How do you understand a dataset when there is no metadata given (no details about the attributes given in the dataset)? It is difficult to comprehend the attribute names as only the short forms are given.

It's given to me that 'pm2.5' is the target variable. How do I understand which independent variables will affect this target variable?

enter image description here

  • $\begingroup$ Do you know data is from which domain? Use that fact or simply thrown in a xgb model first and get the feature importance and then start peeling the data so that you can understand it better! Seems to me it's from Weather Background! $\endgroup$
    – Aditya
    Nov 11, 2018 at 6:16
  • $\begingroup$ dont post the images in community pls $\endgroup$
    – sai saran
    Nov 14, 2018 at 14:51

1 Answer 1


The aim is to predict pm2.5 ( target variable ).

Step 1: Data Cleaning. Remove unwanted features and fill the missing values.

Step 2: To learn about the features, perform data visualization. You can plot a linear plot with TEMP and pm2.5 and see how it varies with change in temp.

Step 3: The next step is to find the relationship between features. Some features are not needed for prediction. Remove those features.

Step 4: Apply a suitable machine learning technique and predict.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.