How to generate points within rectangle, at random locations and without overlap? - python

I have an image with width: 1980 and height: 1080.
Ultimately, I want to place various shapes within the image, but at random locations and in such a way that they do not overlap. The 0,0 coordinates of the image are in the center.
Before rendering the shapes into the image (I don't need help with this), I need to write an algorithm to generate the XY points/locations. I want to be able to specify the minimum distance any given point is allowed to get to any other points.
How can do this?
All I have been able to do, is to generate points at equally spaced locations and then add a bit of randomness to each point. But this is not ideal, because it means points just vary within some 'cell' within a grid, and if the randomness value is too high, they will appear outside of the rectangle. Here is my code:
import numpy as np
import matplotlib.pyplot as plt
from matplotlib.patches import Rectangle
from random import randrange
def is_square(integer):
root = np.sqrt(integer)
return integer == int(root + 0.5) ** 2
def perfect_sqr(n):
nextN = np.floor(np.sqrt(n)) + 1
return int(nextN * nextN)
def generate_cells(width = 1920, height = 1080, n = 9, show_plot=False):
# If the number is not a perfect square, we need to find the next number which is
# so that we can get the root N, which will be used to determine the number of rows/columns
if not is_square(n):
n = perfect_sqr(n)
N = np.sqrt(n)
# generate x and y lists, where each represents an array of points evenly spaced between 0 and the width/height
x = np.array(list(range(0, width, int(width/N))))
y = np.array(list(range(0, height, int(height/N))))
# center the points within each 'cell'
x_centered = x+int(width/N)/2
y_centered = y+int(height/N)/2
x_centered = [a+randrange(50) for a in x_centered]
y_centered = [a+randrange(50) for a in y_centered]
# generate a grid with the points
xv, yv = np.meshgrid(x_centered, y_centered)
if(show_plot):
plt.scatter(xv,yv)
plt.gca().add_patch(Rectangle((0,0),width, height,edgecolor='red', facecolor='none', lw=1))
plt.show()
# convert the arrays to 1D
xx = xv.flatten()
yy = yv.flatten()
# Merge them side-by-side
zips = zip(xx, yy)
# convert to set of points/tuples and return
return set(zips)
coords = generate_cells(width=1920, height=1080, n=15, show_plot=True)
print(coords)

Assuming you simply want to randomly define non-overlapping coordinates within the confines of a maximum image size subject to not having images overlap, this might be a good solution.
import numpy as np
def locateImages(field_height: int, field_width: int, min_sep: int, points: int)-> np.array:
h_range = np.array(range(min_sep//2, field_height - (min_sep//2), min_sep))
w_range = np.array(range(min_sep//2, field_width-(min_sep//2), min_sep))
mx_len = max(len(h_range), len(w_range))
if len(h_range) < mx_len:
xtra = np.random.choice(h_range, mx_len - len(h_range))
h_range = np.append(h_range, xtra)
if len(w_range) < mx_len:
xtra = np.random.choice(w_range, mx_len - len(w_range))
w_range = np.append(w_range, xtra)
h_points = np.random.choice(h_range, points, replace=False)
w_points = np.random.choice(w_range, points, replace=False)
return np.concatenate((np.vstack(h_points), np.vstack(w_points)), axis= 1)
Then given:
field_height = the vertical coordinate of the Image space
field_width = the maximum horizontal coordinate of the Image space
min_sep = the minimum spacing between images
points = number of coordinates to be selected
Then:
locateImages(15, 8, 2, 5) will yield:
array([[13, 1],
[ 7, 3],
[ 1, 5],
[ 5, 5],
[11, 5]])
Render the output:
points = locateImages(1080, 1920, 100, 15)
x,y= zip(*points)
plt.scatter(x,x)
plt.gca().add_patch(Rectangle((0,0),1920, 1080,edgecolor='red', facecolor='none', lw=1))
plt.show()

Related

Converting indices in marching cubes to original x,y,z space - visualizing isosurface 3d skimage

