Finding angle using matplotlib - python

I am fairly new to using matplotlib and cannot find any examples that show how to mark the angle of a point. I need to find the angle in all four quadrants i.e. if the point is (1,1) angle=45 degrees, (-1,1) angle= 135 degrees, (-1,-1) angle=225 degrees and for (1,-1) it should be 315 degrees.
Here is the function to which i need to add this to:
def visualize(val,ar):
plt.figure()
ax = plt.gca()
ax.plot([val-5],[ar-5], marker='o', color='r')
ax.set_xlim([-5,5])
ax.set_ylim([-5,5])
plt.draw()
plt.grid()
plt.show()

I think you need to do the maths on your points yourself and then annotate the points on the plot using annotate(). It's hard to tell from your example whether val and ar are single values or vectors - I think single values given the syntax you're using. Here's an example with a function to do the maths and an example use of annotate - I've tried to keep the plotting bits the same as your code and just add the bits to calculate degrees and then put them on the axes
import math
import matplotlib.pyplot as plt
#This function does the maths - turns co-ordinates into angles
#with 0 on +ve x axis, increasing anti-clockwise
def get_theta(x,y):
theta = math.atan(y*1.0/x) / (2*math.pi) * 360
if x < 0:
theta += 180
if theta < 0:
theta += 360
return theta
def visualize(val,ar):
ax = plt.gca()
ax.plot([val-5],[ar-5], marker='o', color='r')
ax.set_xlim([-5,5])
ax.set_ylim([-5,5])
#insert the following to calculate the angles and
#then annotate them on the plot
x,y = val-5,ar-5
label = get_theta(x, y)
ax.annotate(str(label)+' degrees', xy = (x, y), xytext = (-20, 20),textcoords = 'offset points')
if __name__ == '__main__':
plt.figure()
x = [6,4,4,6]
y = [6,6,4,4]
for (val, ar) in zip(x,y):
visualize(val,ar)
plt.draw()
plt.grid()
plt.show()
Further variations on what you can do with annotations are in the docs.
Output

Related

add text on polarplot

I am trying to plot angles and add the angles as text. This is what I have:
import numpy as np
import matplotlib.pyplot as plt
fig, ax = plt.subplots(subplot_kw=dict(projection='polar'))
ax.set_theta_offset(np.pi/2) # changes the 0 to be at the top
ax.set_theta_direction(-1) # clockwise
# ax.set_facecolor(green_plot_temp) # sets the background color
angle0 = 260
angle1 = 280
actual = np.radians(np.arange(angle0,angle1,1))
expected = np.arange(angle0,angle1,1)
r, theta = np.meshgrid(expected, actual)
values = np.ones((actual.size, expected.size))
# plot slice
ax.contourf(theta, r, values, colors='r') # color of the slice
# add the angles as text
text0_x = str(angle0)
text1_x = str(angle1)
ax.text(np.radians(angle0), ax.get_rmax(), text0_x, color="blue", ha='right', va='bottom', fontdict={'fontsize':11})
ax.text(np.radians(angle1), ax.get_rmax(), text1_x, color="blue", ha='left', va='top', fontdict={'fontsize':11})
This gives:
Now, I don't understand why the text 260 is outside the figure (that's the result I want obv.), and the text 280 is inside.
Replacing the angles with
angle0 = 160
angle1 = 270
Gives this figure:
I am quite lost.
In the end I am looping all that and making a lot of figures with different angles, and so far I have not managed to obtain consistent results with different angles.

How to find the angle of X and Y and then plot a line transecting each grid lines at a variable angle?

I am trying to work out how to find the angles labelled in the image.
I would then like to be able to plot a line intersecting the y or x-axis with a variable angle, say 20 degrees?
I think finding the angle of intersections first is the bit that could then help me work out how to do the variable bit myself.
import matplotlib.pyplot as plt
f, ax = plt.subplots(figsize=(10, 10))
ax.spines['left'].set_position('center')
ax.spines['bottom'].set_position('center')
ax.spines['right'].set_color('none')
ax.spines['top'].set_color('none')
ax.xaxis.set_ticks_position('bottom')
ax.yaxis.set_ticks_position('left')
x = np.linspace(-5,5, 100)
plt.plot(x, -1.5*x+20, '-r', label='y=2x+1')
plt.plot(x, 2.5*x+4, '-r', label='y=2x+1')
plt.show()
Edit
Here is an attempt to rearange the formula given in the correct answer.
formula rearranged
and my attempt to codify it, but it breaks.
my_angle = 45
gradient = np.arctan**(np.pi * my_angle/180 + np.pi)
Since you already know the slopes of your two lines, you can simply compute the inverse tan of the slopes to get the angles. You can then multiply with 180 / np.pi to get the values in degrees.
import numpy as np
angle1 = np.arctan(2.5) * 180 / np.pi # angle in degrees
# 68.19859051364818
angle2 = 180 - abs(np.arctan(-1.5) * 180 / np.pi) # angle in degrees
# 123.69006752597979

Density scatter plot for huge dataset in matplotlib

I wrote some code a while ago that used gaussian kde to make simple density scatter plots. However, for datasets larger than about 100,000 points, it just ran 'forever' (I killed it after a few days). A friend gave me some code in R that could create such a density plot in seconds (plot_fun.R), and it seems like matplotlib should be able to do the same thing.
I think the right place to look is 2d histograms, but I am struggling to get the density to be 'right'. I modified code I found at this question to accomplish this, but the density is not showing, it looks like only the densist posible points are getting any color.
Here is approximately the code I am using:
# initial data
x = -np.log10(np.random.random_sample(10000))
y = -np.log10(np.random.random_sample(10000))
#histogram definition
bins = [1000, 1000] # number of bins
thresh = 3 #density threshold
#data definition
mn = min(x.min(), y.min())
mx = max(x.max(), y.max())
mn = mn-(mn*.1)
mx = mx+(mx*.1)
xyrange = [[mn, mx], [mn, mx]]
# histogram the data
hh, locx, locy = np.histogram2d(x, y, range=xyrange, bins=bins)
posx = np.digitize(x, locx)
posy = np.digitize(y, locy)
#select points within the histogram
ind = (posx > 0) & (posx <= bins[0]) & (posy > 0) & (posy <= bins[1])
hhsub = hh[posx[ind] - 1, posy[ind] - 1] # values of the histogram where the points are
xdat1 = x[ind][hhsub < thresh] # low density points
ydat1 = y[ind][hhsub < thresh]
hh[hh < thresh] = np.nan # fill the areas with low density by NaNs
f, a = plt.subplots(figsize=(12,12))
c = a.imshow(
np.flipud(hh.T), cmap='jet',
extent=np.array(xyrange).flatten(), interpolation='none',
origin='upper'
)
f.colorbar(c, ax=ax, orientation='vertical', shrink=0.75, pad=0.05)
s = a.scatter(
xdat1, ydat1, color='darkblue', edgecolor='', label=None,
picker=True, zorder=2
)
That produces this plot:
The KDE code is here:
f, a = plt.subplots(figsize=(12,12))
xy = np.vstack([x, y])
z = sts.gaussian_kde(xy)(xy)
# Sort the points by density, so that the densest points are
# plotted last
idx = z.argsort()
x2, y2, z = x[idx], y[idx], z[idx]
s = a.scatter(
x2, y2, c=z, s=50, cmap='jet',
edgecolor='', label=None, picker=True, zorder=2
)
That produces this plot:
The problem is, of course, that this code is unusable on large data sets.
My question is: how can I use the 2d histogram to produce a scatter plot like that? ax.hist2d does not produce a useful output, because it colors the whole plot, and all my efforts to get the above 2d histogram data to actually color the dense regions of the plot correctly have failed, I always end up with either no coloring or a tiny percentage of the densest points being colored. Clearly I just don't understand the code very well.
Your histogram code assigns a unique color (color='darkblue') so what are you expecting?
I think you are also over complicating things. This much simpler code works fine:
import numpy as np
import matplotlib.pyplot as plt
x, y = -np.log10(np.random.random_sample((2,10**6)))
#histogram definition
bins = [1000, 1000] # number of bins
# histogram the data
hh, locx, locy = np.histogram2d(x, y, bins=bins)
# Sort the points by density, so that the densest points are plotted last
z = np.array([hh[np.argmax(a<=locx[1:]),np.argmax(b<=locy[1:])] for a,b in zip(x,y)])
idx = z.argsort()
x2, y2, z2 = x[idx], y[idx], z[idx]
plt.figure(1,figsize=(8,8)).clf()
s = plt.scatter(x2, y2, c=z2, cmap='jet', marker='.')

Matplotlib - contour and quiver plot in projected polar coordinates

I need to plot contour and quiver plots of scalar and vector fields defined on an uneven grid in (r,theta) coordinates.
As a minimal example of the problem I have, consider the contour plot of a Stream function for a magnetic dipole, contours of such a function are streamlines of the corresponeding vector field (in this case, the magnetic field).
The code below takes an uneven grid in (r,theta) coordinates, maps it to the cartesian plane and plots a contour plot of the stream function.
import numpy as np
import matplotlib.pyplot as plt
r = np.logspace(0,1,200)
theta = np.linspace(0,np.pi/2,100)
N_r = len(r)
N_theta = len(theta)
# Polar to cartesian coordinates
theta_matrix, r_matrix = np.meshgrid(theta, r)
x = r_matrix * np.cos(theta_matrix)
y = r_matrix * np.sin(theta_matrix)
m = 5
psi = np.zeros((N_r, N_theta))
# Stream function for a magnetic dipole
psi = m * np.sin(theta_matrix)**2 / r_matrix
contour_levels = m * np.sin(np.linspace(0, np.pi/2,40))**2.
fig, ax = plt.subplots()
# ax.plot(x,y,'b.') # plot grid points
ax.set_aspect('equal')
ax.contour(x, y, psi, 100, colors='black',levels=contour_levels)
plt.show()
For some reason though, the plot I get doesn't look right:
If I interchange x and y in the contour function call, I get the desired result:
Same thing happens when I try to make a quiver plot of a vector field defined on the same grid and mapped to the x-y plane, except that interchanging x and y in the function call no longer works.
It seems like I made a stupid mistake somewhere but I can't figure out what it is.
If psi = m * np.sin(theta_matrix)**2 / r_matrix
then psi increases as theta goes from 0 to pi/2 and psi decreases as r increases.
So a contour line for psi should increase in r as theta increases. That results
in a curve that goes counterclockwise as it radiates out from the center. This is
consistent with the first plot you posted, and the result returned by the first version of your code with
ax.contour(x, y, psi, 100, colors='black',levels=contour_levels)
An alternative way to confirm the plausibility of the result is to look at a surface plot of psi:
import numpy as np
import matplotlib.pyplot as plt
import mpl_toolkits.mplot3d.axes3d as axes3d
r = np.logspace(0,1,200)
theta = np.linspace(0,np.pi/2,100)
N_r = len(r)
N_theta = len(theta)
# Polar to cartesian coordinates
theta_matrix, r_matrix = np.meshgrid(theta, r)
x = r_matrix * np.cos(theta_matrix)
y = r_matrix * np.sin(theta_matrix)
m = 5
# Stream function for a magnetic dipole
psi = m * np.sin(theta_matrix)**2 / r_matrix
contour_levels = m * np.sin(np.linspace(0, np.pi/2,40))**2.
fig = plt.figure()
ax = fig.add_subplot(1, 1, 1, projection='3d')
ax.set_aspect('equal')
ax.plot_surface(x, y, psi, rstride=8, cstride=8, alpha=0.3)
ax.contour(x, y, psi, colors='black',levels=contour_levels)
plt.show()

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:

Categories

Resources