize"]
# color=None gives black instead of default color cycle
if color is not None:
if pd.api.types.is_list_like(color):
kwargs["color"] = np.take(color, multiindex)
else:
kwargs["color"] = color
segments = [np.array(linestring)[:, :2] for linestring in geoms]
collection = LineCollection(segments, **kwargs)
if values is not None:
collection.set_array(np.asarray(values))
collection.set_cmap(cmap)
if "norm" not in kwargs:
collection.set_clim(vmin, vmax)
ax.add_collection(collection, autolim=True)
ax.autoscale_view()
return collection
def plot_point_collection(
ax,
geoms,
values=None,
color=None,
cmap=None,
vmin=None,
vmax=None,
marker="o",
markersize=None,
**kwargs
):
"""
Plots a collection of Point and MultiPoint geometries to `ax`
Parameters
----------
ax : matplotlib.axes.Axes
where shapes will be plotted
geoms : sequence of `N` Points or MultiPoints
values : a sequence of `N` values, optional
Values mapped to colors using vmin, vmax, and cmap.
Cannot be specified together with `color`.
markersize : scalar or array-like, optional
Size of the markers. Note that under the hood ``scatter`` is
used, so the specified value will be proportional to the
area of the marker (size in points^2).
Returns
-------
collection : matplotlib.collections.Collection that was plotted
"""
if values is not None and color is not None:
raise ValueError("Can only specify one of 'values' and 'color' kwargs")
geoms, multiindex = _flatten_multi_geoms(geoms, range(len(geoms)))
if values is not None:
values = np.take(values, multiindex)
x = [p.x for p in geoms]
y = [p.y for p in geoms]
# matplotlib 1.4 does not support c=None, and < 2.0 does not support s=None
if values is not None:
kwargs["c"] = values
if markersize is not None:
kwargs["s"] = markersize
if color is not None:
if pd.api.types.is_list_like(color):
color = np.take(color, multiindex)
if "norm" not in kwargs:
collection = ax.scatter(
x, y, color=color, vmin=vmin, vmax=vmax, cmap=cmap, marker=marker, **kwargs
)
else:
collection = ax.scatter(x, y, color=color, cmap=cmap, marker=marker, **kwargs)
return collection
def plot_series(s, cmap=None, color=None, ax=None, figsize=None, **style_kwds):
"""
Plot a GeoSeries.
Generate a plot of a GeoSeries geometry with matplotlib.
Parameters
----------
s : Series
The GeoSeries to be plotted. Currently Polygon,
MultiPolygon, LineString, MultiLineString and Point
geometries can be plotted.
cmap : str (default None)
The name of a colormap recognized by matplotlib. Any
colormap will work, but categorical colormaps are
generally recommended. Examples of useful discrete
colormaps include:
tab10, tab20, Accent, Dark2, Paired, Pastel1, Set1, Set2
color : str (default None)
If specified, all objects will be colored uniformly.
ax : matplotlib.pyplot.Artist (default None)
axes on which to draw the plot
figsize : pair of floats (default None)
Size of the resulting matplotlib.figure.Figure. If the argument
ax is given explicitly, figsize is ignored.
**style_kwds : dict
Color options to be passed on to the actual plot function, such
as ``edgecolor``, ``facecolor``, ``linewidth``, ``markersize``,
``alpha``.
Returns
-------
ax : matplotlib axes instance
"""
if "colormap" in style_kwds:
warnings.warn(
"'colormap' is deprecated, please use 'cmap' instead "
"(for consistency with matplotlib)",
FutureWarning,
)
cmap = style_kwds.pop("colormap")
if "axes" in style_kwds:
warnings.warn(
"'axes' is deprecated, please use 'ax' instead "
"(for consistency with pandas)",
FutureWarning,
)
ax = style_kwds.pop("axes")
import matplotlib.pyplot as plt
if ax is None:
fig, ax = plt.subplots(figsize=figsize)
ax.set_aspect("equal")
if s.empty:
warnings.warn(
"The GeoSeries you are attempting to plot is "
"empty. Nothing has been displayed.",
UserWarning,
)
return ax
# if cmap is specified, create range of colors based on cmap
values = None
if cmap is not None:
values = np.arange(len(s))
if hasattr(cmap, "N"):
values = values % cmap.N
style_kwds["vmin"] = style_kwds.get("vmin", values.min())
style_kwds["vmax"] = style_kwds.get("vmax", values.max())
geom_types = s.geometry.type
poly_idx = np.asarray((geom_types == "Polygon") | (geom_types == "MultiPolygon"))
line_idx = np.asarray(
(geom_types == "LineString") | (geom_types == "MultiLineString")
)
point_idx = np.asarray((geom_types == "Point") | (geom_types == "MultiPoint"))
# plot all Polygons and all MultiPolygon components in the same collection
polys = s.geometry[poly_idx]
if not polys.empty:
# color overrides both face and edgecolor. As we want people to be
# able to use edgecolor as well, pass color to facecolor
facecolor = style_kwds.pop("facecolor", None)
if color is not None:
facecolor = color
values_ = values[poly_idx] if cmap else None
plot_polygon_collection(
ax, polys, values_, facecolor=facecolor, cmap=cmap, **style_kwds
)
# plot all LineStrings and MultiLineString components in same collection
lines = s.geometry[line_idx]
if not lines.empty:
values_ = values[line_idx] if cmap else None
plot_linestring_collection(
ax, lines, values_, color=color, cmap=cmap, **style_kwds
)
# plot all Points in the same collection
points = s.geometry[point_idx]
if not points.empty:
values_ = values[point_idx] if cmap else None
plot_point_collection(ax, points, values_, color=color, cmap=cmap, **style_kwds)
plt.draw()
return ax
def plot_dataframe(
df,
column=None,
cmap=None,
color=None,
ax=None,
cax=None,
categorical=False,
legend=False,
scheme=None,
k=5,
vmin=None,
vmax=None,
markersize=None,
figsize=None,
legend_kwds=None,
classification_kwds=None,
**style_kwds
):
"""
Plot a GeoDataFrame.
Generate a plot of a GeoDataFrame with matplotlib. If a
column is specified, the plot coloring will be based on values
in that column.
Parameters
----------
df : GeoDataFrame
The GeoDataFrame to be plotted. Currently Polygon,
MultiPolygon, LineString, MultiLineString and Point
geometries can be plotted.
column : str, np.array, pd.Series (default None)
The name of the dataframe column, np.array, or pd.Series to be plotted.
If np.array or pd.Series are used then it must have same length as
dataframe. Values are used to color the plot. Ignored if `color` is
also set.
cmap : str (default None)
The name of a colormap recognized by matplotlib.
color : str (default None)
If specified, all objects will be colored uniformly.
ax : matplotlib.pyplot.Artist (default None)
axes on which to draw the plot
cax : matplotlib.pyplot Artist (default None)
axes on which to draw the legend in case of color map.
categorical : bool (default False)
If False, cmap will reflect numerical values of the
column being plotted. For non-numerical columns, this
will be set to True.
legend : bool (default False)
Plot a legend. Ignored if no `column` is given, or if `color` is given.
scheme : str (default None)
Name of a choropleth classification scheme (requires mapclassify).
A mapclassify.MapClassifier object will be used
under the hood. Supported are all schemes provided by mapclassify (e.g.
'BoxPlot', 'EqualInterval', 'FisherJenks', 'FisherJenksSampled',
'HeadTailBreaks', 'JenksCaspall', 'JenksCaspallForced',
'JenksCaspallSampled', 'MaxP', 'MaximumBreaks',
'NaturalBreaks', 'Quantiles', 'Percentiles', 'StdMean',
'UserDefined'). Arguments can be passed in classification_kwds.
k : int (default 5)
Number of classes (ignored if scheme is None)
vmin : None or float (default None)
Minimum value of cmap. If None, the minimum data value
in the column to be plotted is used.
vmax : None or float (default None)
Maximum value of cmap. If None, the maximum data value
in the column to be plotted is used.
markersize : str or float or sequence (default None)
Only applies to point geometries within a frame.
If a str, will use the values in the column of the frame specified
by markersize to set the size of markers. Otherwise can be a value
to apply to all points, or a sequence of the same length as the
number of points.
figsize : tuple of integers (default None)
Size of the resulting matplotlib.figure.Figure. If the argument
axes is given explicitly, figsize is ignored.
legend_kwds : dict (default None)
Keyword arguments to pass to matplotlib.pyplot.legend() or
matplotlib.pyplot.colorbar().
classification_kwds : dict (default None)
Keyword arguments to pass to mapclassify
**style_kwds : dict
Color options to be passed on to the actual plot function, such
as ``edgecolor``, ``facecolor``, ``linewidth``, ``markersize``,
``alpha``.
Returns
-------
ax : matplotlib axes instance
"""
if "colormap" in style_kwds:
warnings.warn(
"'colormap' is deprecated, please use 'cmap' instead "
"(for consistency with matplotlib)",
FutureWarning,
)
cmap = style_kwds.pop("colormap")
if "axes" in style_kwds:
warnings.warn(
"'axes' is deprecated, please use 'ax' instead "
"(for consistency with pandas)",
FutureWarning,
)
ax = style_kwds.pop("axes")
if column is not None and color is not None:
warnings.warn(
"Only specify one of 'column' or 'color'. Using 'color'.", UserWarning
)
column = None
import matplotlib.pyplot as plt
if ax is None:
if cax is not None:
raise ValueError("'ax' can not be None if 'cax' is not.")
fig, ax = plt.subplots(figsize=figsize)
ax.set_aspect("equal")
if df.empty:
warnings.warn(
"The GeoDataFrame you are attempting to plot is "
"empty. Nothing has been displayed.",
UserWarning,
)
return ax
if isinstance(markersize, str):
markersize = df[markersize].values
if column is None:
return plot_series(
df.geometry,
cmap=cmap,
color=color,
ax=ax,
figsize=figsize,
markersize=markersize,
**style_kwds
)
# To accept pd.Series and np.arrays as column
if isinstance(column, (np.ndarray, pd.Series)):
if column.shape[0] != df.shape[0]:
raise ValueError(
"The dataframe and given column have different number of rows."
)
else:
values = np.asarray(column)
else:
values = np.asarray(df[column])
if values.dtype is np.dtype("O"):
categorical = True
# Define `values` as a Series
if categorical:
if cmap is None:
cmap = "tab10"
categories = list(set(values))
categories.sort()
valuemap = dict((k, v) for (v, k) in enumerate(categories))
values = np.array([valuemap[k] for k in values])
if scheme is not None:
if classification_kwds is None:
classification_kwds = {}
if "k" not in classification_kwds:
classification_kwds["k"] = k
binning = _mapclassify_choro(values, scheme, **classification_kwds)
# set categorical to True for creating the legend
categorical = True
binedges = [values.min()] + binning.bins.tolist()
categories = [
"{0:.2f} - {1:.2f}".format(binedges[i], binedges[i + 1])
for i in range(len(binedges) - 1)
]
values = np.array(binning.yb)
mn = values[~np.isnan(values)].min() if vmin is None else vmin
mx = values[~np.isnan(values)].max() if vmax is None else vmax
geom_types = df.geometry.type
poly_idx = np.asarray((geom_types == "Polygon") | (geom_types == "MultiPolygon"))
line_idx = np.asarray(
(geom_types == "LineString") | (geom_types == "MultiLineString")
)
point_idx = np.asarray((geom_types == "Point") | (geom_types == "MultiPoint"))
# plot all Polygons and all MultiPolygon components in the same collection
polys = df.geometry[poly_idx]
if not polys.empty:
plot_polygon_collection(
ax, polys, values[poly_idx], vmin=mn, vmax=mx, cmap=cmap, **style_kwds
)
# plot all LineStrings and MultiLineString components in same collection
lines = df.geometry[line_idx]
if not lines.empty:
plot_linestring_collection(
ax, lines, values[line_idx], vmin=mn, vmax=mx, cmap=cmap, **style_kwds
)
# plot all Points in the same collection
points = df.geometry[point_idx]
if not points.empty:
if isinstance(markersize, np.ndarray):
markersize = markersize[point_idx]
plot_point_collection(
ax,
points,
values[point_idx],
vmin=mn,
vmax=mx,
markersize=markersize,
cmap=cmap,
**style_kwds
)
if legend and not color:
if legend_kwds is None:
legend_kwds = {}
from matplotlib.lines import Line2D
from matplotlib.colors import Normalize
from matplotlib import cm
norm = style_kwds.get("norm", None)
if not norm:
norm = Normalize(vmin=mn, vmax=mx)
n_cmap = cm.ScalarMappable(norm=norm, cmap=cmap)
if categorical:
patches = []
for value, cat in enumerate(categories):
patches.append(
Line2D(
[0],
[0],
linestyle="none",
marker="o",
alpha=style_kwds.get("alpha", 1),
markersize=10,
markerfacecolor=n_cmap.to_rgba(value),
markeredgewidth=0,
)
)
legend_kwds.setdefault("numpoints", 1)
legend_kwds.setdefault("loc", "best")
ax.legend(patches, categories, **legend_kwds)
else:
if cax is not None:
legend_kwds.setdefault("cax", cax)
else:
legend_kwds.setdefault("ax", ax)
n_cmap.set_array([])
ax.get_figure().colorbar(n_cmap, **legend_kwds)
plt.draw()
return ax
def _mapclassify_choro(values, scheme, **classification_kwds):
"""
Wrapper for choropleth schemes from mapclassify for use with plot_dataframe
Parameters
----------
values
Series to be plotted
scheme : str
One of mapclassify classification schemes
Options are BoxPlot, EqualInterval, FisherJenks,
FisherJenksSampled, HeadTailBreaks, JenksCaspall,
JenksCaspallForced, JenksCaspallSampled, MaxP,
MaximumBreaks, NaturalBreaks, Quantiles, Percentiles, StdMean,
UserDefined
**classification_kwds : dict
Keyword arguments for classification scheme
For details see mapclassify documentation:
https://mapclassify.readthedocs.io/en/latest/api.html
Returns
-------
binning
Binning objects that holds the Series with values replaced with
class identifier and the bins.
"""
try:
import mapclassify.classifiers as classifiers
except ImportError:
try:
import pysal.viz.mapclassify.classifiers as classifiers
except ImportError:
raise ImportError(
"The 'mapclassify' or 'pysal' package is required to use the"
" 'scheme' keyword"
)
schemes = {}
for classifier in classifiers.CLASSIFIERS:
schemes[classifier.lower()] = getattr(classifiers, classifier)
scheme = scheme.lower()
# mapclassify < 2.1 cleaned up the scheme names (removing underscores)
# trying both to keep compatibility with older versions and provide
# compatibility with newer versions of mapclassify
oldnew = {
"Box_Plot": "BoxPlot",
"Equal_Interval": "EqualInterval",
"Fisher_Jenks": "FisherJenks",
"Fisher_Jenks_Sampled": "FisherJenksSampled",
"HeadTail_Breaks": "HeadTailBreaks",
"Jenks_Caspall": "JenksCaspall",
"Jenks_Caspall_Forced": "JenksCaspallForced",
"Jenks_Caspall_Sampled": "JenksCaspallSampled",
"Max_P_Plassifier": "MaxP",
"Maximum_Breaks": "MaximumBreaks",
"Natural_Breaks": "NaturalBreaks",
"Std_Mean": "StdMean",
"User_Defined": "UserDefined",
}
scheme_names_mapping = {}
scheme_names_mapping.update(
{old.lower(): new.lower() for old, new in oldnew.items()}
)
scheme_names_mapping.update(
{new.lower(): old.lower() for old, new in oldnew.items()}
)
try:
scheme_class = schemes[scheme]
except KeyError:
scheme = scheme_names_mapping.get(scheme, scheme)
try:
scheme_class = schemes[scheme]
except KeyError:
raise ValueError(
"Invalid scheme. Scheme must be in the set: %r" % schemes.keys()
)
if classification_kwds["k"] is not None:
try:
from inspect import getfullargspec as getspec
except ImportError:
from inspect import getargspec as getspec
spec = getspec(scheme_class.__init__)
if "k" not in spec.args:
del classification_kwds["k"]
try:
binning = scheme_class(values, **classification_kwds)
except TypeError:
raise TypeError("Invalid keyword argument for %r " % scheme)
return binning