Develop Reference

How to create a plot with a repeating color pattern?

For my report, I'm creating a special color plot in jupyter notebook. There are two parameters, x and y.
import numpy as np
x = np.arange(-1,1,0.1)
y = np.arange(1,11,1)
with which I compute a third quantity. Here is an example to demonstrate the concept:
values = []
for i in range(len(y)) :
z = y[i] * x**3
# in my case the value z represents phases of oscillators
# so I will transform the computed values to the intervall [0,2pi)
values.append(z)
values = np.array(values) % 2*np.pi
I'm plotting y vs x. For each y = 1,2,3,4... there will be a horizontal line with total length two. For example: The coordinate (0.5,8) stands for a single point on line 8 at position x = 0.5 and z(0.5,8) is its associated value.
Now I want to represent each point on all ten lines with a unique color that is determined by z(x,y). Since z(x,y) takes only values in [0,2pi) I need a color scheme that starts at zero (for example z=0 corresponds to blue). For increasing z the color continuously changes and in the end at 2pi it takes the same color again (so at z ~ 2pi it becomes blue again).
Does someone know how this can be done in python?

The kind of structure for x, y and z you need, is easier using a meshgrid. Also, to have a lot of x-values between -1 and 1, np.linspace(-1,1,N) divides the range in N even intervals.
Using meshgrid, z can be calculated in one line using numpy's vectorization. This runs much faster.
To set a repeating color, a cyclic colormap such as hsv can be used. There the last color is the same as the starting color.
import numpy as np
from matplotlib import pyplot as plt
x, y = np.meshgrid(np.linspace(-1,1,100), np.arange(1,11,1))
z = (y * x**3) % 2*np.pi
plt.scatter(x, y, c=z, s=6, cmap='hsv')
plt.yticks(range(1,11))
plt.show()
Alternatively, a symmetric colormap could be built taken the colors from and existing map and combining them with the same colors in reverse order.
import numpy as np
from matplotlib import pyplot as plt
import matplotlib.colors as mcolors
colors_orig = plt.cm.viridis_r(np.linspace(0, 1, 128))
# combine the colors with the reversed array and build a new colormap
colors = np.vstack((colors_orig, colors_orig[::-1]))
symcmap = mcolors.LinearSegmentedColormap.from_list('symcmap', colors)
x, y = np.meshgrid(np.linspace(-1,1,100), np.arange(1,11,1))
z = (y * x**3) % 2*np.pi
plt.scatter(x, y, c=z, s=6, cmap=symcmap)
plt.yticks(range(1,11))
plt.show()

Multicolored lines are somewhat more complicated than just scatter plots. The docs have an example using LineCollections. Here is the adapted code. Note that the line segments are colored using their start point, so make sure there are enough x values. Also, the x and y limits aren't set automatically any more.
The code also adds a colorbar to illustrate how the colors map to the z values. Some interesting code from Jake VanderPlas shows how to create ticks for multiples of π.
import numpy as np
from matplotlib import pyplot as plt
from matplotlib.collections import LineCollection
# code from Jake VanderPlas
def format_func(value, tick_number):
# find number of multiples of pi/2
N = int(np.round(2 * value / np.pi))
if N == 0:
return "0"
elif N == 1:
return r"$\pi/2$"
elif N == 2:
return r"$\pi$"
elif N % 2 > 0:
return r"${0}\pi/2$".format(N)
else:
return r"${0}\pi$".format(N // 2)
x = np.linspace(-1, 1, 500)
y_max = 10
# Create a continuous norm to map from data points to colors
norm = plt.Normalize(0, 2 * np.pi)
for y in range(1, y_max + 1):
z = (y * x ** 3) % 2 * np.pi
y_array = y * np.ones_like(x)
points = np.array([x, y_array]).T.reshape(-1, 1, 2)
segments = np.concatenate([points[:-1], points[1:]], axis=1)
lc = LineCollection(segments, cmap='hsv', norm=norm)
lc.set_array(z) # Set the values used for colormapping
lc.set_linewidth(2)
line = plt.gca().add_collection(lc)
# plt.scatter(x, y_array, c=z, s=10, norm=norm, cmap='hsv')
cbar = plt.colorbar(line) # , ticks=[k*np.pi for k in np.arange(0, 2.001, 0.25)])
cbar.locator = plt.MultipleLocator(np.pi / 2)
cbar.minor_locator = plt.MultipleLocator(np.pi / 4)
cbar.formatter = plt.FuncFormatter(format_func)
cbar.ax.minorticks_on()
cbar.update_ticks()
plt.yticks(range(1, y_max + 1)) # one tick for every y
plt.xlim(x.min(), x.max()) # the LineCollection doesn't force the limits
plt.ylim(0.5, y_max + 0.5)
plt.show()

python add values to Line3DCollection

I want to plot multiple lines in a 3d axis plot.
I'm plotting the trajectory of a light ray, each line should be colored depending on the time of propagation for each path.
I want to plot them independently, since I saved them in a binary three structure in which any ray may follow two different trajectories.
I used Line3DCollection, but it doesn't seem to be the right way.
In few words,
import numpy as np
x = np.linspace(0,1,100)
y = x
z = x
t = np.linspace(0,1,100)
#here I need to plot these points coloring them in function of t
x1 = np.linspace(1,2,100)
y1 = x
z1 = x
t1 = np.linspace(1,2,100)
#I need to plot also this used the same colorbar used for former values
x2 = -np.linspace(1,2,100)
y2 = x
z2 = x
t2 = np.linspace(1,2,100)
#idem
having all the lines colored with the same colorbar scale, like this
plot.
I tried with the following but the output is not like I expected
import numpy as np
from matplotlib import pyplot as plt
from mpl_toolkits.mplot3d.art3d import Line3DCollection
x = np.linspace(0,1,100)
y = x
z = x
t = np.linspace(0,1,100)
points = np.array([x,y,z]).transpose().reshape(-1,1,3)
segs = np.concatenate([points[:-1],points[1:]],axis=1)
lc = Line3DCollection(segs, cmap=plt.get_cmap('jet'))
lc.set_array(t)
fig = plt.figure()
ax = fig.add_subplot(111, projection='3d')
ax.add_collection3d(lc)
x1 = np.linspace(1,2,100)
y1 = x1
z1 = x1
t1 = np.linspace(1,2,100)
points1 = np.array([x1,y1,z1]).transpose().reshape(-1,1,3)
segs1 = np.concatenate([points1[:-1],points1[1:]],axis=1)
lc = Line3DCollection(segs1, cmap=plt.get_cmap('jet'))
lc.set_array(t1)
lc.update_scalarmappable()
ax.add_collection3d(lc)
x2 = np.linspace(1,2,100)
y2 = -x2+2
z2 = -x2+2
t2 = np.linspace(1,2,100)
points2 = np.array([x2,y2,z2]).transpose().reshape(-1,1,3)
segs2 = np.concatenate([points2[:-1],points2[1:]],axis=1)
lc = Line3DCollection(segs2, cmap=plt.get_cmap('jet'))
lc.set_array(t1)
lc.update_scalarmappable()
ax.add_collection3d(lc)
ax.set_xlim(0, 2)
ax.set_ylim(0, 2)
ax.set_zlim(0, 2)
fig.colorbar(lc)
plt.show()
plotting this plot
Thanks in advance

scipy: interpolation, cubic & linear

I'm trying to interpolate my set of data (first columnt is the time, third columnt is the actual data):
import numpy as np
import matplotlib.pyplot as plt
from scipy.interpolate import interp1d
data = np.genfromtxt("data.csv", delimiter=" ")
x = data[:, 0]
y = data[:, 2]
xx = np.linspace(x.min(), x.max(), 1000)
y_smooth = interp1d(x, y)(xx)
#y_smooth = interp1d(x, y, kind="cubic")(xx)
fig = plt.figure()
ax = fig.add_subplot(111)
ax.plot(xx, y_smooth, "r-")
plt.show()
but I see some strange difference between linear and cubic interpolation.
Here is the result for linear:
Here is the same for cubic:
I'm not sure, why is graph jumping all the time and y_smooth contains incorrect values?
ipdb> y_smooth_linear.max()
141.5481144
ipdb> y_smooth_cubic.max()
1.2663431888584225e+18
Can anybody explain to me, how can I change my code to achieve correct interpolation?
UPD: here is data.cvs file

Your data contains several y values for the same x value. This violates the assumptions of most interpolation algorithms.
Either discard the rows with duplicate x values, average the y values for each individual x, or obtain a better resolution for the x values such that they aren't the same anymore.

Given cfh's observation that x has duplicate values, you could use np.unique
to select a unique value of y for each x:
x2, idx = np.unique(x, return_index=True)
y2 = y[idx]
return_index=True causes np.unique to return not only the unique values, x2, but also the locations, idx, of the unique xs in the original x array. Note that this selects the first value of y for each unique x.
If you'd like to average all the y values for each unique x, you could use
stats.binned_statistic:
import scipy.stats as stats
x2, inv = np.unique(x, return_inverse=True)
y2, bin_edges, binnumber = stats.binned_statistic(
x=inv, values=y, statistic='mean', bins=inv.max()+1)
return_inverse=True tells np.unique to return indices from which the
original array can be reconstructed. Those indices can also serve as categorical
labels or "factors", which is how they are being used in the call to
binned_statistic above.
import numpy as np
import matplotlib.pyplot as plt
from scipy.interpolate import interp1d
import scipy.stats as stats
data = np.genfromtxt("data.csv", delimiter=" ")
x = data[:, 0]
y = data[:, 1]
x2, idx, inv = np.unique(x, return_index=True, return_inverse=True)
y_uniq = y[idx]
y_ave, bin_edges, binnumber = stats.binned_statistic(
x=inv, values=y, statistic='mean', bins=inv.max()+1)
xx = np.linspace(x.min(), x.max(), 1000)
y_smooth = interp1d(x, y)(xx)
y_smooth2 = interp1d(x2, y_uniq, kind="cubic")(xx)
y_smooth3 = interp1d(x2, y_ave, kind="cubic")(xx)
fig, ax = plt.subplots(nrows=3, sharex=True)
ax[0].plot(xx, y_smooth, "r-", label='linear')
ax[1].plot(xx, y_smooth2, "b-", label='cubic (first y)')
ax[2].plot(xx, y_smooth3, "b-", label='cubic (ave y)')
ax[0].legend(loc='best')
ax[1].legend(loc='best')
ax[2].legend(loc='best')
plt.show()

How do you create a 3D surface plot with missing values matplotlib?

I am trying to create a 3D surface energy diagram where an x,y position on a grid contains an associated z level. The issue is that the grid is not uniform (ie, there is not a z component for every x,y position). Is there a way to refrain from plotting those values by calling them NaN in the corresponding position in the array?
Here is what I have tried so far:
import numpy as np
from matplotlib import pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
import pylab
from matplotlib import cm
#Z levels
energ = np.array([0,3.5,1,-0.3,-1.5,-2,-3.4,-4.8])
#function for getting x,y associated z values?
def fun(x,y,array):
return array[x]
#arrays for grid
x = np.arange(0,7,0.5)
y = np.arange(0,7,0.5)
#create grid
X, Y = np.meshgrid(x,y)
zs = np.array([fun(x,y,energ) for x in zip(np.ravel(X))])
Z = zs.reshape(X.shape)
plt3d = plt.figure().gca(projection='3d')
#gradients now with respect to x and y, but ideally with respect to z only
Gx, Gz = np.gradient(X * Y)
G = (Gx ** 2 + Gz ** 2) ** .5 # gradient magnitude
N = G / G.max() # normalize 0..1
plt3d.plot_surface(X, Y, Z, rstride=1, cstride=1,
facecolors=cm.jet(N), edgecolor='k', linewidth=0, antialiased=False, shade=False)
plt.show()
I cannot post image here of this plot but if you run the code you will see it
But I would like to not plot certain x,y pairs, so the figure should triangle downward to the minimum. Can this be accomplished by using nan values? Also would like spacing between each level, to be connected by lines.
n = np.NAN
#energ represents the z levels, so the overall figure should look like a triangle.
energ = np.array([[0,0,0,0,0,0,0,0,0,0,0,0,0],[n,n,n,n,n,n,n,n,n,n,n,n,n],[n,2.6,n,2.97,n,2.6,n,2.97,n,2.6,n,3.58,n],[n,n,n,n,n,n,n,n,n,n,n,n,n],[n,n,1.09,n,1.23,n,1.09,n,1.23,n,1.7,n,n],[n,n,n,n,n,n,n,n,n,n,n,n,n],[n,n,n,-0.65,n,-0.28,n,-0.65,n,0.33,n,n,n],[n,n,n,n,n,n,n,n,n,n,n,n,n],[n,n,n,n,-2.16,n,-2.02,n,-1.55,n,n,n,n],[n,n,n,n,n,n,n,n,n,n,n,n,n],[n,n,n,n,n,-3.9,n,-2.92,n,n,n,n,n,],[n,n,n,n,n,n,n,n,n,n,n,n,n],[n,n,n,n,n,n,-4.8,n,n,n,n,n,n,]])
plt3d = plt.figure().gca(projection='3d')
Gx, Gz = np.gradient(X * energ) # gradients with respect to x and z
G = (Gx ** 2 + Gz ** 2) ** .5 # gradient magnitude
N = G / G.max() # normalize 0..1
x = np.arange(0,13,1)
y = np.arange(0,13,1)
X, Y = np.meshgrid(x,y)
#but the shapes don't seem to match up
plt3d.plot_surface(X, Y, energ, rstride=1, cstride=1,
facecolors=cm.jet(N), edgecolor='k',
linewidth=0, antialiased=False, shade=False
)
Using masked arrays generates the following error: local Python[7155] : void CGPathCloseSubpath(CGMutablePathRef): no current point.
n = np.NAN
energ = np.array([[0,0,0,0,0,0,0,0,0,0,0,0,0],[n,n,n,n,n,n,n,n,n,n,n,n,n],[n,2.6,n,2.97,n,2.6,n,2.97,n,2.6,n,3.58,n],[n,n,n,n,n,n,n,n,n,n,n,n,n],[n,n,1.09,n,1.23,n,1.09,n,1.23,n,1.7,n,n],[n,n,n,n,n,n,n,n,n,n,n,n,n],[n,n,n,-0.65,n,-0.28,n,-0.65,n,0.33,n,n,n],[n,n,n,n,n,n,n,n,n,n,n,n,n],[n,n,n,n,-2.16,n,-2.02,n,-1.55,n,n,n,n],[n,n,n,n,n,n,n,n,n,n,n,n,n],[n,n,n,n,n,-3.9,n,-2.92,n,n,n,n,n,],[n,n,n,n,n,n,n,n,n,n,n,n,n],[n,n,n,n,n,n,-4.8,n,n,n,n,n,n,]])
x = np.arange(0,13,1)
y = np.arange(0,13,1)
X, Y = np.meshgrid(x,y)
#create masked arrays
mX = ma.masked_array(X, mask=[[0,0,0,0,0,0,0,0,0,0,0,0,0],[1,1,1,1,1,1,1,1,1,1,1,1,1],[1,0,1,0,1,0,1,0,1,0,1,0,1],[1,1,1,1,1,1,1,1,1,1,1,1,1],[1,1,0,1,0,1,0,1,0,1,0,1,1],[1,1,1,1,1,1,1,1,1,1,1,1,1],[1,1,1,0,1,0,1,0,1,0,1,1,1],[1,1,1,1,1,1,1,1,1,1,1,1,1],[1,1,1,1,0,1,0,1,0,1,1,1,1],[1,1,1,1,1,1,1,1,1,1,1,1,1],[1,1,1,1,1,0,1,0,1,1,1,1,1],[1,1,1,1,1,1,1,1,1,1,1,1,1],[1,1,1,1,1,1,0,1,1,1,1,1,1]])
mY = ma.masked_array(Y, mask=[[0,0,0,0,0,0,0,0,0,0,0,0,0],[1,1,1,1,1,1,1,1,1,1,1,1,1],[1,0,1,0,1,0,1,0,1,0,1,0,1],[1,1,1,1,1,1,1,1,1,1,1,1,1],[1,1,0,1,0,1,0,1,0,1,0,1,1],[1,1,1,1,1,1,1,1,1,1,1,1,1],[1,1,1,0,1,0,1,0,1,0,1,1,1],[1,1,1,1,1,1,1,1,1,1,1,1,1],[1,1,1,1,0,1,0,1,0,1,1,1,1],[1,1,1,1,1,1,1,1,1,1,1,1,1],[1,1,1,1,1,0,1,0,1,1,1,1,1],[1,1,1,1,1,1,1,1,1,1,1,1,1],[1,1,1,1,1,1,0,1,1,1,1,1,1]])
m_energ = ma.masked_array(energ, mask=[[0,0,0,0,0,0,0,0,0,0,0,0,0],[1,1,1,1,1,1,1,1,1,1,1,1,1],[1,0,1,0,1,0,1,0,1,0,1,0,1],[1,1,1,1,1,1,1,1,1,1,1,1,1],[1,1,0,1,0,1,0,1,0,1,0,1,1],[1,1,1,1,1,1,1,1,1,1,1,1,1],[1,1,1,0,1,0,1,0,1,0,1,1,1],[1,1,1,1,1,1,1,1,1,1,1,1,1],[1,1,1,1,0,1,0,1,0,1,1,1,1],[1,1,1,1,1,1,1,1,1,1,1,1,1],[1,1,1,1,1,0,1,0,1,1,1,1,1],[1,1,1,1,1,1,1,1,1,1,1,1,1],[1,1,1,1,1,1,0,1,1,1,1,1,1]])
plt3d = plt.figure().gca(projection='3d')
plt3d.plot_surface(mX, mY, m_energ, rstride=1, cstride=1, edgecolor='k', linewidth=0, antialiased=False, shade=False)
plt.show()

I was playing around with the code from this forum post, and I was able to make the graph have missing values. You can try the code yourself! I got it to work using float("nan") for the missing values.
import plotly.graph_objects as go
import numpy as np
x = np.arange(0.1,1.1,0.1)
y = np.linspace(-np.pi,np.pi,10)
#print(x)
#print(y)
X,Y = np.meshgrid(x,y)
#print(X)
#print(Y)
result = []
for i,j in zip(X,Y):
result.append(np.log(i)+np.sin(j))
result[0][0] = float("nan")
upper_bound = np.array(result)+1
lower_bound = np.array(result)-1
fig = go.Figure(data=[
go.Surface(z=result),
go.Surface(z=upper_bound, showscale=False, opacity=0.3,colorscale='purp'),
go.Surface(z=lower_bound, showscale=False, opacity=0.3,colorscale='purp')])
fig.show()

Matplotlib curve with arrow ticks

I was wondering if it is possible to plot a curve in matplotlib with arrow ticks.
Something like:
from pylab import *
y = linspace(0,10,0.01)
x = cos(y)
plot(x, y, '->')
which should come out with a curve made like this --->---->----> when x increases and like this ---<----<----< whenit decreases (and for y as well, of course).
EDIT:
Furthermore, the arrows should be inclined in the curve's direction (for example, 45 degrees for the y=x function)

It is possible to use the same strategy as in matplotlib streamplot function. Based on the example already given by hitzg:
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.lines as mlines
import matplotlib.patches as mpatches
def add_arrow_to_line2D(
axes, line, arrow_locs=[0.2, 0.4, 0.6, 0.8],
arrowstyle='-|>', arrowsize=1, transform=None):
"""
Add arrows to a matplotlib.lines.Line2D at selected locations.
Parameters:
-----------
axes:
line: Line2D object as returned by plot command
arrow_locs: list of locations where to insert arrows, % of total length
arrowstyle: style of the arrow
arrowsize: size of the arrow
transform: a matplotlib transform instance, default to data coordinates
Returns:
--------
arrows: list of arrows
"""
if not isinstance(line, mlines.Line2D):
raise ValueError("expected a matplotlib.lines.Line2D object")
x, y = line.get_xdata(), line.get_ydata()
arrow_kw = {
"arrowstyle": arrowstyle,
"mutation_scale": 10 * arrowsize,
}
color = line.get_color()
use_multicolor_lines = isinstance(color, np.ndarray)
if use_multicolor_lines:
raise NotImplementedError("multicolor lines not supported")
else:
arrow_kw['color'] = color
linewidth = line.get_linewidth()
if isinstance(linewidth, np.ndarray):
raise NotImplementedError("multiwidth lines not supported")
else:
arrow_kw['linewidth'] = linewidth
if transform is None:
transform = axes.transData
arrows = []
for loc in arrow_locs:
s = np.cumsum(np.sqrt(np.diff(x) ** 2 + np.diff(y) ** 2))
n = np.searchsorted(s, s[-1] * loc)
arrow_tail = (x[n], y[n])
arrow_head = (np.mean(x[n:n + 2]), np.mean(y[n:n + 2]))
p = mpatches.FancyArrowPatch(
arrow_tail, arrow_head, transform=transform,
**arrow_kw)
axes.add_patch(p)
arrows.append(p)
return arrows
y = np.linspace(0, 100, 200)
x = np.cos(y/5.)
fig, ax = plt.subplots(1, 1)
# print the line and the markers in seperate steps
line, = ax.plot(x, y, 'k-')
add_arrow_to_line2D(ax, line, arrow_locs=np.linspace(0., 1., 200),
arrowstyle='->')
plt.show()
Also refer to this answer.

Try this:
import numpy as np
import matplotlib.pyplot as plt
y = np.linspace(0,100,100)
x = np.cos(y/5.)
# use masked arrays
x1 = np.ma.masked_array(x[:-1], np.diff(x)>=0)
x2 = np.ma.masked_array(x[:-1], np.diff(x)<=0)
# print the line and the markers in seperate steps
plt.plot(x, y, 'k-')
plt.plot(x1, y[:-1], 'k<')
plt.plot(x2, y[:-1], 'k>')
plt.show()