Python：从matplotlib热图及其图例中保留Numpy NaN值

Question

我有一个numpy数组，需要将其绘制为热图。numpy数组还将包含NaN值，我需要从绘图中排除这些值。在其他帖子中，有人告诉我numpy会自动遮盖图中的NaN值，但是它对我不起作用。这是示例代码

column_labels = list('ABCDEFGH')
row_labels = list('WXYZ')
fig, ax = plt.subplots()
data = np.array([[ 0.96753494,  0.52349944,  0.0254628 ,  0.5104103 ],
         [ 0.07320069,  0.91278731,  0.97094436,  0.70533351],
         [ 0.30162006,  0.49068337,  0.41837729,  0.71139215],
         [ 0.19786101,  0.15882713,  0.59028841,  0.06242765],
         [ 0.51505872,  0.07798389,  0.58790067,  0.44782683],
         [ 0.68975694,  0.53535385,  0.15696023,  0.35641951],
         [ 0.66481995,  0.03576846,  0.9623601 ,  0.96006395],
         [ 0.45865404,  0.50433582,  0.18182575,  0.35126449],])

data[3,:] = np.nan
heatmap = ax.pcolor(data, cmap=plt.cm.seismic)

fig.colorbar(heatmap)
# put the major ticks at the middle of each cell
ax.set_xticks(np.arange(data.shape[1])+0.5, minor=False)
ax.set_yticks(np.arange(data.shape[0])+0.5, minor=False)

# want a more natural, table-like display
ax.invert_yaxis()
ax.xaxis.tick_top()

ax.set_xticklabels(row_labels, minor=False)
ax.set_yticklabels(column_labels, minor=False)
plt.show()

我想完全避免图例中的NaN值，最好用一些符号（例如 X） 标记它。我怎样才能做到这一点？

Answer 1

所述nans干扰pcolor确定包含在值的范围data，因为

In [72]: data.min(), data.max()
Out[72]: (nan, nan)

您可以通过声明自己使用的值范围来解决此问题，np.nanmin并np.nanmax在以下位置找到最小和最大的非NaN值data：

heatmap = ax.pcolor(data, cmap=plt.cm.seismic, 
                    vmin=np.nanmin(data), vmax=np.nanmax(data))

以来

In [73]: np.nanmin(data), np.nanmax(data)
Out[73]: (0.025462800000000001, 0.97094435999999995)

import numpy as np
import matplotlib.pyplot as plt

column_labels = list('ABCDEFGH')
row_labels = list('WXYZ')
fig, ax = plt.subplots()
data = np.array([[ 0.96753494,  0.52349944,  0.0254628 ,  0.5104103 ],
         [ 0.07320069,  0.91278731,  0.97094436,  0.70533351],
         [ 0.30162006,  0.49068337,  0.41837729,  0.71139215],
         [ 0.19786101,  0.15882713,  0.59028841,  0.06242765],
         [ 0.51505872,  0.07798389,  0.58790067,  0.44782683],
         [ 0.68975694,  0.53535385,  0.15696023,  0.35641951],
         [ 0.66481995,  0.03576846,  0.9623601 ,  0.96006395],
         [ 0.45865404,  0.50433582,  0.18182575,  0.35126449],])

data[3,:] = np.nan
heatmap = ax.pcolor(data, cmap=plt.cm.seismic, 
                    vmin=np.nanmin(data), vmax=np.nanmax(data))
heatmap.cmap.set_under('black')

bar = fig.colorbar(heatmap, extend='both')

# put the major ticks at the middle of each cell
ax.set_xticks(np.arange(data.shape[1])+0.5, minor=False)
ax.set_yticks(np.arange(data.shape[0])+0.5, minor=False)

# want a more natural, table-like display
ax.invert_yaxis()
ax.xaxis.tick_top()

ax.set_xticklabels(row_labels, minor=False)
ax.set_yticklabels(column_labels, minor=False)
plt.show()

另一个选择基于JoeKington的解决方案是在dataNaN处绘制带有阴影线的矩形补丁。

上面的示例显示，pcolor具有NaN值的单元格中的颜色好像NaN都是非常负的数字。相反，如果你传递pcolor一个 蒙面阵列
，pcolor叶蒙版区域透明。因此，您可以在轴背景色块上绘制阴影ax.patch，以在被遮罩的区域上显示阴影。

import numpy as np
import matplotlib.pyplot as plt
import matplotlib.patches as mpatches

column_labels = list('ABCDEFGH')
row_labels = list('WXYZ')
fig, ax = plt.subplots()
data = np.array([[ 0.96753494,  0.52349944,  0.0254628 ,  0.5104103 ],
         [ 0.07320069,  0.91278731,  0.97094436,  0.70533351],
         [ 0.30162006,  0.49068337,  0.41837729,  0.71139215],
         [ 0.19786101,  0.15882713,  0.59028841,  0.06242765],
         [ 0.51505872,  0.07798389,  0.58790067,  0.44782683],
         [ 0.68975694,  0.53535385,  0.15696023,  0.35641951],
         [ 0.66481995,  0.03576846,  0.9623601 ,  0.96006395],
         [ 0.45865404,  0.50433582,  0.18182575,  0.35126449],])

data[3,:] = np.nan
data = np.ma.masked_invalid(data)

heatmap = ax.pcolor(data, cmap=plt.cm.seismic, 
                    vmin=np.nanmin(data), vmax=np.nanmax(data))
# https://stackoverflow.com/a/16125413/190597 (Joe Kington)
ax.patch.set(hatch='x', edgecolor='black')
fig.colorbar(heatmap)

# put the major ticks at the middle of each cell
ax.set_xticks(np.arange(data.shape[1])+0.5, minor=False)
ax.set_yticks(np.arange(data.shape[0])+0.5, minor=False)

# want a more natural, table-like display
ax.invert_yaxis()
ax.xaxis.tick_top()

ax.set_xticklabels(row_labels, minor=False)
ax.set_yticklabels(column_labels, minor=False)
plt.show()

如果您希望使用多种阴影线标记，例如对NaN说一种，对负值说另一种，那么您可以使用循环来添加阴影阴影的矩形：

import numpy as np
import matplotlib.pyplot as plt
import matplotlib.patches as mpatches

column_labels = list('ABCDEFGH')
row_labels = list('WXYZ')
fig, ax = plt.subplots()
data = np.array([[ 0.96753494,  0.52349944,  0.0254628 ,  0.5104103 ],
         [ 0.07320069,  0.91278731,  0.97094436,  0.70533351],
         [ 0.30162006,  0.49068337,  0.41837729,  0.71139215],
         [ 0.19786101,  0.15882713,  0.59028841,  0.06242765],
         [ 0.51505872,  0.07798389,  0.58790067,  0.44782683],
         [ 0.68975694,  0.53535385,  0.15696023,  0.35641951],
         [ 0.66481995,  0.03576846,  0.9623601 ,  0.96006395],
         [ 0.45865404,  0.50433582,  0.18182575,  0.35126449],])
data -= 0.5
data[3,:] = np.nan
data = np.ma.masked_invalid(data)
heatmap = ax.pcolor(data, cmap=plt.cm.seismic, 
                    vmin=np.nanmin(data), vmax=np.nanmax(data))

# https://stackoverflow.com/a/16125413/190597 (Joe Kington)
ax.patch.set(hatch='x', edgecolor='black')

# draw a hatched rectangle wherever the data is negative
# http://matthiaseisen.com/pp/patterns/p0203/
mask = data < 0
for j, i in np.column_stack(np.where(mask)):
      ax.add_patch(
          mpatches.Rectangle(
              (i, j),     # (x,y)
              1,          # width
              1,          # height
              fill=False, 
              edgecolor='blue',
              snap=False,
              hatch='x' # the more slashes, the denser the hash lines 
          ))

fig.colorbar(heatmap)

# put the major ticks at the middle of each cell
ax.set_xticks(np.arange(data.shape[1])+0.5, minor=False)
ax.set_yticks(np.arange(data.shape[0])+0.5, minor=False)

# want a more natural, table-like display
ax.invert_yaxis()
ax.xaxis.tick_top()

ax.set_xticklabels(row_labels, minor=False)
ax.set_yticklabels(column_labels, minor=False)
plt.show()