I am using mplot3d from the mpl_toolkits library. When displaying the 3D surface on the figure I'm realized the axis were not positioned as I wished they would.
Let me show, I have added to the following screenshot the position of each axis:
Is there a way to change the position of the axes in order to get this result:
Here's the working code:
import matplotlib.pyplot as plt
import numpy as np
from mpl_toolkits.mplot3d import Axes3D
ax = Axes3D(plt.figure())
def f(x,y) :
return -x**2 - y**2
X = np.arange(-1, 1, 0.02)
Y = np.arange(-1, 1, 0.02)
X, Y = np.meshgrid(X, Y)
Z = f(X, Y)
ax.plot_surface(X, Y, Z, alpha=0.5)
# Hide axes ticks
ax.set_xticks([-1,1])
ax.set_yticks([-1,1])
ax.set_zticks([-2,0])
ax.set_yticklabels([-1,1],rotation=-15, va='center', ha='right')
plt.show()
I have tried using xaxis.set_ticks_position('left') statement, but it doesn't work.
No documented methods, but with some hacking ideas from https://stackoverflow.com/a/15048653/1149007 you can.
import matplotlib.pyplot as plt
import numpy as np
from mpl_toolkits.mplot3d import Axes3D
fig = plt.figure()
ax = ax = fig.add_subplot(111, projection='3d')
ax.view_init(30, 30)
def f(x,y) :
return -x**2 - y**2
X = np.arange(-1, 1, 0.02)
Y = np.arange(-1, 1, 0.02)
X, Y = np.meshgrid(X, Y)
Z = f(X, Y)
ax.plot_surface(X, Y, Z, alpha=0.5)
# Hide axes ticks
ax.set_xticks([-1,1])
ax.set_yticks([-1,1])
ax.set_zticks([-2,0])
ax.xaxis._axinfo['juggled'] = (0,0,0)
ax.yaxis._axinfo['juggled'] = (1,1,1)
ax.zaxis._axinfo['juggled'] = (2,2,2)
plt.show()
I can no idea of the meaning of the third number in triples. If set zeros nothing changes in the figure. So should look in the code for further tuning.
You can also look at related question Changing position of vertical (z) axis of 3D plot (Matplotlib)? with low level hacking of _PLANES property.
Something changed, code blow doesn't work, all axis hide...
ax.xaxis._axinfo['juggled'] = (0,0,0)
ax.yaxis._axinfo['juggled'] = (1,1,1)
ax.zaxis._axinfo['juggled'] = (2,2,2)
I suggest using the plot function to create a graph
Related
I'm trying to graph a 3d mesh surface with matplotlib and constrain the limits of the graph. The X and Y axes are correctly constrained, but there is overflow in the Z-Axis.
What am I missing? Here's my code:
import matplotlib.pyplot as plt
import numpy as np
from mpl_toolkits import mplot3d
from mpl_toolkits.mplot3d import Axes3D
fig = plt.figure(figsize=(10,10))
x = np.linspace(-6,6,100)
y = np.linspace(-6,6,100)
X,Y = np.meshgrid(x,y)
def f(x,y):
return x**2 + 3*y
Z = f(X,Y)
ax = plt.axes(projection = '3d')
ax.plot_surface(X,Y,Z,cmap='viridis')
ax.title.set_text("z=x**2+3y")
ax.set_xlabel('x')
ax.set_ylabel('y')
ax.set_zlabel('z')
ax.set_zlim3d(zmin=-3,zmax=5)
ax.set_xlim3d(xmin=-6,xmax=6)
ax.set_ylim3d(ymin=-6,ymax=6)
plt.show()
The graph:
Edit:
When I add clipping/min/max to the Z values, the graph is a little better, but it sets z values outside the bounds to the bounds themselves. Both of the following suggestions do this. Perhaps it's because I'm on a mac?
z_tmp = np.maximum(np.minimum(5,Z),-3)
z_temp = np.clip(Z, -3, 5, None)
Your data is outside the axis boundaries. Try rotate the view and you will notice.
z = x**2 + 3*y
If you want to only show a defined area of the data you could add a max() min() limitation on the Z data to exclude the data outside your wanted limitations.
Z = f(X,Y)
z_tmp = np.maximum(np.minimum(5,Z),-3)
ax = plt.axes(projection = '3d')
ax.plot_surface(X,Y,z_tmp,cmap='viridis')
I'm not sure the matplotlib behaves as it should in your default case.
I'm trying to create a surface plot using Python Matplotlib. I've read the documentation in an attempt to figure out where my code was wrong or if I've left anything out, but was having trouble.
The code that I've written is
import numpy as np
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
def computeCost(X, y, theta):
m = len(y)
predictions = np.dot(X, theta)
squareErros = (predictions - y) ** 2
J = (1 / (2 * m)) * sum(squareErrors)
return J
data = np.loadtxt("./data1.txt", delimiter=',')
X = data[:, 0].reshape(-1, 1)
y = data[:, 1].reshape(-1, 1)
m = len(y)
X = np.concatenate((np.ones((m, 1)), X), axis=1)
theta0_vals = np.linspace(-10, 10, 100) # size (100,)
theta1_vals = np.linspace(-1, 4, 100) # size (100,)
J_vals = np.zeros((len(theta0_vals), len(theta1_vals)))
for i in range(len(x_values)):
for j in range(len(y_values)):
t = np.array([theta0_vals[i], theta1_vals[j]]).reshape(-1, 1)
J_vals[i][j] = computeCost(X, y, t) # size (100, 100)
fig = plt.figure()
ax = fig.add_subplot(111, projection='3d')
surf = ax.plot_surface(theta0_vals, theta1_vals, J_vals)
plt.show()
When I invoke plt.show() I get no output. The surface plot that I'm expecting to see is similar to this:
Would anybody be kind enough to let me know where my usage of the surface plot library went wrong? Thank you.
EDIT
I've tried to run the demo code provided here and it works fine. Here's the code for that:
from mpl_toolkits.mplot3d import Axes3D
import matplotlib.pyplot as plt
from matplotlib import cm
from matplotlib.ticker import LinearLocator, FormatStrFormatter
import numpy as np
fig = plt.figure()
ax = fig.gca(projection='3d')
# Make data.
X = np.arange(-5, 5, 0.25)
Y = np.arange(-5, 5, 0.25)
X, Y = np.meshgrid(X, Y)
R = np.sqrt(X**2 + Y**2)
Z = np.sin(R)
# Plot the surface.
surf = ax.plot_surface(X, Y, Z, cmap=cm.coolwarm,
linewidth=0, antialiased=False)
# Customize the z axis.
ax.set_zlim(-1.01, 1.01)
ax.zaxis.set_major_locator(LinearLocator(10))
ax.zaxis.set_major_formatter(FormatStrFormatter('%.02f'))
# Add a color bar which maps values to colors.
fig.colorbar(surf, shrink=0.5, aspect=5)
plt.show()
I think I've figured out the issue by changing a couple of the last lines of code from
ax = fig.add_subplot(111, projection='3d')
surf = ax.plot_surface(theta0_vals, theta1_vals, J_vals)
to
ax = plt.axes(projection='3d')
surf = ax.plot_surface(theta0_vals, theta1_vals, J_vals, rstride=1, cstride=1, cmap='viridis', edgecolor='none')
Making this change gives me a surface plot such that:
The link that gave me reference to this was this.
I'd like to make a scatter plot where each point is colored by the spatial density of nearby points.
I've come across a very similar question, which shows an example of this using R:
R Scatter Plot: symbol color represents number of overlapping points
What's the best way to accomplish something similar in python using matplotlib?
In addition to hist2d or hexbin as #askewchan suggested, you can use the same method that the accepted answer in the question you linked to uses.
If you want to do that:
import numpy as np
import matplotlib.pyplot as plt
from scipy.stats import gaussian_kde
# Generate fake data
x = np.random.normal(size=1000)
y = x * 3 + np.random.normal(size=1000)
# Calculate the point density
xy = np.vstack([x,y])
z = gaussian_kde(xy)(xy)
fig, ax = plt.subplots()
ax.scatter(x, y, c=z, s=100)
plt.show()
If you'd like the points to be plotted in order of density so that the densest points are always on top (similar to the linked example), just sort them by the z-values. I'm also going to use a smaller marker size here as it looks a bit better:
import numpy as np
import matplotlib.pyplot as plt
from scipy.stats import gaussian_kde
# Generate fake data
x = np.random.normal(size=1000)
y = x * 3 + np.random.normal(size=1000)
# Calculate the point density
xy = np.vstack([x,y])
z = gaussian_kde(xy)(xy)
# Sort the points by density, so that the densest points are plotted last
idx = z.argsort()
x, y, z = x[idx], y[idx], z[idx]
fig, ax = plt.subplots()
ax.scatter(x, y, c=z, s=50)
plt.show()
Plotting >100k data points?
The accepted answer, using gaussian_kde() will take a lot of time. On my machine, 100k rows took about 11 minutes. Here I will add two alternative methods (mpl-scatter-density and datashader) and compare the given answers with same dataset.
