Problems importing file with SAS Enterprise Miner

[Fargstar]

Hello there!

I am trying to import files to SAS Enterprise Miner using the File Import node. However, I noticed that every file (.txt files) that starts with Xref or Path (capitalized) are imported without any content, just plain blank text files, but if I uncapitalize Xref or Path the all file's content will be imported.
The files I cannot import looks like this:
https://github.com/yassersouri/classify-text/blob/master/dataset/sci.crypt/14987
or this:
http://www.cs.cmu.edu/afs/cs/project/theo-11/www/naive-bayes/20_newsgroup/alt.atheism/51224

See attached another sample file.

I would like to know if there is any setting in SAS Enterprise Miner which I can use to correctly import these files, and I also would like to understand why these files are not being imported.

[DougWielenga · Accepted solution]

From the SAS Enterprise Miner help, the File Import node is designed to convert selected external flat files, spreadsheets, and database tables into a format that Enterprise Miner recognizes as a data source and can use in data mining process flow diagrams.  The files you are describing are text files that can be used by text miner.  These files would not need to be imported into SAS Enterprise Miner to be used as text; instead, they would need to be put in a particular location with other text files where the Text Miner nodes could access them and analyze them.

I hope this helps!

Doug

[Dz600]

I have used the file import node and it has seemed to work. How do work with my data at this point? I looked at the results page and the data is definitely there.

[DougWielenga]

I have used the file import node and it has seemed to work. How do work with my data at this point? I looked at the results page and the data is definitely there.

I'm not sure what you mean by 'work with my data'.  If the data is in SAS Enterprise Miner, you can use any of the tools that are appropriate for the structure of your data.  For example, if you a column with a target variable value for each observation and other columns with input variables for each observation, you can build predictive models.   If you have only input variables in the columns and no target information, you might try to perform cluster analysis.  It really depends on how your data is structured and what methods it will support to investigate the question you hope to use the data to answer.  In general, you will likely find things easier if you use SAS data sets rather than text files which are not optimized for analytical use, but it is the structure and nature of the data which ultimately defines what can be done with it.   If you can provide more detail as to what your data contains and what you are hoping to accomplish with it, I can try and be more specific.  

Cordially,

Doug

[Dz600]

Thank you for your help. I have solved my problem.