def test_stack_merge_aligned_axis():
# If/when non_aligned axis become supported, these can be removed
img3 = tf.Image(np.arange(4, dtype='uint32').reshape((2, 2)),
x_axis=x_axis, y_axis=LinearAxis((1, 20)))
img4 = tf.Image(np.arange(9, dtype='uint32').reshape((3, 3)),
x_axis=x_axis, y_axis=y_axis)
with pytest.raises(NotImplementedError):
tf.stack(img1, img3)
with pytest.raises(NotImplementedError):
tf.stack(img1, img4)
with pytest.raises(NotImplementedError):
tf.merge(img1, img3)
with pytest.raises(NotImplementedError):
tf.merge(img1, img4)
def create_map2():
global cvs
global terrain
global water
global trees
img = stack(shade(terrain, cmap=['black', 'white'], how='linear'))
yield img.to_pil()
img = stack(shade(terrain, cmap=Elevation, how='linear'))
yield img.to_pil()
img = stack(
shade(terrain, cmap=Elevation, how='linear'),
shade(hillshade(terrain, azimuth=210),
cmap=['black', 'white'],
how='linear',
alpha=128),
)
yield img.to_pil()
img = stack(
shade(terrain, cmap=Elevation, how='linear'),
shade(water, cmap=['aqua', 'white']),
shade(hillshade(terrain, azimuth=210),
cmap=['black', 'white'],
how='linear',
alpha=128),
)
yield img.to_pil()
img = stack(
shade(terrain, cmap=Elevation, how='linear'),
shade(water, cmap=['aqua', 'white']),
shade(hillshade(terrain + trees, azimuth=210),
cmap=['black', 'white'],
how='linear',
alpha=128), shade(tree_colorize, cmap='limegreen', how='linear'))
yield img.to_pil()
yield img.to_pil()
yield img.to_pil()
yield img.to_pil()
def _process(self, overlay, key=None):
if not isinstance(overlay, CompositeOverlay):
return overlay
elif len(overlay) == 1:
return overlay.last if isinstance(overlay, NdOverlay) else overlay.get(0)
imgs = []
for rgb in overlay:
if not isinstance(rgb, RGB):
raise TypeError('stack operation expect RGB type elements, '
'not %s name.' % type(rgb).__name__)
rgb = rgb.rgb
dims = [kd.name for kd in rgb.kdims][::-1]
coords = {kd.name: rgb.dimension_values(kd, False)
for kd in rgb.kdims}
imgs.append(tf.Image(self.uint8_to_uint32(rgb), coords=coords, dims=dims))
try:
imgs = xr.align(*imgs, join='exact')
except ValueError:
raise ValueError('RGB inputs to stack operation could not be aligned, '
'ensure they share the same grid sampling.')
stacked = tf.stack(*imgs, how=self.p.compositor)
arr = shade.uint32_to_uint8(stacked.data)[::-1]
data = (coords[dims[1]], coords[dims[0]], arr[:, :, 0],
arr[:, :, 1], arr[:, :, 2])
if arr.shape[-1] == 4:
data = data + (arr[:, :, 3],)
return rgb.clone(data, datatype=[rgb.interface.datatype]+rgb.datatype)
def create_image(x_range, y_range, w, h):
cvs = ds.Canvas(x_range=x_range, y_range=y_range, plot_width=w, plot_height=h)
# agg = cvs.points(df, 'tick', col)
aggs = OrderedDict((c, cvs.points(df, 'tick', c)) for c in ['cpuLat', 'gpuLat'])
# img = tf.shade(agg, cmap=[color])
imgs = [tf.shade(aggs[i], cmap=[c]) for i,c in zip(['cpuLat', 'gpuLat'],['blue', 'red'])]
img = tf.stack(*imgs)
return img
def merged_images(x_range, y_range, w, h, how='log'):
cvs = ds.Canvas(plot_width=w, plot_height=h, x_range=x_range, y_range=y_range)
picks = cvs.points(sep_trips, 'pickup_x', 'pickup_y', ds.count('passenger_count'))
drops = cvs.points(sep_trips, 'dropoff_x', 'dropoff_y', ds.count('passenger_count'))
more_drops = tf.interpolate(drops.where(drops > picks), cmap=["lightblue", 'blue'], how=how)
more_picks = tf.interpolate(picks.where(picks > drops), cmap=["lightpink", 'red'], how=how)
img = tf.stack(more_picks,more_drops)
return tf.dynspread(img, threshold=0.1, max_px=4)
def graphplot(nodes, edges, name="", canvas=None, cat=None):
if canvas is None:
xr = nodes.x.min(), nodes.x.max()
yr = nodes.y.min(), nodes.y.max()
canvas = ds.Canvas(x_range=xr, y_range=yr, **cvsopts)
np = nodesplot(nodes, name + " nodes", canvas, cat)
ep = edgesplot(edges, name + " edges", canvas)
return tf.stack(ep, np, how="over", name=name)
def test_stack():
img = tf.stack(img1, img2)
assert img.x_axis == img1.x_axis and img.y_axis == img1.y_axis
chan = img.img.view([('r', 'uint8'), ('g', 'uint8'),
('b', 'uint8'), ('a', 'uint8')])
assert (chan['r'] == np.array([[255, 0], [0, 255]])).all()
assert (chan['g'] == np.array([[255, 0], [0, 125]])).all()
assert (chan['b'] == np.array([[0, 0], [0, 125]])).all()
assert (chan['a'] == np.array([[255, 0], [255, 125]])).all()
def graphplot(nodes, edges, name="", canvas=None, cat=None):
if canvas is None:
xr = nodes.x.min(), nodes.x.max()
yr = nodes.y.min(), nodes.y.max()
canvas = ds.Canvas(x_range=xr, y_range=yr, **cvsopts)
np = nodesplot(nodes, name + " nodes", canvas, cat)
ep = edgesplot(edges, name + " edges", canvas)
return tf.stack(ep, np, how="over", name=name)
def my_graphplot(nodes, edges, name="", canvas=None, cat=None, margin=0.05):
if canvas is None:
xr = nodes.x.min() - margin, nodes.x.max() + margin
yr = nodes.y.min() - margin, nodes.y.max() + margin
canvas = ds.Canvas(x_range=xr, y_range=yr, **cvsopts)
np = my_nodesplot(nodes, name + " nodes", canvas, cat)
ep = edgesplot(edges, name + " edges", canvas)
return tf.stack(ep, np, how="over", name=name)
def newGraphplot(nodes, edges, name="", canvas=None, cat=None, x_range=None, y_range=None):
if canvas is None:
xr = x_range
yr = y_range
canvas = ds.Canvas(x_range=xr, y_range=yr, **cvsopts)
np = nodesplot(nodes, name + " nodes", canvas, cat)
#print("nodes")
ep = edgesplot(edges, name + " edges", canvas)
#print("edges")
return tf.stack(ep, np, how="over", name=name)
def test_stack():
img = tf.stack(img1, img2)
assert (img.x_axis == img1.x_axis).all()
assert (img.y_axis == img1.y_axis).all()
chan = img.data.view([('r', 'uint8'), ('g', 'uint8'), ('b', 'uint8'),
('a', 'uint8')])
assert (chan['r'] == np.array([[255, 0], [0, 255]])).all()
assert (chan['g'] == np.array([[255, 0], [0, 125]])).all()
assert (chan['b'] == np.array([[0, 0], [0, 125]])).all()
assert (chan['a'] == np.array([[255, 0], [255, 125]])).all()
def newGraphplot(nodes, edges, name="", canvas=None, cat=None, x_range=None, y_range=None):
if canvas is None:
xr = x_range
yr = y_range
canvas = ds.Canvas(x_range=xr, y_range=yr, **cvsopts)
#print(x_range)
np = nodesplot(nodes, name + " nodes", canvas, cat)
#print(np)
ep = edgesplot(edges, name + " edges", canvas)
#print(ep)
return tf.stack(ep, np, how="over", name=name)
def graph_plot(nodes, edges, name="", canvas=None, cat=None, kwargs=cvsopts):
'''
Plot graph using datashader Canvas functions.
returns datashader.transfer_functions.stack().
