Data and AI Learning Group

 View Only
  • 1.  Class Variable

    Posted Wed January 26, 2022 10:57 AM
    Hi , Wish you Happy New Year 2022 to all of you.
    I am a beginner to learn data science with AI. Please guide me regarding, while learning from the available datasets at UCI Machine Learning repository PIMA Indian Data Set. There is one class label that indicates Diabetes Yes or No. But while collecting real-time data from the clinical labortory it does not contain such a class label. So do I create the class label for predicting disease from available laboratory datasets at my place? Does it necessary to have a class value column in the dataset while building a machine learning classifier model? Please suggest.

    Ranjit Gawande
    Asst. Prof. Computer Engg.
    MCOERC. Nashik M.S. Inida

  • 2.  RE: Class Variable

    Posted Thu January 27, 2022 05:02 AM
     Wish Happy New Year 2022 to all of you.

    Hope the year and years to come bring greater success and a lot of happiness to you

    Soumitra Bhattacharya 

  • 3.  RE: Class Variable

    Posted Fri January 28, 2022 03:06 PM
    Hi Ranjit,
    The Diabetes variable is the dependent variable: it is the outcome that is being predicted. A data set like the PIMA Indian data set is used to practice creating a model to predict that outcome (whether or not a person has diabetes), and the outcome variable is not used as input to the model. The other variables are used as input to predict that outcome. Once the model is trained and ready to use, the model would then be applied to new data (such as you have collected from the clinical lab) and the model would generate its prediction of of the outcome (Diabetes - yes or no) for each new patient record it receives.
    I hope this is helpful.

    Jillian Goodwyn