Python：保留来自 matplotlib 热图及其图例的 Numpy NaN 值
Python: Leave Numpy NaN values from matplotlib heatmap and its legend
我有一个需要绘制成热图的 numpy 数组。 numpy 数组还将包含我需要从绘图中排除的 NaN 值。在其他帖子中有人告诉我，numpy 会自动屏蔽图中的 NaN 值，但不知何故它对我不起作用。这是一个示例代码
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()
情节看起来像
很明显，这与没有 Nan 的情节非常不同，看起来像
我想完全避免图例中的 NaN 值，最好用一些符号标记它，例如 X。我怎样才能达到同样的效果？
nans 干扰 pcolor 确定包含在 data 中的值的范围，因为
In [72]: data.min(), data.max()
Out[72]: (nan, nan)
您可以通过使用 np.nanmin 和 np.nanmax 自行声明值的范围来解决此问题，以找到 data:[=30 中的最小和最大非 NaN 值=]
heatmap = ax.pcolor(data, cmap=plt.cm.seismic,
vmin=np.nanmin(data), vmax=np.nanmax(data))
因为
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()
另一个选项（基于 Joe Kington 的
解决方案) 将是绘制
data 为 NaN 时带有影线标记的矩形补丁。
以上示例显示 pcolor 单元格中的颜色为 NaN 值
尽管 NaN 是非常负的数字。相反，如果你传递 pcolor a
遮罩阵列、pcolor 使遮罩区域保持透明。因此，您可以绘制
坐标轴背景补丁 ax.patch 上的影线以显示影线标记
在蒙版区域。
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))
# (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类型的影线标记，比如一种用于 NaN，另一种用于负值，那么您可以使用循环来添加影线矩形：
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))
# (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()
我有一个需要绘制成热图的 numpy 数组。 numpy 数组还将包含我需要从绘图中排除的 NaN 值。在其他帖子中有人告诉我，numpy 会自动屏蔽图中的 NaN 值，但不知何故它对我不起作用。这是一个示例代码
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()
情节看起来像
很明显，这与没有 Nan 的情节非常不同，看起来像
我想完全避免图例中的 NaN 值，最好用一些符号标记它，例如 X。我怎样才能达到同样的效果？
nans 干扰 pcolor 确定包含在 data 中的值的范围，因为
In [72]: data.min(), data.max()
Out[72]: (nan, nan)
您可以通过使用 np.nanmin 和 np.nanmax 自行声明值的范围来解决此问题，以找到 data:[=30 中的最小和最大非 NaN 值=]
heatmap = ax.pcolor(data, cmap=plt.cm.seismic,
vmin=np.nanmin(data), vmax=np.nanmax(data))
因为
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()
另一个选项（基于 Joe Kington 的
解决方案) 将是绘制
data 为 NaN 时带有影线标记的矩形补丁。
以上示例显示 pcolor 单元格中的颜色为 NaN 值
尽管 NaN 是非常负的数字。相反，如果你传递 pcolor a
遮罩阵列、pcolor 使遮罩区域保持透明。因此，您可以绘制
坐标轴背景补丁 ax.patch 上的影线以显示影线标记
在蒙版区域。
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))
# (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类型的影线标记，比如一种用于 NaN，另一种用于负值，那么您可以使用循环来添加影线矩形：
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))
# (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()