I am new to machine learning and what ever I study related to it has an advice that we should understand the data and select features wisely before start creating the model. For this they demonstrate some data visualization plots like histogram and scatter plots.

Though I understand what they represent but I am not able to understand how to interpret them for feature selection. Are there some thumb rules or patterns which we can follow or observe to understand data and decide which features might be good for my model.

  • $\begingroup$ Tukey, John Wilder (1977). Exploratory Data Analysis. Addison-Wesley. ISBN 978-0-201-07616-5. $\endgroup$ – Alexis Jul 27 '19 at 3:51
  • $\begingroup$ Scatter plot is used to display the relation between two variables, and useful for model building. Histogram is used to display the empirical MARGINAL distribution; Modeling is CONDITIONAL distribution. So Histogram is useless for modeling. $\endgroup$ – user158565 Jul 27 '19 at 16:32

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.