In R, there is a function called abline in which a line can be drawn on a plot based on the specification of the intercept (first argument) and the slope (second argument). For instance,
plot(1:10, 1:10)
abline(0, 1)
where the line with an intercept of 0 and the slope of 1 spans the entire range of the plot. Is there such a function in Matplotlib?
A lot of these solutions are focusing on adding a line to the plot that fits the data. Here's a simple solution for adding an arbitrary line to the plot based on a slope and intercept.
import matplotlib.pyplot as plt
import numpy as np
def abline(slope, intercept):
"""Plot a line from slope and intercept"""
axes = plt.gca()
x_vals = np.array(axes.get_xlim())
y_vals = intercept + slope * x_vals
plt.plot(x_vals, y_vals, '--')
I know this question is a couple years old, but since there is no accepted answer, I'll add what works for me.
You could just plot the values in your graph, and then generate another set of values for the coordinates of the best fit line and plot that over your original graph. For example, see the following code:
import matplotlib.pyplot as plt
import numpy as np
# Some dummy data
x = [1, 2, 3, 4, 5, 6, 7]
y = [1, 3, 3, 2, 5, 7, 9]
# Find the slope and intercept of the best fit line
slope, intercept = np.polyfit(x, y, 1)
# Create a list of values in the best fit line
abline_values = [slope * i + intercept for i in x]
# Plot the best fit line over the actual values
plt.plot(x, y, '--')
plt.plot(x, abline_values, 'b')
plt.title(slope)
plt.show()
As of 2021, in matplotlib 3.3.4, it supports drawing lines with slope value and a point.
fig, ax = plt.subplots()
ax.axline((0, 4), slope=3., color='C0', label='by slope')
ax.set_xlim(0, 1)
ax.set_ylim(3, 5)
ax.legend()
X = np.array([1, 2, 3, 4, 5, 6, 7])
Y = np.array([1.1,1.9,3.0,4.1,5.2,5.8,7])
scatter (X,Y)
slope, intercept = np.polyfit(X, Y, 1)
plot(X, X*slope + intercept, 'r')
It looks like this feature will be part of version 3.3.0:
matplotlib.axes.Axes.axline
You'll be, for example, able to draw a red line through points (0, 0) and (1, 1) using
axline((0, 0), (1, 1), linewidth=4, color='r')
I couldn't figure a way to do it without resorting to callbacks, but this seems to work fairly well.
import numpy as np
from matplotlib import pyplot as plt
class ABLine2D(plt.Line2D):
"""
Draw a line based on its slope and y-intercept. Additional arguments are
passed to the <matplotlib.lines.Line2D> constructor.
"""
def __init__(self, slope, intercept, *args, **kwargs):
# get current axes if user has not specified them
if not 'axes' in kwargs:
kwargs.update({'axes':plt.gca()})
ax = kwargs['axes']
# if unspecified, get the current line color from the axes
if not ('color' in kwargs or 'c' in kwargs):
kwargs.update({'color':ax._get_lines.color_cycle.next()})
# init the line, add it to the axes
super(ABLine2D, self).__init__([], [], *args, **kwargs)
self._slope = slope
self._intercept = intercept
ax.add_line(self)
# cache the renderer, draw the line for the first time
ax.figure.canvas.draw()
self._update_lim(None)
# connect to axis callbacks
self.axes.callbacks.connect('xlim_changed', self._update_lim)
self.axes.callbacks.connect('ylim_changed', self._update_lim)
def _update_lim(self, event):
""" called whenever axis x/y limits change """
x = np.array(self.axes.get_xbound())
y = (self._slope * x) + self._intercept
self.set_data(x, y)
self.axes.draw_artist(self)
I suppose for the case of (intercept, slope) of (0, 1) the following function could be used and extended to accommodate other slopes and intercepts, but won't readjust if axis limits are changed or autoscale is turned back on.
def abline():
gca = plt.gca()
gca.set_autoscale_on(False)
gca.plot(gca.get_xlim(),gca.get_ylim())
import matplotlib.pyplot as plt
plt.scatter(range(10),range(10))
abline()
plt.draw()
I'd like to expand on the answer from David Marx, where we are making sure that the sloped line does not expand over the original plotting area.
Since the x-axis limits are used to calculate the y-data for the sloped line, we need to make sure, that the calculated y-data does not extend the given ymin - ymax range. If it does crop the displayed data.
def abline(slope, intercept,**styles):
"""Plot a line from slope and intercept"""
axes = plt.gca()
xmin,xmax = np.array(axes.get_xlim())
ymin,ymax = np.array(axes.get_ylim()) # get also y limits
x_vals = np.linspace(xmin,xmax,num=1000) #increased sampling (only actually needed for large slopes)
y_vals = intercept + slope * x_vals
locpos = np.where(y_vals<ymax)[0] # if data extends above ymax
locneg = np.where(y_vals>ymin)[0] # if data extends below ymin
# select most restricitive condition
if len(locpos) >= len(locneg):
loc = locneg
else:
loc = locpos
plt.plot(x_vals[loc], y_vals[loc], '--',**styles)
return y_vals
Here's a possible workaround I came up with: suppose I have my intercept coordinates stored as x_intercept and y_intercept, and the slope (m) saved as my_slope which was found through the renowned equation m = (y2-y1)/(x2-x1), or in whichever way you managed to find it.
Using the other famous general equation for a line y = mx + q, I define the function find_second_point that first computes the q (since m, x and y are known) and then computes another random point that belongs to that line.
Once I have the two points (the initial x_intercept,y_intercept and the newly found new_x,new_y), I simply plot the segment through those two points. Here's the code:
import numpy as np
import matplotlib.pyplot as plt
x_intercept = 3 # invented x coordinate
y_intercept = 2 # invented y coordinate
my_slope = 1 # invented slope value
def find_second_point(slope,x0,y0):
# this function returns a point which belongs to the line that has the slope
# inserted by the user and that intercepts the point (x0,y0) inserted by the user
q = y0 - (slope*x0) # calculate q
new_x = x0 + 10 # generate random x adding 10 to the intersect x coordinate
new_y = (slope*new_x) + q # calculate new y corresponding to random new_x created
return new_x, new_y # return x and y of new point that belongs to the line
# invoke function to calculate the new point
new_x, new_y = find_second_point(my_slope , x_intercept, y_intercept)
plt.figure(1) # create new figure
plt.plot((x_intercept, new_x),(y_intercept, new_y), c='r', label='Segment')
plt.scatter(x_intercept, y_intercept, c='b', linewidths=3, label='Intercept')
plt.scatter(new_x, new_y, c='g', linewidths=3, label='New Point')
plt.legend() # add legend to image
plt.show()
here is the image generated by the code:
Short answer inspired by kite.com:
plt.plot(x, s*x + i)
Reproducible code:
import numpy as np
import matplotlib.pyplot as plt
i=3 # intercept
s=2 # slope
x=np.linspace(1,10,50) # from 1 to 10, by 50
plt.plot(x, s*x + i) # abline
plt.show()
One can simply create a list with the line's equation obtained from a particular intercept and slope. Put those values in a list and plot it against any set of numbers you would like. For example- (Lr being the Linear regression model)
te= []
for i in range(11):
te.append(Lr.intercept_ + Lr.coef_*i)
plt.plot(te, '--')
Gets the job done.
You can write a simple function by converting Slope-Intercept form to 2-Point Form.
def mxline(slope, intercept, start, end):
y1 = slope*start + intercept
y2 = slope*end + intercept
plt.plot([start, end], [y1, y2])
Calling the function
mxline(m,c, 0, 20)
OUTPUT
Related
I am trying to create a code to produce a failure mode plot for honeycomb beam structures as seen in the image below:
(from M. Sadighi et al. 2009)
There are distinct formulas to calculate the load at which the failure will occur, and given the material/beam parameters, the lowest value is the most likely failure to occur.
I have a triple nested for loop running ranges of values for t, L, and rho. Mesh grid from numpy and the contour plot from matplotlib seemed logical, but throw an error for the z input requiring a 2D array.
I thought that maybe each failure type could be encoded into a value (i.e. 1 for core crush, 2 for indentation, etc.) and you could scan the x and y values to store where the change in failure type happen, but I still don't know how to get that into a plot.
The closest thing I have found so far can be seen here The moons dataset and decision surface graphics in a Jupyter environment where the plot is split into different colored regions.
How can this be plotted?
P.S. I know that you are suppose to attach code, however in this case, a ton of variables are need to do the calculations and would be difficult to pass around.
I am trying to rephrase the question. Let's say we have functions of two coordinates: f1(x, y), f2(x, y)... They correspond for instance at the critical stress for each failure mode. Variables x, y are two of the parameters.
For a given (x, y) the failure mode is obtain by using argmin( f1(x, y), f2(x, y), ... ) i.e. the failure mode for which the critical stress is minimal
Here is the simple solution I could think of to obtain a map of the failure modes:
import numpy as np
import matplotlib.pyplot as plt
from matplotlib.colors import ListedColormap
# Mesh the parameters space
x = np.linspace(0, 2, 35)
y = np.linspace(0, 1, 24)
x_grid, y_grid = np.meshgrid(x, y)
# Compute the functions for each point on the mesh
f1 = x_grid + y_grid
f2 = 0.5 + x_grid**2
f3 = 1 + y_grid**2
# Identify which function is minimal for each point
failure_mode = np.argmin([f1, f2, f3], axis=0)
# Graph
discrete_colormap = ListedColormap(['gold', 'darkorange', 'mediumseagreen'])
plt.pcolormesh(x, y, failure_mode, cmap=discrete_colormap);
cbar = plt.colorbar();
cbar.set_label('failure mode');
cbar.set_ticks(np.arange(np.max(failure_mode)+1));
plt.xlabel('x'); plt.ylabel('y');
which gives:
See for example this answer for discrete colormap.
Here is a solution to plot the contour of each zone:
The contour of the zone i is defined as the points (x, y) such that f_i(x, y) is equal to the minimum of all the remaining functions i.e. min( f_j(x, y) for i != j ). We could use several contour plots with surfaces equal to f_i(x, y) - min( f_j(x, y) for i!=j ). The level of the zone boundary is zero.
import numpy as np
import matplotlib.pyplot as plt
# Mesh the parameters space
x = np.linspace(0, 2, 35)
y = np.linspace(0, 1, 24)
x_grid, y_grid = np.meshgrid(x, y)
# List of functions evaluated for each point of the mesh
f_grid = [x_grid + y_grid,
0.5 + x_grid**2,
1 + y_grid**2]
# Identify which function is minimal for each point
failure_mode = np.argmin(f_grid, axis=0)
# this part is for the background
critical_stress = np.min(f_grid, axis=0)
plt.pcolormesh(x, y, critical_stress, shading='Gouraud')
cbar = plt.colorbar();
cbar.set_label('critical stress');
# Plot the contour of each zone
for i in range(len(f_grid)):
other_functions = [f_j for j, f_j in enumerate(f_grid) if i != j]
level_surface = f_grid[i] - np.min(other_functions, axis=0)
plt.contour(x, y, level_surface,
levels=[0, ],
linewidths=2, colors='black');
# label
barycentre_x = np.mean(x_grid[failure_mode==i])
barycentre_y = np.mean(y_grid[failure_mode==i])
plt.text(barycentre_x, barycentre_y, 'mode %i' % i)
plt.xlabel('x'); plt.ylabel('y');
the graph is:
I've been toying around with this problem and am close to what I want but missing that extra line or two.
Basically, I'd like to plot a single line whose color changes given the value of a third array. Lurking around I have found this works well (albeit pretty slowly) and represents the problem
import numpy as np
import matplotlib.pyplot as plt
c = np.arange(1,100)
x = np.arange(1,100)
y = np.arange(1,100)
cm = plt.get_cmap('hsv')
fig = plt.figure(figsize=(5,5))
ax1 = plt.subplot(111)
no_points = len(c)
ax1.set_color_cycle([cm(1.*i/(no_points-1))
for i in range(no_points-1)])
for i in range(no_points-1):
bar = ax1.plot(x[i:i+2],y[i:i+2])
plt.show()
Which gives me this:
I'd like to be able to include a colorbar along with this plot. So far I haven't been able to crack it just yet. Potentially there will be other lines included with different x,y's but the same c, so I was thinking that a Normalize object would be the right path.
Bigger picture is that this plot is part of a 2x2 sub plot grid. I am already making space for the color bar axes object with matplotlib.colorbar.make_axes(ax4), where ax4 with the 4th subplot.
Take a look at the multicolored_line example in the Matplotlib gallery and dpsanders' colorline notebook:
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.collections as mcoll
def multicolored_lines():
"""
http://nbviewer.ipython.org/github/dpsanders/matplotlib-examples/blob/master/colorline.ipynb
http://matplotlib.org/examples/pylab_examples/multicolored_line.html
"""
x = np.linspace(0, 4. * np.pi, 100)
y = np.sin(x)
fig, ax = plt.subplots()
lc = colorline(x, y, cmap='hsv')
plt.colorbar(lc)
plt.xlim(x.min(), x.max())
plt.ylim(-1.0, 1.0)
plt.show()
def colorline(
x, y, z=None, cmap='copper', norm=plt.Normalize(0.0, 1.0),
linewidth=3, alpha=1.0):
"""
http://nbviewer.ipython.org/github/dpsanders/matplotlib-examples/blob/master/colorline.ipynb
http://matplotlib.org/examples/pylab_examples/multicolored_line.html
Plot a colored line with coordinates x and y
Optionally specify colors in the array z
Optionally specify a colormap, a norm function and a line width
"""
# Default colors equally spaced on [0,1]:
if z is None:
z = np.linspace(0.0, 1.0, len(x))
# Special case if a single number:
# to check for numerical input -- this is a hack
if not hasattr(z, "__iter__"):
z = np.array([z])
z = np.asarray(z)
segments = make_segments(x, y)
lc = mcoll.LineCollection(segments, array=z, cmap=cmap, norm=norm,
linewidth=linewidth, alpha=alpha)
ax = plt.gca()
ax.add_collection(lc)
return lc
def make_segments(x, y):
"""
Create list of line segments from x and y coordinates, in the correct format
for LineCollection: an array of the form numlines x (points per line) x 2 (x
and y) array
"""
points = np.array([x, y]).T.reshape(-1, 1, 2)
segments = np.concatenate([points[:-1], points[1:]], axis=1)
return segments
multicolored_lines()
Note that calling plt.plot hundreds of times tends to kill performance.
Using a LineCollection to build multi-colored line segments is much much faster.
In Matplotlib, it's not too tough to make a legend (example_legend(), below), but I think it's better style to put labels right on the curves being plotted (as in example_inline(), below). This can be very fiddly, because I have to specify coordinates by hand, and, if I re-format the plot, I probably have to reposition the labels. Is there a way to automatically generate labels on curves in Matplotlib? Bonus points for being able to orient the text at an angle corresponding to the angle of the curve.
import numpy as np
import matplotlib.pyplot as plt
def example_legend():
plt.clf()
x = np.linspace(0, 1, 101)
y1 = np.sin(x * np.pi / 2)
y2 = np.cos(x * np.pi / 2)
plt.plot(x, y1, label='sin')
plt.plot(x, y2, label='cos')
plt.legend()
def example_inline():
plt.clf()
x = np.linspace(0, 1, 101)
y1 = np.sin(x * np.pi / 2)
y2 = np.cos(x * np.pi / 2)
plt.plot(x, y1, label='sin')
plt.plot(x, y2, label='cos')
plt.text(0.08, 0.2, 'sin')
plt.text(0.9, 0.2, 'cos')
Update: User cphyc has kindly created a Github repository for the code in this answer (see here), and bundled the code into a package which may be installed using pip install matplotlib-label-lines.
Pretty Picture:
In matplotlib it's pretty easy to label contour plots (either automatically or by manually placing labels with mouse clicks). There does not (yet) appear to be any equivalent capability to label data series in this fashion! There may be some semantic reason for not including this feature which I am missing.
Regardless, I have written the following module which takes any allows for semi-automatic plot labelling. It requires only numpy and a couple of functions from the standard math library.
Description
The default behaviour of the labelLines function is to space the labels evenly along the x axis (automatically placing at the correct y-value of course). If you want you can just pass an array of the x co-ordinates of each of the labels. You can even tweak the location of one label (as shown in the bottom right plot) and space the rest evenly if you like.
In addition, the label_lines function does not account for the lines which have not had a label assigned in the plot command (or more accurately if the label contains '_line').
Keyword arguments passed to labelLines or labelLine are passed on to the text function call (some keyword arguments are set if the calling code chooses not to specify).
Issues
Annotation bounding boxes sometimes interfere undesirably with other curves. As shown by the 1 and 10 annotations in the top left plot. I'm not even sure this can be avoided.
It would be nice to specify a y position instead sometimes.
It's still an iterative process to get annotations in the right location
It only works when the x-axis values are floats
Gotchas
By default, the labelLines function assumes that all data series span the range specified by the axis limits. Take a look at the blue curve in the top left plot of the pretty picture. If there were only data available for the x range 0.5-1 then then we couldn't possibly place a label at the desired location (which is a little less than 0.2). See this question for a particularly nasty example. Right now, the code does not intelligently identify this scenario and re-arrange the labels, however there is a reasonable workaround. The labelLines function takes the xvals argument; a list of x-values specified by the user instead of the default linear distribution across the width. So the user can decide which x-values to use for the label placement of each data series.
Also, I believe this is the first answer to complete the bonus objective of aligning the labels with the curve they're on. :)
label_lines.py:
from math import atan2,degrees
import numpy as np
#Label line with line2D label data
def labelLine(line,x,label=None,align=True,**kwargs):
ax = line.axes
xdata = line.get_xdata()
ydata = line.get_ydata()
if (x < xdata[0]) or (x > xdata[-1]):
print('x label location is outside data range!')
return
#Find corresponding y co-ordinate and angle of the line
ip = 1
for i in range(len(xdata)):
if x < xdata[i]:
ip = i
break
y = ydata[ip-1] + (ydata[ip]-ydata[ip-1])*(x-xdata[ip-1])/(xdata[ip]-xdata[ip-1])
if not label:
label = line.get_label()
if align:
#Compute the slope
dx = xdata[ip] - xdata[ip-1]
dy = ydata[ip] - ydata[ip-1]
ang = degrees(atan2(dy,dx))
#Transform to screen co-ordinates
pt = np.array([x,y]).reshape((1,2))
trans_angle = ax.transData.transform_angles(np.array((ang,)),pt)[0]
else:
trans_angle = 0
#Set a bunch of keyword arguments
if 'color' not in kwargs:
kwargs['color'] = line.get_color()
if ('horizontalalignment' not in kwargs) and ('ha' not in kwargs):
kwargs['ha'] = 'center'
if ('verticalalignment' not in kwargs) and ('va' not in kwargs):
kwargs['va'] = 'center'
if 'backgroundcolor' not in kwargs:
kwargs['backgroundcolor'] = ax.get_facecolor()
if 'clip_on' not in kwargs:
kwargs['clip_on'] = True
if 'zorder' not in kwargs:
kwargs['zorder'] = 2.5
ax.text(x,y,label,rotation=trans_angle,**kwargs)
def labelLines(lines,align=True,xvals=None,**kwargs):
ax = lines[0].axes
labLines = []
labels = []
#Take only the lines which have labels other than the default ones
for line in lines:
label = line.get_label()
if "_line" not in label:
labLines.append(line)
labels.append(label)
if xvals is None:
xmin,xmax = ax.get_xlim()
xvals = np.linspace(xmin,xmax,len(labLines)+2)[1:-1]
for line,x,label in zip(labLines,xvals,labels):
labelLine(line,x,label,align,**kwargs)
Test code to generate the pretty picture above:
from matplotlib import pyplot as plt
from scipy.stats import loglaplace,chi2
from labellines import *
X = np.linspace(0,1,500)
A = [1,2,5,10,20]
funcs = [np.arctan,np.sin,loglaplace(4).pdf,chi2(5).pdf]
plt.subplot(221)
for a in A:
plt.plot(X,np.arctan(a*X),label=str(a))
labelLines(plt.gca().get_lines(),zorder=2.5)
plt.subplot(222)
for a in A:
plt.plot(X,np.sin(a*X),label=str(a))
labelLines(plt.gca().get_lines(),align=False,fontsize=14)
plt.subplot(223)
for a in A:
plt.plot(X,loglaplace(4).pdf(a*X),label=str(a))
xvals = [0.8,0.55,0.22,0.104,0.045]
labelLines(plt.gca().get_lines(),align=False,xvals=xvals,color='k')
plt.subplot(224)
for a in A:
plt.plot(X,chi2(5).pdf(a*X),label=str(a))
lines = plt.gca().get_lines()
l1=lines[-1]
labelLine(l1,0.6,label=r'$Re=${}'.format(l1.get_label()),ha='left',va='bottom',align = False)
labelLines(lines[:-1],align=False)
plt.show()
#Jan Kuiken's answer is certainly well-thought and thorough, but there are some caveats:
it does not work in all cases
it requires a fair amount of extra code
it may vary considerably from one plot to the next
A much simpler approach is to annotate the last point of each plot. The point can also be circled, for emphasis. This can be accomplished with one extra line:
import matplotlib.pyplot as plt
for i, (x, y) in enumerate(samples):
plt.plot(x, y)
plt.text(x[-1], y[-1], f'sample {i}')
A variant would be to use the method matplotlib.axes.Axes.annotate.
Nice question, a while ago I've experimented a bit with this, but haven't used it a lot because it's still not bulletproof. I divided the plot area into a 32x32 grid and calculated a 'potential field' for the best position of a label for each line according the following rules:
white space is a good place for a label
Label should be near corresponding line
Label should be away from the other lines
The code was something like this:
import matplotlib.pyplot as plt
import numpy as np
from scipy import ndimage
def my_legend(axis = None):
if axis == None:
axis = plt.gca()
N = 32
Nlines = len(axis.lines)
print Nlines
xmin, xmax = axis.get_xlim()
ymin, ymax = axis.get_ylim()
# the 'point of presence' matrix
pop = np.zeros((Nlines, N, N), dtype=np.float)
for l in range(Nlines):
# get xy data and scale it to the NxN squares
xy = axis.lines[l].get_xydata()
xy = (xy - [xmin,ymin]) / ([xmax-xmin, ymax-ymin]) * N
xy = xy.astype(np.int32)
# mask stuff outside plot
mask = (xy[:,0] >= 0) & (xy[:,0] < N) & (xy[:,1] >= 0) & (xy[:,1] < N)
xy = xy[mask]
# add to pop
for p in xy:
pop[l][tuple(p)] = 1.0
# find whitespace, nice place for labels
ws = 1.0 - (np.sum(pop, axis=0) > 0) * 1.0
# don't use the borders
ws[:,0] = 0
ws[:,N-1] = 0
ws[0,:] = 0
ws[N-1,:] = 0
# blur the pop's
for l in range(Nlines):
pop[l] = ndimage.gaussian_filter(pop[l], sigma=N/5)
for l in range(Nlines):
# positive weights for current line, negative weight for others....
w = -0.3 * np.ones(Nlines, dtype=np.float)
w[l] = 0.5
# calculate a field
p = ws + np.sum(w[:, np.newaxis, np.newaxis] * pop, axis=0)
plt.figure()
plt.imshow(p, interpolation='nearest')
plt.title(axis.lines[l].get_label())
pos = np.argmax(p) # note, argmax flattens the array first
best_x, best_y = (pos / N, pos % N)
x = xmin + (xmax-xmin) * best_x / N
y = ymin + (ymax-ymin) * best_y / N
axis.text(x, y, axis.lines[l].get_label(),
horizontalalignment='center',
verticalalignment='center')
plt.close('all')
x = np.linspace(0, 1, 101)
y1 = np.sin(x * np.pi / 2)
y2 = np.cos(x * np.pi / 2)
y3 = x * x
plt.plot(x, y1, 'b', label='blue')
plt.plot(x, y2, 'r', label='red')
plt.plot(x, y3, 'g', label='green')
my_legend()
plt.show()
And the resulting plot:
matplotx (which I wrote) has line_labels() which plots the labels to the right of the lines. It's also smart enough to avoid overlaps when too many lines are concentrated in one spot. (See stargraph for examples.) It does that by solving a particular non-negative-least-squares problem on the target positions of the labels. Anyway, in many cases where there's no overlap to begin with, such as the example below, that's not even necessary.
import matplotlib.pyplot as plt
import matplotx
import numpy as np
# create data
rng = np.random.default_rng(0)
offsets = [1.0, 1.50, 1.60]
labels = ["no balancing", "CRV-27", "CRV-27*"]
x0 = np.linspace(0.0, 3.0, 100)
y = [offset * x0 / (x0 + 1) + 0.1 * rng.random(len(x0)) for offset in offsets]
# plot
with plt.style.context(matplotx.styles.dufte):
for yy, label in zip(y, labels):
plt.plot(x0, yy, label=label)
plt.xlabel("distance [m]")
matplotx.ylabel_top("voltage [V]") # move ylabel to the top, rotate
matplotx.line_labels() # line labels to the right
plt.show()
# plt.savefig("out.png", bbox_inches="tight")
A simpler approach like the one Ioannis Filippidis do :
import matplotlib.pyplot as plt
import numpy as np
# evenly sampled time at 200ms intervals
tMin=-1 ;tMax=10
t = np.arange(tMin, tMax, 0.1)
# red dashes, blue points default
plt.plot(t, 22*t, 'r--', t, t**2, 'b')
factor=3/4 ;offset=20 # text position in view
textPosition=[(tMax+tMin)*factor,22*(tMax+tMin)*factor]
plt.text(textPosition[0],textPosition[1]+offset,'22 t',color='red',fontsize=20)
textPosition=[(tMax+tMin)*factor,((tMax+tMin)*factor)**2+20]
plt.text(textPosition[0],textPosition[1]+offset, 't^2', bbox=dict(facecolor='blue', alpha=0.5),fontsize=20)
plt.show()
code python 3 on sageCell
I'd like to plot implicit equation F(x,y,z) = 0 in 3D. Is it possible in Matplotlib?
You can trick matplotlib into plotting implicit equations in 3D. Just make a one-level contour plot of the equation for each z value within the desired limits. You can repeat the process along the y and z axes as well for a more solid-looking shape.
from mpl_toolkits.mplot3d import axes3d
import matplotlib.pyplot as plt
import numpy as np
def plot_implicit(fn, bbox=(-2.5,2.5)):
''' create a plot of an implicit function
fn ...implicit function (plot where fn==0)
bbox ..the x,y,and z limits of plotted interval'''
xmin, xmax, ymin, ymax, zmin, zmax = bbox*3
fig = plt.figure()
ax = fig.add_subplot(111, projection='3d')
A = np.linspace(xmin, xmax, 100) # resolution of the contour
B = np.linspace(xmin, xmax, 15) # number of slices
A1,A2 = np.meshgrid(A,A) # grid on which the contour is plotted
for z in B: # plot contours in the XY plane
X,Y = A1,A2
Z = fn(X,Y,z)
cset = ax.contour(X, Y, Z+z, [z], zdir='z')
# [z] defines the only level to plot for this contour for this value of z
for y in B: # plot contours in the XZ plane
X,Z = A1,A2
Y = fn(X,y,Z)
cset = ax.contour(X, Y+y, Z, [y], zdir='y')
for x in B: # plot contours in the YZ plane
Y,Z = A1,A2
X = fn(x,Y,Z)
cset = ax.contour(X+x, Y, Z, [x], zdir='x')
# must set plot limits because the contour will likely extend
# way beyond the displayed level. Otherwise matplotlib extends the plot limits
# to encompass all values in the contour.
ax.set_zlim3d(zmin,zmax)
ax.set_xlim3d(xmin,xmax)
ax.set_ylim3d(ymin,ymax)
plt.show()
Here's the plot of the Goursat Tangle:
def goursat_tangle(x,y,z):
a,b,c = 0.0,-5.0,11.8
return x**4+y**4+z**4+a*(x**2+y**2+z**2)**2+b*(x**2+y**2+z**2)+c
plot_implicit(goursat_tangle)
You can make it easier to visualize by adding depth cues with creative colormapping:
Here's how the OP's plot looks:
def hyp_part1(x,y,z):
return -(x**2) - (y**2) + (z**2) - 1
plot_implicit(hyp_part1, bbox=(-100.,100.))
Bonus: You can use python to functionally combine these implicit functions:
def sphere(x,y,z):
return x**2 + y**2 + z**2 - 2.0**2
def translate(fn,x,y,z):
return lambda a,b,c: fn(x-a,y-b,z-c)
def union(*fns):
return lambda x,y,z: np.min(
[fn(x,y,z) for fn in fns], 0)
def intersect(*fns):
return lambda x,y,z: np.max(
[fn(x,y,z) for fn in fns], 0)
def subtract(fn1, fn2):
return intersect(fn1, lambda *args:-fn2(*args))
plot_implicit(union(sphere,translate(sphere, 1.,1.,1.)), (-2.,3.))
Update: I finally have found an easy way to render 3D implicit surface with matplotlib and scikit-image, see my other answer. I left this one for whom is interested in plotting parametric 3D surfaces.
Motivation
Late answer, I just needed to do the same and I found another way to do it at some extent. So I am sharing this another perspective.
This post does not answer: (1) How to plot any implicit function F(x,y,z)=0? But does answer: (2) How to plot parametric surfaces (not all implicit functions, but some of them) using mesh with matplotlib?
#Paul's method has the advantage to be non parametric, therefore we can plot almost anything we want using contour method on each axe, it fully addresses (1). But matplotlib cannot easily build a mesh from this method, so we cannot directly get a surface from it, instead we get plane curves in all directions. This is what motivated my answer, I wanted to address (2).
Rendering mesh
If we are able to parametrize (this may be hard or impossible), with at most 2 parameters, the surface we want to plot then we can plot it with matplotlib.plot_trisurf method.
That is, from an implicit equation F(x,y,z)=0, if we are able to get a parametric system S={x=f(u,v), y=g(u,v), z=h(u,v)} then we can plot it easily with matplotlib without having to resort to contour.
Then, rendering such a 3D surface boils down to:
# Render:
ax = plt.axes(projection='3d')
ax.plot_trisurf(x, y, z, triangles=tri.triangles, cmap='jet', antialiased=True)
Where (x, y, z) are vectors (not meshgrid, see ravel) functionally computed from parameters (u, v) and triangles parameter is a Triangulation derived from (u,v) parameters to shoulder the mesh construction.
Imports
Required imports are:
import numpy as np
import matplotlib.pyplot as plt
from mpl_toolkits import mplot3d
from matplotlib.tri import Triangulation
Some surfaces
Lets parametrize some surfaces...
Sphere
# Parameters:
theta = np.linspace(0, 2*np.pi, 20)
phi = np.linspace(0, np.pi, 20)
theta, phi = np.meshgrid(theta, phi)
rho = 1
# Parametrization:
x = np.ravel(rho*np.cos(theta)*np.sin(phi))
y = np.ravel(rho*np.sin(theta)*np.sin(phi))
z = np.ravel(rho*np.cos(phi))
# Triangulation:
tri = Triangulation(np.ravel(theta), np.ravel(phi))
Cone
theta = np.linspace(0, 2*np.pi, 20)
rho = np.linspace(-2, 2, 20)
theta, rho = np.meshgrid(theta, rho)
x = np.ravel(rho*np.cos(theta))
y = np.ravel(rho*np.sin(theta))
z = np.ravel(rho)
tri = Triangulation(np.ravel(theta), np.ravel(rho))
Torus
a, c = 1, 4
u = np.linspace(0, 2*np.pi, 20)
v = u.copy()
u, v = np.meshgrid(u, v)
x = np.ravel((c + a*np.cos(v))*np.cos(u))
y = np.ravel((c + a*np.cos(v))*np.sin(u))
z = np.ravel(a*np.sin(v))
tri = Triangulation(np.ravel(u), np.ravel(v))
Möbius Strip
u = np.linspace(0, 2*np.pi, 20)
v = np.linspace(-1, 1, 20)
u, v = np.meshgrid(u, v)
x = np.ravel((2 + (v/2)*np.cos(u/2))*np.cos(u))
y = np.ravel((2 + (v/2)*np.cos(u/2))*np.sin(u))
z = np.ravel(v/2*np.sin(u/2))
tri = Triangulation(np.ravel(u), np.ravel(v))
Limitation
Most of the time, Triangulation is required in order to coordinate mesh construction of plot_trisurf method, and this object only accepts two parameters, so we are limited to 2D parametric surfaces. It is unlikely we could represent the Goursat Tangle with this method.
Matplotlib expects a series of points; it will do the plotting if you can figure out how to render your equation.
Referring to Is it possible to plot implicit equations using Matplotlib? Mike Graham's answer suggests using scipy.optimize to numerically explore the implicit function.
There is an interesting gallery at http://xrt.wikidot.com/gallery:implicit showing a variety of raytraced implicit functions - if your equation matches one of these, it might give you a better idea what you are looking at.
Failing that, if you care to share the actual equation, maybe someone can suggest an easier approach.
As far as I know, it is not possible. You have to solve this equation numerically by yourself. Using scipy.optimize is a good idea. The simplest case is that you know the range of the surface that you want to plot, and just make a regular grid in x and y, and try to solve equation F(xi,yi,z)=0 for z, giving a starting point of z. Following is a very dirty code that might help you
from scipy import *
from scipy import optimize
xrange = (0,1)
yrange = (0,1)
density = 100
startz = 1
def F(x,y,z):
return x**2+y**2+z**2-10
x = linspace(xrange[0],xrange[1],density)
y = linspace(yrange[0],yrange[1],density)
points = []
for xi in x:
for yi in y:
g = lambda z:F(xi,yi,z)
res = optimize.fsolve(g, startz, full_output=1)
if res[2] == 1:
zi = res[0]
points.append([xi,yi,zi])
points = array(points)
Actually there is an easy way to plot implicit 3D surface with the scikit-image package. The key is the marching_cubes method.
import numpy as np
from skimage import measure
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import axes3d
Then we compute the function over a 3D meshgrid, in this example we use the goursat_tangle method #Paul defined in its answer:
xl = np.linspace(-3, 3, 50)
X, Y, Z = np.meshgrid(xl, xl, xl)
F = goursat_tangle(X, Y, Z)
The magic is happening here with marching_cubes:
verts, faces, normals, values = measure.marching_cubes(F, 0, spacing=[np.diff(xl)[0]]*3)
verts -= 3
We just need to correct vertices coordinates as they are expressed in Voxel coordinates (hence scaling using spacing switch and the subsequent origin shift).
Finally it is just about rendering the iso-surface using tri_surface:
fig = plt.figure()
ax = fig.add_subplot(111, projection='3d')
ax.plot_trisurf(verts[:, 0], verts[:, 1], faces, verts[:, 2], cmap='jet', lw=0)
Which returns:
Have you looked at mplot3d on matplotlib?
Finally, I did it (I updated my matplotlib to 1.0.1).
Here is code:
import matplotlib.pyplot as plt
import numpy as np
from mpl_toolkits.mplot3d import Axes3D
def hyp_part1(x,y,z):
return -(x**2) - (y**2) + (z**2) - 1
fig = plt.figure()
ax = fig.add_subplot(111, projection='3d')
x_range = np.arange(-100,100,10)
y_range = np.arange(-100,100,10)
X,Y = np.meshgrid(x_range,y_range)
A = np.linspace(-100, 100, 15)
A1,A2 = np.meshgrid(A,A)
for z in A:
X,Y = A1, A2
Z = hyp_part1(X,Y,z)
ax.contour(X, Y, Z+z, [z], zdir='z')
for y in A:
X,Z= A1, A2
Y = hyp_part1(X,y,Z)
ax.contour(X, Y+y, Z, [y], zdir='y')
for x in A:
Y,Z = A1, A2
X = hyp_part1(x,Y,Z)
ax.contour(X+x, Y, Z, [x], zdir='x')
ax.set_zlim3d(-100,100)
ax.set_xlim3d(-100,100)
ax.set_ylim3d(-100,100)
Here is result:
Thank You, Paul!
MathGL (GPL plotting library) can plot it easily. Just create a data mesh with function values f[i,j,k] and use Surf3() function to make isosurface at value f[i,j,k]=0. See this sample.
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: