# Why initialization of Xgboost DMatrix reducec features number?

I am trying to understand following case:

1. when I create new xgbost DMatrix

xgX = xgb.DMatrix(X, label=Y, missing=np.nan)

2. based on input data X with 64 features

3. I got the new DMatrix with 55 features

What the magic is doing here? Any advise would be great!

• Without looking at the code it is difficult to tell what is happening. Can you share your X and Y shape. Apr 7 '18 at 17:33