Question

我有一个包含20列的pandas数据框，其中包含数字和分类数据的混合。我想绘制一个5x4矩阵的数据图。使用matplotlib和子图我现在有所有数字数据的图，但对于我的生活，我无法弄清楚如何包含分类数据。

我想要像

这样的东西

df['RBC'].value_counts().plot(kind='bar')

但是在一个子情节中。

以下是一些代码（为了简洁起见，我省略了一些重复）。

from rdkit.Chem import AllChem as Chem
from rdkit.Chem.Draw import IPythonConsole
from rdkit.Chem import PandasTools
from rdkit.Chem import Draw
import pybel
import pandas as pd
import matplotlib
import matplotlib.pyplot as p
import matplotlib.ticker as plticker
%matplotlib inline 


#commandline application to calculate properties
output = !/Applications/ChemAxon/MarvinBeans/bin/evaluate /Users/username/Desktop/SampleFiles/Fragments.sdf -g -e "field('IDNUMBER'); molString('smiles'); logp(); logd('7.4'); apka('1'); bpka('1'); atomCount(); mass(); acceptorcount(); donorcount(); topologicalPolarSurfaceArea(); rotatablebondcount(); refractivity(); ASAHydrophobic('7.4'); ASAPolar('7.4'); atomCount()-atomCount('1');aromaticAtomCount()/(atomCount()-atomCount('1'))"

[line.split(';') for line in output]

cols = ['ID', 'smiles', 'logP', 'logD', 'apKa', 'bpKa', 'atomCount', 'mass', 'HBA', 'HBD', 'TPSA', 'RBC', 'MR', 'ASAh', 'ASAp', 'HAC', 'FractionAromatic']
df = pd.DataFrame([line.split(';') for line in output], columns=cols)
df = df.convert_objects(convert_numeric=True)

#series of calculations using the calculated data to add several categorical numeric and text fields to dataframe.

myLogP = df['logP']
myLogD = df['logD']
myMass = df['mass']
myTPSA = df['TPSA']
myRBC = df['RBC']
myRBCmax = max(myRBC) +1
myHBA = df['HBA']
myHBAmax = max(myHBA) +1
myHBD = df['HBD']
myHBDmax = max(myHBD) +1
myHAC = df['HAC']
myHACmax= range(min(myHAC), max(myHAC) + 1)


myFraromatic = df['FractionAromatic']

fig, axes = plt.subplots(nrows=5, ncols=4)
ax0, ax1, ax2, ax3, ax4, ax5, ax6, ax7, ax8, ax9, ax10, ax11, ax12, ax13, ax14, ax15, ax17, ax18, ax19 = axes.flat
axis_font = {'fontname':'Arial', 'size':'14'}
title_font = {'fontname':'Arial', 'size':'14', 'color' :'blue'}

loc = plticker.MultipleLocator(base=1.0)

ax0.hist(myLogP, histtype='bar')
ax0.set_title('LogP', title_font)
ax0.set_xlabel('Range of LogP', axis_font)
ax0.set_ylabel('Count')

ax1.hist(myLogD, histtype='bar')
ax1.set_title('LogD', title_font)
ax1.set_xlabel('Range of LogD', axis_font)
ax1.set_ylabel('Count', axis_font)

ax2.hist(myMass, histtype='bar', color = 'red')
ax2.set_title('Mass', title_font)
ax2.set_xlabel('Range of MWt', axis_font)
ax2.set_ylabel('Count', axis_font)

ax3.hist(myTPSA,  histtype='bar', color = 'yellow')
ax3.set_title('TPSA', title_font)
ax3.set_xlabel('Range of TPSA', axis_font)
ax3.set_ylabel('Count', axis_font)

#etc.

#ax8 'AZBN' is a categorical text field 

ax9.hist(myFraromatic, bins= 10, histtype='bar')
ax9.set_title('Aromatic', title_font)
ax9.set_xlabel('Fraction of Aromatic atoms', axis_font)
ax9.set_ylabel('Count', axis_font)

#further categorical plots




fig.set_size_inches(20, 15)

plt.tight_layout()

plt.show()

Answer 1

你应该发布你尝试过的代码和一些示例数据。否则，不可能知道最好的方法。但是，我认为您可能希望尝试使用matplotlib API而不是pandas的以下方法，并让您更好地控制每个图中的内容：

from matplotlib import pyplot as plt
fig, axes = plt.subplots(5, 4)   # axes is a numpy array of pyplot Axes
axes = iter(axes.ravel())   # set up an iterator for the set of axes. 

categoricals = df.columns[df.dtypes == 'category']
numeric = df.columns[df.dtypes != 'category']

for col in categoricals: 
    ax = df[col].value_counts().plot(kind='bar', ax=axes.next())
    # do other stuff with ax, formatting etc.  
    # the plot method returns the axis used for the plot for further manipulation

for col in numeric: 
     ax = df[col].plot(ax=axes.next())
     # etc.

这只是为了给你提供想法，因为我不知道你的数据的具体细节以及你想如何绘制每一列，你有什么样的数据类型等。

子图中的分类数据

1 个答案: