two data set

Far
Far New Altair Community Member
edited November 2024 in Community Q&A
hi everyone,

i am trying to use two data set (training and testing) for applying a model. as my data is consisting of both text and structured attributes i divided it into two part (text and structured) and i stored both data separately. but when i am applying the model ( i need to use 3 model multiple regression, GBT and Neural Net) and i want to test the model with anothet data set which is test.data, i don't know how i can apply all processes to test data and check the model.


so, i used sub process operator and put all process are used for training data set and just sync it to apply model.

but i'm note sure i'm doing the write thing or not.
however i have to use both data set and i cannot use split operator instead.

can anyone help me with that?
Tagged:

Best Answer

  • Telcontar120
    Telcontar120 New Altair Community Member
    Answer ✓
    I don't know how large your dataset is, but I would generally recommend using Cross Validation.  In your process you are training your model on a single sample.

Answers

  • varunm1
    varunm1 New Altair Community Member
    Hello @Far,

    Can you share XML code? To access the code, you need to go to View --> Show Panel --> XML and copy that and paste it here.

    Thanks
  • Far
    Far New Altair Community Member
    edited October 2019
    here is my xml:



    thanks
  • Far
    Far New Altair Community Member
    this is the path i'm following to use both training and testing data set
  • varunm1
    varunm1 New Altair Community Member
    Hello @Far

    Are you encountering any error or are you just asking us if this is the right way to do? 

    Your process looks fine based on my assumption that you already processed train data similar to test data earlier. 
  • Telcontar120
    Telcontar120 New Altair Community Member
    Answer ✓
    I don't know how large your dataset is, but I would generally recommend using Cross Validation.  In your process you are training your model on a single sample.