Last active
March 1, 2016 16:38
-
-
Save waltonjones/7065718 to your computer and use it in GitHub Desktop.
This gist includes a function called stylable_groupby_boxplot() that receives a pandas dataframe object and the column you want to groupby and returns a dictionary that includes all the boxplot's parts just like the standard matplotlib boxplot function does.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from numpy.random import rand | |
import matplotlib.pyplot as plt | |
import pandas as pd | |
# 2 columns produces an array of 2 matplotlib.axes.AxesSubplot objects | |
df2 = pd.DataFrame(rand(10,2), columns=['Col1', 'Col2'] ) | |
df2['X'] = pd.Series(['A','B','A','B','A','B','A','B','A','B']) | |
#1 column produces a single matplotlib.axes.AxesSubplot object | |
df1 = pd.DataFrame(rand(10), columns=['Col1'] ) | |
df1['X'] = pd.Series(['A','B','A','B','A','B','A','B','A','B']) | |
def stylable_groupby_boxplot(df, by): | |
''' | |
If you plot only one column, boxplot returns a single AxesSubplot object. | |
If there are several columns, boxplot returns an array of several AxesSubplot objects. | |
''' | |
bp = df.boxplot(by=by, grid=False) | |
bptype = str(type(bp)) | |
if bptype == "<class 'matplotlib.axes.AxesSubplot'>": | |
cl = bp.get_children() | |
cl=[item for item in cl if isinstance(item, matplotlib.lines.Line2D)] | |
bpdict = {} | |
groups = df.groupby(by).groups.keys() | |
for i in range(len(groups)): | |
bpdict[groups[i]] = {'boxes': [], 'caps': [], 'fliers': [], 'medians': [], 'whiskers': []} | |
bpdict[groups[i]]['boxes'] = [cl[4+8*i]] | |
bpdict[groups[i]]['caps'] = [cl[2+8*i], cl[3+8*i]] | |
bpdict[groups[i]]['fliers'] = [cl[6+8*i], cl[7+8*i]] | |
bpdict[groups[i]]['medians'] = [cl[5+8*i]] | |
bpdict[groups[i]]['whiskers'] = [cl[0+8*i], cl[1+8*i]] | |
else: | |
bpdict = {} | |
groups = df.groupby(by).groups.keys() | |
keys = range(len(bp)) | |
for i in keys: | |
bpdict[keys[i]] = {} | |
cl = bp[i].get_children() | |
cl=[item for item in cl if isinstance(item, matplotlib.lines.Line2D)] | |
for j in range(len(groups)): | |
bpdict[keys[i]][groups[j]] = {'boxes': [], 'caps': [], 'fliers': [], 'medians': [], 'whiskers': []} | |
bpdict[keys[i]][groups[j]]['boxes'] = [cl[4+8*j]] | |
bpdict[keys[i]][groups[j]]['caps'] = [cl[2+8*j], cl[3+8*j]] | |
bpdict[keys[i]][groups[j]]['fliers'] = [cl[6+8*j], cl[7+8*j]] | |
bpdict[keys[i]][groups[j]]['medians'] = [cl[5+8*j]] | |
bpdict[keys[i]][groups[j]]['whiskers'] = [cl[0+8*j], cl[1+8*j]] | |
return bpdict | |
bp2 = stylable_groupby_boxplot(df2, by="X") | |
bp1 = stylable_groupby_boxplot(df1, by="X") | |
# 2 column styling | |
plt.suptitle("") | |
plt.setp(bp2[0]['A']['boxes'], color='blue') | |
plt.setp(bp2[0]['A']['medians'], color='red') | |
plt.setp(bp2[0]['A']['whiskers'], color='blue') | |
plt.setp(bp2[0]['A']['fliers'], color='blue') | |
plt.setp(bp2[0]['A']['caps'], color='blue') | |
plt.setp(bp2[0]['B']['boxes'], color='red') | |
plt.setp(bp2[0]['B']['medians'], color='blue') | |
plt.setp(bp2[0]['B']['whiskers'], color='red') | |
plt.setp(bp2[0]['B']['fliers'], color='red') | |
plt.setp(bp2[0]['B']['caps'], color='red') | |
plt.setp(bp2[1]['A']['boxes'], color='green') | |
plt.setp(bp2[1]['A']['medians'], color='purple') | |
plt.setp(bp2[1]['A']['whiskers'], color='green') | |
plt.setp(bp2[1]['A']['fliers'], color='green') | |
plt.setp(bp2[1]['A']['caps'], color='green') | |
plt.setp(bp2[1]['B']['boxes'], color='purple') | |
plt.setp(bp2[1]['B']['medians'], color='green') | |
plt.setp(bp2[1]['B']['whiskers'], color='purple') | |
plt.setp(bp2[1]['B']['fliers'], color='purple') | |
plt.setp(bp2[1]['B']['caps'], color='purple') | |
# 1 column styling | |
plt.suptitle("") | |
plt.setp(bp1['A']['boxes'], color='blue') | |
plt.setp(bp1['A']['medians'], color='red') | |
plt.setp(bp1['A']['whiskers'], color='blue') | |
plt.setp(bp1['A']['fliers'], color='blue') | |
plt.setp(bp1['A']['caps'], color='blue') | |
plt.setp(bp1['B']['boxes'], color='red') | |
plt.setp(bp1['B']['medians'], color='blue') | |
plt.setp(bp1['B']['whiskers'], color='red') | |
plt.setp(bp1['B']['fliers'], color='red') | |
plt.setp(bp1['B']['caps'], color='red') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment