Predictive analysis of text

amotley

I am using predictive analysis to predict missing valolues in my data set. However, I can only get it to predict numerical values, and only based on patterns of other numerical values. 

How can I predict textual values, based on both numerical and text values that are in my data set, and do the same thing for numerical values?

YYH

You are working on the missing data. Have you tried missing value imputation operator Impute Missing Values in Rapidminer?

Let's give you an example.

Recall that we have missing values in titanic passenger data. In the attached process we can leverage some supervised learners, K-NN or Naïve Bayes or any preferred algorithm, nested inside the ‘impute missing values’ to estimate missing values. I used a K-NN (k=3) scheme to impute the missing values of Age (num), Passenger Fare(num), and Cabin(polynomial or 'text' as you name), Port of Embarkation (polynomial), etc. 

Hope this helps.

 

imputation.PNG

imputation.zip