Skip to content

Instantly share code, notes, and snippets.



Last active Nov 23, 2020
What would you like to do?
import numpy as np
import matplotlib.pyplot as plt
def map_hist(x, y, h, bins):
xi = np.digitize(x, bins[0]) - 1
yi = np.digitize(y, bins[1]) - 1
inds = np.ravel_multi_index((xi, yi),
(len(bins[0]) - 1, len(bins[1]) - 1),
vals = h.flatten()[inds]
bads = ((x < bins[0][0]) | (x > bins[0][-1]) |
(y < bins[1][0]) | (y > bins[1][-1]))
vals[bads] = np.NaN
return vals
def scatter_hist2d(x, y,
s=20, marker=u'o',
bins=10, range=None,
normed=False, weights=None, # np.histogram2d args
ax=None, dens_func=None,
Make a scattered-histogram plot.
x, y : array_like, shape (n, )
Input data
s : scalar or array_like, shape (n, ), optional, default: 20
size in points^2.
marker : `~matplotlib.markers.MarkerStyle`, optional, default: 'o'
See `~matplotlib.markers` for more information on the different
styles of markers scatter supports. `marker` can be either
an instance of the class or the text shorthand for a particular
mode: [None | 'mountain' (default) | 'valley']
Possible values are:
- None : The points are plotted as one scatter object, in the
order in-which they are specified at input.
- 'mountain' : The points are sorted/plotted in the order of
the number of points in their 'bin'. This means that points
in the highest density will be plotted on-top of others. This
cleans-up the edges a bit, the points near the edges will
- 'valley' : The reverse order of 'mountain'. The low density
bins are plotted on top of the high-density ones.
bins : int or array_like or [int, int] or [array, array], optional
The bin specification:
* If int, the number of bins for the two dimensions (nx=ny=bins).
* If array_like, the bin edges for the two dimensions
* If [int, int], the number of bins in each dimension
(nx, ny = bins).
* If [array, array], the bin edges in each dimension
(x_edges, y_edges = bins).
* A combination [int, array] or [array, int], where int
is the number of bins and array is the bin edges.
range : array_like, shape(2,2), optional
The leftmost and rightmost edges of the bins along each dimension
(if not specified explicitly in the `bins` parameters):
``[[xmin, xmax], [ymin, ymax]]``. All values outside of this range
will be considered outliers and not tallied in the histogram.
normed : bool, optional
If False, returns the number of samples in each bin. If True,
returns the bin density ``bin_count / sample_count / bin_area``.
weights : array_like, shape(N,), optional
An array of values ``w_i`` weighing each sample ``(x_i, y_i)``.
Weights are normalized to 1 if `normed` is True. If `normed` is
False, the values of the returned histogram are equal to the sum of
the weights belonging to the samples falling into each bin.
edgecolors : color or sequence of color, optional, default: 'none'
If None, defaults to (patch.edgecolor).
If 'face', the edge color will always be the same as
the face color. If it is 'none', the patch boundary will not
be drawn. For non-filled markers, the `edgecolors` kwarg
is ignored; color is determined by `c`.
ax : an axes instance to plot into.
dens_func : function or callable (default: None)
A function that modifies (inputs and returns) the dens
values (e.g., np.log10). The default is to not modify the
values, which will modify their coloring.
kwargs : these are all passed on to scatter.
paths : `~matplotlib.collections.PathCollection`
The scatter instance.
if ax is None:
ax = plt.gca()
h, xe, ye = np.histogram2d(x, y, bins=bins,
range=range, normed=normed,
# bins = (xe, ye)
dens = map_hist(x, y, h, bins=(xe, ye))
if dens_func is not None:
dens = dens_func(dens)
iorder = slice(None) # No ordering by default
if mode == 'mountain':
iorder = np.argsort(dens)
elif mode == 'valley':
iorder = np.argsort(dens)[::-1]
x = x[iorder]
y = y[iorder]
dens = dens[iorder]
return ax.scatter(x, y,
s=s, c=dens,
if __name__ == '__main__':
randgen = np.random.RandomState(84309242)
npoint = 10000
x = randgen.randn(npoint)
y = 2 * randgen.randn(npoint) + x
lims = [-10, 10]
bins = np.linspace(lims[0], lims[1], 50)
fig, axs = plt.subplots(3, 1, figsize=[4, 8],
ax = axs[0]
ax.plot(x, y, '.', color='b', )
ax.set_title("Traditional Scatterplot")
ax = axs[1]
ax.hist2d(x, y, bins=[bins, bins])
ax.set_title("Traditional 2-D Histogram")
ax = axs[2]
scatter_hist2d(x, y, bins=[bins, bins], ax=ax, s=5)
ax.set_title("Scatter histogram combined!")
for ax in axs:
fig.savefig('ScatterHist_Example.png', dpi=200)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment