Develop Reference

Create a heat map out of three 1D arrays

I want to create a heatmap out of 3 1dimensional arrays. Something that looks like this:
Up to this point, I was only able to create a scatter plot where the markers have a different color and marker size depending on the third value:
My code:
xf = np.random.rand(1000)
yf = np.random.rand(1000)
zf = 1e5*np.random.rand(1000)
ms1 = (zf).astype('int')
from matplotlib.colors import LinearSegmentedColormap
# Remove the middle 40% of the RdBu_r colormap
interval = np.hstack([np.linspace(0, 0.4), np.linspace(0.6, 1)])
colors = plt.cm.RdBu_r(interval)
cmap = LinearSegmentedColormap.from_list('name', colors)
col = cmap(np.linspace(0,1,len(ms1)))
#for i in range(len(ms1)):
plt.scatter(xf, yf, c=zf, s=5*ms1/1e4, cmap=cmap,alpha=0.8)#, norm =matplotlib.colors.LogNorm())
ax1 =plt.colorbar(pad=0.01)
is giving me this result:
Any idea how I could make it look like the first figure?
Essentially what I want to do is find the average of the z value for groups of the x and y arrays

I think the functionality you are looking for is provided by scipy.stats.binned_statistic_2d. You can use it to organize values of xf and yf arrays into 2-dimensional bins, and compute the mean of zf values in each bin:
import numpy as np
from scipy import stats
np.random.seed(0)
xf = np.random.rand(1000)
yf = np.random.rand(1000)
zf = 1e5 * np.random.rand(1000)
means = stats.binned_statistic_2d(xf,
yf,
values=zf,
statistic='mean',
bins=(5, 5))[0]
Then you can use e.g. seaborn to plot a heatmap of the array of mean values:
import matplotlib.pyplot as plt
import seaborn as sns
plt.figure(figsize=(10, 8))
sns.heatmap(means,
cmap="Reds_r",
annot=True,
annot_kws={"fontsize": 16},
cbar=True,
linewidth=2,
square=True)
plt.show()
This gives:

Matplot: How to plot true/false or active/deactive data?

I want to plot a true/false or active/deactive binary data similar to the following picture:
The horizontal axis is time and the vertical axis is some entities(Here some sensors) which is active(white) or deactive(black). How can I plot such a graphs using pyplot.
I searched to find the name of these graphs but I couldn't find it.

What you are looking for is imshow:
import matplotlib.pyplot as plt
import numpy as np
# get some data with true # probability 80 %
data = np.random.random((20, 500)) > .2
fig = plt.figure()
ax = fig.add_subplot(111)
ax.imshow(data, aspect='auto', cmap=plt.cm.gray, interpolation='nearest')
Then you will just have to get the Y labels from somewhere.
It seems that the image in your question has some interpolation in the image. Let us set a few more things:
import matplotlib.pyplot as plt
import numpy as np
# create a bit more realistic-looking data
# - looks complicated, but just has a constant switch-off and switch-on probabilities
# per column
# - the result is a 20 x 500 array of booleans
p_switchon = 0.02
p_switchoff = 0.05
data = np.empty((20,500), dtype='bool')
data[:,0] = np.random.random(20) < .2
for c in range(1, 500):
r = np.random.random(20)
data[data[:,c-1],c] = (r > p_switchoff)[data[:,c-1]]
data[-data[:,c-1],c] = (r < p_switchon)[-data[:,c-1]]
# create some labels
labels = [ "label_{0:d}".format(i) for i in range(20) ]
# this is the real plotting part
fig = plt.figure()
ax = fig.add_subplot(111)
ax.imshow(data, aspect='auto', cmap=plt.cm.gray)
ax.set_yticks(np.arange(len(labels)))
ax.set_yticklabels(labels)
creates
However, the interpolation is not necessarily a good thing here. To make the different rows easier to separate, one might use colors:
import matplotlib.pyplot as plt
import matplotlib.colors
import numpy as np
# create a bit more realistic-looking data
# - looks complicated, but just has a constant switch-off and switch-on probabilities
# per column
# - the result is a 20 x 500 array of booleans
p_switchon = 0.02
p_switchoff = 0.05
data = np.empty((20,500), dtype='bool')
data[:,0] = np.random.random(20) < .2
for c in range(1, 500):
r = np.random.random(20)
data[data[:,c-1],c] = (r > p_switchoff)[data[:,c-1]]
data[-data[:,c-1],c] = (r < p_switchon)[-data[:,c-1]]
# create some labels
labels = [ "label_{0:d}".format(i) for i in range(20) ]
# create a color map with random colors
colmap = matplotlib.colors.ListedColormap(np.random.random((21,3)))
colmap.colors[0] = [0,0,0]
# create some colorful data:
data_color = (1 + np.arange(data.shape[0]))[:, None] * data
# this is the real plotting part
fig = plt.figure()
ax = fig.add_subplot(111)
ax.imshow(data_color, aspect='auto', cmap=colmap, interpolation='nearest')
ax.set_yticks(np.arange(len(labels)))
ax.set_yticklabels(labels)
creates
Of course, you will want to use something less strange as the coloring scheme, but that is really up to your artistic views. Here the trick is that all True elements on row n have value n+1 and, and all False elements are 0 in data_color. This makes it possible to create a color map. Naturally, if you want a cyclic color map with two or three colors, just use the modulus of data_color in imshow by, e.g. data_color % 3.

Color-coding a histogram

I have a set of N objects with two properties: x and y.
I would like to depict the distribution of x with a histogram in MATPLOTLIB using hist(). Easy enough. Now, I would like to color-code EACH bar of the histogram with a color that represents the average value of y in that set with a colormap. Is there an easy way to do this? Here, x and y are both N-d numpy arrays. Thanks!
fig = plt.figure()
n, bins, patches = plt.hist(x, 100, normed=1, histtype='stepfilled')
plt.setp(patches, 'facecolor', 'g', 'alpha', 0.1)
plt.xlabel('x')
plt.ylabel('Normalized frequency')
plt.show()

import numpy as np
import matplotlib
import matplotlib.pyplot as plt
# set up the bins
Nbins = 10
bins = np.linspace(0, 1, Nbins +1, endpoint=True)
# get some fake data
x = np.random.rand(300)
y = np.arange(300)
# figure out which bin each x goes into
bin_num = np.digitize(x, bins, right=True) - 1
# compute the counts per bin
hist_vals = np.bincount(bin_num)
# set up array for bins
means = np.zeros(Nbins)
# numpy slicing magic to sum the y values by bin
means[bin_num] += y
# take the average
means /= hist_vals
# make the figure/axes objects
fig, ax = plt.subplots(1,1)
# get a color map
my_cmap = cm.get_cmap('jet')
# get normalize function (takes data in range [vmin, vmax] -> [0, 1])
my_norm = Normalize()
# use bar plot
ax.bar(bins[:-1], hist_vals, color=my_cmap(my_norm(means)), width=np.diff(bins))
# make sure the figure updates
plt.draw()
plt.show()
related: vary the color of each bar in bargraph using particular value

How to plot one line in different colors

I have two list as below:
latt=[42.0,41.978567980875397,41.96622693388357,41.963791391892457,...,41.972407378075879]
lont=[-66.706920989908909,-66.703116557977069,-66.707351643324543,...-66.718218142021925]
now I want to plot this as a line, separate each 10 of those 'latt' and 'lont' records as a period and give it a unique color.
what should I do?

There are several different ways to do this. The "best" approach will depend mostly on how many line segments you want to plot.
If you're just going to be plotting a handful (e.g. 10) line segments, then just do something like:
import numpy as np
import matplotlib.pyplot as plt
def uniqueish_color():
"""There're better ways to generate unique colors, but this isn't awful."""
return plt.cm.gist_ncar(np.random.random())
xy = (np.random.random((10, 2)) - 0.5).cumsum(axis=0)
fig, ax = plt.subplots()
for start, stop in zip(xy[:-1], xy[1:]):
x, y = zip(start, stop)
ax.plot(x, y, color=uniqueish_color())
plt.show()
If you're plotting something with a million line segments, though, this will be terribly slow to draw. In that case, use a LineCollection. E.g.
import numpy as np
import matplotlib.pyplot as plt
from matplotlib.collections import LineCollection
xy = (np.random.random((1000, 2)) - 0.5).cumsum(axis=0)
# Reshape things so that we have a sequence of:
# [[(x0,y0),(x1,y1)],[(x0,y0),(x1,y1)],...]
xy = xy.reshape(-1, 1, 2)
segments = np.hstack([xy[:-1], xy[1:]])
fig, ax = plt.subplots()
coll = LineCollection(segments, cmap=plt.cm.gist_ncar)
coll.set_array(np.random.random(xy.shape[0]))
ax.add_collection(coll)
ax.autoscale_view()
plt.show()
For both of these cases, we're just drawing random colors from the "gist_ncar" coloramp. Have a look at the colormaps here (gist_ncar is about 2/3 of the way down): http://matplotlib.org/examples/color/colormaps_reference.html

Copied from this example:
import numpy as np
import matplotlib.pyplot as plt
from matplotlib.collections import LineCollection
from matplotlib.colors import ListedColormap, BoundaryNorm
x = np.linspace(0, 3 * np.pi, 500)
y = np.sin(x)
z = np.cos(0.5 * (x[:-1] + x[1:])) # first derivative
# Create a colormap for red, green and blue and a norm to color
# f' < -0.5 red, f' > 0.5 blue, and the rest green
cmap = ListedColormap(['r', 'g', 'b'])
norm = BoundaryNorm([-1, -0.5, 0.5, 1], cmap.N)
# Create a set of line segments so that we can color them individually
# This creates the points as a N x 1 x 2 array so that we can stack points
# together easily to get the segments. The segments array for line collection
# needs to be numlines x points per line x 2 (x and y)
points = np.array([x, y]).T.reshape(-1, 1, 2)
segments = np.concatenate([points[:-1], points[1:]], axis=1)
# Create the line collection object, setting the colormapping parameters.
# Have to set the actual values used for colormapping separately.
lc = LineCollection(segments, cmap=cmap, norm=norm)
lc.set_array(z)
lc.set_linewidth(3)
fig1 = plt.figure()
plt.gca().add_collection(lc)
plt.xlim(x.min(), x.max())
plt.ylim(-1.1, 1.1)
plt.show()

See the answer here to generate the "periods" and then use the matplotlib scatter function as #tcaswell mentioned. Using the plot.hold function you can plot each period, colors will increment automatically.

Cribbing the color choice off of #JoeKington,
import numpy as np
import matplotlib.pyplot as plt
def uniqueish_color(n):
"""There're better ways to generate unique colors, but this isn't awful."""
return plt.cm.gist_ncar(np.random.random(n))
plt.scatter(latt, lont, c=uniqueish_color(len(latt)))
You can do this with scatter.

I have been searching for a short solution how to use pyplots line plot to show a time series coloured by a label feature without using scatter due to the amount of data points.
I came up with the following workaround:
plt.plot(np.where(df["label"]==1, df["myvalue"], None), color="red", label="1")
plt.plot(np.where(df["label"]==0, df["myvalue"], None), color="blue", label="0")
plt.legend()
The drawback is you are creating two different line plots so the connection between the different classes is not shown. For my purposes it is not a big deal. It may help someone.

Generate a heatmap using a scatter data set

I have a set of X,Y data points (about 10k) that are easy to plot as a scatter plot but that I would like to represent as a heatmap.
I looked through the examples in Matplotlib and they all seem to already start with heatmap cell values to generate the image.
Is there a method that converts a bunch of x, y, all different, to a heatmap (where zones with higher frequency of x, y would be "warmer")?

If you don't want hexagons, you can use numpy's histogram2d function:
import numpy as np
import numpy.random
import matplotlib.pyplot as plt
# Generate some test data
x = np.random.randn(8873)
y = np.random.randn(8873)
heatmap, xedges, yedges = np.histogram2d(x, y, bins=50)
extent = [xedges[0], xedges[-1], yedges[0], yedges[-1]]
plt.clf()
plt.imshow(heatmap.T, extent=extent, origin='lower')
plt.show()
This makes a 50x50 heatmap. If you want, say, 512x384, you can put bins=(512, 384) in the call to histogram2d.
Example:

In Matplotlib lexicon, i think you want a hexbin plot.
If you're not familiar with this type of plot, it's just a bivariate histogram in which the xy-plane is tessellated by a regular grid of hexagons.
So from a histogram, you can just count the number of points falling in each hexagon, discretiize the plotting region as a set of windows, assign each point to one of these windows; finally, map the windows onto a color array, and you've got a hexbin diagram.
Though less commonly used than e.g., circles, or squares, that hexagons are a better choice for the geometry of the binning container is intuitive:
hexagons have nearest-neighbor symmetry (e.g., square bins don't,
e.g., the distance from a point on a square's border to a point
inside that square is not everywhere equal) and
hexagon is the highest n-polygon that gives regular plane
tessellation (i.e., you can safely re-model your kitchen floor with hexagonal-shaped tiles because you won't have any void space between the tiles when you are finished--not true for all other higher-n, n >= 7, polygons).
(Matplotlib uses the term hexbin plot; so do (AFAIK) all of the plotting libraries for R; still i don't know if this is the generally accepted term for plots of this type, though i suspect it's likely given that hexbin is short for hexagonal binning, which is describes the essential step in preparing the data for display.)
from matplotlib import pyplot as PLT
from matplotlib import cm as CM
from matplotlib import mlab as ML
import numpy as NP
n = 1e5
x = y = NP.linspace(-5, 5, 100)
X, Y = NP.meshgrid(x, y)
Z1 = ML.bivariate_normal(X, Y, 2, 2, 0, 0)
Z2 = ML.bivariate_normal(X, Y, 4, 1, 1, 1)
ZD = Z2 - Z1
x = X.ravel()
y = Y.ravel()
z = ZD.ravel()
gridsize=30
PLT.subplot(111)
# if 'bins=None', then color of each hexagon corresponds directly to its count
# 'C' is optional--it maps values to x-y coordinates; if 'C' is None (default) then
# the result is a pure 2D histogram
PLT.hexbin(x, y, C=z, gridsize=gridsize, cmap=CM.jet, bins=None)
PLT.axis([x.min(), x.max(), y.min(), y.max()])
cb = PLT.colorbar()
cb.set_label('mean value')
PLT.show()

Edit: For a better approximation of Alejandro's answer, see below.
I know this is an old question, but wanted to add something to Alejandro's anwser: If you want a nice smoothed image without using py-sphviewer you can instead use np.histogram2d and apply a gaussian filter (from scipy.ndimage.filters) to the heatmap:
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.cm as cm
from scipy.ndimage.filters import gaussian_filter
def myplot(x, y, s, bins=1000):
heatmap, xedges, yedges = np.histogram2d(x, y, bins=bins)
heatmap = gaussian_filter(heatmap, sigma=s)
extent = [xedges[0], xedges[-1], yedges[0], yedges[-1]]
return heatmap.T, extent
fig, axs = plt.subplots(2, 2)
# Generate some test data
x = np.random.randn(1000)
y = np.random.randn(1000)
sigmas = [0, 16, 32, 64]
for ax, s in zip(axs.flatten(), sigmas):
if s == 0:
ax.plot(x, y, 'k.', markersize=5)
ax.set_title("Scatter plot")
else:
img, extent = myplot(x, y, s)
ax.imshow(img, extent=extent, origin='lower', cmap=cm.jet)
ax.set_title("Smoothing with $\sigma$ = %d" % s)
plt.show()
Produces:
The scatter plot and s=16 plotted on top of eachother for Agape Gal'lo (click for better view):
One difference I noticed with my gaussian filter approach and Alejandro's approach was that his method shows local structures much better than mine. Therefore I implemented a simple nearest neighbour method at pixel level. This method calculates for each pixel the inverse sum of the distances of the n closest points in the data. This method is at a high resolution pretty computationally expensive and I think there's a quicker way, so let me know if you have any improvements.
Update: As I suspected, there's a much faster method using Scipy's scipy.cKDTree. See Gabriel's answer for the implementation.
Anyway, here's my code:
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.cm as cm
def data_coord2view_coord(p, vlen, pmin, pmax):
dp = pmax - pmin
dv = (p - pmin) / dp * vlen
return dv
def nearest_neighbours(xs, ys, reso, n_neighbours):
im = np.zeros([reso, reso])
extent = [np.min(xs), np.max(xs), np.min(ys), np.max(ys)]
xv = data_coord2view_coord(xs, reso, extent[0], extent[1])
yv = data_coord2view_coord(ys, reso, extent[2], extent[3])
for x in range(reso):
for y in range(reso):
xp = (xv - x)
yp = (yv - y)
d = np.sqrt(xp**2 + yp**2)
im[y][x] = 1 / np.sum(d[np.argpartition(d.ravel(), n_neighbours)[:n_neighbours]])
return im, extent
n = 1000
xs = np.random.randn(n)
ys = np.random.randn(n)
resolution = 250
fig, axes = plt.subplots(2, 2)
for ax, neighbours in zip(axes.flatten(), [0, 16, 32, 64]):
if neighbours == 0:
ax.plot(xs, ys, 'k.', markersize=2)
ax.set_aspect('equal')
ax.set_title("Scatter Plot")
else:
im, extent = nearest_neighbours(xs, ys, resolution, neighbours)
ax.imshow(im, origin='lower', extent=extent, cmap=cm.jet)
ax.set_title("Smoothing over %d neighbours" % neighbours)
ax.set_xlim(extent[0], extent[1])
ax.set_ylim(extent[2], extent[3])
plt.show()
Result:

Instead of using np.hist2d, which in general produces quite ugly histograms, I would like to recycle py-sphviewer, a python package for rendering particle simulations using an adaptive smoothing kernel and that can be easily installed from pip (see webpage documentation). Consider the following code, which is based on the example:
import numpy as np
import numpy.random
import matplotlib.pyplot as plt
import sphviewer as sph
def myplot(x, y, nb=32, xsize=500, ysize=500):
xmin = np.min(x)
xmax = np.max(x)
ymin = np.min(y)
ymax = np.max(y)
x0 = (xmin+xmax)/2.
y0 = (ymin+ymax)/2.
pos = np.zeros([len(x),3])
pos[:,0] = x
pos[:,1] = y
w = np.ones(len(x))
P = sph.Particles(pos, w, nb=nb)
S = sph.Scene(P)
S.update_camera(r='infinity', x=x0, y=y0, z=0,
xsize=xsize, ysize=ysize)
R = sph.Render(S)
R.set_logscale()
img = R.get_image()
extent = R.get_extent()
for i, j in zip(xrange(4), [x0,x0,y0,y0]):
extent[i] += j
print extent
return img, extent
fig = plt.figure(1, figsize=(10,10))
ax1 = fig.add_subplot(221)
ax2 = fig.add_subplot(222)
ax3 = fig.add_subplot(223)
ax4 = fig.add_subplot(224)
# Generate some test data
x = np.random.randn(1000)
y = np.random.randn(1000)
#Plotting a regular scatter plot
ax1.plot(x,y,'k.', markersize=5)
ax1.set_xlim(-3,3)
ax1.set_ylim(-3,3)
heatmap_16, extent_16 = myplot(x,y, nb=16)
heatmap_32, extent_32 = myplot(x,y, nb=32)
heatmap_64, extent_64 = myplot(x,y, nb=64)
ax2.imshow(heatmap_16, extent=extent_16, origin='lower', aspect='auto')
ax2.set_title("Smoothing over 16 neighbors")
ax3.imshow(heatmap_32, extent=extent_32, origin='lower', aspect='auto')
ax3.set_title("Smoothing over 32 neighbors")
#Make the heatmap using a smoothing over 64 neighbors
ax4.imshow(heatmap_64, extent=extent_64, origin='lower', aspect='auto')
ax4.set_title("Smoothing over 64 neighbors")
plt.show()
which produces the following image:
As you see, the images look pretty nice, and we are able to identify different substructures on it. These images are constructed spreading a given weight for every point within a certain domain, defined by the smoothing length, which in turns is given by the distance to the closer nb neighbor (I've chosen 16, 32 and 64 for the examples). So, higher density regions typically are spread over smaller regions compared to lower density regions.
The function myplot is just a very simple function that I've written in order to give the x,y data to py-sphviewer to do the magic.

If you are using 1.2.x
import numpy as np
import matplotlib.pyplot as plt
x = np.random.randn(100000)
y = np.random.randn(100000)
plt.hist2d(x,y,bins=100)
plt.show()

Seaborn now has the jointplot function which should work nicely here:
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
# Generate some test data
x = np.random.randn(8873)
y = np.random.randn(8873)
sns.jointplot(x=x, y=y, kind='hex')
plt.show()

Here's Jurgy's great nearest neighbour approach but implemented using scipy.cKDTree. In my tests it's about 100x faster.
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.cm as cm
from scipy.spatial import cKDTree
def data_coord2view_coord(p, resolution, pmin, pmax):
dp = pmax - pmin
dv = (p - pmin) / dp * resolution
return dv
n = 1000
xs = np.random.randn(n)
ys = np.random.randn(n)
resolution = 250
extent = [np.min(xs), np.max(xs), np.min(ys), np.max(ys)]
xv = data_coord2view_coord(xs, resolution, extent[0], extent[1])
yv = data_coord2view_coord(ys, resolution, extent[2], extent[3])
def kNN2DDens(xv, yv, resolution, neighbours, dim=2):
"""
"""
# Create the tree
tree = cKDTree(np.array([xv, yv]).T)
# Find the closest nnmax-1 neighbors (first entry is the point itself)
grid = np.mgrid[0:resolution, 0:resolution].T.reshape(resolution**2, dim)
dists = tree.query(grid, neighbours)
# Inverse of the sum of distances to each grid point.
inv_sum_dists = 1. / dists[0].sum(1)
# Reshape
im = inv_sum_dists.reshape(resolution, resolution)
return im
fig, axes = plt.subplots(2, 2, figsize=(15, 15))
for ax, neighbours in zip(axes.flatten(), [0, 16, 32, 63]):
if neighbours == 0:
ax.plot(xs, ys, 'k.', markersize=5)
ax.set_aspect('equal')
ax.set_title("Scatter Plot")
else:
im = kNN2DDens(xv, yv, resolution, neighbours)
ax.imshow(im, origin='lower', extent=extent, cmap=cm.Blues)
ax.set_title("Smoothing over %d neighbours" % neighbours)
ax.set_xlim(extent[0], extent[1])
ax.set_ylim(extent[2], extent[3])
plt.savefig('new.png', dpi=150, bbox_inches='tight')

and the initial question was... how to convert scatter values to grid values, right?
histogram2d does count the frequency per cell, however, if you have other data per cell than just the frequency, you'd need some additional work to do.
x = data_x # between -10 and 4, log-gamma of an svc
y = data_y # between -4 and 11, log-C of an svc
z = data_z #between 0 and 0.78, f1-values from a difficult dataset
So, I have a dataset with Z-results for X and Y coordinates. However, I was calculating few points outside the area of interest (large gaps), and heaps of points in a small area of interest.
Yes here it becomes more difficult but also more fun. Some libraries (sorry):
from matplotlib import pyplot as plt
from matplotlib import cm
import numpy as np
from scipy.interpolate import griddata
pyplot is my graphic engine today,
cm is a range of color maps with some initeresting choice.
numpy for the calculations,
and griddata for attaching values to a fixed grid.
The last one is important especially because the frequency of xy points is not equally distributed in my data. First, let's start with some boundaries fitting to my data and an arbitrary grid size. The original data has datapoints also outside those x and y boundaries.
#determine grid boundaries
gridsize = 500
x_min = -8
x_max = 2.5
y_min = -2
y_max = 7
So we have defined a grid with 500 pixels between the min and max values of x and y.
In my data, there are lots more than the 500 values available in the area of high interest; whereas in the low-interest-area, there are not even 200 values in the total grid; between the graphic boundaries of x_min and x_max there are even less.
So for getting a nice picture, the task is to get an average for the high interest values and to fill the gaps elsewhere.
I define my grid now. For each xx-yy pair, i want to have a color.
xx = np.linspace(x_min, x_max, gridsize) # array of x values
yy = np.linspace(y_min, y_max, gridsize) # array of y values
grid = np.array(np.meshgrid(xx, yy.T))
grid = grid.reshape(2, grid.shape[1]*grid.shape[2]).T
Why the strange shape? scipy.griddata wants a shape of (n, D).
Griddata calculates one value per point in the grid, by a predefined method.
I choose "nearest" - empty grid points will be filled with values from the nearest neighbor. This looks as if the areas with less information have bigger cells (even if it is not the case). One could choose to interpolate "linear", then areas with less information look less sharp. Matter of taste, really.
points = np.array([x, y]).T # because griddata wants it that way
z_grid2 = griddata(points, z, grid, method='nearest')
# you get a 1D vector as result. Reshape to picture format!
z_grid2 = z_grid2.reshape(xx.shape[0], yy.shape[0])
And hop, we hand over to matplotlib to display the plot
fig = plt.figure(1, figsize=(10, 10))
ax1 = fig.add_subplot(111)
ax1.imshow(z_grid2, extent=[x_min, x_max,y_min, y_max, ],
origin='lower', cmap=cm.magma)
ax1.set_title("SVC: empty spots filled by nearest neighbours")
ax1.set_xlabel('log gamma')
ax1.set_ylabel('log C')
plt.show()
Around the pointy part of the V-Shape, you see I did a lot of calculations during my search for the sweet spot, whereas the less interesting parts almost everywhere else have a lower resolution.

Make a 2-dimensional array that corresponds to the cells in your final image, called say heatmap_cells and instantiate it as all zeroes.
Choose two scaling factors that define the difference between each array element in real units, for each dimension, say x_scale and y_scale. Choose these such that all your datapoints will fall within the bounds of the heatmap array.
For each raw datapoint with x_value and y_value:
heatmap_cells[floor(x_value/x_scale),floor(y_value/y_scale)]+=1

Very similar to #Piti's answer, but using 1 call instead of 2 to generate the points:
import numpy as np
import matplotlib.pyplot as plt
pts = 1000000
mean = [0.0, 0.0]
cov = [[1.0,0.0],[0.0,1.0]]
x,y = np.random.multivariate_normal(mean, cov, pts).T
plt.hist2d(x, y, bins=50, cmap=plt.cm.jet)
plt.show()
Output:

Here's one I made on a 1 Million point set with 3 categories (colored Red, Green, and Blue). Here's a link to the repository if you'd like to try the function. Github Repo
histplot(
X,
Y,
labels,
bins=2000,
range=((-3,3),(-3,3)),
normalize_each_label=True,
colors = [
[1,0,0],
[0,1,0],
[0,0,1]],
gain=50)

I'm afraid I'm a little late to the party but I had a similar question a while ago. The accepted answer (by #ptomato) helped me out but I'd also want to post this in case it's of use to someone.
''' I wanted to create a heatmap resembling a football pitch which would show the different actions performed '''
import numpy as np
import matplotlib.pyplot as plt
import random
#fixing random state for reproducibility
np.random.seed(1234324)
fig = plt.figure(12)
ax1 = fig.add_subplot(121)
ax2 = fig.add_subplot(122)
#Ratio of the pitch with respect to UEFA standards
hmap= np.full((6, 10), 0)
#print(hmap)
xlist = np.random.uniform(low=0.0, high=100.0, size=(20))
ylist = np.random.uniform(low=0.0, high =100.0, size =(20))
#UEFA Pitch Standards are 105m x 68m
xlist = (xlist/100)*10.5
ylist = (ylist/100)*6.5
ax1.scatter(xlist,ylist)
#int of the co-ordinates to populate the array
xlist_int = xlist.astype (int)
ylist_int = ylist.astype (int)
#print(xlist_int, ylist_int)
for i, j in zip(xlist_int, ylist_int):
#this populates the array according to the x,y co-ordinate values it encounters
hmap[j][i]= hmap[j][i] + 1
#Reversing the rows is necessary
hmap = hmap[::-1]
#print(hmap)
im = ax2.imshow(hmap)
Here's the result

None of these solutions worked for my application, so this is what I came up with. Essentially I am placing a 2D Gaussian at every single point:
import cv2
import numpy as np
import matplotlib.pyplot as plt
def getGaussian2D(ksize, sigma, norm=True):
oneD = cv2.getGaussianKernel(ksize=ksize, sigma=sigma)
twoD = np.outer(oneD.T, oneD)
return twoD / np.sum(twoD) if norm else twoD
def pt2heat(pts, shape, kernel=16, sigma=5):
heat = np.zeros(shape)
k = getGaussian2D(kernel, sigma)
for y,x in pts:
x, y = int(x), int(y)
for i in range(-kernel//2, kernel//2):
for j in range(-kernel//2, kernel//2):
if 0 <= x+i < shape[0] and 0 <= y+j < shape[1]:
heat[x+i, y+j] = heat[x+i, y+j] + k[i+kernel//2, j+kernel//2]
return heat
heat = pts2heat(pts, img.shape[:2])
plt.imshow(heat, cmap='heat')
Here are the points overlayed ontop of it's associated image, along with the resulting heat map: