I used below code to generate the colorbar plot of an image:
plt.imshow(distance)
cb = plt.colorbar()
plt.savefig(generate_filename("test_images.png"))
cb.remove()
The image looks likes this:
I want to draw a single contour line on this image where the signed distance value is equal to 0. I checked the doc of pyplot.contour but it needs a X and Y vector that represents the coordinates and a Z that represents heights. Is there a method to generate X, Y, and Z? Or is there a better function to achieve this? Thanks!
If you leave out X and Y, by default, plt.contour uses the array indices (in this case the range 0-1023 in both x and y).
To only draw a contour line at a given level, you can use levels=[0]. The colors= parameter can fix one or more colors. Optionally, you can draw a line on the colorbar to indicate the value of the level.
import matplotlib.pyplot as plt
import numpy as np
from scipy import ndimage # to smooth a test image
# create a test image with similar properties as the given one
np.random.seed(20221230)
distance = np.pad(np.random.randn(1001, 1001), (11, 11), constant_values=-0.02)
distance = ndimage.filters.gaussian_filter(distance, 100)
distance -= distance.min()
distance = distance / distance.max() * 0.78 - 0.73
plt.imshow(distance)
cbar = plt.colorbar()
level = 0
color = 'red'
plt.contour(distance, levels=[level], colors=color)
cbar.ax.axhline(level, color=color) # show the level on the colorbar
plt.show()
Reference: https://matplotlib.org/stable/api/_as_gen/matplotlib.pyplot.contour.html
You can accomplish this by setting the [levels] parameter in contour([X, Y,] Z, [levels], **kwargs).
You can draw contour lines at the specified levels by giving an array that is in increasing order.
import matplotlib.pyplot as plt
import numpy as np
x = y = np.arange(-3.0, 3.0, 0.02)
X, Y = np.meshgrid(x, y)
Z1 = np.exp(-X ** 2 - Y ** 2)
Z2 = np.exp(-(X - 1) ** 2 - (Y - 1) ** 2)
Z3 = np.exp(-(X + 1) ** 2 - (Y + 1) ** 2)
Z = (Z1 - Z2 - Z3) * 2
fig, ax = plt.subplots()
im = ax.imshow(Z, interpolation='gaussian',
origin='lower', extent=[-4, 4, -4, 4],
vmax=abs(Z).max(), vmin=-abs(Z).max())
plt.colorbar(im)
CS = ax.contour(X, Y, Z, levels=[0.9], colors='black')
ax.clabel(CS, fmt='%1.1f', fontsize=12)
plt.show()
Result (levels=[0.9]):
Related
I am facing a problem to plot the geometry in the python using matplotlib. I would like to have a plot which can have the equal lenth in all three axes (X, Y, Z). I have written below code but it does not show any equal axes in the obtained geometry.
How can I get the plot with equal axes?
def plotting(x, y, z, figname):
fig = plt.figure(figsize = (50,50))
ax = plt.axes(projection='3d')
ax.grid()
ax.scatter(x, y, z, c = 'r', s = 50)
ax.set_title(figname)
ax.set_xlabel('x', labelpad=20)
ax.set_ylabel('y', labelpad=20)
ax.set_zlabel('z', labelpad=20)
Matplotlib makes this very difficult. One way you could "achieve" that is by setting the same limits to xlim, ylim, zlim:
import numpy as np
import matplotlib.pyplot as plt
n = 1000
t = np.random.uniform(0, 2*np.pi, n)
p = np.random.uniform(0, 2*np.pi, n)
x = (4 + np.cos(t)) * np.cos(p)
y = (1.5 + np.cos(t)) * np.sin(p)
z = np.sin(t)
fig = plt.figure()
ax = fig.add_subplot(projection="3d")
ax.scatter(x, y, z)
ax.set_xlim(-4, 4)
ax.set_ylim(-4, 4)
ax.set_zlim(-4, 4)
plt.show()
Otherwise, your best bet is to use a different plotting library for 3D plots. Plotly allows to easily set equal aspect ratio. K3D-Jupyter and Mayavi uses equal aspect ratio by default.
I have 2 sets of datapoints:
import random
import pandas as pd
A = pd.DataFrame({'x':[random.uniform(0, 1) for i in range(0,100)], 'y':[random.uniform(0, 1) for i in range(0,100)]})
B = pd.DataFrame({'x':[random.uniform(0, 1) for i in range(0,100)], 'y':[random.uniform(0, 1) for i in range(0,100)]})
For each one of these dataset I can produce the jointplot like this:
import seaborn as sns
sns.jointplot(x=A["x"], y=A["y"], kind='kde')
sns.jointplot(x=B["x"], y=B["y"], kind='kde')
Is there a way to calculate the "common area" between these 2 joint plots ?
By common area, I mean, if you put one joint plot "inside" the other, what is the total area of intersection. So if you imagine these 2 joint plots as mountains, and you put one mountain inside the other, how much does one fall inside the other ?
EDIT
To make my question more clear:
import matplotlib.pyplot as plt
import scipy.stats as st
def plot_2d_kde(df):
# Extract x and y
x = df['x']
y = df['y']
# Define the borders
deltaX = (max(x) - min(x))/10
deltaY = (max(y) - min(y))/10
xmin = min(x) - deltaX
xmax = max(x) + deltaX
ymin = min(y) - deltaY
ymax = max(y) + deltaY
# Create meshgrid
xx, yy = np.mgrid[xmin:xmax:100j, ymin:ymax:100j]
# We will fit a gaussian kernel using the scipy’s gaussian_kde method
positions = np.vstack([xx.ravel(), yy.ravel()])
values = np.vstack([x, y])
kernel = st.gaussian_kde(values)
f = np.reshape(kernel(positions).T, xx.shape)
fig = plt.figure(figsize=(13, 7))
ax = plt.axes(projection='3d')
surf = ax.plot_surface(xx, yy, f, rstride=1, cstride=1, cmap='coolwarm', edgecolor='none')
ax.set_xlabel('x')
ax.set_ylabel('y')
ax.set_zlabel('PDF')
ax.set_title('Surface plot of Gaussian 2D KDE')
fig.colorbar(surf, shrink=0.5, aspect=5) # add color bar indicating the PDF
ax.view_init(60, 35)
I am interested in finding the interection/common volume (just the number) of these 2 kde plots:
plot_2d_kde(A)
plot_2d_kde(B)
Credits: The code for the kde plots is from here
I believe this is what you're looking for. I'm basically calculating the space (integration) of the intersection (overlay) of the two KDE distributions.
A = pd.DataFrame({'x':[random.uniform(0, 1) for i in range(0,100)], 'y':[random.uniform(0, 1) for i in range(0,100)]})
B = pd.DataFrame({'x':[random.uniform(0, 1) for i in range(0,100)], 'y':[random.uniform(0, 1) for i in range(0,100)]})
# KDE fro both A and B
kde_a = scipy.stats.gaussian_kde([A.x, A.y])
kde_b = scipy.stats.gaussian_kde([B.x, B.y])
min_x = min(A.x.min(), B.x.min())
min_y = min(A.y.min(), B.y.min())
max_x = max(A.x.max(), B.x.max())
max_y = max(A.y.max(), B.y.max())
print(f"x is from {min_x} to {max_x}")
print(f"y is from {min_y} to {max_y}")
x = [a[0] for a in itertools.product(np.arange(min_x, max_x, 0.01), np.arange(min_y, max_y, 0.01))]
y = [a[1] for a in itertools.product(np.arange(min_x, max_x, 0.01), np.arange(min_y, max_y, 0.01))]
# sample across 100x100 points.
a_dist = kde_a([x, y])
b_dist = kde_b([x, y])
print(a_dist.sum() / len(x)) # intergral of A
print(b_dist.sum() / len(x)) # intergral of B
print(np.minimum(a_dist, b_dist).sum() / len(x)) # intergral of the intersection between A and B
The following code compares calculating the volume of the intersection either via scipy's dblquad or via taking the average value over a grid.
