Greetings to all.
First of all I'd like to say thanks publicly to Albyn Jones, John
Maindonald, Nick Ellis and John Wallace for their advice.
I was given the data frames in excel format and I used the import.file
command. For some strange reason the columns involved (factors) in my
warning messages gave the same output when applied functions such as mode,
levels,attributes and class but not to the summary command !!, summary said
that one of the columns had NAs and blanks ("") and the other did not, so
the warning message only said that the blanks were converted to NAs. So this
was probably a problem in the Excel files' cell properties.
What I don't get to understand is why levels() did not tell me about this
difference (?).
The conclusion is: use every mean you can imagine to check that both data
frames have same class and levels in every pair of columns.
Regards.
Ignacio Ramos
Escuela de Finanzas BBV - Data Mining
mailto:ira@hti-task.com
-----------------------------------------------------------------------
This message was distributed by s-news@wubios.wustl.edu. To unsubscribe
send e-mail to s-news-request@wubios.wustl.edu with the BODY of the
message: unsubscribe s-news
|