python - 如何在seaborn clustermap中将Y刻度标签标记为组/类别？

Question

我想制作来自患者的基因存在/不存在数据的聚类图/热图，其中基因将被分组为类别(例如趋化性、内毒素等)并适当标记。我在seaborn文档中没有找到任何这样的选项。我知道如何生成热图，只是不知道如何将 yticks 标记为类别。这是我想要实现的目标的示例(与我的工作无关):

此处，yticklabels 一月、二月和三月被赋予组标签 Winter，其他 yticklabel 也具有类似的标签。

Answer 1

我复制了您在seaborn中给出的示例，改编自@Stein的答案here .

import pandas as pd
import numpy as np
from matplotlib import pyplot as plt
from itertools import groupby
import datetime
import seaborn as sns

def test_table():
    months = [datetime.date(2008, i+1, 1).strftime('%B') for i in range(12)]
    seasons = ['Winter',]*3 + ['Spring',]*2 + ['Summer']*3 + ['Pre-Winter',]*4
    tuples = list(zip(months, seasons))
    index = pd.MultiIndex.from_tuples(tuples, names=['first', 'second'])
    d = {i: [np.random.randint(0,50) for _ in range(12)] for i in range(1950, 1960)}
    df = pd.DataFrame(d, index=index)
    return df

def add_line(ax, xpos, ypos):
    line = plt.Line2D([ypos, ypos+ .2], [xpos, xpos], color='black', transform=ax.transAxes)
    line.set_clip_on(False)
    ax.add_line(line)

def label_len(my_index,level):
    labels = my_index.get_level_values(level)
    return [(k, sum(1 for i in g)) for k,g in groupby(labels)]

def label_group_bar_table(ax, df):
    xpos = -.2
    scale = 1./df.index.size
    for level in range(df.index.nlevels):
        pos = df.index.size
        for label, rpos in label_len(df.index,level):
            add_line(ax, pos*scale, xpos)
            pos -= rpos
            lypos = (pos + .5 * rpos)*scale
            ax.text(xpos+.1, lypos, label, ha='center', transform=ax.transAxes) 
        add_line(ax, pos*scale , xpos)
        xpos -= .2

df = test_table()

fig = plt.figure(figsize = (10, 10))
ax = fig.add_subplot(111)
sns.heatmap(df)

#Below 3 lines remove default labels
labels = ['' for item in ax.get_yticklabels()]
ax.set_yticklabels(labels)
ax.set_ylabel('')

label_group_bar_table(ax, df)
fig.subplots_adjust(bottom=.1*df.index.nlevels)
plt.show()

给予:

希望有帮助。