python - pandas numpy matplotlib 溢出错误 : date value out of range

Question

我有代码可以爬行目录中的每个文件并绘制遇到的每个 csv 文件。每个 CSV 都有一个格式为

的标题

`Timestamp, P1rms (A), P2rms (A), P3rms (A), P4rms (A), P5rms (A), Vrms (V), P1 theta, P2 theta, P3 theta, P4 theta, P5 theta`. 

Mon Sep 30 00:00:00 2013, 128, 128, 180, 177, 192, 43, 7, 7, 8, 8, 48
Mon Sep 30 00:00:01 2013, 127, 127, 182, 178, 193, 43, 8, 8, 8, 8, 49
# ect....

我正在开发一个 fft 可视化选项，当我 fft 数据集时遇到溢出错误。这是我的确切问题:

当我运行代码时:

#!/usr/bin/env python
from pandas import *
import matplotlib.pyplot as plt
import os
import sys
import platform
import numpy.fft as np

# name of plots folder
plotfold='plots'

# System specific info
if platform.system()=='Darwin':comsep="/"
else: comsep="\\"

# How many columns should I plot?
numcol=6

if len(sys.argv)<2:
   print 'usage: ./canaryCrawler.py [-c] or [-f] rootdir'
   quit()

if len(sys.argv)>2:
   ylim=1500
   root = sys.argv[2]
else:
   ylim=1200
   root = sys.argv[1]

for subdir, dirs, files in os.walk(root):

    # plot each file
    for file in files:

        if str(file)[-4:]=='.csv':

            print 'plotting '+str(file)+'...'
            # load csv as data frame
            df=pandas.io.parsers.read_csv(subdir+comsep+file)
            for i in range(0,len(df.Timestamp)):
                df.Timestamp[i] = datetime.strptime(df.Timestamp[i], '%a %b %d %H:%M:%S %Y')

            # We only want the first 6 collumns
            df = df.ix[:,0:numcol]

            if len(sys.argv)>=2:
                if sys.argv[1]=='-c' or sys.argv[1]=='-f':
                    plotfold='plots_Specialty'
                    df2 = df
                    df=pandas.DataFrame(df2.Timestamp)
                    df['Residence']=df2['P1rms (A)']+df2['P2rms (A)']
                    df['Specialty']=df2['P3rms (A)']+df2['P4rms (A)']
                    if sys.argv[1]=='-f':
                       df2['Residence']=np.fft(df['Residence'])
                       df2['Specialty']=np.fft(df['Specialty'])
                       df=df2
                       print 'Fourier Transformation Complete'
                       plotfold='plots_Specialty_fft'

            # set up plot
            plt.figure()
            df.plot(df.Timestamp,alpha=0.6,linewidth=2.3) # add transparency to see overlapping colors
            plt.tight_layout(pad=1.08)
            plt.legend(loc='best') # add legend in non-intrusive location
            plt.legend(loc=5,prop={'size':14}) # 
            plt.ylabel('Current')
            plt.xlabel('Time')
            plt.gcf().autofmt_xdate()
            plt.gcf().set_size_inches(12.7,9.2)
            plt.gca().set_ylim([0,ylim])

            stamp = df.Timestamp[0]
            day = datetime.strftime(stamp,'%a')
            DOM=datetime.strftime(stamp,'%d')
            month =  datetime.strftime(stamp,'%b')
            year =  datetime.strftime(stamp,'%Y')

            plt.title(subdir+'   '+day+' '+month+' '+DOM+' '+year)

            # keep plot

            # check for existing plots folder, 
            # create one if it doesn't exist
            if plotfold not in os.listdir(subdir):
                print '** adding plots directory to ',subdir
                os.mkdir(subdir+comsep+plotfold)

            # save in plots directory
            spsubs = str(subdir).split(comsep)
            filnam=''
            for piece in range(len(spsubs)-4,len(spsubs)-1):
                filnam+='_'+spsubs[piece]
            filnam+='_'+str(file)[:-4]
            saveto=subdir+comsep+plotfold+comsep+filnam
            print '**** saving plot to ',saveto
            plt.savefig(saveto)
plt.close()

