I have three 1D arrays (A, B, C) of equal length/size. I plot a scatter plot of B vs. A where I color each scatter plot bullet by the corresponding value in the C array (see the code below).
# Imports
import matplotlib.cm as cm
import matplotlib.colors as colors
import matplotlib as mpl
import matplotlib.pyplot as plt
import numpy as np
# Create the Arrays
A = 10 * np.random.random_sample((20, 20))
B = 10 * np.random.random_sample((20, 20))
C = 100 * np.random.random_sample((20, 20))
A = A.reshape(20*20)
B = B.reshape(20*20)
C = C.reshape(20*20)
# Create the Colormap and Define Boundaries
cmap_C = cm.jet
cmap_C.set_bad(color='white')
bounds_C = np.arange(0, 110, 10)
norm_C = mpl.colors.BoundaryNorm(bounds_C, cmap_C.N)
# Plot the Figure
plt.figure()
plt.scatter(A, B, c=C, marker='o', s=100, cmap=cmap_C, norm=norm_C)
plt.xlim([-1, 11])
plt.ylim([-1, 11])
plt.xticks(np.arange(0, 11, 1))
plt.yticks(np.arange(0, 11, 1))
plt.xlabel('A')
plt.ylabel('B')
plt.grid()
plt.colorbar(label='Value of C')
plt.show()
Some bullets overlap in the figure so we cannot see them clearly. Therfore, next I now want to compute and plot the mean C value of all scatter plot bullets within each 1 integer x 1 integer bin in the figure so that each square grid point is colored by one single color (these bins are illustrated by the figure gridding). How can I do this?
Below is a solution that works for my purposes.
# Imports
import matplotlib.cm as cm
import matplotlib.colors as colors
import matplotlib as mpl
import matplotlib.pyplot as plt
import numpy as np
from zipfile import ZipFile
# Create the Arrays
xx = 5
yy = 5
A = 10 * np.random.random_sample((xx, yy))
B = 10 * np.random.random_sample((xx, yy))
C = 100 * np.random.random_sample((xx, yy))
A = A.reshape(xx*yy)
B = B.reshape(xx*yy)
C = C.reshape(xx*yy)
color_map = {(x, y): color for x, y, color in zip(A,B,C)}
xedges = np.arange(11)
yedges = np.arange(11)
H, xedges, yedges = np.histogram2d(A, B, bins=(xedges, yedges))
HT = H.T
ca = np.asarray(list(color_map))
print(ca)
cai = ca.astype(int)
print(cai)
# Extracting all dictionary values using loop + keys()
res = []
for key in color_map.keys() :
res.append(color_map[key])
res = np.asarray(res)
resi = res.astype(int)
print(resi)
BMC = np.zeros([10, 10])
for i in np.arange(len(resi)):
BMC[cai[i,1],cai[i,0]] = BMC[cai[i,1],cai[i,0]] + resi[i]
print(cai[i])
print(resi[i])
print(BMC[cai[i,1],cai[i,0]])
print(HT)
print(BMC)
BMC = BMC/HT
print(BMC)
# Create the Colormap and Define Boundaries
cmap_C = cm.jet
cmap_C.set_bad(color='white')
bounds_C = np.arange(-5, 115, 10)
norm_C = mpl.colors.BoundaryNorm(bounds_C, cmap_C.N)
cmap_hist2d = cm.CMRmap_r
cmap_hist2d.set_bad(color='white')
bounds_hist2d = np.arange(-0.5, 4.5, 1)
norm_hist2d = mpl.colors.BoundaryNorm(bounds_hist2d, cmap_hist2d.N)
cmap_C = cm.jet
cmap_C.set_bad(color='white')
BMC_plot = np.ma.array ( BMC, mask=np.isnan(BMC)) # Mask NaN
bounds_C = np.arange(-5, 115, 10)
norm_C = mpl.colors.BoundaryNorm(bounds_C, cmap_C.N)
plt.subplot(311)
plt.scatter(A, B, c=C, marker='o', s=100, cmap=cmap_C, norm=norm_C)
plt.xlim([-1, 11])
plt.ylim([-1, 11])
plt.xticks(np.arange(0, 11, 1))
plt.yticks(np.arange(0, 11, 1))
plt.ylabel('B')
plt.grid()
plt.colorbar(label='Value of C', ticks=[0, 10, 20, 30, 40, 50, 60, 70, 80, 90, 100])
plt.subplot(312)
x, y = np.meshgrid(xedges, yedges)
plt.pcolor(x, y, HT, cmap=cmap_hist2d, norm=norm_hist2d)
plt.xlim([-1, 11])
plt.ylim([-1, 11])
plt.xticks(np.arange(0, 11, 1))
plt.yticks(np.arange(0, 11, 1))
plt.ylabel('B')
plt.grid()
plt.colorbar(label='Number of Data in Bin', ticks=[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10])
plt.subplot(313)
plt.pcolor(x, y, BMC_plot, cmap=cmap_C, norm=norm_C)
plt.xlim([-1, 11])
plt.ylim([-1, 11])
plt.xticks(np.arange(0, 11, 1))
plt.yticks(np.arange(0, 11, 1))
plt.xlabel('A')
plt.ylabel('B')
plt.grid()
plt.colorbar(label='Bin-Mean C Value', ticks=[0, 10, 20, 30, 40, 50, 60, 70, 80, 90, 100])
plt.show()