Remarks:
For the 2D case (and with only 100 sample points), it seems the delta's need to be quite larger than 10%. The code below uses 25%. With a delta of 10%, the calculated values for f1 and f2 are about 0.90, while in theory they should be 1.0. With a delta of 25%, these values are around 0.994.
To approximate the volume the simple way, the average needs to be multiplied by the area (here (xmax - xmin)*(ymax - ymin)). Also, the more grid points are considered, the better the approximation. The code below uses 1000x1000 grid points.
Scipy has some special functions to calculate the integral, such as scipy.integrate.dblquad. This is much slower than the 'simple' method, but a bit more precise. The default precision didn't work, so the code below reduces that precision considerably. (dblquad outputs two numbers: the approximate integral and an indication of the error. To only get the integral, dblquad()[0] is used in the code.)
The same approach can be used for more dimensions. For the 'simple' method, create a more dimensional grid (xx, yy, zz = np.mgrid[xmin:xmax:100j, ymin:ymax:100j, zmin:zmax:100j]). Note that a subdivision by 1000 in each dimension would create a grid that's too large to work with.
When using scipy.integrate, dblquad needs to be replaced by tplquad for 3 dimensions or nquad for N dimensions. This probably will also be rather slow, so the accuracy needs to be reduced further.
import numpy as np
import pandas as pd
import scipy.stats as st
from scipy.integrate import dblquad
df1 = pd.DataFrame({'x':np.random.uniform(0, 1, 100), 'y':np.random.uniform(0, 1, 100)})
df2 = pd.DataFrame({'x':np.random.uniform(0, 1, 100), 'y':np.random.uniform(0, 1, 100)})
# Extract x and y
x1 = df1['x']
y1 = df1['y']
x2 = df2['x']
y2 = df2['y']
# Define the borders
deltaX = (np.max([x1, x2]) - np.min([x1, x2])) / 4
deltaY = (np.max([y1, y2]) - np.min([y1, y2])) / 4
xmin = np.min([x1, x2]) - deltaX
xmax = np.max([x1, x2]) + deltaX
ymin = np.min([y1, y2]) - deltaY
ymax = np.max([y1, y2]) + deltaY
# fit a gaussian kernel using scipy’s gaussian_kde method
kernel1 = st.gaussian_kde(np.vstack([x1, y1]))
kernel2 = st.gaussian_kde(np.vstack([x2, y2]))
print('volumes via scipy`s dblquad (volume):')
print(' volume_f1 =', dblquad(lambda y, x: kernel1((x, y)), xmin, xmax, ymin, ymax, epsabs=1e-4, epsrel=1e-4)[0])
print(' volume_f2 =', dblquad(lambda y, x: kernel2((x, y)), xmin, xmax, ymin, ymax, epsabs=1e-4, epsrel=1e-4)[0])
print(' volume_intersection =',
dblquad(lambda y, x: np.minimum(kernel1((x, y)), kernel2((x, y))), xmin, xmax, ymin, ymax, epsabs=1e-4, epsrel=1e-4)[0])
Alternatively, one can calculate the mean value over a grid of points, and multiply the result by the area of the grid. Note that np.mgrid is much faster than creating a list via itertools.
# Create meshgrid
xx, yy = np.mgrid[xmin:xmax:1000j, ymin:ymax:1000j]
positions = np.vstack([xx.ravel(), yy.ravel()])
f1 = np.reshape(kernel1(positions).T, xx.shape)
f2 = np.reshape(kernel2(positions).T, xx.shape)
intersection = np.minimum(f1, f2)
print('volumes via the mean value multiplied by the area:')
print(' volume_f1 =', np.sum(f1) / f1.size * ((xmax - xmin)*(ymax - ymin)))
print(' volume_f2 =', np.sum(f2) / f2.size * ((xmax - xmin)*(ymax - ymin)))
print(' volume_intersection =', np.sum(intersection) / intersection.size * ((xmax - xmin)*(ymax - ymin)))
Example output:
volumes via scipy`s dblquad (volume):
volume_f1 = 0.9946974276169385
volume_f2 = 0.9928998852123891
volume_intersection = 0.9046421634401607
volumes via the mean value multiplied by the area:
volume_f1 = 0.9927873844924111
volume_f2 = 0.9910132867915901
volume_intersection = 0.9028999384136771
The figure above is a great artwork showing the wind speed, wind direction and temperature simultaneously. detailedly:
The X axes represent the date
The Y axes shows the wind direction(Southern, western, etc)
The variant widths of the line were stand for the wind speed through timeseries
The variant colors of the line were stand for the atmospheric temperature
This simple figure visualized 3 different attribute without redundancy.
So, I really want to reproduce similar plot in matplotlib.
My attempt now
## Reference 1 http://stackoverflow.com/questions/19390895/matplotlib-plot-with-variable-line-width
## Reference 2 http://stackoverflow.com/questions/17240694/python-how-to-plot-one-line-in-different-colors
def plot_colourline(x,y,c):
c = plt.cm.jet((c-np.min(c))/(np.max(c)-np.min(c)))
lwidths=1+x[:-1]
ax = plt.gca()
for i in np.arange(len(x)-1):
ax.plot([x[i],x[i+1]], [y[i],y[i+1]], c=c[i],linewidth = lwidths[i])# = lwidths[i])
return
x=np.linspace(0,4*math.pi,100)
y=np.cos(x)
lwidths=1+x[:-1]
fig = plt.figure(1, figsize=(5,5))
ax = fig.add_subplot(111)
plot_colourline(x,y,prop)
ax.set_xlim(0,4*math.pi)
ax.set_ylim(-1.1,1.1)
Does someone has a more interested way to achieve this? Any advice would be appreciate!
Using as inspiration another question.
One option would be to use fill_between. But perhaps not in the way it was intended. Instead of using it to create your line, use it to mask everything that is not the line. Under it you can have a pcolormesh or contourf (for example) to map color any way you want.
Look, for instance, at this example:
import matplotlib.pyplot as plt
import numpy as np
from scipy.interpolate import interp1d
def windline(x,y,deviation,color):
y1 = y-deviation/2
y2 = y+deviation/2
tol = (y2.max()-y1.min())*0.05
X, Y = np.meshgrid(np.linspace(x.min(), x.max(), 100), np.linspace(y1.min()-tol, y2.max()+tol, 100))
Z = X.copy()
for i in range(Z.shape[0]):
Z[i,:] = c
#plt.pcolormesh(X, Y, Z)
plt.contourf(X, Y, Z, cmap='seismic')
plt.fill_between(x, y2, y2=np.ones(x.shape)*(y2.max()+tol), color='w')
plt.fill_between(x, np.ones(x.shape) * (y1.min() - tol), y2=y1, color='w')
plt.xlim(x.min(), x.max())
plt.ylim(y1.min()-tol, y2.max()+tol)
plt.show()
x = np.arange(100)
yo = np.random.randint(20, 60, 21)
y = interp1d(np.arange(0, 101, 5), yo, kind='cubic')(x)
dv = np.random.randint(2, 10, 21)
d = interp1d(np.arange(0, 101, 5), dv, kind='cubic')(x)
co = np.random.randint(20, 60, 21)
c = interp1d(np.arange(0, 101, 5), co, kind='cubic')(x)
windline(x, y, d, c)
, which results in this:
The function windline accepts as arguments numpy arrays with x, y , a deviation (like a thickness value per x value), and color array for color mapping. I think it can be greatly improved by messing around with other details but the principle, although not perfect, should be solid.