I want to draw a volume in x1,x2,x3-space. The volume is an isocurve found by the marching cubes algorithm in skimage. The function generating the volume is pdf_grid = f(x1,x2,x3) and
I want to draw the volume where pdf = 60% max(pdf).
My issue is that the marching cubes algorithm generates vertices and faces, but how do I map those back to the x1, x2, x3-space?
My (rather limited) understanding of marching cubes is that "vertices" refer to the indices in the volume (pdf_grid in my case). If "vertices" contained only the exact indices in the grid this would have been easy, but "vertices" contains floats and not integers. It seems like marching cubes do some interpolation between grid points (according to https://www.cs.carleton.edu/cs_comps/0405/shape/marching_cubes.html), so the question is then how to recover exactly the values of x1,x2,x3?
import numpy as np
import scipy.stats
import matplotlib.pyplot as plt
#Make some random data
cov = np.array([[1, .2, -.5],
[.2, 1.2, .1],
[-.5, .1, .8]])
dist = scipy.stats.multivariate_normal(mean = [1., 3., 2], cov = cov)
N = 500
x_samples = dist.rvs(size=N).T
#Create the kernel density estimator - approximation of a pdf
kernel = scipy.stats.gaussian_kde(x_samples)
x_mean = x_samples.mean(axis=1)
#Find the mode
res = scipy.optimize.minimize(lambda x: -kernel.logpdf(x),
x_mean #x0, initial guess
)
x_mode = res["x"]
num_el = 50 #number of elements in the grid
x_min = np.min(x_samples, axis = 1)
x_max = np.max(x_samples, axis = 1)
x1g, x2g, x3g = np.mgrid[x_min[0]:x_max[0]:num_el*1j,
x_min[1]:x_max[1]:num_el*1j,
x_min[2]:x_max[2]:num_el*1j
]
pdf_grid = np.zeros(x1g.shape) #implicit function/grid for the marching cubes
for an in range(x1g.shape[0]):
for b in range(x1g.shape[1]):
for c in range(x1g.shape[2]):
pdf_grid[a,b,c] = kernel(np.array([x1g[a,b,c],
x2g[a,b,c],
x3g[a,b,c]]
))
from mpl_toolkits.mplot3d.art3d import Poly3DCollection
from skimage import measure
iso_level = .6 #draw a volume which contains pdf_val(mode)*60%
verts, faces, normals, values = measure.marching_cubes(pdf_grid, kernel(x_mode)*iso_level)
#How to convert the figure back to x1,x2,x3 space? I just draw the output as it was done in the skimage example here https://scikit-image.org/docs/0.16.x/auto_examples/edges/plot_marching_cubes.html#sphx-glr-auto-examples-edges-plot-marching-cubes-py so you can see the volume
# Fancy indexing: `verts[faces]` to generate a collection of triangles
mesh = Poly3DCollection(verts[faces],
alpha = .5,
label = f"KDE = {iso_level}"+r"$x_{mode}$",
linewidth = .1)
mesh.set_edgecolor('k')
fig, ax = plt.subplots(subplot_kw=dict(projection='3d'))
c1 = ax.add_collection3d(mesh)
c1._facecolors2d=c1._facecolor3d
c1._edgecolors2d=c1._edgecolor3d
#Plot the samples. Marching cubes volume does not capture these samples
pdf_val = kernel(x_samples) #get density value for each point (for color-coding)
x1, x2, x3 = x_samples
scatter_plot = ax.scatter(x1, x2, x3, c=pdf_val, alpha = .2, label = r" samples")
ax.scatter(x_mode[0], x_mode[1], x_mode[2], c = "r", alpha = .2, label = r"$x_{mode}$")
ax.set_xlabel(r"$x_1$")
ax.set_ylabel(r"$x_2$")
ax.set_zlabel(r"$x_3$")
# ax.set_box_aspect([np.ptp(i) for me in x_samples]) # equal aspect ratio
cbar = fig.color bar(scatter_plot, ax=ax)
cbar.set_label(r"$KDE(w) \approx pdf(w)$")
ax.legend()
#Make the axis limit so that the volume and samples are shown.
ax.set_xlim(- 5, np.max(verts, axis=0)[0] + 3)
ax.set_ylim(- 5, np.max(verts, axis=0)[1] + 3)
ax.set_zlim(- 5, np.max(verts, axis=0)[2] + 3)
This is probably way too late of an answer to help OP, but in case anyone else comes across this post looking for a solution to this problem, the issue stems from the marching cubes algorithm outputting the relevant vertices in array space. This space is defined by the number of elements per dimension of the mesh grid and the marching cubes algorithm does indeed do some interpolation in this space (explaining the presence of floats).
Anyways, in order to transform the vertices back into x1,x2,x3 space you just need to scale and shift them by the appropriate quantities. These quantities are defined by the range, number of elements of the mesh grid, and the minimum value in each dimension respectively. So using the variables defined in the OP, the following will provide the actual location of the vertices:
verts_actual = verts*((x_max-x_min)/pdf_grid.shape) + x_min

