Python 将matplotlib图像插入数据帧

目的：我目前正在与rdkit合作，根据

rdkit.Chem.Draw.SimilarityMaps

为我的分子结构着色。现在，我想使用matplotlib images

SimilarityMaps

函数在pandas数据框中引入它们，并以html文件的形式导出此表

代码：我尝试用以下代码来实现

import pandas as pd
from rdkit import Chem
from rdkit.Chem import Draw
from rdkit.Chem.Draw import SimilarityMaps
from rdkit.Chem.Draw import IPythonConsole #Needed to show molecules
from rdkit.Chem.Draw.MolDrawing import MolDrawing, DrawingOptions

df = pd.DataFrame({'smiles':['Nc1nc(NC2CC2)c3ncn([C@@H]4C[C@H](CO)C=C4)c3n1','CCCC(=O)Nc1ccc(OCC(O)CNC(C)C)c(c1)C(C)=O','CCN(CC)CCNC(=O)C1=CC=C(C=C1)NC(=O)C','CC(=O)NC1=CC=C(C=C1)O','CC(=O)Nc1sc(nn1)[S](N)(=O)=O']})

def getSim(smi):
    mol = Chem.MolFromSmiles(smi)
    refmol = Chem.MolFromSmiles('c1ccccc1')
    fp = SimilarityMaps.GetMorganFingerprint(mol, fpType='bv')
    fig, maxweight = SimilarityMaps.GetSimilarityMapForFingerprint(refmol, mol, SimilarityMaps.GetMorganFingerprint)
    return fig

df['map'] = df['smiles'].map(getSim)
df.to_html('/.../test.html')

当我打开文件

test.html

时，map列包含信息“Figure（200x200）”。我检查我的dataframe映射列是否包含object：在python中可以，但在html文件中不能

问题：我不确定如何获得带有图像的数据帧，我希望社区能帮助我澄清这个问题

---

提前感谢

您所看到的

图形（200x200）

是matplotlib图形类的

\uuurepr\uuuuu

字符串。它是python对象的文本表示形式（与执行

print（图）

时看到的相同）

相反，您希望在表中有一个实际的图像。一个简单的选择是将matplotlib图形保存为png图像，创建一个html标记，

，然后显示表格

import pandas as pd
import numpy as np;np.random.seed(1)
import matplotlib.pyplot as plt
import matplotlib.colors

df = pd.DataFrame({"info" : np.random.randint(0,10,10), 
                   "status" : np.random.randint(0,3,10)})

cmap = matplotlib.colors.ListedColormap(["crimson","orange","limegreen"])

def createFigure(i):
    fig, ax = plt.subplots(figsize=(.4,.4))
    fig.subplots_adjust(0,0,1,1)
    ax.axis("off")
    ax.axis([0,1,0,1])
    c = plt.Circle((.5,.5), .4, color=cmap(i))
    ax.add_patch(c)
    ax.text(.5,.5, str(i), ha="center", va="center")
    return fig

def mapping(i):
    fig = createFigure(i)
    fname = "data/map_{}.png".format(i)
    fig.savefig(fname)
    imgstr = '<img src="{}" /> '.format(fname)
    return imgstr


df['image'] = df['status'].map(mapping)
df.to_html('test.html', escape=False)

---

你。。。谢谢。你的回答很酷。我找到了大致相同的解决方案，但您的解决方案更简单……我想：）

import pandas as pd
import numpy as np;np.random.seed(1)
import matplotlib.pyplot as plt
import matplotlib.colors
from io import BytesIO
import base64

df = pd.DataFrame({"info" : np.random.randint(0,10,10), 
                   "status" : np.random.randint(0,3,10)})

cmap = matplotlib.colors.ListedColormap(["crimson","orange","limegreen"])

def createFigure(i):
    fig, ax = plt.subplots(figsize=(.4,.4))
    fig.subplots_adjust(0,0,1,1)
    ax.axis("off")
    ax.axis([0,1,0,1])
    c = plt.Circle((.5,.5), .4, color=cmap(i))
    ax.add_patch(c)
    ax.text(.5,.5, str(i), ha="center", va="center")
    return fig

def fig2inlinehtml(fig,i):
    figfile = BytesIO()
    fig.savefig(figfile, format='png')
    figfile.seek(0) 
    # for python 2.7:
    #figdata_png = base64.b64encode(figfile.getvalue())
    # for python 3.x:
    figdata_png = base64.b64encode(figfile.getvalue()).decode()
    imgstr = '<img src="data:image/png;base64,{}" />'.format(figdata_png)
    return imgstr

def mapping(i):
    fig = createFigure(i)
    return fig2inlinehtml(fig,i)


with pd.option_context('display.max_colwidth', -1):
    df.to_html('test.html', escape=False, formatters=dict(status=mapping))

from IPython.display import HTML
# ...
pd.set_option('display.max_colwidth', -1)
HTML(df.to_html(escape=False, formatters=dict(status=mapping)))