import numpy as np
import matplotlib.pyplot as plt
from matplotlib.collections import LineCollection
x = np.linspace(0,4*np.pi,10000) # x data
y = np.cos(x) # y data
r = np.piecewise(x, [x < 2*np.pi, x >= 2*np.pi], [lambda x: 1-x/(2*np.pi), 0]) # red
g = np.piecewise(x, [x < 2*np.pi, x >= 2*np.pi], [lambda x: x/(2*np.pi), lambda x: -x/(2*np.pi)+2]) # green
b = np.piecewise(x, [x < 2*np.pi, x >= 2*np.pi], [0, lambda x: x/(2*np.pi)-1]) # blue
a = np.ones(10000) # alpha
w = x # width
fig, ax = plt.subplots(2)
ax[0].plot(x, r, color='r')
ax[0].plot(x, g, color='g')
ax[0].plot(x, b, color='b')
# mysterious parts
points = np.array([x, y]).T.reshape(-1, 1, 2)
segments = np.concatenate([points[:-1], points[1:]], axis=1)
# mysterious parts
rgba = list(zip(r,g,b,a))
lc = LineCollection(segments, linewidths=w, colors=rgba)
ax[1].add_collection(lc)
ax[1].set_xlim(0,4*np.pi)
ax[1].set_ylim(-1.1,1.1)
fig.show()
I notice this is what I suffered.
As an exercise in learning Matplotlib and improving my math/coding I decided to try and plot a trigonometric function (x squared plus y squared equals one).
Trigonometric functions are also called "circular" functions but I am only producing half the circle.
#Attempt to plot equation x^2 + y^2 == 1
import numpy as np
import matplotlib.pyplot as plt
import math
x = np.linspace(-1, 1, 21) #generate np.array of X values -1 to 1 in 0.1 increments
x_sq = [i**2 for i in x]
y = [math.sqrt(1-(math.pow(i, 2))) for i in x] #calculate y for each value in x
y_sq = [i**2 for i in y]
#Print for debugging / sanity check
for i,j in zip(x_sq, y_sq):
print('x: {:1.4f} y: {:1.4f} x^2: {:1.4f} y^2: {:1.4f} x^2 + Y^2 = {:1.4f}'.format(math.sqrt(i), math.sqrt(j), i, j, i+j))
#Format how the chart displays
plt.figure(figsize=(6, 4))
plt.axhline(y=0, color='y')
plt.axvline(x=0, color='y')
plt.grid()
plt.plot(x, y, 'rx')
plt.show()
I want to plot the full circle. My code only produces the positive y values and I want to plot the full circle.
Here is how the full plot should look. I used Wolfram Alpha to generate it.
Ideally I don't want solutions where the lifting is done for me such as using matplotlib.pyplot.contour. As a learning exercise, I want to "see the working" so to speak. Namely I ideally want to generate all the values and plot them "manually".
The only method I can think of is to re-arrange the equation and generate a set of negative y values with calculated x values then plot them separately. I am sure there is a better way to achieve the outcome and I am sure one of the gurus on Stack Overflow will know what those options are.
Any help will be gratefully received. :-)
The equation x**2 + y**2 = 1 describes a circle with radius 1 around the origin.
But suppose you wouldn't know this already, you can still try to write this equation in polar coordinates,
x = r*cos(phi)
y = r*sin(phi)
(r*cos(phi))**2 + (r*sin(phi))**2 == 1
r**2*(cos(phi)**2 + sin(phi)**2) == 1
Due to the trigonometric identity cos(phi)**2 + sin(phi)**2 == 1 this reduces to
r**2 == 1
and since r should be real,
r == 1
(for any phi).
Plugging this into python:
import numpy as np
import matplotlib.pyplot as plt
phi = np.linspace(0, 2*np.pi, 200)
r = 1
x = r*np.cos(phi)
y = r*np.sin(phi)
plt.plot(x,y)
plt.axis("equal")
plt.show()
This happens because the square root returns only the positive value, so you need to take those values and turn them into negative values.
You can do something like this:
import numpy as np
import matplotlib.pyplot as plt
r = 1 # radius
x = np.linspace(-r, r, 1000)
y = np.sqrt(r-x**2)
plt.figure(figsize=(5,5), dpi=100) # figsize=(n,n), n needs to be equal so the image doesn't flatten out
plt.grid(linestyle='-', linewidth=2)
plt.plot(x, y, color='g')
plt.plot(x, -y, color='r')
plt.legend(['Positive y', 'Negative y'], loc='lower right')
plt.axhline(y=0, color='b')
plt.axvline(x=0, color='b')
plt.show()
And that should return this:
PLOT
I have reviewed the response to this question: How would I iterate over a list of files and plot them as subplots on a single figure?
But am none the wiser on how to achieve my goal. I would like to plot multiple data sets, with differing x axes, onto a single figure in Python. I have included a snippet of my code below, which performs an FFT on a dataset, then calculates 3 Butterworth filter outputs. Ideally I would like to have all plotted on a single figure, which I have attempted to achieve in the code below.
The for loop calculates the 3 Butterworth filter outputs, the code above - the FFT and the code directly below attempts to append the FFT curve and sqrt(0.5) line to the previously generated plots for display.
Any Direction or advice would be appreciated.
"""Performs a Fast Fourier Transform on the data specified at the base of the code"""
def FFT(col):
x = io2.loc[1:,'Time']
y = io2.loc[1:,col]
# Number of samplepoints
#N = 600
N = pd.Series.count(x)
N2 = int(N/2)
# sample spacing
#T = 1.0 / 800.0
T = 1/(io2.loc[2,'Time'] - io2.loc[1,'Time'])
#x = np.linspace(0.0, N*T, N)
#y = np.sin(50.0 * 2.0*np.pi*x) + 0.5*np.sin(80.0 * 2.0*np.pi*x)
yf = scipy.fftpack.fft(y)
xf = np.linspace(0.0, 1.0/(2.0*T), N2)
fig=plt.figure()
plt.clf()
i=1
for order in [3, 6, 9]:
ax=fig.add_subplot(111, label="order = %d" % order)
b, a = butter_lowpass(cutoff, fs, order=order)
w, h = freqz(b, a, worN=2000)
ax.plot((fs * 0.5 / np.pi) * w, abs(h))
i=i+1
ax4=fig.add_subplot(111, label='sqrt(0.5)', frame_on=False)
ax5=fig.add_subplot(111, label="FFT of "+col, frame_on=False)
ax4.plot([0, 0.5 * fs], [np.sqrt(0.5), np.sqrt(0.5)], '--')
ax5.plot(xf, 2.0/N * np.abs(yf[:N2]))
plt.xlabel('Frequency (Hz)')
plt.ylabel('Gain')
plt.grid(True)
plt.legend(loc='best')
#fig, ax = plt.subplots()
#ax.plot(xf, 2.0/N * np.abs(yf[:N2]), label="FFT of "+col)
plt.axis([0,5000,0,0.1])
#plt.xlabel('Frequency (Hz)')
#plt.ylabel('Amplitude (mm)')
#plt.legend(loc=0)
plt.show()
return
Kind Regards,
Here you can find a minimal example of how to plot multiple lines with different x and y datasets. You are recreating the plot every time you type add_subplot(111). Instead, you should call plot multiple times. I have added an example for a single plot with multiple lines, as well as an example for one subplot per line.
import numpy as np
import matplotlib.pyplot as plt
x1 = np.arange(0, 10, 1)
x2 = np.arange(3, 12, 0.1)
x3 = np.arange(2, 8, 0.01)
y1 = np.sin(x1)
y2 = np.cos(x2**0.8)
y3 = np.sin(4.*x3)**3
data = []
data.append((x1, y1, 'label1'))
data.append((x2, y2, 'label2'))
data.append((x3, y3, 'label3'))
# All lines in one plot.
plt.figure()
for n in data:
plt.plot(n[0], n[1], label=n[2])
plt.legend(loc=0, frameon=False)
# One subplot per data set.
cols = 2
rows = len(data)//2 + len(data)%2
plt.figure()
gs = plt.GridSpec(rows, cols)
for n in range(len(data)):
i = n%2
j = n//2
plt.subplot(gs[j,i])
plt.plot(data[n][0], data[n][1])
plt.title(data[n][2])
plt.tight_layout()
plt.show()