matplotlib-users Mailing List for matplotlib

the following code runs ok with py2.4 and matplotlib.0.98.3
however no legend appears with py2.7.3 and matplotlib-1.2.1/1.3. and I get
[quote]
e:\prg\py\python-2.7.3\lib\site-packages\_matplotlib\matplotlib\legend.py:629: U
serWarning: Legend does not support [<matplotlib.patches.Wedge object at 0x03842
0F0>, <matplotlib.patches.Wedge object at 0x03842530>, <matplotlib.patches.Wedge
 object at 0x03842930>, <matplotlib.patches.Wedge object at 0x03842D30>, <matplo
tlib.patches.Wedge object at 0x038B0150>]
Use proxy artist instead.
http://matplotlib.sourceforge.net/users/legend_guide.html#using-proxy-artist
 (str(orig_handle),))
e:\prg\py\python-2.7.3\lib\site-packages\_matplotlib\matplotlib\legend.py:629: U
serWarning: Legend does not support [<matplotlib.text.Text object at 0x03842310>
, <matplotlib.text.Text object at 0x03842750>, <matplotlib.text.Text object at 0
x03842B50>, <matplotlib.text.Text object at 0x03842F50>, <matplotlib.text.Text o
bject at 0x038B0370>]
Use proxy artist instead.
http://matplotlib.sourceforge.net/users/legend_guide.html#using-proxy-artist
 (str(orig_handle),))
[/quote]
what's the matter? thanks
[code]
#coding=utf-8
from pylab import *
val2010 = [2, 10, 20, 15, 3]
figure()
pie2010=pie(val2010, labels=[u'%i persons' % i for i in val2010])
plt.legend( (pie2010), [u'<60', u'60~70', u'70~80', u'80~90',
u'90~100'], loc = 'best', bbox_to_anchor = (0.90, 0.75) )
axis('equal')
show()
[/code]

Hi,
I have problems with constrained rectangular zoom to x-y axis with
PyQt4 / PySide backend. When I use the "Zoom-to-rectangle" button of
the navigation toolbar while holding the x or y key, sometimes nothing
happens when the mouse is released. Constrained panning and
pan-zooming ("Pan/Zoom" button) works well.
I used the following dummy code to set up the environment:
import numpy as np
import matplotlib as mpl
if mpl.get_backend() != 'Qt4Agg':
 mpl.use('Qt4Agg')
 # mpl.rcParams['backend.qt4']='PySide'
 # mpl.rcParams['backend.qt4']='PyQt4'
import matplotlib.pyplot as plt
x = np.linspace(0,1)
y = np.random.rand(x.size)
fig = plt.figure()
ax = fig.add_subplot(111)
ax.plot(x,y)
plt.show()
Looking at the mail archives and the issue tracker gave me no relevant
result. Has anyone experienced a similar issue?
python 2.7.4 win32
matplotlib 1.1.1 and 1.2.1
PyQt4 QtCore 4.8.3
PySide QtCore 4.8.3
PySide 1.1.2
Thanks,
Gregorio

ChaoYue wrote:
> Hi Martin,
> 
> I don't know tight_layout quite well. Probably you could also split the handlers of the barplot into
> and 2 or 3 or 4 parts depending on the number, and then show them in sperate axes?
> 
> then you create n+1 subplots for the whole figure?
No, the reason why I use stacked bar chart is that I can squeeze the data
into a single figure. It is only difficult for the reader to compare 20
separate barcharts between each other whereas seeing 20 stacked bars in a
single chart on top of each other is easy.
I think your approach combined with something like a future improvement:
fig.savefig('foobar.png', bbox_inches='tight', keep_fig_width=True)
will do the best for me (unused space below the legend will be chopped away
while figure width will be untouched).
Lets see what Ben or others say about the tight_layout rescaling issue and the
"feature request". ;-)
Maritn
> 
> probably this is quite stupid.
> 
> cheers,
> 
> Chao
> 
> On Wed, May 22, 2013 at 1:03 PM, Martin Mokrejs [via matplotlib] <[hidden email] </user/SendEmail.jtp?type=node&node=41105&i=0>> wrote:
> 
> Hi Chao,
> 
> ChaoYue wrote:
> > Dear Martin,
> >
> > I worked out a similar example for your reference as I don't catch your example very well.
> 
> I think you got the idea quite well.
> 
> >
> > fig = plt.figure() 
> > ax1 = fig.add_subplot(211) 
> > ax2 = fig.add_subplot(212) 
> > arrlist = [np.random.normal(size=100) for i in range(50)] 
> > ret = ax1.hist(arrlist,histtype='barstacked') 
> > reclist = [patchlist[0] for patchlist in ret[2]] 
> > labellist = ['data'+str(i) for i in range(50)] 
> > ax2.legend(reclist,labellist,loc='upper left',bbox_to_anchor=(0,0,1,1),borderaxespad=0.,ncol=5,mode='expand')
> > ax2.set_frame_on(False) 
> > ax2.tick_params(bottom='off',left='off',right='off',top='off') 
> > plt.setp(ax2.get_yticklabels(),visible=False) 
> > plt.setp(ax2.get_xticklabels(),visible=False) 
> >
> I added plt.show() and it demonstrates my problem: the legend is not complete in the
> figure. That is why I think I could instead use:
> 
> import pylab as plt
> import numpy as np
> 
> fig = plt.figure()
> DefaultSize = tuple(fig.get_size_inches())
> fig.set_size_inches(DefaultSize[0], 4*DefaultSize[1])
> ax1 = fig.add_subplot(411)
> ax2 = fig.add_subplot(412)
> arrlist = [np.random.normal(size=100) for i in range(50)]
> ret = ax1.hist(arrlist,histtype='barstacked')
> reclist = [patchlist[0] for patchlist in ret[2]]
> labellist = ['data'+str(i) for i in range(50)]
> ax2.legend(reclist,labellist,loc='upper left',bbox_to_anchor=(0,0,1,1),borderaxespad=0.,ncol=5,mode='expand')
> ax2.set_frame_on(False)
> ax2.tick_params(bottom='off',left='off',right='off',top='off')
> plt.setp(ax2.get_yticklabels(),visible=False)
> plt.setp(ax2.get_xticklabels(),visible=False)
> plt.show()
> 
> But, this does not make the image 4* taller than I thought. But thank you
> for the example how to extract the legend of ax1 and place it under ax2.
> 
> 
> 
> >
> > you're asking some object-oriented way, I personally don't think
> > using pylab and set_tight_layout are the good way to be
> > "object-oriented" as pylab is only a bounding wrapper by my
> > understanding (maybe I am wrong!). legend and hist are all
> > matplotlib.axes.Axes method.
> >
> > Also, I think it's unrealistic to ask the figure do a nice job for
> > you if there are 50 legend handlers and you want to show them in 2
> > columns with a very high width/height ratio of the figure....
> 
> The problem is that the data are calculated dynamically and sometimes
> I need to display data for 20 data types while sometimes for 200 data
> types (and for each I need a legend).
> 
> I did not show that but I do calculate how many columns I could use
> legend display and pass that via pylab.legend(..., ncol= ). Of course
> at the same time I could calculate whether I will need 2 or 3 or 4
> subplots on the page (the first will be the barchart itself), the
> remaining space will be used by the long legend of subplot(211).
> I would hope that matplotlib does not mind that I actually issue any
> fig.add_subplot() foe the third or even fourth subplot at all. That
> would be just a trick to get more space for the legend. If I can live
> with just with subplot(211) and subplot(212)
> 
> The fig.savefig('foobar.png', bbox_inches='tight') which Ben mentioned
> yesterday is nice but I want it to crop the image only vertically.
> An optional argument like:
> fig.savefig('foobar.png', bbox_inches='tight', keep_fig_width=True)
> would maybe do the job for me.
> 
> 
> What I still don't understand what is resizing the image in tight_layout.
> It doesn't seem to me that just the unused border space is chopped away.
> Fonts look different, ratio between x and y axes lengths seems different.
> Certainly not what I want.
> 
> 
> > hope it could be of a bit help,
> 
> Sure, I am still learning to use matplotlib.
> 
> Martin
> 
> >
> > cheers,
> >
> > Chao
> >
> 
> >
> > On Mon, May 20, 2013 at 6:43 PM, Martin Mokrejs [via matplotlib] <[hidden email] </user/SendEmail.jtp?type=node&node=41102&i=0>> wrote:
> >
> > Hi Ben,
> >
> > Benjamin Root wrote:
> >
> > >
> > >
> > >
> > > On Mon, May 20, 2013 at 12:02 PM, Martin Mokrejs <[hidden email] <http://user/SendEmail.jtp?type=node&node=41090&i=0> <mailto:[hidden email] <http://user/SendEmail.jtp?type=node&node=41090&i=1>>> wrote:
> 
> > >
> > > Hi,
> > > I am having trouble to get space allocated for a long legend text,
> > > lets say spanning 2/3 - 3/4 of the whole output. I would like to have
> > > stacked barchart as 1st subplot and the place of remaining 3 subplots
> > > to be actually allocated by the legend. Alternatively, could I get the
> > > legend saved into a separate figure?
> > >
> > > Or could the space for legend text be allocated automatically minimizing
> > > output figure size? For example, the width would be 1120px while height
> > > be multiples of 840px (840 for each subplot)?
> > >
> > > Attached is a quick example. It shows also that I tried tight_layout()
> > > but wasn't successful with this either. I would be glad for some help,
> > > ideally converting the whole thing into an object-oriented approach.
> > > I am generating several figures in a row and would like to clear()/del()
> > > any previously used data ASAP.
> > >
> > >
> > > Thank you,
> > > Martin
> > > Am using mpl-1.2.2
> > >
> > >
> > > Try "fig.savefig('foobar.png', bbox_inches='tight')" when saving the
> > > image. It will make the figure size such that all the visible
> > > elements of the figure will fit into the saved output. tight_layout()
> > > is meant to make sure the elements don't overlap each other, but does
> > > nothing about making sure nothing gets clipped.
> > Ah, would be nice to make this clear in the docs. So far was doing
> >
> >
> > import pylab
> > F = pylab.gcf()
> > F.set_tight_layout(True)
> >
> > which as you say does not help the way I thought.
> >
> >
> > Unfortunately, while
> >
> > fig.savefig('foobar.png', bbox_inches='tight')
> >
> > helped to get everything into the .png file (attached), the barchart itself
> > should span according to the code I posted just 1/2 of the figure. But somehow
> > it is enlarged and rescaled so that it occupies *more than* 1/2 of the figure.
> > What in pylab is resizing my image? Note: the final image is 625x1075.
> >
> > Martin

Hi Martin,
I don't know tight_layout quite well. Probably you could also split the
handlers of the barplot into
and 2 or 3 or 4 parts depending on the number, and then show them in
sperate axes?
then you create n+1 subplots for the whole figure?
probably this is quite stupid.
cheers,
Chao
On Wed, May 22, 2013 at 1:03 PM, Martin Mokrejs [via matplotlib] <
ml-...@n5...> wrote:
> Hi Chao,
>
> ChaoYue wrote:
> > Dear Martin,
> >
> > I worked out a similar example for your reference as I don't catch your
> example very well.
>
> I think you got the idea quite well.
>
> >
> > fig = plt.figure()
>
> > ax1 = fig.add_subplot(211)
>
> > ax2 = fig.add_subplot(212)
>
> > arrlist = [np.random.normal(size=100) for i in range(50)]
>
> > ret = ax1.hist(arrlist,histtype='barstacked')
>
> > reclist = [patchlist[0] for patchlist in ret[2]]
>
> > labellist = ['data'+str(i) for i in range(50)]
>
> > ax2.legend(reclist,labellist,loc='upper
> left',bbox_to_anchor=(0,0,1,1),borderaxespad=0.,ncol=5,mode='expand')
> > ax2.set_frame_on(False)
>
> > ax2.tick_params(bottom='off',left='off',right='off',top='off')
>
> > plt.setp(ax2.get_yticklabels(),visible=False)
>
> > plt.setp(ax2.get_xticklabels(),visible=False)
> >
>
> I added plt.show() and it demonstrates my problem: the legend is not
> complete in the
> figure. That is why I think I could instead use:
>
> import pylab as plt
> import numpy as np
>
> fig = plt.figure()
> DefaultSize = tuple(fig.get_size_inches())
> fig.set_size_inches(DefaultSize[0], 4*DefaultSize[1])
> ax1 = fig.add_subplot(411)
> ax2 = fig.add_subplot(412)
> arrlist = [np.random.normal(size=100) for i in range(50)]
> ret = ax1.hist(arrlist,histtype='barstacked')
> reclist = [patchlist[0] for patchlist in ret[2]]
> labellist = ['data'+str(i) for i in range(50)]
> ax2.legend(reclist,labellist,loc='upper
> left',bbox_to_anchor=(0,0,1,1),borderaxespad=0.,ncol=5,mode='expand')
> ax2.set_frame_on(False)
> ax2.tick_params(bottom='off',left='off',right='off',top='off')
> plt.setp(ax2.get_yticklabels(),visible=False)
> plt.setp(ax2.get_xticklabels(),visible=False)
> plt.show()
>
> But, this does not make the image 4* taller than I thought. But thank you
> for the example how to extract the legend of ax1 and place it under ax2.
>
>
>
> >
> > you're asking some object-oriented way, I personally don't think
> > using pylab and set_tight_layout are the good way to be
> > "object-oriented" as pylab is only a bounding wrapper by my
> > understanding (maybe I am wrong!). legend and hist are all
> > matplotlib.axes.Axes method.
> >
> > Also, I think it's unrealistic to ask the figure do a nice job for
> > you if there are 50 legend handlers and you want to show them in 2
> > columns with a very high width/height ratio of the figure....
>
> The problem is that the data are calculated dynamically and sometimes
> I need to display data for 20 data types while sometimes for 200 data
> types (and for each I need a legend).
>
> I did not show that but I do calculate how many columns I could use
> legend display and pass that via pylab.legend(..., ncol= ). Of course
> at the same time I could calculate whether I will need 2 or 3 or 4
> subplots on the page (the first will be the barchart itself), the
> remaining space will be used by the long legend of subplot(211).
> I would hope that matplotlib does not mind that I actually issue any
> fig.add_subplot() foe the third or even fourth subplot at all. That
> would be just a trick to get more space for the legend. If I can live
> with just with subplot(211) and subplot(212)
>
> The fig.savefig('foobar.png', bbox_inches='tight') which Ben mentioned
> yesterday is nice but I want it to crop the image only vertically.
> An optional argument like:
> fig.savefig('foobar.png', bbox_inches='tight', keep_fig_width=True)
> would maybe do the job for me.
>
>
> What I still don't understand what is resizing the image in tight_layout.
> It doesn't seem to me that just the unused border space is chopped away.
> Fonts look different, ratio between x and y axes lengths seems different.
> Certainly not what I want.
>
>
> > hope it could be of a bit help,
>
> Sure, I am still learning to use matplotlib.
>
> Martin
>
> >
> > cheers,
> >
> > Chao
> >
> >
> > On Mon, May 20, 2013 at 6:43 PM, Martin Mokrejs [via matplotlib]
> <[hidden email] </user/SendEmail.jtp?type=node&node=41102&i=0>> wrote:
> >
> > Hi Ben,
> >
> > Benjamin Root wrote:
> >
> > >
> > >
> > >
> > > On Mon, May 20, 2013 at 12:02 PM, Martin Mokrejs <[hidden email] <
> http://user/SendEmail.jtp?type=node&node=41090&i=0> <mailto:[hidden
> email] <http://user/SendEmail.jtp?type=node&node=41090&i=1>>> wrote:
> > >
> > > Hi,
> > > I am having trouble to get space allocated for a long legend
> text,
> > > lets say spanning 2/3 - 3/4 of the whole output. I would like
> to have
> > > stacked barchart as 1st subplot and the place of remaining 3
> subplots
> > > to be actually allocated by the legend. Alternatively, could I
> get the
> > > legend saved into a separate figure?
> > >
> > > Or could the space for legend text be allocated automatically
> minimizing
> > > output figure size? For example, the width would be 1120px
> while height
> > > be multiples of 840px (840 for each subplot)?
> > >
> > > Attached is a quick example. It shows also that I tried
> tight_layout()
> > > but wasn't successful with this either. I would be glad for
> some help,
> > > ideally converting the whole thing into an object-oriented
> approach.
> > > I am generating several figures in a row and would like to
> clear()/del()
> > > any previously used data ASAP.
> > >
> > >
> > > Thank you,
> > > Martin
> > > Am using mpl-1.2.2
> > >
> > >
> > > Try "fig.savefig('foobar.png', bbox_inches='tight')" when saving
> the
> > > image. It will make the figure size such that all the visible
> > > elements of the figure will fit into the saved output.
> tight_layout()
> > > is meant to make sure the elements don't overlap each other, but
> does
> > > nothing about making sure nothing gets clipped.
> > Ah, would be nice to make this clear in the docs. So far was doing
> >
> >
> > import pylab
> > F = pylab.gcf()
> > F.set_tight_layout(True)
> >
> > which as you say does not help the way I thought.
> >
> >
> > Unfortunately, while
> >
> > fig.savefig('foobar.png', bbox_inches='tight')
> >
> > helped to get everything into the .png file (attached), the barchart
> itself
> > should span according to the code I posted just 1/2 of the figure.
> But somehow
> > it is enlarged and rescaled so that it occupies *more than* 1/2 of
> the figure.
> > What in pylab is resizing my image? Note: the final image is
> 625x1075.
> >
> > Martin
> >
> >
> ------------------------------------------------------------------------------
>
> > AlienVault Unified Security Management (USM) platform delivers
> complete
> > security visibility with the essential security capabilities. Easily
> and
> > efficiently configure, manage, and operate all of your security
> controls
> > from a single console and one unified framework. Download a free
> trial.
> > http://p.sf.net/sfu/alienvault_d2d
> > _______________________________________________
> > Matplotlib-users mailing list
> > [hidden email] <http://user/SendEmail.jtp?type=node&node=41090&i=2>
> > https://lists.sourceforge.net/lists/listinfo/matplotlib-users
> >
> > *foobar.png* (132K) Download Attachment <
> http://matplotlib.1069221.n5.nabble.com/attachment/41090/0/foobar.png>
> >
> >
> >
> ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
>
> > If you reply to this email, your message will be added to the
> discussion below:
> >
> http://matplotlib.1069221.n5.nabble.com/Making-space-for-a-long-legend-outside-of-a-barchart-tp41088p41090.html
> > To start a new topic under matplotlib - users, email [hidden email]
> </user/SendEmail.jtp?type=node&node=41102&i=1>
> > To unsubscribe from matplotlib, click here.
> > NAML <
> http://matplotlib.1069221.n5.nabble.com/template/NamlServlet.jtp?macro=macro_viewer&id=instant_html%21nabble%3Aemail.naml&base=nabble.naml.namespaces.BasicNamespace-nabble.view.web.template.NabbleNamespace-nabble.view.web.template.NodeNamespace&breadcrumbs=notify_subscribers%21nabble%3Aemail.naml-instant_emails%21nabble%3Aemail.naml-send_instant_email%21nabble%3Aemail.naml>
>
> >
> >
> >
> >
> > --
> >
> ***********************************************************************************
>
> > Chao YUE
> > Laboratoire des Sciences du Climat et de l'Environnement (LSCE-IPSL)
> > UMR 1572 CEA-CNRS-UVSQ
> > Batiment 712 - Pe 119
> > 91191 GIF Sur YVETTE Cedex
> > Tel: (33) 01 69 08 29 02; Fax:01.69.08.77.16
> >
> ************************************************************************************
>
> >
> >
> ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
>
> > View this message in context: Re: Making space for a long legend outside
> of a barchart <
> http://matplotlib.1069221.n5.nabble.com/Making-space-for-a-long-legend-outside-of-a-barchart-tp41088p41102.html>
>
> > Sent from the matplotlib - users mailing list archive <
> http://matplotlib.1069221.n5.nabble.com/matplotlib-users-f3.html> at
> Nabble.com.
> >
> >
> >
> ------------------------------------------------------------------------------
>
> > Try New Relic Now & We'll Send You this Cool Shirt
> > New Relic is the only SaaS-based application performance monitoring
> service
> > that delivers powerful full stack analytics. Optimize and monitor your
> > browser, app, & servers with just a few lines of code. Try New Relic
> > and get this awesome Nerd Life shirt!
> http://p.sf.net/sfu/newrelic_d2d_may
> >
> >
> >
> > _______________________________________________
> > Matplotlib-users mailing list
> > [hidden email] <http://user/SendEmail.jtp?type=node&node=41104&i=0>
> > https://lists.sourceforge.net/lists/listinfo/matplotlib-users
> >
>
> ------------------------------------------------------------------------------
>
> Try New Relic Now & We'll Send You this Cool Shirt
> New Relic is the only SaaS-based application performance monitoring
> service
> that delivers powerful full stack analytics. Optimize and monitor your
> browser, app, & servers with just a few lines of code. Try New Relic
> and get this awesome Nerd Life shirt! http://p.sf.net/sfu/newrelic_d2d_may
> _______________________________________________
> Matplotlib-users mailing list
> [hidden email] <http://user/SendEmail.jtp?type=node&node=41104&i=1>
> https://lists.sourceforge.net/lists/listinfo/matplotlib-users
>
>
> ------------------------------
> If you reply to this email, your message will be added to the discussion
> below:
>
> http://matplotlib.1069221.n5.nabble.com/Making-space-for-a-long-legend-outside-of-a-barchart-tp41088p41104.html
> To start a new topic under matplotlib - users, email
> ml-...@n5...
> To unsubscribe from matplotlib, click here<http://matplotlib.1069221.n5.nabble.com/template/NamlServlet.jtp?macro=unsubscribe_by_code&node=2&code=Y2hhb3l1ZWpveUBnbWFpbC5jb218MnwxMzg1NzAzMzQx>
> .
> NAML<http://matplotlib.1069221.n5.nabble.com/template/NamlServlet.jtp?macro=macro_viewer&id=instant_html%21nabble%3Aemail.naml&base=nabble.naml.namespaces.BasicNamespace-nabble.view.web.template.NabbleNamespace-nabble.view.web.template.NodeNamespace&breadcrumbs=notify_subscribers%21nabble%3Aemail.naml-instant_emails%21nabble%3Aemail.naml-send_instant_email%21nabble%3Aemail.naml>
>
-- 
***********************************************************************************
Chao YUE
Laboratoire des Sciences du Climat et de l'Environnement (LSCE-IPSL)
UMR 1572 CEA-CNRS-UVSQ
Batiment 712 - Pe 119
91191 GIF Sur YVETTE Cedex
Tel: (33) 01 69 08 29 02; Fax:01.69.08.77.16
************************************************************************************
--
View this message in context: http://matplotlib.1069221.n5.nabble.com/Making-space-for-a-long-legend-outside-of-a-barchart-tp41088p41105.html
Sent from the matplotlib - users mailing list archive at Nabble.com.

Hi Chao,
ChaoYue wrote:
> Dear Martin,
> 
> I worked out a similar example for your reference as I don't catch your example very well.
I think you got the idea quite well.
> 
> fig = plt.figure() 
> ax1 = fig.add_subplot(211) 
> ax2 = fig.add_subplot(212) 
> arrlist = [np.random.normal(size=100) for i in range(50)] 
> ret = ax1.hist(arrlist,histtype='barstacked') 
> reclist = [patchlist[0] for patchlist in ret[2]] 
> labellist = ['data'+str(i) for i in range(50)] 
> ax2.legend(reclist,labellist,loc='upper left',bbox_to_anchor=(0,0,1,1),borderaxespad=0.,ncol=5,mode='expand')
> ax2.set_frame_on(False) 
> ax2.tick_params(bottom='off',left='off',right='off',top='off') 
> plt.setp(ax2.get_yticklabels(),visible=False) 
> plt.setp(ax2.get_xticklabels(),visible=False) 
> 
I added plt.show() and it demonstrates my problem: the legend is not complete in the
figure. That is why I think I could instead use:
import pylab as plt
import numpy as np
fig = plt.figure()
DefaultSize = tuple(fig.get_size_inches())
fig.set_size_inches(DefaultSize[0], 4*DefaultSize[1])
ax1 = fig.add_subplot(411)
ax2 = fig.add_subplot(412)
arrlist = [np.random.normal(size=100) for i in range(50)]
ret = ax1.hist(arrlist,histtype='barstacked')
reclist = [patchlist[0] for patchlist in ret[2]]
labellist = ['data'+str(i) for i in range(50)]
ax2.legend(reclist,labellist,loc='upper left',bbox_to_anchor=(0,0,1,1),borderaxespad=0.,ncol=5,mode='expand')
ax2.set_frame_on(False)
ax2.tick_params(bottom='off',left='off',right='off',top='off')
plt.setp(ax2.get_yticklabels(),visible=False)
plt.setp(ax2.get_xticklabels(),visible=False)
plt.show()
But, this does not make the image 4* taller than I thought. But thank you
for the example how to extract the legend of ax1 and place it under ax2.
> 
> you're asking some object-oriented way, I personally don't think
> using pylab and set_tight_layout are the good way to be
> "object-oriented" as pylab is only a bounding wrapper by my
> understanding (maybe I am wrong!). legend and hist are all
> matplotlib.axes.Axes method.
> 
> Also, I think it's unrealistic to ask the figure do a nice job for
> you if there are 50 legend handlers and you want to show them in 2
> columns with a very high width/height ratio of the figure....
The problem is that the data are calculated dynamically and sometimes
I need to display data for 20 data types while sometimes for 200 data
types (and for each I need a legend).
I did not show that but I do calculate how many columns I could use
legend display and pass that via pylab.legend(..., ncol= ). Of course
at the same time I could calculate whether I will need 2 or 3 or 4
subplots on the page (the first will be the barchart itself), the
remaining space will be used by the long legend of subplot(211).
I would hope that matplotlib does not mind that I actually issue any
fig.add_subplot() foe the third or even fourth subplot at all. That
would be just a trick to get more space for the legend. If I can live
with just with subplot(211) and subplot(212)
The fig.savefig('foobar.png', bbox_inches='tight') which Ben mentioned
yesterday is nice but I want it to crop the image only vertically.
An optional argument like:
fig.savefig('foobar.png', bbox_inches='tight', keep_fig_width=True)
would maybe do the job for me.
What I still don't understand what is resizing the image in tight_layout.
It doesn't seem to me that just the unused border space is chopped away.
Fonts look different, ratio between x and y axes lengths seems different.
Certainly not what I want.
> hope it could be of a bit help,
Sure, I am still learning to use matplotlib. 
Martin
> 
> cheers,
> 
> Chao
> 
> 
> On Mon, May 20, 2013 at 6:43 PM, Martin Mokrejs [via matplotlib] <[hidden email] </user/SendEmail.jtp?type=node&node=41102&i=0>> wrote:
> 
> Hi Ben,
> 
> Benjamin Root wrote:
> 
> >
> >
> >
> > On Mon, May 20, 2013 at 12:02 PM, Martin Mokrejs <[hidden email] <http://user/SendEmail.jtp?type=node&node=41090&i=0> <mailto:[hidden email] <http://user/SendEmail.jtp?type=node&node=41090&i=1>>> wrote:
> >
> > Hi,
> > I am having trouble to get space allocated for a long legend text,
> > lets say spanning 2/3 - 3/4 of the whole output. I would like to have
> > stacked barchart as 1st subplot and the place of remaining 3 subplots
> > to be actually allocated by the legend. Alternatively, could I get the
> > legend saved into a separate figure?
> >
> > Or could the space for legend text be allocated automatically minimizing
> > output figure size? For example, the width would be 1120px while height
> > be multiples of 840px (840 for each subplot)?
> >
> > Attached is a quick example. It shows also that I tried tight_layout()
> > but wasn't successful with this either. I would be glad for some help,
> > ideally converting the whole thing into an object-oriented approach.
> > I am generating several figures in a row and would like to clear()/del()
> > any previously used data ASAP.
> >
> >
> > Thank you,
> > Martin
> > Am using mpl-1.2.2
> >
> >
> > Try "fig.savefig('foobar.png', bbox_inches='tight')" when saving the
> > image. It will make the figure size such that all the visible
> > elements of the figure will fit into the saved output. tight_layout()
> > is meant to make sure the elements don't overlap each other, but does
> > nothing about making sure nothing gets clipped.
> Ah, would be nice to make this clear in the docs. So far was doing
> 
> 
> import pylab
> F = pylab.gcf()
> F.set_tight_layout(True)
> 
> which as you say does not help the way I thought.
> 
> 
> Unfortunately, while
> 
> fig.savefig('foobar.png', bbox_inches='tight')
> 
> helped to get everything into the .png file (attached), the barchart itself
> should span according to the code I posted just 1/2 of the figure. But somehow
> it is enlarged and rescaled so that it occupies *more than* 1/2 of the figure.
> What in pylab is resizing my image? Note: the final image is 625x1075.
> 
> Martin
> 
> ------------------------------------------------------------------------------
> AlienVault Unified Security Management (USM) platform delivers complete
> security visibility with the essential security capabilities. Easily and
> efficiently configure, manage, and operate all of your security controls
> from a single console and one unified framework. Download a free trial.
> http://p.sf.net/sfu/alienvault_d2d
> _______________________________________________
> Matplotlib-users mailing list
> [hidden email] <http://user/SendEmail.jtp?type=node&node=41090&i=2>
> https://lists.sourceforge.net/lists/listinfo/matplotlib-users
> 
> *foobar.png* (132K) Download Attachment <http://matplotlib.1069221.n5.nabble.com/attachment/41090/0/foobar.png>
> 
> 
> ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
> If you reply to this email, your message will be added to the discussion below:
> http://matplotlib.1069221.n5.nabble.com/Making-space-for-a-long-legend-outside-of-a-barchart-tp41088p41090.html
> To start a new topic under matplotlib - users, email [hidden email] </user/SendEmail.jtp?type=node&node=41102&i=1>
> To unsubscribe from matplotlib, click here.
> NAML <http://matplotlib.1069221.n5.nabble.com/template/NamlServlet.jtp?macro=macro_viewer&id=instant_html%21nabble%3Aemail.naml&base=nabble.naml.namespaces.BasicNamespace-nabble.view.web.template.NabbleNamespace-nabble.view.web.template.NodeNamespace&breadcrumbs=notify_subscribers%21nabble%3Aemail.naml-instant_emails%21nabble%3Aemail.naml-send_instant_email%21nabble%3Aemail.naml> 
> 
> 
> 
> 
> -- 
> ***********************************************************************************
> Chao YUE
> Laboratoire des Sciences du Climat et de l'Environnement (LSCE-IPSL)
> UMR 1572 CEA-CNRS-UVSQ
> Batiment 712 - Pe 119
> 91191 GIF Sur YVETTE Cedex
> Tel: (33) 01 69 08 29 02; Fax:01.69.08.77.16
> ************************************************************************************
> 
> ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
> View this message in context: Re: Making space for a long legend outside of a barchart <http://matplotlib.1069221.n5.nabble.com/Making-space-for-a-long-legend-outside-of-a-barchart-tp41088p41102.html>
> Sent from the matplotlib - users mailing list archive <http://matplotlib.1069221.n5.nabble.com/matplotlib-users-f3.html> at Nabble.com.
> 
> 
> ------------------------------------------------------------------------------
> Try New Relic Now & We'll Send You this Cool Shirt
> New Relic is the only SaaS-based application performance monitoring service 
> that delivers powerful full stack analytics. Optimize and monitor your
> browser, app, & servers with just a few lines of code. Try New Relic
> and get this awesome Nerd Life shirt! http://p.sf.net/sfu/newrelic_d2d_may
> 
> 
> 
> _______________________________________________
> Matplotlib-users mailing list
> Mat...@li...
> https://lists.sourceforge.net/lists/listinfo/matplotlib-users
>