In the following, I used a test data set of 100k rows:
import matplotlib.pyplot as plt
import numpy as np
# Fake data for testing
x = np.random.normal(size=100000)
y = x * 3 + np.random.normal(size=100000)
Output & computation time comparison
Below is a comparison of different methods.
1: mpl-scatter-density
Installation
pip install mpl-scatter-density
Example code
import mpl_scatter_density # adds projection='scatter_density'
from matplotlib.colors import LinearSegmentedColormap
# "Viridis-like" colormap with white background
white_viridis = LinearSegmentedColormap.from_list('white_viridis', [
(0, '#ffffff'),
(1e-20, '#440053'),
(0.2, '#404388'),
(0.4, '#2a788e'),
(0.6, '#21a784'),
(0.8, '#78d151'),
(1, '#fde624'),
], N=256)
def using_mpl_scatter_density(fig, x, y):
ax = fig.add_subplot(1, 1, 1, projection='scatter_density')
density = ax.scatter_density(x, y, cmap=white_viridis)
fig.colorbar(density, label='Number of points per pixel')
fig = plt.figure()
using_mpl_scatter_density(fig, x, y)
plt.show()
Drawing this took 0.05 seconds:
And the zoom-in looks quite nice:
2: datashader
Datashader is an interesting project. It has added support for matplotlib in datashader 0.12.
Installation
pip install datashader
Code (source & parameterer listing for dsshow):
import datashader as ds
from datashader.mpl_ext import dsshow
import pandas as pd
def using_datashader(ax, x, y):
df = pd.DataFrame(dict(x=x, y=y))
dsartist = dsshow(
df,
ds.Point("x", "y"),
ds.count(),
vmin=0,
vmax=35,
norm="linear",
aspect="auto",
ax=ax,
)
plt.colorbar(dsartist)
fig, ax = plt.subplots()
using_datashader(ax, x, y)
plt.show()
It took 0.83 s to draw this:
There is also possibility to colorize by third variable. The third parameter for dsshow controls the coloring. See more examples here and the source for dsshow here.
3: scatter_with_gaussian_kde
def scatter_with_gaussian_kde(ax, x, y):
# https://stackoverflow.com/a/20107592/3015186
# Answer by Joel Kington
xy = np.vstack([x, y])
z = gaussian_kde(xy)(xy)
ax.scatter(x, y, c=z, s=100, edgecolor='')
It took 11 minutes to draw this:
4: using_hist2d
import matplotlib.pyplot as plt
def using_hist2d(ax, x, y, bins=(50, 50)):
# https://stackoverflow.com/a/20105673/3015186
# Answer by askewchan
ax.hist2d(x, y, bins, cmap=plt.cm.jet)
It took 0.021 s to draw this bins=(50,50):
It took 0.173 s to draw this bins=(1000,1000):
Cons: The zoomed-in data does not look as good as in with mpl-scatter-density or datashader. Also you have to determine the number of bins yourself.
5: density_scatter
The code is as in the answer by Guillaume.
It took 0.073 s to draw this with bins=(50,50):
It took 0.368 s to draw this with bins=(1000,1000):
Also, if the number of point makes KDE calculation too slow, color can be interpolated in np.histogram2d [Update in response to comments: If you wish to show the colorbar, use plt.scatter() instead of ax.scatter() followed by plt.colorbar()]:
import numpy as np
import matplotlib.pyplot as plt
from matplotlib import cm
from matplotlib.colors import Normalize
from scipy.interpolate import interpn
def density_scatter( x , y, ax = None, sort = True, bins = 20, **kwargs ) :
"""
Scatter plot colored by 2d histogram
"""
if ax is None :
fig , ax = plt.subplots()
data , x_e, y_e = np.histogram2d( x, y, bins = bins, density = True )
z = interpn( ( 0.5*(x_e[1:] + x_e[:-1]) , 0.5*(y_e[1:]+y_e[:-1]) ) , data , np.vstack([x,y]).T , method = "splinef2d", bounds_error = False)
#To be sure to plot all data
z[np.where(np.isnan(z))] = 0.0
# Sort the points by density, so that the densest points are plotted last
if sort :
idx = z.argsort()
x, y, z = x[idx], y[idx], z[idx]
ax.scatter( x, y, c=z, **kwargs )
norm = Normalize(vmin = np.min(z), vmax = np.max(z))
cbar = fig.colorbar(cm.ScalarMappable(norm = norm), ax=ax)
cbar.ax.set_ylabel('Density')
return ax
if "__main__" == __name__ :
x = np.random.normal(size=100000)
y = x * 3 + np.random.normal(size=100000)
density_scatter( x, y, bins = [30,30] )
You could make a histogram:
import numpy as np
import matplotlib.pyplot as plt
# fake data:
a = np.random.normal(size=1000)
b = a*3 + np.random.normal(size=1000)
plt.hist2d(a, b, (50, 50), cmap=plt.cm.jet)
plt.colorbar()
Just trying to make a 3D plot of a constant (0). So I have
width = 1
dx = 0.1
X = np.arange(-width, width, dx)
Y = np.arange(-width, width, dx)
X, Y = np.meshgrid(X, Y)
Z = []
for i in range(len(X)):
Z.append(np.zeros(len(X[i])))
But when I try to run Axes3D.plot_wireframe(X,Y,Z) I get plot_wireframe() missing 1 required positional argument: 'Z'. I need help understanding why this is, because Z is a 2D array like it should be, and I can't find many helpful examples with 3D plotting with matplotlib.
The main point is that you cannot run Axes3D.plot_wireframe(X,Y,Z) by itself. Instead you need to create an instance of Axes3D and call its method [*]. Just like in the 2D case where you wouldn't call matplotlib.axes.Axes.plot(x,y) but ax.plot(x,y) where ax is the instance created e.g. via fig.add_subplot.
An example for the wireframe plot can be found here.
The following code (using the code from the question)
from mpl_toolkits.mplot3d import Axes3D
import matplotlib.pyplot as plt
import numpy as np
fig = plt.figure()
ax = fig.add_subplot(111, projection='3d')
width = 1
dx = 0.1
X = np.arange(-width, width, dx)
Y = np.arange(-width, width, dx)
X, Y = np.meshgrid(X, Y)
Z = []
for i in range(len(X)):
Z.append(np.zeros(len(X[i])))
ax.plot_wireframe(X, Y, Z)
plt.show()
produses the following plot
[*] To be precise here; you can call the class method plot_wireframe, but you would then need to supply it with the instance like
Axes3D.plot_wireframe(ax, X, Y, Z)
I found this example online.
I've pasted it in your code example and I got the following code + plot:
import numpy as np
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
width = 1
dx = 0.1
X = np.arange(-width, width, dx)
Y = np.arange(-width, width, dx)
X, Y = np.meshgrid(X, Y)
Z = []
for i in range(len(X)):
Z.append(np.zeros(len(X[i])))
fig = plt.figure()
ax = fig.add_subplot(111, projection='3d')
ax.plot_wireframe(X, Y, Z)
plt.show()
Hope this helps! I ran it with python 3.5, using the spyder IDE.
Cheers,
Dave
I'd like to make a scatter plot where each point is colored by the spatial density of nearby points.
I've come across a very similar question, which shows an example of this using R:
R Scatter Plot: symbol color represents number of overlapping points
What's the best way to accomplish something similar in python using matplotlib?
In addition to hist2d or hexbin as #askewchan suggested, you can use the same method that the accepted answer in the question you linked to uses.
If you want to do that:
import numpy as np
import matplotlib.pyplot as plt
from scipy.stats import gaussian_kde
# Generate fake data
x = np.random.normal(size=1000)
y = x * 3 + np.random.normal(size=1000)
# Calculate the point density
xy = np.vstack([x,y])
z = gaussian_kde(xy)(xy)
fig, ax = plt.subplots()
ax.scatter(x, y, c=z, s=100)
plt.show()
If you'd like the points to be plotted in order of density so that the densest points are always on top (similar to the linked example), just sort them by the z-values. I'm also going to use a smaller marker size here as it looks a bit better:
import numpy as np
import matplotlib.pyplot as plt
from scipy.stats import gaussian_kde
# Generate fake data
x = np.random.normal(size=1000)
y = x * 3 + np.random.normal(size=1000)
# Calculate the point density
xy = np.vstack([x,y])
z = gaussian_kde(xy)(xy)
# Sort the points by density, so that the densest points are plotted last
idx = z.argsort()
x, y, z = x[idx], y[idx], z[idx]
fig, ax = plt.subplots()
ax.scatter(x, y, c=z, s=50)
plt.show()
Plotting >100k data points?
The accepted answer, using gaussian_kde() will take a lot of time. On my machine, 100k rows took about 11 minutes. Here I will add two alternative methods (mpl-scatter-density and datashader) and compare the given answers with same dataset.
In the following, I used a test data set of 100k rows:
import matplotlib.pyplot as plt
import numpy as np
# Fake data for testing
x = np.random.normal(size=100000)
y = x * 3 + np.random.normal(size=100000)
Output & computation time comparison
Below is a comparison of different methods.
1: mpl-scatter-density
Installation
pip install mpl-scatter-density
Example code
import mpl_scatter_density # adds projection='scatter_density'
from matplotlib.colors import LinearSegmentedColormap
# "Viridis-like" colormap with white background
white_viridis = LinearSegmentedColormap.from_list('white_viridis', [
(0, '#ffffff'),
(1e-20, '#440053'),
(0.2, '#404388'),
(0.4, '#2a788e'),
(0.6, '#21a784'),
(0.8, '#78d151'),
(1, '#fde624'),
], N=256)
def using_mpl_scatter_density(fig, x, y):
ax = fig.add_subplot(1, 1, 1, projection='scatter_density')
density = ax.scatter_density(x, y, cmap=white_viridis)
fig.colorbar(density, label='Number of points per pixel')
fig = plt.figure()
using_mpl_scatter_density(fig, x, y)
plt.show()
Drawing this took 0.05 seconds:
And the zoom-in looks quite nice:
2: datashader
Datashader is an interesting project. It has added support for matplotlib in datashader 0.12.
Installation
pip install datashader
Code (source & parameterer listing for dsshow):
import datashader as ds
from datashader.mpl_ext import dsshow
import pandas as pd
def using_datashader(ax, x, y):
df = pd.DataFrame(dict(x=x, y=y))
dsartist = dsshow(
df,
ds.Point("x", "y"),
ds.count(),
vmin=0,
vmax=35,
norm="linear",
aspect="auto",
ax=ax,
)
plt.colorbar(dsartist)
fig, ax = plt.subplots()
using_datashader(ax, x, y)
plt.show()
It took 0.83 s to draw this:
There is also possibility to colorize by third variable. The third parameter for dsshow controls the coloring. See more examples here and the source for dsshow here.
3: scatter_with_gaussian_kde
def scatter_with_gaussian_kde(ax, x, y):
# https://stackoverflow.com/a/20107592/3015186
# Answer by Joel Kington
xy = np.vstack([x, y])
z = gaussian_kde(xy)(xy)
ax.scatter(x, y, c=z, s=100, edgecolor='')
It took 11 minutes to draw this:
4: using_hist2d
import matplotlib.pyplot as plt
def using_hist2d(ax, x, y, bins=(50, 50)):
# https://stackoverflow.com/a/20105673/3015186
# Answer by askewchan
ax.hist2d(x, y, bins, cmap=plt.cm.jet)
It took 0.021 s to draw this bins=(50,50):
It took 0.173 s to draw this bins=(1000,1000):
Cons: The zoomed-in data does not look as good as in with mpl-scatter-density or datashader. Also you have to determine the number of bins yourself.
5: density_scatter
The code is as in the answer by Guillaume.
It took 0.073 s to draw this with bins=(50,50):
It took 0.368 s to draw this with bins=(1000,1000):
Also, if the number of point makes KDE calculation too slow, color can be interpolated in np.histogram2d [Update in response to comments: If you wish to show the colorbar, use plt.scatter() instead of ax.scatter() followed by plt.colorbar()]:
import numpy as np
import matplotlib.pyplot as plt
from matplotlib import cm
from matplotlib.colors import Normalize
from scipy.interpolate import interpn
def density_scatter( x , y, ax = None, sort = True, bins = 20, **kwargs ) :
"""
Scatter plot colored by 2d histogram
"""
if ax is None :
fig , ax = plt.subplots()
data , x_e, y_e = np.histogram2d( x, y, bins = bins, density = True )
z = interpn( ( 0.5*(x_e[1:] + x_e[:-1]) , 0.5*(y_e[1:]+y_e[:-1]) ) , data , np.vstack([x,y]).T , method = "splinef2d", bounds_error = False)
#To be sure to plot all data
z[np.where(np.isnan(z))] = 0.0
# Sort the points by density, so that the densest points are plotted last
if sort :
idx = z.argsort()
x, y, z = x[idx], y[idx], z[idx]
ax.scatter( x, y, c=z, **kwargs )
norm = Normalize(vmin = np.min(z), vmax = np.max(z))
cbar = fig.colorbar(cm.ScalarMappable(norm = norm), ax=ax)
cbar.ax.set_ylabel('Density')
return ax
if "__main__" == __name__ :
x = np.random.normal(size=100000)
y = x * 3 + np.random.normal(size=100000)
density_scatter( x, y, bins = [30,30] )
You could make a histogram:
import numpy as np
import matplotlib.pyplot as plt
# fake data:
a = np.random.normal(size=1000)
b = a*3 + np.random.normal(size=1000)
plt.hist2d(a, b, (50, 50), cmap=plt.cm.jet)
plt.colorbar()