Moving window averages on unequal dimensions

TL;DR: Is there anyway I can get rid of my second for-loop?
I have a time series of points on a 2D-grid. To get rid of fast fluctuations of their position, I average the coordinates over a window of frames. Now in my case, it's possible for the points to cover a larger distance than usual. I don't want to include frames for a specific point, if it travels farther than the cut_off value.
In the first for-loop, I go over all frames and define the moving window. I then calculate the distances between the current frame and each frame in the moving window. After I grab only those positions from all frames, where both the x and y component did not travel farther than cut_off. Now I want to calculate the mean positions for every point from all these selected frames of the moving window (note: the number of selected frames can be smaller than n_window). This leads me to the second for-loop. Here I iterate over all points and actually grab the positions from the frames, in which the current point did not travel farther than cut_off. From these selected frames I calculate the mean value of the coordinates and use it as the new value for the current frame.
This very last for-loop slows down the whole processing. I can't come up with a better way to accomplish this calculation. Any suggestions?
MWE
Put in comments for clarification.
import numpy as np
# Generate a timeseries with 1000 frames, each
# containing 50 individual points defined by their
# x and y coordinates
n_frames = 1000
n_points = 50
n_coordinates = 2
timeseries = np.random.randint(-100, 100, [n_frames, n_points, n_coordinates])
# Set window size to 20 frames
n_window = 20
# Distance cut off
cut_off = 60
# Set up empty array to hold results
avg_data_store = np.zeros([n_frames, timeseries.shape[1], 2])
# Iterate over all frames
for frame in np.arange(0, n_frames):
# Set the frame according to the window size that we're looking at
t_before = int(frame - (n_window / 2))
t_after = int(frame + (n_window / 2))
# If we're trying to access frames below 0, set the lowest one to 0
if t_before < 0:
t_before = 0
# Trying to access frames that are not in the trajectory, set to last frame
if t_after > n_frames - 1:
t_after = n_frames - 1
# Grab x and y coordinates for all points in the corresponding window
pos_before = timeseries[t_before:frame]
pos_after = timeseries[frame + 1:t_after + 1]
pos_now = timeseries[frame]
# Calculate the distance between the current frame and the windows before/after
d_before = np.abs(pos_before - pos_now)
d_after = np.abs(pos_after - pos_now)
# Grab indices of frames+points, that are below the cut off
arg_before = np.argwhere(np.all(d_before < cut_off, axis=2))
arg_after = np.argwhere(np.all(d_after < cut_off, axis=2))
# Iterate over all points
for i in range(0, timeseries.shape[1]):
# Create temp array
temp_stack = pos_now[i]
# Grab all frames in which the current point did _not_
# travel farther than `cut_off`
all_before = arg_before[arg_before[:, 1] == i][:, 0]
all_after = arg_after[arg_after[:, 1] == i][:, 0]
# Grab the corresponding positions for this points in these frames
all_pos_before = pos_before[all_before, i]
all_pos_after = pos_after[all_after, i]
# If we have any frames for that point before / after
# stack them into the temp array
if all_pos_before.size > 0:
temp_stack = np.vstack([all_pos_before, temp_stack])
if all_pos_after.size > 0:
temp_stack = np.vstack([temp_stack, all_pos_after])
# Calculate the moving window average for the selection of frames
avg_data_store[frame, i] = temp_stack.mean(axis=0)
If you are fine with calculating the cutoff distance in x and y separately, you can use scipy.ndimage.generic_filter.
import numpy as np
from scipy.ndimage import generic_filter
def _mean(x, cutoff):
is_too_different = np.abs(x - x[len(x) / 2]) > cutoff
return np.mean(x[~is_too_different])
def _smooth(x, window_length=5, cutoff=1.):
return generic_filter(x, _mean, size=window_length, mode='nearest', extra_keywords=dict(cutoff=cutoff))
def smooth(arr, window_length=5, cutoff=1., axis=-1):
return np.apply_along_axis(_smooth, axis, arr, window_length=window_length, cutoff=cutoff)
# --------------------------------------------------------------------------------
def _simulate_movement_2d(T, fraction_is_jump=0.01):
# generate random velocities with a few "jumps"
velocity = np.random.randn(T, 2)
is_jump = np.random.rand(T) < fraction_is_jump
jump = 10 * np.random.randn(T, 2)
jump[~is_jump] = 0.
# pre-allocate position and momentum arrays
position = np.zeros((T,2))
momentum = np.zeros((T,2))
# initialise the first position
position[0] = np.random.randn(2)
# update position using velocity vector:
# smooth movement by not applying the velocity directly
# but rather by keeping track of the momentum
for ii in range(2,T):
momentum[ii] = 0.9 * momentum[ii-1] + 0.1 * velocity[ii-1]
position[ii] = position[ii-1] + momentum[ii] + jump[ii]
# add some measurement noise
noise = np.random.randn(T,2)
position += noise
return position
def demo(nframes=1000, npoints=3):
# create data
positions = np.array([_simulate_movement_2d(nframes) for ii in range(npoints)])
# format to (nframes, npoints, 2)
position = positions.transpose([1, 0, 2])
# smooth
smoothed = smooth(positions, window_length=11, cutoff=5., axis=1)
# plot
x, y = positions.T
xs, ys = smoothed.T
import matplotlib.pyplot as plt
fig, ax = plt.subplots(1,1)
ax.plot(x, y, 'o')
ax.plot(xs, ys, 'k-', alpha=0.3, lw=2)
plt.show()
demo()

