python - 计算不规则间距点密度的有效方法

Question

我正在尝试生成有助于识别热点的 map 叠加图像，即 map 上具有高密度数据点的区域。我尝试过的所有方法都不足以满足我的需求。注意:我忘了提到该算法应该在低缩放场景和高缩放场景(或低和高数据点密度)下都能很好地工作。

我查看了 numpy、pyplot 和 scipy 库，我能找到的最接近的是 numpy.histogram2d。如下图所示， histogram2d 输出相当粗糙。 (每张图片都包含覆盖热图的点以便更好地理解)

我的第二次尝试是遍历所有数据点，然后计算热点值作为距离的函数。这产生了一个更好看的图像，但是在我的应用程序中使用它太慢了。因为它是 O(n)，所以它在 100 个点上工作正常，但是当我使用我的 30000 个点的实际数据集时就崩溃了。

我最后的尝试是将数据存储在 KDTree 中，并使用最接近的 5 个点来计算热点值。这个算法是 O(1)，对于大型数据集来说要快得多。它仍然不够快，生成 256x256 位图大约需要 20 秒，我希望这在 1 秒左右发生。

编辑

6502 提供的 boxsum 平滑解决方案在所有缩放级别都运行良好，并且比我原来的方法快得多。

Luke 和 Neil G 建议的高斯滤波器解决方案是最快的。

您可以在下面看到所有四种方法，总共使用 1000 个数据点，在 3 倍缩放下大约有 60 个点可见。

生成我最初的 3 次尝试的完整代码、6502 提供的 boxsum 平滑解决方案和 Luke 建议的高斯滤波器(经过改进以更好地处理边缘并允许放大)在这里:

import matplotlib
import numpy as np
from matplotlib.mlab import griddata
import matplotlib.cm as cm
import matplotlib.pyplot as plt
import math
from scipy.spatial import KDTree
import time
import scipy.ndimage as ndi


def grid_density_kdtree(xl, yl, xi, yi, dfactor):
    zz = np.empty([len(xi),len(yi)], dtype=np.uint8)
    zipped = zip(xl, yl)
    kdtree = KDTree(zipped)
    for xci in range(0, len(xi)):
        xc = xi[xci]
        for yci in range(0, len(yi)):
            yc = yi[yci]
            density = 0.
            retvalset = kdtree.query((xc,yc), k=5)
            for dist in retvalset[0]:
                density = density + math.exp(-dfactor * pow(dist, 2)) / 5
            zz[yci][xci] = min(density, 1.0) * 255
    return zz

def grid_density(xl, yl, xi, yi):
    ximin, ximax = min(xi), max(xi)
    yimin, yimax = min(yi), max(yi)
    xxi,yyi = np.meshgrid(xi,yi)
    #zz = np.empty_like(xxi)
    zz = np.empty([len(xi),len(yi)])
    for xci in range(0, len(xi)):
        xc = xi[xci]
        for yci in range(0, len(yi)):
            yc = yi[yci]
            density = 0.
            for i in range(0,len(xl)):
                xd = math.fabs(xl[i] - xc)
                yd = math.fabs(yl[i] - yc)
                if xd < 1 and yd < 1:
                    dist = math.sqrt(math.pow(xd, 2) + math.pow(yd, 2))
                    density = density + math.exp(-5.0 * pow(dist, 2))
            zz[yci][xci] = density
    return zz

def boxsum(img, w, h, r):
    st = [0] * (w+1) * (h+1)
    for x in xrange(w):
        st[x+1] = st[x] + img[x]
    for y in xrange(h):
        st[(y+1)*(w+1)] = st[y*(w+1)] + img[y*w]
        for x in xrange(w):
            st[(y+1)*(w+1)+(x+1)] = st[(y+1)*(w+1)+x] + st[y*(w+1)+(x+1)] - st[y*(w+1)+x] + img[y*w+x]
    for y in xrange(h):
        y0 = max(0, y - r)
        y1 = min(h, y + r + 1)
        for x in xrange(w):
            x0 = max(0, x - r)
            x1 = min(w, x + r + 1)
            img[y*w+x] = st[y0*(w+1)+x0] + st[y1*(w+1)+x1] - st[y1*(w+1)+x0] - st[y0*(w+1)+x1]

def grid_density_boxsum(x0, y0, x1, y1, w, h, data):
    kx = (w - 1) / (x1 - x0)
    ky = (h - 1) / (y1 - y0)
    r = 15
    border = r * 2
    imgw = (w + 2 * border)
    imgh = (h + 2 * border)
    img = [0] * (imgw * imgh)
    for x, y in data:
        ix = int((x - x0) * kx) + border
        iy = int((y - y0) * ky) + border
        if 0 <= ix < imgw and 0 <= iy < imgh:
            img[iy * imgw + ix] += 1
    for p in xrange(4):
        boxsum(img, imgw, imgh, r)
    a = np.array(img).reshape(imgh,imgw)
    b = a[border:(border+h),border:(border+w)]
    return b

def grid_density_gaussian_filter(x0, y0, x1, y1, w, h, data):
    kx = (w - 1) / (x1 - x0)
    ky = (h - 1) / (y1 - y0)
    r = 20
    border = r
    imgw = (w + 2 * border)
    imgh = (h + 2 * border)
    img = np.zeros((imgh,imgw))
    for x, y in data:
        ix = int((x - x0) * kx) + border
        iy = int((y - y0) * ky) + border
        if 0 <= ix < imgw and 0 <= iy < imgh:
            img[iy][ix] += 1
    return ndi.gaussian_filter(img, (r,r))  ## gaussian convolution

def generate_graph():    
    n = 1000
    # data points range
    data_ymin = -2.
    data_ymax = 2.
    data_xmin = -2.
    data_xmax = 2.
    # view area range
    view_ymin = -.5
    view_ymax = .5
    view_xmin = -.5
    view_xmax = .5
    # generate data
    xl = np.random.uniform(data_xmin, data_xmax, n)    
    yl = np.random.uniform(data_ymin, data_ymax, n)
    zl = np.random.uniform(0, 1, n)

    # get visible data points
    xlvis = []
    ylvis = []
    for i in range(0,len(xl)):
        if view_xmin < xl[i] < view_xmax and view_ymin < yl[i] < view_ymax:
            xlvis.append(xl[i])
            ylvis.append(yl[i])

    fig = plt.figure()


    # plot histogram
    plt1 = fig.add_subplot(221)
    plt1.set_axis_off()
    t0 = time.clock()
    zd, xe, ye = np.histogram2d(yl, xl, bins=10, range=[[view_ymin, view_ymax],[view_xmin, view_xmax]], normed=True)
    plt.title('numpy.histogram2d - '+str(time.clock()-t0)+"sec")
    plt.imshow(zd, origin='lower', extent=[view_xmin, view_xmax, view_ymin, view_ymax])
    plt.scatter(xlvis, ylvis)


    # plot density calculated with kdtree
    plt2 = fig.add_subplot(222)
    plt2.set_axis_off()
    xi = np.linspace(view_xmin, view_xmax, 256)
    yi = np.linspace(view_ymin, view_ymax, 256)
    t0 = time.clock()
    zd = grid_density_kdtree(xl, yl, xi, yi, 70)
    plt.title('function of 5 nearest using kdtree\n'+str(time.clock()-t0)+"sec")
    cmap=cm.jet
    A = (cmap(zd/256.0)*255).astype(np.uint8)
    #A[:,:,3] = zd  
    plt.imshow(A , origin='lower', extent=[view_xmin, view_xmax, view_ymin, view_ymax])
    plt.scatter(xlvis, ylvis)

    # gaussian filter
    plt3 = fig.add_subplot(223)
    plt3.set_axis_off()
    t0 = time.clock()
    zd = grid_density_gaussian_filter(view_xmin, view_ymin, view_xmax, view_ymax, 256, 256, zip(xl, yl))
    plt.title('ndi.gaussian_filter - '+str(time.clock()-t0)+"sec")
    plt.imshow(zd , origin='lower', extent=[view_xmin, view_xmax, view_ymin, view_ymax])
    plt.scatter(xlvis, ylvis)

    # boxsum smoothing
    plt3 = fig.add_subplot(224)
    plt3.set_axis_off()
    t0 = time.clock()
    zd = grid_density_boxsum(view_xmin, view_ymin, view_xmax, view_ymax, 256, 256, zip(xl, yl))
    plt.title('boxsum smoothing - '+str(time.clock()-t0)+"sec")
    plt.imshow(zd, origin='lower', extent=[view_xmin, view_xmax, view_ymin, view_ymax])
    plt.scatter(xlvis, ylvis)

if __name__=='__main__':
    generate_graph()
    plt.show()

Answer 1

这种方法与之前的一些答案类似:为每个点增加一个像素，然后使用高斯滤波器对图像进行平滑处理。在我使用了 6 年的笔记本电脑上运行 256x256 图像大约需要 350 毫秒。

import numpy as np
import scipy.ndimage as ndi

data = np.random.rand(30000,2)           ## create random dataset
inds = (data * 255).astype('uint')       ## convert to indices

img = np.zeros((256,256))                ## blank image
for i in xrange(data.shape[0]):          ## draw pixels
    img[inds[i,0], inds[i,1]] += 1

img = ndi.gaussian_filter(img, (10,10))