seaborn 热图中的离散图例
Discrete legend in seaborn heatmap plot
我正在使用此处提供的数据使用 seaborn 和 pandas 构建此热图。
代码：
import pandas
import seaborn.apionly as sns
# Read in csv file
df_trans = pandas.read_csv('LUH2_trans_matrix.csv')
sns.set(font_scale=0.8)
cmap = sns.cubehelix_palette(start=2.8, rot=.1, light=0.9, as_cmap=True)
cmap.set_under('gray') # 0 values in activity matrix are shown in gray (inactive transitions)
df_trans = df_trans.set_index(['Unnamed: 0'])
ax = sns.heatmap(df_trans, cmap=cmap, linewidths=.5, linecolor='lightgray')
# X - Y axis labels
ax.set_ylabel('FROM')
ax.set_xlabel('TO')
# Rotate tick labels
locs, labels = plt.xticks()
plt.setp(labels, rotation=0)
locs, labels = plt.yticks()
plt.setp(labels, rotation=0)
# revert matplotlib params
sns.reset_orig()
正如您从 csv 文件中看到的那样，它包含 3 个离散值：0、-1 和 1。我想要一个离散图例而不是颜色条。将 0 标记为 A，将 -1 标记为 B，将 1 标记为 C。我该怎么做？
@Fabio Lamanna 提供的 link 是一个很好的开始。
从那里开始，您仍然希望在正确的位置设置颜色栏标签并使用与您的数据相对应的刻度标签。
假设您的数据中有等间距的水平，这会产生一个漂亮的离散颜色条：
基本上，这归结为关闭 seaborn 颜色条并自己用离散化颜色条替换它。
import pandas
import seaborn.apionly as sns
import matplotlib.pyplot as plt
import numpy as np
import matplotlib
def cmap_discretize(cmap, N):
"""Return a discrete colormap from the continuous colormap cmap.
cmap: colormap instance, eg. cm.jet.
N: number of colors.
Example
x = resize(arange(100), (5,100))
djet = cmap_discretize(cm.jet, 5)
imshow(x, cmap=djet)
"""
if type(cmap) == str:
cmap = plt.get_cmap(cmap)
colors_i = np.concatenate((np.linspace(0, 1., N), (0.,0.,0.,0.)))
colors_rgba = cmap(colors_i)
indices = np.linspace(0, 1., N+1)
cdict = {}
for ki,key in enumerate(('red','green','blue')):
cdict[key] = [ (indices[i], colors_rgba[i-1,ki], colors_rgba[i,ki]) for i in xrange(N+1) ]
# Return colormap object.
return matplotlib.colors.LinearSegmentedColormap(cmap.name + "_%d"%N, cdict, 1024)
def colorbar_index(ncolors, cmap, data):
"""Put the colorbar labels in the correct positions
using uique levels of data as tickLabels
"""
cmap = cmap_discretize(cmap, ncolors)
mappable = matplotlib.cm.ScalarMappable(cmap=cmap)
mappable.set_array([])
mappable.set_clim(-0.5, ncolors+0.5)
colorbar = plt.colorbar(mappable)
colorbar.set_ticks(np.linspace(0, ncolors, ncolors))
colorbar.set_ticklabels(np.unique(data))
# Read in csv file
df_trans = pandas.read_csv('d:/LUH2_trans_matrix.csv')
sns.set(font_scale=0.8)
cmap = sns.cubehelix_palette(n_colors=3,start=2.8, rot=.1, light=0.9, as_cmap=True)
cmap.set_under('gray') # 0 values in activity matrix are shown in gray (inactive transitions)
df_trans = df_trans.set_index(['Unnamed: 0'])
N = df_trans.max().max() - df_trans.min().min() + 1
f, ax = plt.subplots()
ax = sns.heatmap(df_trans, cmap=cmap, linewidths=.5, linecolor='lightgray',cbar=False)
colorbar_index(ncolors=N, cmap=cmap,data=df_trans)
# X - Y axis labels
ax.set_ylabel('FROM')
ax.set_xlabel('TO')
# Rotate tick labels
locs, labels = plt.xticks()
plt.setp(labels, rotation=0)
locs, labels = plt.yticks()
plt.setp(labels, rotation=0)
# revert matplotlib params
sns.reset_orig()
点点滴滴回收并改编自 here and here
我发现如果使用 ListedColormap，在 seaborn 中创建离散化的颜色条会容易得多。无需定义自己的函数，只需添加几行即可基本自定义坐标轴。
import pandas
import matplotlib.pyplot as plt
import seaborn as sns
from matplotlib.colors import ListedColormap
# Read in csv file
df_trans = pandas.read_csv('LUH2_trans_matrix.csv')
sns.set(font_scale=0.8)
# cmap is now a list of colors
cmap = sns.cubehelix_palette(start=2.8, rot=.1, light=0.9, n_colors=3)
df_trans = df_trans.set_index(['Unnamed: 0'])
# Create two appropriately sized subplots
grid_kws = {'width_ratios': (0.9, 0.03), 'wspace': 0.18}
fig, (ax, cbar_ax) = plt.subplots(1, 2, gridspec_kw=grid_kws)
ax = sns.heatmap(df_trans, ax=ax, cbar_ax=cbar_ax, cmap=ListedColormap(cmap),
linewidths=.5, linecolor='lightgray',
cbar_kws={'orientation': 'vertical'})
# Customize tick marks and positions
cbar_ax.set_yticklabels(['B', 'A', 'C'])
cbar_ax.yaxis.set_ticks([ 0.16666667, 0.5, 0.83333333])
# X - Y axis labels
ax.set_ylabel('FROM')
ax.set_xlabel('TO')
# Rotate tick labels
locs, labels = plt.xticks()
plt.setp(labels, rotation=0)
locs, labels = plt.yticks()
plt.setp(labels, rotation=0)
好吧，肯定有不止一种方法可以做到这一点。在这种情况下，只需要三种颜色，我会通过创建 LinearSegmentedColormap 而不是使用 cubehelix_palette 生成它们来自己选择颜色。如果有足够的颜色可以保证使用 cubehelix_palette，我会使用 cbar_kws 参数的 boundaries 选项在颜色图上定义段。无论哪种方式，都可以使用 set_ticks 和 set_ticklabels.
手动指定刻度
以下代码示例演示了 LinearSegmentedColormap 的手动创建，并包含有关在改用 cubehelix_palette 时如何指定边界的注释。
import matplotlib.pyplot as plt
import pandas
import seaborn.apionly as sns
from matplotlib.colors import LinearSegmentedColormap
sns.set(font_scale=0.8)
dataFrame = pandas.read_csv('LUH2_trans_matrix.csv').set_index(['Unnamed: 0'])
# For only three colors, it's easier to choose them yourself.
# If you still really want to generate a colormap with cubehelix_palette instead,
# add a cbar_kws={"boundaries": linspace(-1, 1, 4)} to the heatmap invocation
# to have it generate a discrete colorbar instead of a continous one.
myColors = ((0.8, 0.0, 0.0, 1.0), (0.0, 0.8, 0.0, 1.0), (0.0, 0.0, 0.8, 1.0))
cmap = LinearSegmentedColormap.from_list('Custom', myColors, len(myColors))
ax = sns.heatmap(dataFrame, cmap=cmap, linewidths=.5, linecolor='lightgray')
# Manually specify colorbar labelling after it's been generated
colorbar = ax.collections[0].colorbar
colorbar.set_ticks([-0.667, 0, 0.667])
colorbar.set_ticklabels(['B', 'A', 'C'])
# X - Y axis labels
ax.set_ylabel('FROM')
ax.set_xlabel('TO')
# Only y-axis labels need their rotation set, x-axis labels already have a rotation of 0
_, labels = plt.yticks()
plt.setp(labels, rotation=0)
plt.show()
这是一个基于其他答案的简单解决方案，它概括了 3 个类别并使用字典 (vmap) 来定义标签。
import seaborn as sns
import numpy as np
# This just makes some sample 2D data and a corresponding vmap dict with labels for the values in the data
data = [[1, 2, 3], [4, 5, 6], [7, 8, 9]]
vmap = {i: chr(65 + i) for i in range(len(np.ravel(data)))}
n = len(vmap)
print(vmap)
cmap = sns.color_palette("deep", n)
ax = sns.heatmap(data, cmap=cmap)
# Get the colorbar object from the Seaborn heatmap
colorbar = ax.collections[0].colorbar
# The list comprehension calculates the positions to place the labels to be evenly distributed across the colorbar
r = colorbar.vmax - colorbar.vmin
colorbar.set_ticks([colorbar.vmin + 0.5 * r / (n) + r * i / (n) for i in range(n)])
colorbar.set_ticklabels(list(vmap.values()))
我正在使用此处提供的数据使用 seaborn 和 pandas 构建此热图。
代码：
import pandas
import seaborn.apionly as sns
# Read in csv file
df_trans = pandas.read_csv('LUH2_trans_matrix.csv')
sns.set(font_scale=0.8)
cmap = sns.cubehelix_palette(start=2.8, rot=.1, light=0.9, as_cmap=True)
cmap.set_under('gray') # 0 values in activity matrix are shown in gray (inactive transitions)
df_trans = df_trans.set_index(['Unnamed: 0'])
ax = sns.heatmap(df_trans, cmap=cmap, linewidths=.5, linecolor='lightgray')
# X - Y axis labels
ax.set_ylabel('FROM')
ax.set_xlabel('TO')
# Rotate tick labels
locs, labels = plt.xticks()
plt.setp(labels, rotation=0)
locs, labels = plt.yticks()
plt.setp(labels, rotation=0)
# revert matplotlib params
sns.reset_orig()
正如您从 csv 文件中看到的那样，它包含 3 个离散值：0、-1 和 1。我想要一个离散图例而不是颜色条。将 0 标记为 A，将 -1 标记为 B，将 1 标记为 C。我该怎么做？
@Fabio Lamanna 提供的 link 是一个很好的开始。
从那里开始，您仍然希望在正确的位置设置颜色栏标签并使用与您的数据相对应的刻度标签。
假设您的数据中有等间距的水平，这会产生一个漂亮的离散颜色条：
基本上，这归结为关闭 seaborn 颜色条并自己用离散化颜色条替换它。
import pandas
import seaborn.apionly as sns
import matplotlib.pyplot as plt
import numpy as np
import matplotlib
def cmap_discretize(cmap, N):
"""Return a discrete colormap from the continuous colormap cmap.
cmap: colormap instance, eg. cm.jet.
N: number of colors.
Example
x = resize(arange(100), (5,100))
djet = cmap_discretize(cm.jet, 5)
imshow(x, cmap=djet)
"""
if type(cmap) == str:
cmap = plt.get_cmap(cmap)
colors_i = np.concatenate((np.linspace(0, 1., N), (0.,0.,0.,0.)))
colors_rgba = cmap(colors_i)
indices = np.linspace(0, 1., N+1)
cdict = {}
for ki,key in enumerate(('red','green','blue')):
cdict[key] = [ (indices[i], colors_rgba[i-1,ki], colors_rgba[i,ki]) for i in xrange(N+1) ]
# Return colormap object.
return matplotlib.colors.LinearSegmentedColormap(cmap.name + "_%d"%N, cdict, 1024)
def colorbar_index(ncolors, cmap, data):
"""Put the colorbar labels in the correct positions
using uique levels of data as tickLabels
"""
cmap = cmap_discretize(cmap, ncolors)
mappable = matplotlib.cm.ScalarMappable(cmap=cmap)
mappable.set_array([])
mappable.set_clim(-0.5, ncolors+0.5)
colorbar = plt.colorbar(mappable)
colorbar.set_ticks(np.linspace(0, ncolors, ncolors))
colorbar.set_ticklabels(np.unique(data))
# Read in csv file
df_trans = pandas.read_csv('d:/LUH2_trans_matrix.csv')
sns.set(font_scale=0.8)
cmap = sns.cubehelix_palette(n_colors=3,start=2.8, rot=.1, light=0.9, as_cmap=True)
cmap.set_under('gray') # 0 values in activity matrix are shown in gray (inactive transitions)
df_trans = df_trans.set_index(['Unnamed: 0'])
N = df_trans.max().max() - df_trans.min().min() + 1
f, ax = plt.subplots()
ax = sns.heatmap(df_trans, cmap=cmap, linewidths=.5, linecolor='lightgray',cbar=False)
colorbar_index(ncolors=N, cmap=cmap,data=df_trans)
# X - Y axis labels
ax.set_ylabel('FROM')
ax.set_xlabel('TO')
# Rotate tick labels
locs, labels = plt.xticks()
plt.setp(labels, rotation=0)
locs, labels = plt.yticks()
plt.setp(labels, rotation=0)
# revert matplotlib params
sns.reset_orig()
点点滴滴回收并改编自 here and here
我发现如果使用 ListedColormap，在 seaborn 中创建离散化的颜色条会容易得多。无需定义自己的函数，只需添加几行即可基本自定义坐标轴。
import pandas
import matplotlib.pyplot as plt
import seaborn as sns
from matplotlib.colors import ListedColormap
# Read in csv file
df_trans = pandas.read_csv('LUH2_trans_matrix.csv')
sns.set(font_scale=0.8)
# cmap is now a list of colors
cmap = sns.cubehelix_palette(start=2.8, rot=.1, light=0.9, n_colors=3)
df_trans = df_trans.set_index(['Unnamed: 0'])
# Create two appropriately sized subplots
grid_kws = {'width_ratios': (0.9, 0.03), 'wspace': 0.18}
fig, (ax, cbar_ax) = plt.subplots(1, 2, gridspec_kw=grid_kws)
ax = sns.heatmap(df_trans, ax=ax, cbar_ax=cbar_ax, cmap=ListedColormap(cmap),
linewidths=.5, linecolor='lightgray',
cbar_kws={'orientation': 'vertical'})
# Customize tick marks and positions
cbar_ax.set_yticklabels(['B', 'A', 'C'])
cbar_ax.yaxis.set_ticks([ 0.16666667, 0.5, 0.83333333])
# X - Y axis labels
ax.set_ylabel('FROM')
ax.set_xlabel('TO')
# Rotate tick labels
locs, labels = plt.xticks()
plt.setp(labels, rotation=0)
locs, labels = plt.yticks()
plt.setp(labels, rotation=0)
好吧，肯定有不止一种方法可以做到这一点。在这种情况下，只需要三种颜色，我会通过创建 LinearSegmentedColormap 而不是使用 cubehelix_palette 生成它们来自己选择颜色。如果有足够的颜色可以保证使用 cubehelix_palette，我会使用 cbar_kws 参数的 boundaries 选项在颜色图上定义段。无论哪种方式，都可以使用 set_ticks 和 set_ticklabels.
以下代码示例演示了 LinearSegmentedColormap 的手动创建，并包含有关在改用 cubehelix_palette 时如何指定边界的注释。
import matplotlib.pyplot as plt
import pandas
import seaborn.apionly as sns
from matplotlib.colors import LinearSegmentedColormap
sns.set(font_scale=0.8)
dataFrame = pandas.read_csv('LUH2_trans_matrix.csv').set_index(['Unnamed: 0'])
# For only three colors, it's easier to choose them yourself.
# If you still really want to generate a colormap with cubehelix_palette instead,
# add a cbar_kws={"boundaries": linspace(-1, 1, 4)} to the heatmap invocation
# to have it generate a discrete colorbar instead of a continous one.
myColors = ((0.8, 0.0, 0.0, 1.0), (0.0, 0.8, 0.0, 1.0), (0.0, 0.0, 0.8, 1.0))
cmap = LinearSegmentedColormap.from_list('Custom', myColors, len(myColors))
ax = sns.heatmap(dataFrame, cmap=cmap, linewidths=.5, linecolor='lightgray')
# Manually specify colorbar labelling after it's been generated
colorbar = ax.collections[0].colorbar
colorbar.set_ticks([-0.667, 0, 0.667])
colorbar.set_ticklabels(['B', 'A', 'C'])
# X - Y axis labels
ax.set_ylabel('FROM')
ax.set_xlabel('TO')
# Only y-axis labels need their rotation set, x-axis labels already have a rotation of 0
_, labels = plt.yticks()
plt.setp(labels, rotation=0)
plt.show()
这是一个基于其他答案的简单解决方案，它概括了 3 个类别并使用字典 (vmap) 来定义标签。
import seaborn as sns
import numpy as np
# This just makes some sample 2D data and a corresponding vmap dict with labels for the values in the data
data = [[1, 2, 3], [4, 5, 6], [7, 8, 9]]
vmap = {i: chr(65 + i) for i in range(len(np.ravel(data)))}
n = len(vmap)
print(vmap)
cmap = sns.color_palette("deep", n)
ax = sns.heatmap(data, cmap=cmap)
# Get the colorbar object from the Seaborn heatmap
colorbar = ax.collections[0].colorbar
# The list comprehension calculates the positions to place the labels to be evenly distributed across the colorbar
r = colorbar.vmax - colorbar.vmin
colorbar.set_ticks([colorbar.vmin + 0.5 * r / (n) + r * i / (n) for i in range(n)])
colorbar.set_ticklabels(list(vmap.values()))