如何使用matplotlib在python中绘制3D密度图

Question

我有一个大的（x，y，z）蛋白质位置数据​​集，并希望绘制高占有率的区域作为热图。理想情况下，输出应该与下面的体积可视化类似，但我不确定如何使用matplotlib实现此目的。

我最初的想法是将我的位置显示为3D散点图，并通过KDE为其密度着色。我用测试数据将其编码如下：

import numpy as np
from scipy import stats
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D 

mu, sigma = 0, 0.1 
x = np.random.normal(mu, sigma, 1000)
y = np.random.normal(mu, sigma, 1000)
z = np.random.normal(mu, sigma, 1000)

xyz = np.vstack([x,y,z])
density = stats.gaussian_kde(xyz)(xyz) 

idx = density.argsort()
x, y, z, density = x[idx], y[idx], z[idx], density[idx]

fig = plt.figure()
ax = fig.add_subplot(111, projection='3d')
ax.scatter(x, y, z, c=density)
plt.show()

这很好用！但是，我的真实数据包含数千个数据点，并且计算kde和散点图变得非常慢。

我的真实数据的一小部分样本：

我的研究表明，更好的选择是评估网格上的高斯kde。我只是不确定如何用3D：

import numpy as np
from scipy import stats
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D 

mu, sigma = 0, 0.1 
x = np.random.normal(mu, sigma, 1000)
y = np.random.normal(mu, sigma, 1000)

nbins = 50

xy = np.vstack([x,y])
density = stats.gaussian_kde(xy) 

xi, yi = np.mgrid[x.min():x.max():nbins*1j, y.min():y.max():nbins*1j]
di = density(np.vstack([xi.flatten(), yi.flatten()]))

fig = plt.figure()
ax = fig.add_subplot(111)
ax.pcolormesh(xi, yi, di.reshape(xi.shape))
plt.show() 

Answer 1

感谢mwaskon - 建议mayavi库。

我在mayavi中重建了密度散点图，如下所示：

import numpy as np
from scipy import stats
from mayavi import mlab

mu, sigma = 0, 0.1 
x = 10*np.random.normal(mu, sigma, 5000)
y = 10*np.random.normal(mu, sigma, 5000)
z = 10*np.random.normal(mu, sigma, 5000)

xyz = np.vstack([x,y,z])
kde = stats.gaussian_kde(xyz)
density = kde(xyz)

# Plot scatter with mayavi
figure = mlab.figure('DensityPlot')
pts = mlab.points3d(x, y, z, density, scale_mode='none', scale_factor=0.07)
mlab.axes()
mlab.show()

将scale_mode设置为＆＃39; none＆＃39;防止字形与密度向量成比例缩放。此外，对于大型数据集，我禁用了场景渲染并使用了遮罩来减少点数。

# Plot scatter with mayavi
figure = mlab.figure('DensityPlot')
figure.scene.disable_render = True

pts = mlab.points3d(x, y, z, density, scale_mode='none', scale_factor=0.07) 
mask = pts.glyph.mask_points
mask.maximum_number_of_points = x.size
mask.on_ratio = 1
pts.glyph.mask_input_points = True

figure.scene.disable_render = False 
mlab.axes()
mlab.show()

接下来，评估网格上的高斯kde：

import numpy as np
from scipy import stats
from mayavi import mlab

mu, sigma = 0, 0.1 
x = 10*np.random.normal(mu, sigma, 5000)
y = 10*np.random.normal(mu, sigma, 5000)    
z = 10*np.random.normal(mu, sigma, 5000)

xyz = np.vstack([x,y,z])
kde = stats.gaussian_kde(xyz)

# Evaluate kde on a grid
xmin, ymin, zmin = x.min(), y.min(), z.min()
xmax, ymax, zmax = x.max(), y.max(), z.max()
xi, yi, zi = np.mgrid[xmin:xmax:30j, ymin:ymax:30j, zmin:zmax:30j]
coords = np.vstack([item.ravel() for item in [xi, yi, zi]]) 
density = kde(coords).reshape(xi.shape)

# Plot scatter with mayavi
figure = mlab.figure('DensityPlot')

grid = mlab.pipeline.scalar_field(xi, yi, zi, density)
min = density.min()
max=density.max()
mlab.pipeline.volume(grid, vmin=min, vmax=min + .5*(max-min))

mlab.axes()
mlab.show()

作为最后的改进，我通过并行调用kde函数加快了Kensity密度函数的评估。

import numpy as np
from scipy import stats
from mayavi import mlab
import multiprocessing

def calc_kde(data):
    return kde(data.T)

mu, sigma = 0, 0.1 
x = 10*np.random.normal(mu, sigma, 5000)
y = 10*np.random.normal(mu, sigma, 5000)
z = 10*np.random.normal(mu, sigma, 5000)

xyz = np.vstack([x,y,z])
kde = stats.gaussian_kde(xyz)

# Evaluate kde on a grid
xmin, ymin, zmin = x.min(), y.min(), z.min()
xmax, ymax, zmax = x.max(), y.max(), z.max()
xi, yi, zi = np.mgrid[xmin:xmax:30j, ymin:ymax:30j, zmin:zmax:30j]
coords = np.vstack([item.ravel() for item in [xi, yi, zi]]) 

# Multiprocessing
cores = multiprocessing.cpu_count()
pool = multiprocessing.Pool(processes=cores)
results = pool.map(calc_kde, np.array_split(coords.T, 2))
density = np.concatenate(results).reshape(xi.shape)

# Plot scatter with mayavi
figure = mlab.figure('DensityPlot')

grid = mlab.pipeline.scalar_field(xi, yi, zi, density)
min = density.min()
max=density.max()
mlab.pipeline.volume(grid, vmin=min, vmax=min + .5*(max-min))

mlab.axes()
mlab.show()