seaborn 热图 auto-ordering 标签以平滑颜色偏移

seaborn heatmap auto-ordering labels to smoothen color shifts

我想知道是否有 built-in 功能或至少有 'smart' 方式来根据它们的值结合 seaborn 热图对 x- 和 y-labels 进行排序。

假设无序热图如下所示:

但是,目标是重新排序颜色偏移的标签 'smoothened'。之后应该看起来更像:

感谢您的建议!

此致

第二个图按 x 和 y 轴标签排序,而不是按值排序。您将无法让随机数据看起来像有序数据。您可以按一行和一列的值对数据进行排序,但其余数据将是固定的。这是绘制热图的代码,该热图按第 0 行和第 0 列的值排序。请注意图中间的 "cross":

import numpy as np; np.random.seed(0)
import seaborn as sns; sns.set()

uniform_data = np.random.rand(10, 12)
df = pd.DataFrame(uniform_data)
df2 = df.sort_values(by=0).T.sort_values(by=0).T
ax = sns.heatmap(df2)

需要以某种方式量化 "smoothened colorshifts"。为此,可以定义成本函数。在最简单的情况下,这可能是相邻像素之间差异的总和。如果总和很小,则相邻像素的颜色差异很小。

然后可以随机交换矩阵中的列和行,并检查是否产生了更小的成本。迭代地执行此操作,会在某个时候产生平滑的热图。然而,这当然取决于初始热图中的随机程度。对于完全随机的像素,预计不会有太多优化。

下面class实现了这样的优化。这将需要 nrand 个不同的起始排列,并且对于每个排列,进行 niter 次交换。最好的结果被存储并可以通过 .get_opt.

检索
import matplotlib.pyplot as plt
import numpy as np

class ReOrder():
    def __init__(self, array, nrand=2, niter=800):
        self.a = array
        self.indi = np.arange(self.a.shape[0])
        self.indj = np.arange(self.a.shape[1])
        self.i = np.arange(self.a.shape[0])
        self.j = np.arange(self.a.shape[1])
        self.nrand = nrand
        self.niter = niter

    def apply(self, a, i, j):
        return a[:,j][i,:]

    def get_opt(self):
        return self.apply(self.a, self.i, self.j)

    def get_labels(self, x=None, y=None):
        if x is None:
            x = self.indj
        if y is None:
            y = self.indi
        return np.array(x)[self.j], np.array(y)[self.i]

    def cost(self, a=None):
        if a is None:
            a = self.get_opt()
        m = a[1:-1, 1:-1]
        b = 0.5 * ((m - a[0:-2, 0:-2])**2 + \
                   (m - a[2:  , 2:  ])**2 + \
                   (m - a[0:-2, 2:  ])**2 + \
                   (m - a[2:  , 0:-2])**2) + \
            (m - a[0:-2, 1:-1])**2 + \
            (m - a[1:-1, 0:-2])**2 + \
            (m - a[2:  , 1:-1])**2 + \
            (m - a[1:-1, 2:  ])**2 
        return b.sum()

    def randomize(self):
        newj = np.random.permutation(self.a.shape[1])
        newi = np.random.permutation(self.a.shape[0])
        return newi, newj

    def compare(self, i1, j1, i2, j2, a=None):
        if a is None:
            a = self.a
        if self.cost(self.apply(a,i1,j1)) < self.cost(self.apply(a,i2,j2)):
            return i1, j1
        else:
            return i2, j2

    def rowswap(self, i, j):
        rows = np.random.choice(self.indi, replace=False, size=2)
        ir = np.copy(i)
        ir[rows] = ir[rows[::-1]]
        return ir, j

    def colswap(self, i, j):
        cols = np.random.choice(self.indj, replace=False, size=2)
        jr = np.copy(j)
        jr[cols] = jr[cols[::-1]]
        return i, jr

    def swap(self, i, j):
        ic, jc = self.rowswap(i,j)
        ir, jr = self.colswap(i,j)
        io, jo = self.compare(ic,jc, ir,jr)
        return self.compare(i,j, io,jo)

    def optimize(self, nrand=None, niter=None):
        nrand = nrand or self.nrand
        niter = niter or self.niter
        i,j = self.i, self.j
        for kk in range(niter):
            i,j = self.swap(i,j)
        self.i, self.j = self.compare(i,j, self.i, self.j)
        print(self.cost())
        for ii in range(nrand):
            i,j = self.randomize()
            for kk in range(niter):
                i,j = self.swap(i,j)
            self.i, self.j = self.compare(i,j, self.i, self.j)
            print(self.cost())
        print("finished")

所以让我们取两个起始数组,

def get_sample_ord():
    x,y = np.meshgrid(np.arange(12), np.arange(10))
    z = x+y
    j = np.random.permutation(12)
    i = np.random.permutation(10)
    return z[:,j][i,:] 

def get_sample():
    return np.random.randint(0,120,size=(10,12))

和运行就通过上面的class.

def reorder_plot(nrand=4, niter=10000):
    fig, ((ax1, ax2),(ax3,ax4)) = plt.subplots(nrows=2, ncols=2, 
                                               constrained_layout=True)
    fig.suptitle("nrand={}, niter={}".format(nrand, niter))

    z1 = get_sample()
    r1 = ReOrder(z1)
    r1.optimize(nrand=nrand, niter=niter)
    ax1.imshow(z1)
    ax3.imshow(r1.get_opt())
    xl, yl = r1.get_labels()
    ax1.set(xticks = np.arange(z1.shape[1]),
            yticks = np.arange(z1.shape[0]),
            title=f"Start, cost={r1.cost(z1)}")
    ax3.set(xticks = np.arange(z1.shape[1]), xticklabels=xl, 
            yticks = np.arange(z1.shape[0]), yticklabels=yl, 
            title=f"Optimized, cost={r1.cost()}")

    z2 = get_sample_ord()   
    r2 = ReOrder(z2)
    r2.optimize(nrand=nrand, niter=niter)
    ax2.imshow(z2)
    ax4.imshow(r2.get_opt())
    xl, yl = r2.get_labels()
    ax2.set(xticks = np.arange(z2.shape[1]),
            yticks = np.arange(z2.shape[0]),
            title=f"Start, cost={r2.cost(z2)}")
    ax4.set(xticks = np.arange(z2.shape[1]), xticklabels=xl, 
            yticks = np.arange(z2.shape[0]), yticklabels=yl, 
            title=f"Optimized, cost={r2.cost()}")


reorder_plot(nrand=4, niter=10000)

plt.show()

完全随机的矩阵(左列)只平滑了很少 - 它看起来仍然有点排序。成本值仍然很高。然而,一个不那么随机的矩阵被完美平滑并且成本显着降低。