Memory error while plotting dataframe (matplotlib)

Question

I'm using Pandas with Jupyter Notebook and trying to plot a small dataframe:

and when i'm inserting the following line:

df9.plot(x='Time', y='Pressure mean')

I'm getting the following error:

---------------------------------------------------------------------------
MemoryError                               Traceback (most recent call last)
<ipython-input-8-c789b8162a1a> in <module>()
----> 1 df9.plot(x='Time', y='Pressure mean')

C:\Anaconda3\lib\site-packages\pandas\tools\plotting.py in __call__(self, x, y, kind, ax, subplots, sharex, sharey, layout, figsize, use_index, title, grid, legend, style, logx, logy, loglog, xticks, yticks, xlim, ylim, rot, fontsize, colormap, table, yerr, xerr, secondary_y, sort_columns, **kwds)
   3735                           fontsize=fontsize, colormap=colormap, table=table,
   3736                           yerr=yerr, xerr=xerr, secondary_y=secondary_y,
-> 3737                           sort_columns=sort_columns, **kwds)
   3738     __call__.__doc__ = plot_frame.__doc__
   3739 

C:\Anaconda3\lib\site-packages\pandas\tools\plotting.py in plot_frame(data, x, y, kind, ax, subplots, sharex, sharey, layout, figsize, use_index, title, grid, legend, style, logx, logy, loglog, xticks, yticks, xlim, ylim, rot, fontsize, colormap, table, yerr, xerr, secondary_y, sort_columns, **kwds)
   2609                  yerr=yerr, xerr=xerr,
   2610                  secondary_y=secondary_y, sort_columns=sort_columns,
-> 2611                  **kwds)
   2612 
   2613 

C:\Anaconda3\lib\site-packages\pandas\tools\plotting.py in _plot(data, x, y, subplots, ax, kind, **kwds)
   2436         plot_obj = klass(data, subplots=subplots, ax=ax, kind=kind, **kwds)
   2437 
-> 2438     plot_obj.generate()
   2439     plot_obj.draw()
   2440     return plot_obj.result

C:\Anaconda3\lib\site-packages\pandas\tools\plotting.py in generate(self)
   1029 
   1030         for ax in self.axes:
-> 1031             self._post_plot_logic_common(ax, self.data)
   1032             self._post_plot_logic(ax, self.data)
   1033 

C:\Anaconda3\lib\site-packages\pandas\tools\plotting.py in _post_plot_logic_common(self, ax, data)
   1157                 ax.set_xticklabels(xticklabels)
   1158             self._apply_axis_properties(ax.xaxis, rot=self.rot,
-> 1159                                         fontsize=self.fontsize)
   1160             self._apply_axis_properties(ax.yaxis, fontsize=self.fontsize)
   1161         elif self.orientation == 'horizontal':

C:\Anaconda3\lib\site-packages\pandas\tools\plotting.py in _apply_axis_properties(self, axis, rot, fontsize)
   1205 
   1206     def _apply_axis_properties(self, axis, rot=None, fontsize=None):
-> 1207         labels = axis.get_majorticklabels() + axis.get_minorticklabels()
   1208         for label in labels:
   1209             if rot is not None:

C:\Anaconda3\lib\site-packages\matplotlib\axis.py in get_majorticklabels(self)
   1159     def get_majorticklabels(self):
   1160         'Return a list of Text instances for the major ticklabels'
-> 1161         ticks = self.get_major_ticks()
   1162         labels1 = [tick.label1 for tick in ticks if tick.label1On]
   1163         labels2 = [tick.label2 for tick in ticks if tick.label2On]

C:\Anaconda3\lib\site-packages\matplotlib\axis.py in get_major_ticks(self, numticks)
   1288         'get the tick instances; grow as necessary'
   1289         if numticks is None:
-> 1290             numticks = len(self.get_major_locator()())
   1291         if len(self.majorTicks) < numticks:
   1292             # update the new tick label properties from the old

C:\Anaconda3\lib\site-packages\pandas\tseries\converter.py in __call__(self)
    876             vmin, vmax = vmax, vmin
    877         if self.isdynamic:
--> 878             locs = self._get_default_locs(vmin, vmax)
    879         else:  # pragma: no cover
    880             base = self.base

C:\Anaconda3\lib\site-packages\pandas\tseries\converter.py in _get_default_locs(self, vmin, vmax)
    857 
    858         if self.plot_obj.date_axis_info is None:
--> 859             self.plot_obj.date_axis_info = self.finder(vmin, vmax, self.freq)
    860 
    861         locator = self.plot_obj.date_axis_info

C:\Anaconda3\lib\site-packages\pandas\tseries\converter.py in _daily_finder(vmin, vmax, freq)
    481                     Period(ordinal=int(vmax), freq=freq))
    482     span = vmax.ordinal - vmin.ordinal + 1
--> 483     dates_ = PeriodIndex(start=vmin, end=vmax, freq=freq)
    484     # Initialize the output
    485     info = np.zeros(span,

C:\Anaconda3\lib\site-packages\pandas\tseries\period.py in __new__(cls, data, ordinal, freq, start, end, periods, copy, name, tz, **kwargs)
    186             else:
    187                 data, freq = cls._generate_range(start, end, periods,
--> 188                                                  freq, kwargs)
    189         else:
    190             ordinal, freq = cls._from_arraylike(data, freq, tz)

C:\Anaconda3\lib\site-packages\pandas\tseries\period.py in _generate_range(cls, start, end, periods, freq, fields)
    200                 raise ValueError('Can either instantiate from fields '
    201                                  'or endpoints, but not both')
--> 202             subarr, freq = _get_ordinal_range(start, end, periods, freq)
    203         elif field_count > 0:
    204             subarr, freq = _range_from_fields(freq=freq, **fields)

C:\Anaconda3\lib\site-packages\pandas\tseries\period.py in _get_ordinal_range(start, end, periods, freq, mult)
   1026                              dtype=np.int64)
   1027     else:
-> 1028         data = np.arange(start.ordinal, end.ordinal + 1, mult, dtype=np.int64)
   1029 
   1030     return data, freq

MemoryError:

What is the problem ? I can't figure it out. Thanks !

How many rows are in your dataframe?

Mike Müller
– Mike Müller

2016-04-23 07:23:16 +00:00
Commented Apr 23, 2016 at 7:23 — Mike Müller
– Mike Müller, Commented Apr 23, 2016 at 7:23
24, it's a very small one

ValientProcess
– ValientProcess

2016-04-23 07:30:03 +00:00
Commented Apr 23, 2016 at 7:30 — ValientProcess
– ValientProcess, Commented Apr 23, 2016 at 7:30

hyamanieu · Accepted Answer · 2016-11-07 13:49:47Z

2

The issue originates from using TimedeltaIndex (or timedelta) for your time column. It was reported there: https://github.com/pydata/pandas/issues/8711 No solution has been brought to us yet.

As an alternative solution, I invite you to convert your data to DateTime or DateTimeIndex. Let's say YourDate contains the starting date of your observations.

df9.index = pd.DatetimeIndex(pd.datetime.strptime(YourDate,'%d.%m.%Y %H:%M:%S')
                            +df9['Time'])
df9.plot(y='Pressure mean')

Note that it will plot only the hours if you have less than 24 hours.

EDIT (2016-11-07): I can now use timedelta as index and plot correctly. This is how I proceed (assuming I have float numbers indicating hours):

converter = {'Time[h]' : lambda x: pd.to_timedelta(float(x),unit='h')}#converts float to timedelta
df = pd.read_csv(fpath, sep='\t', 
                 skiprows=len(comments),#header
                 names=dt.keys(),#you need of course your own dtype
                 dtype=dt,#you need of course your own dtype
                 encoding='latin-1',#European data...
                 skipinitialspace=True,
                 converters=converter)
df = df.set_index('Time[h]')#time column to index.

edited Nov 7, 2016 at 13:49

answered Sep 8, 2016 at 15:01

hyamanieu

1,11510 silver badges28 bronze badges

Sign up to request clarification or add additional context in comments.

2 Comments

djmac Over a year ago

Have also come across this issue with a very small data frame (as small as 3*12). Similar to above, reseting index (to integers) allowed data to plot.. (and setting xticklabels to Timedelta column in re-indexed dataframe allows timedelta information to display). Only really relevant/useful for for small dataframes I guess.

hyamanieu Over a year ago

I could use time delta as index with the last pandas update and updated my own packages accordingly. I'm editing my answer on this matter.

ManJan · Accepted Answer · 2017-03-21 23:10:30Z

0

As Wli mentioned, it is a bug still to be fixed. But as a workaround this worked for me. -

plt.plot(s.index,s.values)

answered Mar 21, 2017 at 23:10

ManJan

4,0113 gold badges22 silver badges22 bronze badges

Collectives™ on Stack Overflow

Memory error while plotting dataframe (matplotlib)

2 Answers 2

2 Comments

Comments

Your Answer

Linked

Hot Network Questions

Collectives™ on Stack Overflow

2 Answers 2

2 Comments

Comments

Your Answer

Sign up or log in

Post as a guest

Linked

Related