'''
if canvas is None:
xr = nodes.x.min(), nodes.x.max()
yr = nodes.y.min(), nodes.y.max()
canvas = ds.Canvas(**kwargs, x_range=xr, y_range=yr)
np = nodes_plot(nodes, name + " nodes", canvas, cat)
ep = edges_plot(edges, name + " edges", canvas)
return tf.stack(ep, np, how="over", name=name)
def test_stack():
img = tf.stack(img1, img2)
out = np.array([[0xff00ffff, 0x00000000], [0x00000000, 0xff3dbfbc]],
dtype='uint32')
assert (img.x_axis == img1.x_axis).all()
assert (img.y_axis == img1.y_axis).all()
np.testing.assert_equal(img.data, out)
img = tf.stack(img2, img1)
out = np.array([[0xff00ffff, 0x00000000], [0x00000000, 0xff00ff7d]],
dtype='uint32')
assert (img.x_axis == img1.x_axis).all()
assert (img.y_axis == img1.y_axis).all()
np.testing.assert_equal(img.data, out)
img = tf.stack(img1, img2, how='add')
out = np.array([[0xff00ffff, 0x00000000], [0x00000000, 0xff3d3cfa]],
dtype='uint32')
assert (img.x_axis == img1.x_axis).all()
assert (img.y_axis == img1.y_axis).all()
np.testing.assert_equal(img.data, out)
def viewInteractiveImage(x_range, y_range, w, h, data_source):
cvs = cds.Canvas(
plot_width=w, plot_height=h, x_range=x_range, y_range=y_range
)
aggs = dict(
(_y, cvs.line(data_source, x=self.x, y=_y)) for _y in self.y
)
imgs = [
tf.shade(aggs[_y], cmap=["white", color])
for _y, color in zip(self.y, self.colors)
]
return tf.stack(*imgs)
def test_stack():
img = tf.stack(img1, img2)
out = np.array([[0xff00ffff, 0x00000000],
[0x00000000, 0xff3dbfbc]], dtype='uint32')
assert (img.x_axis == img1.x_axis).all()
assert (img.y_axis == img1.y_axis).all()
np.testing.assert_equal(img.data, out)
img = tf.stack(img2, img1)
out = np.array([[0xff00ffff, 0x00000000],
[0x00000000, 0xff00ff7d]], dtype='uint32')
assert (img.x_axis == img1.x_axis).all()
assert (img.y_axis == img1.y_axis).all()
np.testing.assert_equal(img.data, out)
img = tf.stack(img1, img2, how='add')
out = np.array([[0xff00ffff, 0x00000000],
[0x00000000, 0xff3dfffa]], dtype='uint32')
assert (img.x_axis == img1.x_axis).all()
assert (img.y_axis == img1.y_axis).all()
np.testing.assert_equal(img.data, out)
def create_map(azimuth):
global cvs
global terrain
global water
global trees
img = stack(
shade(terrain, cmap=Elevation, how='linear'),
shade(water, cmap=['aqua', 'white']),
shade(hillshade(terrain + trees, azimuth=azimuth),
cmap=['black', 'white'],
how='linear',
alpha=128), shade(tree_colorize, cmap='limegreen', how='linear'))
print('image created')
return img.to_pil()
def viewInteractiveImage(
x_range,
y_range,
w,
h,
data_source=self.nodes,
nodes_plot=self.nodes_plot,
edges_plot=self.edges_plot,
chart=self.chart,
**kwargs,
):
dd = data_source[[
self.node_id,
self.node_x,
self.node_y,
self.node_aggregate_col,
]]
dd[self.node_x] = self._to_xaxis_type(dd[self.node_x])
dd[self.node_y] = self._to_yaxis_type(dd[self.node_y])
x_range = self._to_xaxis_type(x_range)
y_range = self._to_yaxis_type(y_range)
cvs = ds.Canvas(plot_width=w,
plot_height=h,
x_range=x_range,
y_range=y_range)
plot = None
if self.source is not None:
self.source.data = {
self.node_x: [],
self.node_y: [],
self.node_aggregate_col: [],
self.node_aggregate_col + "_color": [],
}
np = nodes_plot(cvs, dd)
if self.display_edges._active:
ep = edges_plot(cvs, dd)
plot = tf.stack(ep, np, how="over")
else:
plot = np
return plot
def newGraphplot(nodes,
edges,
name="",
canvas=None,
cat=None,
x_range=None,
y_range=None):
if canvas is None:
xr = x_range
yr = y_range
canvas = ds.Canvas(x_range=xr, y_range=yr, **cvsopts)
#print(x_range)
np = nodesplot(nodes, name + " nodes", canvas, cat)
print('Nodes plot created', file=sys.stdout)
#print(np)
#issue is here with edges
ep = edgesplot(edges, name + " edges", canvas)
print('Edges plot created', file=sys.stdout)
#print(ep)
return tf.stack(ep, np, how="over", name=name)
def viewInteractiveImage(x_range, y_range, w, h, data_source,
**kwargs):
dd = data_source[[self.x] + self.y]
dd[self.x] = self._to_xaxis_type(dd[self.x])
for _y in self.y:
dd[_y] = self._to_yaxis_type(dd[_y])
x_range = self._to_xaxis_type(x_range)
y_range = self._to_yaxis_type(y_range)
cvs = ds.Canvas(plot_width=w,
plot_height=h,
x_range=x_range,
y_range=y_range)
aggs = dict((_y, cvs.line(dd, x=self.x, y=_y)) for _y in self.y)
imgs = [
tf.shade(aggs[_y], cmap=["white", color])
for _y, color in zip(self.y, self.colors)
]
return tf.stack(*imgs)
def create_plot(data, out, width):
"""Creates a figure of the ZVV transit network using ZVV's color scheme.
Args:
data: a csv file containing data usable for line plots
out: the generated imnage is saved here
Returns:
None
"""
plot_data = pd.read_csv(data, low_memory=False)
x_range = (plot_data.shape_pt_lon.min(), plot_data.shape_pt_lon.max())
y_range = (plot_data.shape_pt_lat.min(), plot_data.shape_pt_lat.max())
height = int(
round(width * (y_range[1] - y_range[0]) / (x_range[1] - x_range[0])))
cvs = ds.Canvas(plot_width=width,
plot_height=height,
x_range=x_range,
y_range=y_range)
layers = []
for color, data_part in plot_data.groupby('route_color'):
agg = cvs.line(data_part,
'shape_pt_lon',
'shape_pt_lat',
agg=ds.sum('times_taken'))
image_part = tf.shade(agg,
cmap=['#000000', '#' + color],
how='eq_hist')
layers.append(image_part)
image = tf.stack(*layers, how='add')
if out.endswith('.png'):
out = out[:-4]
export_image(image, filename=out, background='black')
def connectivity_base(
x: int,
y: int,
edge_df: pd.DataFrame,
highlights: Optional[list] = None,
edge_bundling: Optional[str] = None,
edge_cmap: str = "gray_r",
show_points: bool = True,
labels: Optional[list] = None,
values: Optional[list] = None,
theme: Optional[str] = None,
cmap: str = "Blues",
color_key: Union[dict, list, None] = None,
color_key_cmap: str = "Spectral",
background: str = "black",
figsize: tuple = (7, 5),
ax: Optional[Axes] = None,
sort: str = "raw",
save_show_or_return: str = "return",
save_kwargs: dict = {},
) -> Union[None, Axes]:
"""Plot connectivity relationships of the underlying UMAP
simplicial set data structure. Internally UMAP will make
use of what can be viewed as a weighted graph. This graph
can be plotted using the layout provided by UMAP as a
potential diagnostic view of the embedding. Currently this only works
for 2D embeddings. While there are many optional parameters
to further control and tailor the plotting, you need only
pass in the trained/fit umap model to get results. This plot
utility will attempt to do the hard work of avoiding
overplotting issues and provide options for plotting the
points as well as using edge bundling for graph visualization.
Parameters
----------
x: `int`
The first component of the embedding.
y: `int`
The second component of the embedding.
edge_df `pd.DataFrame`
The dataframe denotes the graph edge pairs. The three columns
include 'source', 'target' and 'weight'.
highlights: `list`, `list of list` or None (default: `None`)
The list that cells will be restricted to.
edge_bundling: string or None (optional, default None)
The edge bundling method to use. Currently supported
are None or 'hammer'. See the datashader docs
on graph visualization for more details.
edge_cmap: string (default 'gray_r')
The name of a matplotlib colormap to use for shading/
coloring the edges of the connectivity graph. Note that
the ``theme``, if specified, will override this.
show_points: bool (optional False)
Whether to display the points over top of the edge
connectivity. Further options allow for coloring/
shading the points accordingly.
labels: array, shape (n_samples,) (optional, default None)
An array of labels (assumed integer or categorical),
one for each data sample.
This will be used for coloring the points in
the plot according to their label. Note that
this option is mutually exclusive to the ``values``
option.
values: array, shape (n_samples,) (optional, default None)
An array of values (assumed float or continuous),
one for each sample.
This will be used for coloring the points in
the plot according to a colorscale associated
to the total range of values. Note that this
option is mutually exclusive to the ``labels``
option.
theme: string (optional, default None)
A color theme to use for plotting. A small set of
predefined themes are provided which have relatively
good aesthetics. Available themes are:
* 'blue'
* 'red'
* 'green'
* 'inferno'
* 'fire'
* 'viridis'
* 'darkblue'
* 'darkred'
* 'darkgreen'
cmap: string (optional, default 'Blues')
The name of a matplotlib colormap to use for coloring
or shading points. If no labels or values are passed
this will be used for shading points according to
density (largely only of relevance for very large
datasets). If values are passed this will be used for
shading according the value. Note that if theme
is passed then this value will be overridden by the
corresponding option of the theme.
color_key: dict or array, shape (n_categories) (optional, default None)
A way to assign colors to categoricals. This can either be
an explicit dict mapping labels to colors (as strings of form
'#RRGGBB'), or an array like object providing one color for
each distinct category being provided in ``labels``. Either
way this mapping will be used to color points according to
the label. Note that if theme
is passed then this value will be overridden by the
corresponding option of the theme.
color_key_cmap: string (optional, default 'Spectral')
The name of a matplotlib colormap to use for categorical coloring.
If an explicit ``color_key`` is not given a color mapping for
categories can be generated from the label list and selecting
a matching list of colors from the given colormap. Note
that if theme
is passed then this value will be overridden by the
corresponding option of the theme.
background: string (optional, default 'white)
The color of the background. Usually this will be either
'white' or 'black', but any color name will work. Ideally
one wants to match this appropriately to the colors being
used for points etc. This is one of the things that themes
handle for you. Note that if theme
is passed then this value will be overridden by the
corresponding option of the theme.
width: int (optional, default 800)
The desired width of the plot in pixels.
height: int (optional, default 800)
The desired height of the plot in pixels
sort: `str` (optional, default `raw`)
The method to reorder data so that high values points will be on top of background points. Can be one of
{'raw', 'abs'}, i.e. sorted by raw data or sort by absolute values.
save_show_or_return: {'show', 'save', 'return'} (default: `return`)
Whether to save, show or return the figure.
save_kwargs: `dict` (default: `{}`)
A dictionary that will passed to the save_fig function. By default it is an empty dictionary and the save_fig function
will use the {"path": None, "prefix": 'connectivity_base', "dpi": None, "ext": 'pdf', "transparent": True, "close":
True, "verbose": True} as its parameters. Otherwise you can provide a dictionary that properly modify those keys
according to your needs.
Returns
-------
result:
Either return None or a matplotlib axis with the relevant plot displayed based on arguments.
If you are using a notbooks and have ``%matplotlib inline`` set
then this will simply display inline.
"""
import matplotlib.pyplot as plt
import datashader as ds
import datashader.transfer_functions as tf
import datashader.bundling as bd
dpi = plt.rcParams["figure.dpi"]
if theme is not None:
cmap = _themes[theme]["cmap"]
color_key_cmap = _themes[theme]["color_key_cmap"]
edge_cmap = _themes[theme]["edge_cmap"]
background = _themes[theme]["background"]
points = np.array([x, y]).T
point_df = pd.DataFrame(points, columns=("x", "y"))
point_size = 500.0 / np.sqrt(points.shape[0])
if point_size > 1:
px_size = int(np.round(point_size))
else:
px_size = 1
if show_points:
edge_how = "log"
else:
edge_how = "eq_hist"
extent = _get_extent(points)
canvas = ds.Canvas(
plot_width=int(figsize[0] * dpi),
plot_height=int(figsize[1] * dpi),
x_range=(extent[0], extent[1]),
y_range=(extent[2], extent[3]),
)
if edge_bundling is None:
edges = bd.directly_connect_edges(point_df, edge_df, weight="weight")
elif edge_bundling == "hammer":
warn("Hammer edge bundling is expensive for large graphs!\n"
"This may take a long time to compute!")
edges = bd.hammer_bundle(point_df, edge_df, weight="weight")
else:
raise ValueError(
"{} is not a recognised bundling method".format(edge_bundling))
edge_img = tf.shade(
canvas.line(edges, "x", "y", agg=ds.sum("weight")),
cmap=plt.get_cmap(edge_cmap),
how=edge_how,
)
edge_img = tf.set_background(edge_img, background)
if show_points:
point_img = _datashade_points(
points,
None,
labels,
values,
highlights,
cmap,
color_key,
color_key_cmap,
None,
figsize[0] * dpi,
figsize[1] * dpi,
True,
sort=sort,
)
if px_size > 1:
point_img = tf.dynspread(point_img, threshold=0.5, max_px=px_size)
result = tf.stack(edge_img, point_img, how="over")
else:
result = edge_img
if ax is None:
fig = plt.figure(figsize=figsize)
ax = fig.add_subplot(111)
_embed_datashader_in_an_axis(result, ax)
ax.set(xticks=[], yticks=[])
if save_show_or_return == "save":
s_kwargs = {
"path": None,
"prefix": "connectivity_base",
"dpi": None,
"ext": "pdf",
"transparent": True,
"close": True,
"verbose": True,
}
s_kwargs = update_dict(s_kwargs, save_kwargs)
save_fig(**s_kwargs)
elif save_show_or_return == "show":
plt.tight_layout()
plt.show()
elif save_show_or_return == "return":
return ax
bkg=reductions.mean('Background'))
canvas = datashader.Canvas(plot_width=x_end - x_start,
plot_height=y_end - y_start,
x_range=[x_start, x_end],
y_range=[y_start, y_end])
agg = canvas.points(data, 'x', 'y', agg=reduction_op)
imgs = []
for morph, color in [(agg.sph, 'red'), (agg.dk, 'green'), (agg.ps, 'blue'),
(agg.bkg, 'black')]:
imgs.append(
t_func.shade(morph, cmap=['white', color], span=[0, 1], how='linear'))
img = t_func.stack(*imgs, how='add')
#img = t_func.set_background(img, color='black')
img_plt = f.image_rgba(image=[img.data],
x=x_start,
y=y_start,
dw=width,
dh=height)
outputs.append(f)
# ==============================================================================
# ==============================================================================
# plot in-segmap PDFs
pdf_cdf = []
img = tf.shade(aggs['a'])
img
mask = (df.index % 10) == 0
tf.shade(cvs.line(df[mask][['a','ITime']], 'ITime', 'a'))
renamed = [aggs[key].rename({key: 'value'}) for key in aggs]
merged = xr.concat(renamed, 'cols')
tf.shade(merged.any(dim='cols'))
colors = ["red", "grey", "black", "purple", "pink",
"yellow", "brown", "green", "orange", "blue"]
imgs = [tf.shade(aggs[i], cmap=[c]) for i, c in zip(cols, colors)]
tf.stack(*imgs)
tf.stack(*reversed(imgs))
total = tf.shade(merged.sum(dim='cols'), how='linear')
total
tf.stack(total, tf.shade(aggs['z'], cmap=["lightblue", "red"]))
tf.stack(total, tf.shade(aggs['y'], cmap=["lightblue", "red"]))
cvs = ds.Canvas(x_range=x_range, y_range=y_range, plot_height=300, plot_width=900)
agg = cvs.area(df, x='ITime', y='a')
img = tf.shade(agg)
img
def shade_line(data, colors=None, **kwargs):
""""""
if "plot_width" not in kwargs or "plot_height" not in kwargs:
raise ValueError(
"Please provide plot_width and plot_height for the canvas.")
if isinstance(data, (list, tuple)) and isinstance(colors, (list, tuple)):
if len(data) != len(colors):
raise ValueError("colors should have the same length as data.")
if isinstance(data, (dict, pd.DataFrame)):
data = [data]
if colors and isinstance(colors, str):
colors = [colors] * len(data)
if "x_range" not in kwargs or "y_range" not in kwargs:
x_range, y_range = get_ranges(data)
if "x_range" not in kwargs:
kwargs["x_range"] = x_range
if "y_range" not in kwargs:
kwargs["y_range"] = y_range
kwargs["x_range"], kwargs["y_range"] = _normalize_ranges(
kwargs["x_range"], kwargs["y_range"])
cvs = ds.Canvas(**kwargs)
aggs = []
cs = []
for i, line in enumerate(data):
df = line
if not isinstance(line, pd.DataFrame):
df = pd.DataFrame(line).astype(float)
plot = True
if "x_range" in kwargs and "y_range" in kwargs:
plot = _is_data_in_range(df, "x", "y", kwargs["x_range"],
kwargs["y_range"])
elif "x_range" in kwargs:
plot = _is_data_in_range(df, "x", "y", kwargs["x_range"])
elif "y_range" in kwargs:
plot = _is_data_in_range(df, "x", "y", y_range=kwargs["y_range"])
if len(df["x"]) == 0 or len(df["y"]) == 0:
plot = False
if plot:
aggs.append(cvs.line(df, "x", "y"))
if colors:
cs.append(colors[i])
if not aggs:
return xr.DataArray(
np.zeros((kwargs["plot_height"], kwargs["plot_width"]), dtype=int))
if colors:
imgs = [tf.shade(aggs[i], cmap=[c]) for i, c in enumerate(cs)]
return tf.stack(*imgs)
else:
imgs = [tf.shade(aggs[i]) for i in range(len(data))]
return tf.stack(*imgs)
def connectivity(
umap_object,
edge_bundling=None,
edge_cmap="gray_r",
show_points=False,
labels=None,
values=None,
theme=None,
cmap="Blues",
color_key=None,
color_key_cmap="Spectral",
background="white",
width=800,
height=800,
):
"""Plot connectivity relationships of the underlying UMAP
simplicial set data structure. Internally UMAP will make
use of what can be viewed as a weighted graph. This graph
can be plotted using the layout provided by UMAP as a
potential diagnostic view of the embedding. Currently this only works
for 2D embeddings. While there are many optional parameters
to further control and tailor the plotting, you need only
pass in the trained/fit umap model to get results. This plot
utility will attempt to do the hard work of avoiding
overplotting issues and provide options for plotting the
points as well as using edge bundling for graph visualization.
Parameters
----------
umap_object: trained UMAP object
A trained UMAP object that has a 2D embedding.
edge_bundling: string or None (optional, default None)
The edge bundling method to use. Currently supported
are None or 'hammer'. See the datashader docs
on graph visualization for more details.
edge_cmap: string (default 'gray_r')
The name of a matplotlib colormap to use for shading/
coloring the edges of the connectivity graph. Note that
the ``theme``, if specified, will override this.
show_points: bool (optional False)
Whether to display the points over top of the edge
connectivity. Further options allow for coloring/
shading the points accordingly.
labels: array, shape (n_samples,) (optional, default None)
An array of labels (assumed integer or categorical),
one for each data sample.
This will be used for coloring the points in
the plot according to their label. Note that
this option is mutually exclusive to the ``values``
option.
values: array, shape (n_samples,) (optional, default None)
An array of values (assumed float or continuous),
one for each sample.
This will be used for coloring the points in
the plot according to a colorscale associated
to the total range of values. Note that this
option is mutually exclusive to the ``labels``
option.
theme: string (optional, default None)
A color theme to use for plotting. A small set of
predefined themes are provided which have relatively
good aesthetics. Available themes are:
* 'blue'
* 'red'
* 'green'
* 'inferno'
* 'fire'
* 'viridis'
* 'darkblue'
* 'darkred'
* 'darkgreen'
cmap: string (optional, default 'Blues')
The name of a matplotlib colormap to use for coloring
or shading points. If no labels or values are passed
this will be used for shading points according to
density (largely only of relevance for very large
datasets). If values are passed this will be used for
shading according the value. Note that if theme
is passed then this value will be overridden by the
corresponding option of the theme.
color_key: dict or array, shape (n_categories) (optional, default None)
A way to assign colors to categoricals. This can either be
an explicit dict mapping labels to colors (as strings of form
'#RRGGBB'), or an array like object providing one color for
each distinct category being provided in ``labels``. Either
way this mapping will be used to color points according to
the label. Note that if theme
is passed then this value will be overridden by the
corresponding option of the theme.
color_key_cmap: string (optional, default 'Spectral')
The name of a matplotlib colormap to use for categorical coloring.
If an explicit ``color_key`` is not given a color mapping for
categories can be generated from the label list and selecting
a matching list of colors from the given colormap. Note
that if theme
is passed then this value will be overridden by the
corresponding option of the theme.
background: string (optional, default 'white)
The color of the background. Usually this will be either
'white' or 'black', but any color name will work. Ideally
one wants to match this appropriately to the colors being
used for points etc. This is one of the things that themes
handle for you. Note that if theme
is passed then this value will be overridden by the
corresponding option of the theme.
width: int (optional, default 800)
The desired width of the plot in pixels.
height: int (optional, default 800)
The desired height of the plot in pixels
Returns
-------
result: matplotlib axis
The result is a matplotlib axis with the relevant plot displayed.
If you are using a notbooks and have ``%matplotlib inline`` set
then this will simply display inline.
"""
if theme is not None:
cmap = _themes[theme]["cmap"]
color_key_cmap = _themes[theme]["color_key_cmap"]
edge_cmap = _themes[theme]["edge_cmap"]
background = _themes[theme]["background"]
points = umap_object.embedding_
point_df = pd.DataFrame(points, columns=("x", "y"))
point_size = 100.0 / np.sqrt(points.shape[0])
if point_size > 1:
px_size = int(np.round(point_size))
else:
px_size = 1
if show_points:
edge_how = "log"
else:
edge_how = "eq_hist"
coo_graph = umap_object.graph_.tocoo()
edge_df = pd.DataFrame(
np.vstack([coo_graph.row, coo_graph.col, coo_graph.data]).T,
columns=("source", "target", "weight"),
)
edge_df["source"] = edge_df.source.astype(np.int32)
edge_df["target"] = edge_df.target.astype(np.int32)
extent = _get_extent(points)
canvas = ds.Canvas(
plot_width=width,
plot_height=height,
x_range=(extent[0], extent[1]),
y_range=(extent[2], extent[3]),
)
if edge_bundling is None:
edges = bd.directly_connect_edges(point_df, edge_df, weight="weight")
elif edge_bundling == "hammer":
warn("Hammer edge bundling is expensive for large graphs!\n"
"This may take a long time to compute!")
edges = bd.hammer_bundle(point_df, edge_df, weight="weight")
else:
raise ValueError(
"{} is not a recognised bundling method".format(edge_bundling))
edge_img = tf.shade(
canvas.line(edges, "x", "y", agg=ds.sum("weight")),
cmap=plt.get_cmap(edge_cmap),
how=edge_how,
)
edge_img = tf.set_background(edge_img, background)
if show_points:
point_img = _datashade_points(
points,
None,
labels,
values,
cmap,
color_key,
color_key_cmap,
None,
width,
height,
False,
)
if px_size > 1:
point_img = tf.dynspread(point_img, threshold=0.5, max_px=px_size)
result = tf.stack(edge_img, point_img, how="over")
else:
result = edge_img
font_color = _select_font_color(background)
dpi = plt.rcParams["figure.dpi"]
fig = plt.figure(figsize=(width / dpi, height / dpi))
ax = fig.add_subplot(111)
_embed_datashader_in_an_axis(result, ax)
ax.set(xticks=[], yticks=[])
ax.text(
0.99,
0.01,
"UMAP: n_neighbors={}, min_dist={}".format(umap_object.n_neighbors,
umap_object.min_dist),
transform=ax.transAxes,
horizontalalignment="right",
color=font_color,
)
return ax