In matplotlib, how can I plot a multi-colored line, like a rainbow

I would like to plot parallel lines with different colors. E.g. rather than a single red line of thickness 6, I would like to have two parallel lines of thickness 3, with one red and one blue.
Any thoughts would be appreciated.
Merci
Even with the smart offsetting (s. below), there is still an issue in a view that has sharp angles between consecutive points.
Zoomed view of smart offsetting:
Overlaying lines of varying thickness:
Plotting parallel lines is not an easy task. Using a simple uniform offset will of course not show the desired result. This is shown in the left picture below.
Such a simple offset can be produced in matplotlib as shown in the transformation tutorial.
Method1
A better solution may be to use the idea sketched on the right side. To calculate the offset of the nth point we can use the normal vector to the line between the n-1st and the n+1st point and use the same distance along this normal vector to calculate the offset point.
The advantage of this method is that we have the same number of points in the original line as in the offset line. The disadvantage is that it is not completely accurate, as can be see in the picture.
This method is implemented in the function offset in the code below.
In order to make this useful for a matplotlib plot, we need to consider that the linewidth should be independent of the data units. Linewidth is usually given in units of points, and the offset would best be given in the same unit, such that e.g. the requirement from the question ("two parallel lines of width 3") can be met.
The idea is therefore to transform the coordinates from data to display coordinates, using ax.transData.transform. Also the offset in points o can be transformed to the same units: Using the dpi and the standard of ppi=72, the offset in display coordinates is o*dpi/ppi. After the offset in display coordinates has been applied, the inverse transform (ax.transData.inverted().transform) allows a backtransformation.
Now there is another dimension of the problem: How to assure that the offset remains the same independent of the zoom and size of the figure?
This last point can be addressed by recalculating the offset each time a zooming of resizing event has taken place.
Here is how a rainbow curve would look like produced by this method.
And here is the code to produce the image.
import numpy as np
import matplotlib.pyplot as plt
dpi = 100
def offset(x,y, o):
""" Offset coordinates given by array x,y by o """
X = np.c_[x,y].T
m = np.array([[0,-1],[1,0]])
R = np.zeros_like(X)
S = X[:,2:]-X[:,:-2]
R[:,1:-1] = np.dot(m, S)
R[:,0] = np.dot(m, X[:,1]-X[:,0])
R[:,-1] = np.dot(m, X[:,-1]-X[:,-2])
On = R/np.sqrt(R[0,:]**2+R[1,:]**2)*o
Out = On+X
return Out[0,:], Out[1,:]
def offset_curve(ax, x,y, o):
""" Offset array x,y in data coordinates
by o in points """
trans = ax.transData.transform
inv = ax.transData.inverted().transform
X = np.c_[x,y]
Xt = trans(X)
xto, yto = offset(Xt[:,0],Xt[:,1],o*dpi/72. )
Xto = np.c_[xto, yto]
Xo = inv(Xto)
return Xo[:,0], Xo[:,1]
# some single points
y = np.array([1,2,2,3,3,0])
x = np.arange(len(y))
#or try a sinus
x = np.linspace(0,9)
y=np.sin(x)*x/3.
fig, ax=plt.subplots(figsize=(4,2.5), dpi=dpi)
cols = ["#fff40b", "#00e103", "#ff9921", "#3a00ef", "#ff2121", "#af00e7"]
lw = 2.
lines = []
for i in range(len(cols)):
l, = plt.plot(x,y, lw=lw, color=cols[i])
lines.append(l)
def plot_rainbow(event=None):
xr = range(6); yr = range(6);
xr[0],yr[0] = offset_curve(ax, x,y, lw/2.)
xr[1],yr[1] = offset_curve(ax, x,y, -lw/2.)
xr[2],yr[2] = offset_curve(ax, xr[0],yr[0], lw)
xr[3],yr[3] = offset_curve(ax, xr[1],yr[1], -lw)
xr[4],yr[4] = offset_curve(ax, xr[2],yr[2], lw)
