When I want to export the Document Term Matrix I need to specify Maximum Number of Terms and Minimum Term Frequency. So when the table is exported, is there are an order in which the term columns as whole are shown?
Hi @statlover,
The document term matrix is saved in descending order of term count. So, the term with the highest incidence will be the first column in the "Document Terms" column group, and the term with the lowest incidence will be the last column. If terms have the same count they will be ordered alphabetically by the term.
Did you try it?
I generated the DTM and saved it. But I am not sure which terms show up as the first set of columns and which terms come in the lst set of columns, that are exported. Is there a numeric order in which they are displayed? Do terms with high overall frequency come first?
Hi @statlover,
The document term matrix is saved in descending order of term count. So, the term with the highest incidence will be the first column in the "Document Terms" column group, and the term with the lowest incidence will be the last column. If terms have the same count they will be ordered alphabetically by the term.
Thank you very much Julian