Erro ao plotar DataFrame contendo NaN com Pandas 0.12.0 e Matplotlib 1.3.1 no Python 3.3.2
Primeiro de tudo, esta questão énão o mesmo queeste.
O problema que estou tendo é que quando tento plotar um DataFrame que contém um NaN numpy em uma célula, recebo um erro:
C:\>\Python33x86\python.exe
Python 3.3.2 (v3.3.2:d047928ae3f6, May 16 2013, 00:03:43) [MSC v.1600 32 bit (Intel)] on win32
Type "help", "copyright", "credits" or "license" for more information.
>>> import pandas as pd
>>> import numpy as np
>>> import matplotlib.pyplot as plt
>>>
>>> dates = pd.date_range('20131201', periods=5, freq='H')
>>> data = [[1, 2], [4, 5], [9, np.nan], [16, 17], [25, 26]]
>>> df = pd.DataFrame(data, index=dates,
... columns=list('AB'))
>>>
>>> print(df.to_string())
A B
2013-12-01 00:00:00 1 2
2013-12-01 01:00:00 4 5
2013-12-01 02:00:00 9 NaN
2013-12-01 03:00:00 16 17
2013-12-01 04:00:00 25 26
>>> df.plot()
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "C:\Python33x86\lib\site-packages\pandas\tools\plotting.py", line 1636, in plot_frame
plot_obj.generate()
File "C:\Python33x86\lib\site-packages\pandas\tools\plotting.py", line 856, in generate
self._make_plot()
File "C:\Python33x86\lib\site-packages\pandas\tools\plotting.py", line 1240, in _make_plot
self._make_ts_plot(data, **self.kwds)
File "C:\Python33x86\lib\site-packages\pandas\tools\plotting.py", line 1321, in _make_ts_plot
_plot(data[col], i, ax, label, style, **kwds)
File "C:\Python33x86\lib\site-packages\pandas\tools\plotting.py", line 1295, in _plot
style=style, **kwds)
File "C:\Python33x86\lib\site-packages\pandas\tseries\plotting.py", line 77, in tsplot
lines = plotf(ax, *args, **kwargs)
File "C:\Python33x86\lib\site-packages\matplotlib\axes.py", line 4139, in plot
for line in self._get_lines(*args, **kwargs):
File "C:\Python33x86\lib\site-packages\matplotlib\axes.py", line 319, in _grab_next_args
for seg in self._plot_args(remaining, kwargs):
File "C:\Python33x86\lib\site-packages\matplotlib\axes.py", line 297, in _plot_args
x, y = self._xy_from_xy(x, y)
File "C:\Python33x86\lib\site-packages\matplotlib\axes.py", line 216, in _xy_from_xy
by = self.axes.yaxis.update_units(y)
File "C:\Python33x86\lib\site-packages\matplotlib\axis.py", line 1337, in update_units
converter = munits.registry.get_converter(data)
File "C:\Python33x86\lib\site-packages\matplotlib\units.py", line 137, in get_converter
xravel = x.ravel()
File "C:\Python33x86\lib\site-packages\numpy\ma\core.py", line 3969, in ravel
r._mask = ndarray.ravel(self._mask).reshape(r.shape)
File "C:\Python33x86\lib\site-packages\pandas\core\series.py", line 981, in reshape
return ndarray.reshape(self, newshape, order)
TypeError: an integer is required
O código acima funciona se eu substituir o np.NaN por um número, como "2.3".
Plotagem como duas séries separadas também não funciona (falha quando eu adiciono a série contendo o NaN ao gráfico):
C:\>\Python33x86\python.exe
Python 3.3.2 (v3.3.2:d047928ae3f6, May 16 2013, 00:03:43) [MSC v.1600 32 bit (Intel)] on win32
Type "help", "copyright", "credits" or "license" for more information.
>>> import pandas as pd
>>> import numpy as np
>>> import matplotlib.pyplot as plt
>>>
>>> dates = pd.date_range('20131201', periods=5, freq='H')
>>> data = [[1, 2], [4, 5], [9, np.nan], [16, 17], [25, 26]]
>>> df = pd.DataFrame(data, index=dates,
... columns=list('AB'))
>>>
>>> print(df.to_string())
A B
2013-12-01 00:00:00 1 2
2013-12-01 01:00:00 4 5
2013-12-01 02:00:00 9 NaN
2013-12-01 03:00:00 16 17
2013-12-01 04:00:00 25 26
>>> df['A'].plot(label='This is A', style='k')
<matplotlib.axes.AxesSubplot object at 0x02ACFF90>
>>> df['B'].plot(label='This is B', style='g')
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "C:\Python33x86\lib\site-packages\pandas\tools\plotting.py", line 1730, in plot_series
plot_obj.generate()
File "C:\Python33x86\lib\site-packages\pandas\tools\plotting.py", line 856, in generate
self._make_plot()
File "C:\Python33x86\lib\site-packages\pandas\tools\plotting.py", line 1240, in _make_plot
self._make_ts_plot(data, **self.kwds)
File "C:\Python33x86\lib\site-packages\pandas\tools\plotting.py", line 1311, in _make_ts_plot
_plot(data, 0, ax, label, self.style, **kwds)
File "C:\Python33x86\lib\site-packages\pandas\tools\plotting.py", line 1295, in _plot
style=style, **kwds)
File "C:\Python33x86\lib\site-packages\pandas\tseries\plotting.py", line 77, in tsplot
lines = plotf(ax, *args, **kwargs)
File "C:\Python33x86\lib\site-packages\matplotlib\axes.py", line 4139, in plot
for line in self._get_lines(*args, **kwargs):
File "C:\Python33x86\lib\site-packages\matplotlib\axes.py", line 319, in _grab_next_args
for seg in self._plot_args(remaining, kwargs):
File "C:\Python33x86\lib\site-packages\matplotlib\axes.py", line 297, in _plot_args
x, y = self._xy_from_xy(x, y)
File "C:\Python33x86\lib\site-packages\matplotlib\axes.py", line 216, in _xy_from_xy
by = self.axes.yaxis.update_units(y)
File "C:\Python33x86\lib\site-packages\matplotlib\axis.py", line 1337, in update_units
converter = munits.registry.get_converter(data)
File "C:\Python33x86\lib\site-packages\matplotlib\units.py", line 137, in get_converter
xravel = x.ravel()
File "C:\Python33x86\lib\site-packages\numpy\ma\core.py", line 3969, in ravel
r._mask = ndarray.ravel(self._mask).reshape(r.shape)
File "C:\Python33x86\lib\site-packages\pandas\core\series.py", line 981, in reshape
return ndarray.reshape(self, newshape, order)
TypeError: an integer is required
No entanto, se eu fizer isso diretamente com o plot do Pyplot do Matplotlib (), em vez de usar a função plot () do Pandas, ele funciona:
C:\>\Python33x86\python.exe
Python 3.3.2 (v3.3.2:d047928ae3f6, May 16 2013, 00:03:43) [MSC v.1600 32 bit (Intel)] on win32
Type "help", "copyright", "credits" or "license" for more information.
>>> import pandas as pd
>>> import numpy as np
>>> import matplotlib.pyplot as plt
>>> dates = pd.date_range('20131201', periods=5, freq='H')
>>> plt.plot(dates, [1, 4, 9, 16, 25], 'k', dates, [2, 5, np.NAN, 17, 26], 'g')
[<matplotlib.lines.Line2D object at 0x03E98650>, <matplotlib.lines.Line2D object at 0x040929B0>]
>>> plt.show()
>>>
Então, parece que eu tenho uma solução alternativa, mas como eu plato grandes DataFrames, eu preferiria usar o método plot () do Pandas, o que é mais conveniente. Eu tentei seguir o rastreamento de pilha, mas depois de um tempo fica complicado (eu não estou familiarizado com o código-fonte Pandas, Numpy e Matplotlib). Estou fazendo algo errado, ou isso é um possível bug no enredo do Pandas?
Obrigado pela ajuda!
Eu tentei tanto no Windows x86 e no Linux AMD64 com os mesmos resultados com estas versões:
Python 3.3.2Pandas 0.12.0Matplotlib 1.3.1Numpy 1.7.1