xr[5],yr[5] = offset_curve(ax, xr[3],yr[3], -lw)
for i in range(6):
lines[i].set_data(xr[i], yr[i])
plot_rainbow()
fig.canvas.mpl_connect("resize_event", plot_rainbow)
fig.canvas.mpl_connect("button_release_event", plot_rainbow)
plt.savefig(__file__+".png", dpi=dpi)
plt.show()
Method2
To avoid overlapping lines, one has to use a more complicated solution.
One could first offset every point normal to the two line segments it is part of (green points in the picture below). Then calculate the line through those offset points and find their intersection.
A particular case would be when the slopes of two subsequent line segments equal. This has to be taken care of (eps in the code below).
from __future__ import division
import numpy as np
import matplotlib.pyplot as plt
dpi = 100
def intersect(p1, p2, q1, q2, eps=1.e-10):
""" given two lines, first through points pn, second through qn,
find the intersection """
x1 = p1[0]; y1 = p1[1]; x2 = p2[0]; y2 = p2[1]
x3 = q1[0]; y3 = q1[1]; x4 = q2[0]; y4 = q2[1]
nomX = ((x1*y2-y1*x2)*(x3-x4)- (x1-x2)*(x3*y4-y3*x4))
denom = float( (x1-x2)*(y3-y4) - (y1-y2)*(x3-x4) )
nomY = (x1*y2-y1*x2)*(y3-y4) - (y1-y2)*(x3*y4-y3*x4)
if np.abs(denom) < eps:
#print "intersection undefined", p1
return np.array( p1 )
else:
return np.array( [ nomX/denom , nomY/denom ])
def offset(x,y, o, eps=1.e-10):
""" Offset coordinates given by array x,y by o """
X = np.c_[x,y].T
m = np.array([[0,-1],[1,0]])
S = X[:,1:]-X[:,:-1]
R = np.dot(m, S)
norm = np.sqrt(R[0,:]**2+R[1,:]**2) / o
On = R/norm
Outa = On+X[:,1:]
Outb = On+X[:,:-1]
G = np.zeros_like(X)
for i in xrange(0, len(X[0,:])-2):
p = intersect(Outa[:,i], Outb[:,i], Outa[:,i+1], Outb[:,i+1], eps=eps)
G[:,i+1] = p
G[:,0] = Outb[:,0]
G[:,-1] = Outa[:,-1]
return G[0,:], G[1,:]
def offset_curve(ax, x,y, o, eps=1.e-10):
""" Offset array x,y in data coordinates
by o in points """
trans = ax.transData.transform
inv = ax.transData.inverted().transform
X = np.c_[x,y]
Xt = trans(X)
xto, yto = offset(Xt[:,0],Xt[:,1],o*dpi/72., eps=eps )
Xto = np.c_[xto, yto]
Xo = inv(Xto)
return Xo[:,0], Xo[:,1]
# some single points
y = np.array([1,1,2,0,3,2,1.,4,3]) *1.e9
x = np.arange(len(y))
x[3]=x[4]
#or try a sinus
#x = np.linspace(0,9)
#y=np.sin(x)*x/3.
fig, ax=plt.subplots(figsize=(4,2.5), dpi=dpi)
cols = ["r", "b"]
lw = 11.
lines = []
for i in range(len(cols)):
l, = plt.plot(x,y, lw=lw, color=cols[i], solid_joinstyle="miter")
lines.append(l)
def plot_rainbow(event=None):
xr = range(2); yr = range(2);
xr[0],yr[0] = offset_curve(ax, x,y, lw/2.)
xr[1],yr[1] = offset_curve(ax, x,y, -lw/2.)
for i in range(2):
lines[i].set_data(xr[i], yr[i])
plot_rainbow()
fig.canvas.mpl_connect("resize_event", plot_rainbow)
fig.canvas.mpl_connect("button_release_event", plot_rainbow)
plt.show()
Note that this method should work well as long as the offset between the lines is smaller then the distance between subsequent points on the line. Otherwise method 1 may be better suited.
The best that I can think of is to take your data, generate a series of small offsets, and use fill_between to make bands of whatever color you like.
I wrote a function to do this. I don't know what shape you're trying to plot, so this may or may not work for you. I tested it on a parabola and got decent results. You can also play around with the list of colors.
def rainbow_plot(x, y, spacing=0.1):
fig, ax = plt.subplots()
colors = ['red', 'yellow', 'green', 'cyan','blue']
top = max(y)
lines = []
for i in range(len(colors)+1):
newline_data = y - top*spacing*i
lines.append(newline_data)
for i, c in enumerate(colors):
ax.fill_between(x, lines[i], lines[i+1], facecolor=c)
return fig, ax
x = np.linspace(0,1,51)
y = 1-(x-0.5)**2
rainbow_plot(x,y)

Find a easier way to cluster 2-d scatter data into grid array data

I have figured out a method to cluster disperse point data into structured 2-d array(like rasterize function). And I hope there are some better ways to achieve that target.
My work
1. Intro
1000 point data has there dimensions of properties (lon, lat, emission) whicn represent one factory located at (x,y) emit certain amount of CO2 into atmosphere
grid network: predefine the 2-d array in the shape of 20x20
http://i4.tietuku.com/02fbaf32d2f09fff.png
The code reproduced here:
#### define the map area
xc1,xc2,yc1,yc2 = 113.49805889531724,115.5030664238035,37.39995194888143,38.789235929357105
map = Basemap(llcrnrlon=xc1,llcrnrlat=yc1,urcrnrlon=xc2,urcrnrlat=yc2)
#### reading the point data and scatter plot by their position
df = pd.read_csv("xxxxx.csv")
px,py = map(df.lon, df.lat)
map.scatter(px, py, color = "red", s= 5,zorder =3)
#### predefine the grid networks
lon_grid,lat_grid = np.linspace(xc1,xc2,21), np.linspace(yc1,yc2,21)
lon_x,lat_y = np.meshgrid(lon_grid,lat_grid)
grids = np.zeros(20*20).reshape(20,20)
plt.pcolormesh(lon_x,lat_y,grids,cmap = 'gray', facecolor = 'none',edgecolor = 'k',zorder=3)
2. My target
Finding the nearest grid point for each factory
Add the emission data into this grid number
3. Algorithm realization
3.1 Raster grid
note: 20x20 grid points are distributed in this area represented by blue dot.
http://i4.tietuku.com/8548554587b0cb3a.png
3.2 KD-tree
Find the nearest blue dot of each red point
sh = (20*20,2)
grids = np.zeros(20*20*2).reshape(*sh)
sh_emission = (20*20)
grids_em = np.zeros(20*20).reshape(sh_emission)
k = 0
for j in range(0,yy.shape[0],1):
for i in range(0,xx.shape[0],1):
grids[k] = np.array([lon_grid[i],lat_grid[j]])
k+=1
T = KDTree(grids)
x_delta = (lon_grid[2] - lon_grid[1])
y_delta = (lat_grid[2] - lat_grid[1])
R = np.sqrt(x_delta**2 + y_delta**2)
for i in range(0,len(df.lon),1):
idx = T.query_ball_point([df.lon.iloc[i],df.lat.iloc[i]], r=R)
# there are more than one blue dot which are founded sometimes,
# So I'll calculate the distances between the factory(red point)
# and all blue dots which are listed
if (idx > 1):
distance = []
for k in range(0,len(idx),1):
distance.append(np.sqrt((df.lon.iloc[i] - grids[k][0])**2 + (df.lat.iloc[i] - grids[k][1])**2))
pos_index = distance.index(min(distance))
pos = idx[pos_index]
# Only find 1 point
else:
pos = idx
grids_em[pos] += df.so2[i]
4. Result
co2 = grids_em.reshape(20,20)
plt.pcolormesh(lon_x,lat_y,co2,cmap =plt.cm.Spectral_r,zorder=3)
http://i4.tietuku.com/6ded65c4ac301294.png
5. My question
Can someone point out some drawbacks or error of this method?
Is there some algorithms more aligned with my target?
Thanks a lot!
There are many for-loop in your code, it's not the numpy way.
Make some sample data first:
import numpy as np
import pandas as pd
from scipy.spatial import KDTree
import pylab as pl
xc1, xc2, yc1, yc2 = 113.49805889531724, 115.5030664238035, 37.39995194888143, 38.789235929357105
N = 1000
GSIZE = 20
x, y = np.random.multivariate_normal([(xc1 + xc2)*0.5, (yc1 + yc2)*0.5], [[0.1, 0.02], [0.02, 0.1]], size=N).T
value = np.ones(N)
df_points = pd.DataFrame({"x":x, "y":y, "v":value})
For equal space grids you can use hist2d():
pl.hist2d(df_points.x, df_points.y, weights=df_points.v, bins=20, cmap="viridis");
Here is the output:
Here is the code to use KdTree:
X, Y = np.mgrid[x.min():x.max():GSIZE*1j, y.min():y.max():GSIZE*1j]
grid = np.c_[X.ravel(), Y.ravel()]
points = np.c_[df_points.x, df_points.y]
tree = KDTree(grid)
dist, indices = tree.query(points)
grid_values = df_points.groupby(indices).v.sum()
df_grid = pd.DataFrame(grid, columns=["x", "y"])
df_grid["v"] = grid_values
fig, ax = pl.subplots(figsize=(10, 8))
ax.plot(df_points.x, df_points.y, "kx", alpha=0.2)
mapper = ax.scatter(df_grid.x, df_grid.y, c=df_grid.v,
cmap="viridis",
linewidths=0,
s=100, marker="o")
pl.colorbar(mapper, ax=ax);
the output is:

How can an almost arbitrary plane in a 3D dataset be plotted by matplotlib?

There is an array containing 3D data of shape e.g. (64,64,64), how do you plot a plane given by a point and a normal (similar to hkl planes in crystallography), through this dataset?
Similar to what can be done in MayaVi by rotating a plane through the data.
The resulting plot will contain non-square planes in most cases.
Can those be done with matplotlib (some sort of non-rectangular patch)?
Edit: I almost solved this myself (see below) but still wonder how non-rectangular patches can be plotted in matplotlib...?
Edit: Due to discussions below I restated the question.
This is funny, a similar question I replied to just today. The way to go is: interpolation. You can use griddata from scipy.interpolate:
Griddata
This page features a very nice example, and the signature of the function is really close to your data.
You still have to somehow define the points on you plane for which you want to interpolate the data. I will have a look at this, my linear algebra lessons where a couple of years ago
I have the penultimate solution for this problem. Partially solved by using the second answer to Plot a plane based on a normal vector and a point in Matlab or matplotlib :
# coding: utf-8
import numpy as np
from matplotlib.pyplot import imshow,show
A=np.empty((64,64,64)) #This is the data array
def f(x,y):
return np.sin(x/(2*np.pi))+np.cos(y/(2*np.pi))
xx,yy= np.meshgrid(range(64), range(64))
for x in range(64):
A[:,:,x]=f(xx,yy)*np.cos(x/np.pi)
N=np.zeros((64,64))
"""This is the plane we cut from A.
It should be larger than 64, due to diagonal planes being larger.
Will be fixed."""
normal=np.array([-1,-1,1]) #Define cut plane here. Normal vector components restricted to integers
point=np.array([0,0,0])
d = -np.sum(point*normal)
def plane(x,y): # Get plane's z values
return (-normal[0]*x-normal[1]*y-d)/normal[2]
def getZZ(x,y): #Get z for all values x,y. If z>64 it's out of range
for i in x:
for j in y:
if plane(i,j)<64:
N[i,j]=A[i,j,plane(i,j)]
getZZ(range(64),range(64))
imshow(N, interpolation="Nearest")
show()
It's not the ultimate solution since the plot is not restricted to points having a z value, planes larger than 64 * 64 are not accounted for and the planes have to be defined at (0,0,0).
For the reduced requirements, I prepared a simple example
import numpy as np
import pylab as plt
data = np.arange((64**3))
data.resize((64,64,64))
def get_slice(volume, orientation, index):
orientation2slicefunc = {
"x" : lambda ar:ar[index,:,:],
"y" : lambda ar:ar[:,index,:],
"z" : lambda ar:ar[:,:,index]
}
return orientation2slicefunc[orientation](volume)
plt.subplot(221)
plt.imshow(get_slice(data, "x", 10), vmin=0, vmax=64**3)
plt.subplot(222)
plt.imshow(get_slice(data, "x", 39), vmin=0, vmax=64**3)
plt.subplot(223)
plt.imshow(get_slice(data, "y", 15), vmin=0, vmax=64**3)
plt.subplot(224)
plt.imshow(get_slice(data, "z", 25), vmin=0, vmax=64**3)
plt.show()
This leads to the following plot:
The main trick is dictionary mapping orienations to lambda-methods, which saves us from writing annoying if-then-else-blocks. Of course you can decide to give different names,
e.g., numbers, for the orientations.
Maybe this helps you.
Thorsten
P.S.: I didn't care about "IndexOutOfRange", for me it's o.k. to let this exception pop out since it is perfectly understandable in this context.
I had to do something similar for a MRI data enhancement:
Probably the code can be optimized but it works as it is.
My data is 3 dimension numpy array representing an MRI scanner. It has size [128,128,128] but the code can be modified to accept any dimensions. Also when the plane is outside the cube boundary you have to give the default values to the variable fill in the main function, in my case I choose: data_cube[0:5,0:5,0:5].mean()
def create_normal_vector(x, y,z):
normal = np.asarray([x,y,z])
normal = normal/np.sqrt(sum(normal**2))
return normal
def get_plane_equation_parameters(normal,point):
a,b,c = normal
d = np.dot(normal,point)
return a,b,c,d #ax+by+cz=d
def get_point_plane_proximity(plane,point):
#just aproximation
return np.dot(plane[0:-1],point) - plane[-1]
def get_corner_interesections(plane, cube_dim = 128): #to reduce the search space
#dimension is 128,128,128
corners_list = []
only_x = np.zeros(4)
min_prox_x = 9999
min_prox_y = 9999
min_prox_z = 9999
min_prox_yz = 9999
for i in range(cube_dim):
temp_min_prox_x=abs(get_point_plane_proximity(plane,np.asarray([i,0,0])))
# print("pseudo distance x: {0}, point: [{1},0,0]".format(temp_min_prox_x,i))
if temp_min_prox_x < min_prox_x:
min_prox_x = temp_min_prox_x
corner_intersection_x = np.asarray([i,0,0])
only_x[0]= i
temp_min_prox_y=abs(get_point_plane_proximity(plane,np.asarray([i,cube_dim,0])))
# print("pseudo distance y: {0}, point: [{1},{2},0]".format(temp_min_prox_y,i,cube_dim))
if temp_min_prox_y < min_prox_y:
min_prox_y = temp_min_prox_y
corner_intersection_y = np.asarray([i,cube_dim,0])
only_x[1]= i
temp_min_prox_z=abs(get_point_plane_proximity(plane,np.asarray([i,0,cube_dim])))
#print("pseudo distance z: {0}, point: [{1},0,{2}]".format(temp_min_prox_z,i,cube_dim))
if temp_min_prox_z < min_prox_z:
min_prox_z = temp_min_prox_z
corner_intersection_z = np.asarray([i,0,cube_dim])
only_x[2]= i
temp_min_prox_yz=abs(get_point_plane_proximity(plane,np.asarray([i,cube_dim,cube_dim])))
#print("pseudo distance z: {0}, point: [{1},{2},{2}]".format(temp_min_prox_yz,i,cube_dim))
if temp_min_prox_yz < min_prox_yz:
min_prox_yz = temp_min_prox_yz
corner_intersection_yz = np.asarray([i,cube_dim,cube_dim])
only_x[3]= i
corners_list.append(corner_intersection_x)
corners_list.append(corner_intersection_y)
corners_list.append(corner_intersection_z)
corners_list.append(corner_intersection_yz)
corners_list.append(only_x.min())
corners_list.append(only_x.max())
return corners_list
def get_points_intersection(plane,min_x,max_x,data_cube,shape=128):
fill = data_cube[0:5,0:5,0:5].mean() #this can be a parameter
extended_data_cube = np.ones([shape+2,shape,shape])*fill
extended_data_cube[1:shape+1,:,:] = data_cube
diag_image = np.zeros([shape,shape])
min_x_value = 999999
for i in range(shape):
for j in range(shape):
for k in range(int(min_x),int(max_x)+1):
current_value = abs(get_point_plane_proximity(plane,np.asarray([k,i,j])))
#print("current_value:{0}, val: [{1},{2},{3}]".format(current_value,k,i,j))
if current_value < min_x_value:
diag_image[i,j] = extended_data_cube[k,i,j]
min_x_value = current_value
min_x_value = 999999
return diag_image
The way it works is the following:
you create a normal vector:
for example [5,0,3]
normal1=create_normal_vector(5, 0,3) #this is only to normalize
then you create a point:
(my cube data shape is [128,128,128])
point = [64,64,64]
You calculate the plane equation parameters, [a,b,c,d] where ax+by+cz=d
plane1=get_plane_equation_parameters(normal1,point)
then to reduce the search space you can calculate the intersection of the plane with the cube:
corners1 = get_corner_interesections(plane1,128)
where corners1 = [intersection [x,0,0],intersection [x,128,0],intersection [x,0,128],intersection [x,128,128], min intersection [x,y,z], max intersection [x,y,z]]
With all these you can calculate the intersection between the cube and the plane:
image1 = get_points_intersection(plane1,corners1[-2],corners1[-1],data_cube)
Some examples:
normal is [1,0,0] point is [64,64,64]
normal is [5,1,0],[5,1,1],[5,0,1] point is [64,64,64]:
normal is [5,3,0],[5,3,3],[5,0,3] point is [64,64,64]:
normal is [5,-5,0],[5,-5,-5],[5,0,-5] point is [64,64,64]:
Thank you.
The other answers here do not appear to be very efficient with explicit loops over pixels or using scipy.interpolate.griddata, which is designed for unstructured input data. Here is an efficient (vectorized) and generic solution.
There is a pure numpy implementation (for nearest-neighbor "interpolation") and one for linear interpolation, which delegates the interpolation to scipy.ndimage.map_coordinates. (The latter function probably didn't exist in 2013, when this question was asked.)
import numpy as np
from scipy.ndimage import map_coordinates
def slice_datacube(cube, center, eXY, mXY, fill=np.nan, interp=True):
"""Get a 2D slice from a 3-D array.
Copyright: Han-Kwang Nienhuys, 2020.
License: any of CC-BY-SA, CC-BY, BSD, GPL, LGPL
Reference: https://stackoverflow.com/a/62733930/6228891
Parameters:
- cube: 3D array, assumed shape (nx, ny, nz).
- center: shape (3,) with coordinates of center.
can be float.
- eXY: unit vectors, shape (2, 3) - for X and Y axes of the slice.
(unit vectors must be orthogonal; normalization is optional).
- mXY: size tuple of output array (mX, mY) - int.
- fill: value to use for out-of-range points.
- interp: whether to interpolate (rather than using 'nearest')
Return:
- slice: array, shape (mX, mY).
"""
center = np.array(center, dtype=float)
assert center.shape == (3,)
eXY = np.array(eXY)/np.linalg.norm(eXY, axis=1)[:, np.newaxis]
if not np.isclose(eXY[0] # eXY[1], 0, atol=1e-6):
raise ValueError(f'eX and eY not orthogonal.')
# R: rotation matrix: data_coords = center + R # slice_coords
eZ = np.cross(eXY[0], eXY[1])
R = np.array([eXY[0], eXY[1], eZ], dtype=np.float32).T
# setup slice points P with coordinates (X, Y, 0)
mX, mY = int(mXY[0]), int(mXY[1])
Xs = np.arange(0.5-mX/2, 0.5+mX/2)
Ys = np.arange(0.5-mY/2, 0.5+mY/2)
PP = np.zeros((3, mX, mY), dtype=np.float32)
PP[0, :, :] = Xs.reshape(mX, 1)
PP[1, :, :] = Ys.reshape(1, mY)
# Transform to data coordinates (x, y, z) - idx.shape == (3, mX, mY)
if interp:
idx = np.einsum('il,ljk->ijk', R, PP) + center.reshape(3, 1, 1)
slice = map_coordinates(cube, idx, order=1, mode='constant', cval=fill)
else:
idx = np.einsum('il,ljk->ijk', R, PP) + (0.5 + center.reshape(3, 1, 1))
idx = idx.astype(np.int16)
# Find out which coordinates are out of range - shape (mX, mY)
badpoints = np.any([
idx[0, :, :] < 0,
idx[0, :, :] >= cube.shape[0],
idx[1, :, :] < 0,
idx[1, :, :] >= cube.shape[1],
idx[2, :, :] < 0,
idx[2, :, :] >= cube.shape[2],
], axis=0)
idx[:, badpoints] = 0
slice = cube[idx[0], idx[1], idx[2]]
slice[badpoints] = fill
return slice
# Demonstration
nx, ny, nz = 50, 70, 100
cube = np.full((nx, ny, nz), np.float32(1))
cube[nx//4:nx*3//4, :, :] += 1
cube[:, ny//2:ny*3//4, :] += 3
cube[:, :, nz//4:nz//2] += 7
cube[nx//3-2:nx//3+2, ny//2-2:ny//2+2, :] = 0 # black dot
Rz, Rx = np.pi/6, np.pi/4 # rotation angles around z and x
cz, sz = np.cos(Rz), np.sin(Rz)
cx, sx = np.cos(Rx), np.sin(Rx)
Rmz = np.array([[cz, -sz, 0], [sz, cz, 0], [0, 0, 1]])
Rmx = np.array([[1, 0, 0], [0, cx, -sx], [0, sx, cx]])
eXY = (Rmx # Rmz).T[:2]
slice = slice_datacube(
cube,
center=[nx/3, ny/2, nz*0.7],
eXY=eXY,
mXY=[80, 90],
fill=np.nan,
interp=False
)
import matplotlib.pyplot as plt
plt.close('all')
plt.imshow(slice.T) # imshow expects shape (mY, mX)
plt.colorbar()
Output (for interp=False):
For this test case (50x70x100 datacube, 80x90 slice size) the run time is 376 µs (interp=False) and 550 µs (interp=True) on my laptop.

Categories

Resources