"newbie: Excel to text"

shilaskishilaski MemberPosts:8Contributor II
edited May 2019 inHelp
Here is my project scope. I have an excel spreadsheet of warranty claims with around 9100 entries. One of the columns within the spreadsheet contains a comment section. This section is where a tech will write what was wrong with the vehicle. These sections are what I want to text mine.

I have figured out how to load the sheet and run it thru the filter so I am just concentrating on data that I am interested in. Now I am guessing that I need to use the text plugin tool to create word vectors (please tell me if I am wrong). It appears that the textinput operator expects an exampleset as it's input from a directory. My question is how to correctly load the textinput operator. Of couse I could be completely wrong...maybe there is a better way to do this?

Here is what I have




















Answers

  • TobiasMalbrechtTobiasMalbrecht Moderator, Employee, MemberPosts:294RM Product Management
    Hi Stacy,

    in principal you are right. You simply have to use the [tt]StringTextInput[/tt] operator instead of the [tt]TextInput[/tt]. The first one will load the texts from strings form an already present example set. The latter one will load the texts from files directly.

    Hope that helps,
    regards,
    Tobias
  • shilaskishilaski MemberPosts:8Contributor II
    Alright...Here is where I am at..


















    <操作符名称= " EnglishStopwordFilter " class = "英格兰ishStopwordFilter">







    <操作符名称= " CorpusBasedWeighting" class="CorpusBasedWeighting">






    Problem now is that I keep on getting an error

    Error in: StringTextInput (StringTextInput) The input example set does not contain any attributes with value type string. Some operators require example sets with attributes of a specific value type. Please refer to the documentation of the used operators for further details.
  • shilaskishilaski MemberPosts:8Contributor II
    figured it out. Somehow I missed called out the parameter for which column I wanted. Had it called out before, but I supposed I should have troubleshot it before posting to the forums.

    Thanks
Sign InorRegisterto comment.