我收到此错误:

kilojoules$ ./canaryCrawler.py -f 35ca7/
/opt/local/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/pandas-0.14.0-py2.7-macosx-10.9-x86_64.egg/pandas/io/excel.py:626: UserWarning: Installed openpyxl is not supported at this time. Use >=1.6.1 and <2.0.0.
  .format(openpyxl_compat.start_ver, openpyxl_compat.stop_ver))
plotting 2014Aug04.csv...
Fourier Transformation Complete
/opt/local/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/numpy-1.8.1-py2.7-macosx-10.9-x86_64.egg/numpy/core/numeric.py:460: ComplexWarning: Casting complex values to real discards the imaginary part
  return array(a, dtype, copy=False, order=order)
/opt/local/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/matplotlib/tight_layout.py:225: UserWarning: tight_layout : falling back to Agg renderer
  warnings.warn("tight_layout : falling back to Agg renderer")
**** saving plot to  35ca7/2014/Aug/plots_Specialty_fft/_Aug_35ca7_2014_2014Aug04
plotting 2014Aug05.csv...
Fourier Transformation Complete
**** saving plot to  35ca7/2014/Aug/plots_Specialty_fft/_Aug_35ca7_2014_2014Aug05
plotting 2014Aug07.csv...
Fourier Transformation Complete
**** saving plot to  35ca7/2014/Aug/plots_Specialty_fft/_Aug_35ca7_2014_2014Aug07
Traceback (most recent call last):
  File "./canaryCrawler.py", line 97, in <module>
    plt.savefig(saveto)
  File "/opt/local/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/matplotlib/pyplot.py", line 561, in savefig
    return fig.savefig(*args, **kwargs)
  File "/opt/local/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/matplotlib/figure.py", line 1421, in savefig
    self.canvas.print_figure(*args, **kwargs)
  File "/opt/local/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/matplotlib/backend_bases.py", line 2220, in print_figure
    **kwargs)
  File "/opt/local/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/matplotlib/backends/backend_agg.py", line 505, in print_png
    FigureCanvasAgg.draw(self)
  File "/opt/local/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/matplotlib/backends/backend_agg.py", line 451, in draw
    self.figure.draw(self.renderer)
  File "/opt/local/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/matplotlib/artist.py", line 55, in draw_wrapper
    draw(artist, renderer, *args, **kwargs)
  File "/opt/local/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/matplotlib/figure.py", line 1034, in draw
    func(*args)
  File "/opt/local/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/matplotlib/artist.py", line 55, in draw_wrapper
    draw(artist, renderer, *args, **kwargs)
  File "/opt/local/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/matplotlib/axes.py", line 2086, in draw
    a.draw(renderer)
  File "/opt/local/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/matplotlib/artist.py", line 55, in draw_wrapper
    draw(artist, renderer, *args, **kwargs)
  File "/opt/local/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/matplotlib/lines.py", line 562, in draw
    drawFunc(renderer, gc, tpath, affine.frozen())
  File "/opt/local/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/matplotlib/lines.py", line 938, in _draw_lines
    self._lineFunc(renderer, gc, path, trans)
  File "/opt/local/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/matplotlib/lines.py", line 978, in _draw_solid
    renderer.draw_path(gc, path, trans)
  File "/opt/local/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/matplotlib/backends/backend_agg.py", line 145, in draw_path
    self._renderer.draw_path(gc, path, transform, rgbFace)
OverflowError: Allocated too many blocks

我将matplotlibrc中的agg.path.chunksize参数指定为agg.path.chunksize:10000000。仅当我运行 -f fft 选项时才会出现此错误。我怎样才能防止这个错误？

Answer 1

不确定，但尝试 pdf、svg 后端

#!/usr/bin/env python
from pandas import *
import matplotlib.pyplot as plt # Insert just before import matplotlib as mpl
mpl.use('pdf')                  # Insert just before import matplotlib as mpl
import matplotlib as mpl

# ['pdf', 'pgf', 'Qt4Agg', 'GTK', 'GTKAgg', 'ps', 'agg', 
# 'cairo', 'MacOSX', 'GTKCairo', 'WXAgg', 'template', 'TkAgg', 
# 'GTK3Cairo', 'GTK3Agg', 'svg', 'WebAgg', 'CocoaAgg', 'emf', 'gdk', 'WX']

# (...)
plt.savefig('svg.pdf') # Consider file extension (!)