python - 根据数据框中单元格中的值将颜色应用于单元格

Question

工作代码

 import pandas as pd
import seaborn as sns
import matplotlib as mpl
import numpy as np
from matplotlib import colors,cm
from matplotlib import pyplot as plt

filename = r'c:\Users\91956\Desktop\time_50.csv'
df = pd.read_csv(filename,index_col=0)
select_col = df.columns[1:]

cmap = mpl.colors.LinearSegmentedColormap.from_list("", ["red","white", "green"])

def background_gradient(s, cmap='PuBu', low=0, high=0):
    s = pd.to_numeric(s, errors='coerce') #<-- here, string will become nan.
    m = s.min() #<---------- here
    M = s.max() #<-----------here
    rng = M - m
    norm = colors.TwoSlopeNorm(vmin=m - (rng * low), vcenter=0., vmax=M + (rng * high))
    normed = norm(s.values)
    c = [colors.rgb2hex(x) for x in plt.cm.get_cmap(cmap)(normed)]
    return ['background-color: %s' % color for color in c]

S = df.style.apply( background_gradient,
                    cmap=cmap,
                    low=0.5,
                    high=0.5,
                    subset= pd.IndexSlice[:, select_col],
                    axis=1
                )

html = S.render()
with open("output.html","w") as fp:
    fp.write(html)

我收到了这个错误

文件“c:\Users\91956\Desktop\asdf.py”，第 29 行，在 m=df.min().min() 中，文件“C:\Users\91956\AppData\Local\Programs\Python\Python39 \lib\site-packages\pandas\core\generic.py"，第 11468 行，在 stat_func 中返回 self._reduce( 文件 "C:\Users\91956\AppData\Local\Programs\Python\Python39\lib\site-packages \pandas\core\series.py”，第 4248 行，在 _reduce 返回 op(delegate, skipna=skipna, **kwds) 文件“C:\Users\91956\AppData\Local\Programs\Python\Python39\lib\site -packages\pandas\core\nanops.py"，第 129 行，在 f 结果 = alt(values, axis=axis, skipna=skipna, **kwds) 文件“C:\Users\91956\AppData\Local\Programs\ Python\Python39\lib\site-packages\pandas\core\nanops.py"，第 873 行，减少结果 = getattr(values, meth)(axis) File "C:\Users\91956\AppData\Local\Programs\Python\Python39\lib\site-packages\numpy\core_methods.py"，第 43 行，in _amin 返回 umr_minimum(a, axis, None, out, keepdims, initial, where) TypeError：“numpy.ndarray”和“str”的实例之间不支持“>=”

更新 2 做了必要的更改。能够获得所需的输出。

标签： pythonpandasmatplotlibseaborn

Answer 1

这个答案和这个答案都会有所帮助。

要创建示例 df：

import pandas as pd
import numpy as np

np.random.seed(24)
df = pd.DataFrame({'A': np.linspace(1, 10, 10)})
df = pd.concat([df, pd.DataFrame(np.random.randn(10, 4), columns=list('BCDE'))],
               axis=1)
df.iloc[3, 3] = np.nan
df.iloc[0, 2] = np.nan

---

from matplotlib import colors

cmap=LinearSegmentedColormap.from_list('rg',["r","w","g"], N=256) 

def background_gradient(s, m, M, cmap='PuBu', low=0, high=0):
    s = pd.to_numeric(s, errors='coerce') #<-- here, string will become nan.
    print(s)
    rng = M - m
    norm = colors.DivergingNorm(vmin=m - (rng * low), vcenter=0., vmax=M + (rng * high))
    normed = norm(s.values)
    c = [colors.rgb2hex(x) for x in plt.cm.get_cmap(cmap)(normed)]
    return ['background-color: %s' % color for color in c]

x = df.apply(pd.to_numeric, errors='coerce') #<--- here string will be converted to `NaN` so that I can find out the max and min value.
df.style.apply(background_gradient,
               cmap=cmap,
               m=x.min().min(),
               M=x.max().max(),
               low=0.5,
               high=0.5, subset=pd.IndexSlice[:, ['B', 'C']]
              )

---

编辑：

通过subset=pd.IndexSlice[:, ['B', 'C']]应用<--我想在列B上应用颜色。C

df.style.apply(background_gradient,
               cmap=cmap,
               m=df.min().min(),
               M=df.max().max(),
               low=0.5,
               high=0.5, subset=pd.IndexSlice[:, ['B', 'C']]
              )

编辑2：

from matplotlib import colors

cmap=LinearSegmentedColormap.from_list('rg',["r","w","g"], N=256) 

def background_gradient(s, cmap='PuBu', low=0, high=0):
    s = pd.to_numeric(s, errors='coerce')
    m = s.min() #<---------- here
    M = s.max() #<-----------here
    rng = M - m
    norm = colors.DivergingNorm(vmin=m - (rng * low), vcenter=0., vmax=M + (rng * high))
    normed = norm(s.values)
    c = [colors.rgb2hex(x) for x in plt.cm.get_cmap(cmap)(normed)]
    return ['background-color: %s' % color for color in c]

# x = df.apply(pd.to_numeric, errors='coerce')
df.style.apply(background_gradient,
               cmap=cmap,
               low=0.5,
               high=0.5, subset=pd.IndexSlice[:, ['B', 'C', 'D']],  axis=1
              )

在应用中使用axis=1（沿着每行的列比较）

---