In [3]:
%matplotlib inline

In [4]:
import dask.dataframe as dd
import glob
import os

In [5]:
filenames = [ os.path.splitext(wholeFilename)[0] for wholeFilename in 
             [ os.path.basename(wholePath) for wholePath in glob.glob("../input/2*.xlsx") ] ]

In [6]:
dataFiles = dd.DataFrame({"filename": filenames})
dataFiles["year"], dataFiles["pollutant"], dataFiles["resolution"] = dataFiles["filename"].str.split('_', 2).str


---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-6-30023cd82c41> in <module>()
----> 1 dataFiles = dd.DataFrame({"filename": filenames})
      2 dataFiles["year"], dataFiles["pollutant"], dataFiles["resolution"] = dataFiles["filename"].str.split('_', 2).str

TypeError: __init__() takes exactly 5 arguments (2 given)

In [ ]: