Names show importance after preprocessing

Question

Before building the model, I do the scaling as follows:

X = StandardScaler(with_mean = 0, with_std = 1).fit_transform(X)

and after plotting the importance of functions

xgb.plot_importance(bst, color='red')
plt.title('importance', fontsize = 20)
plt.yticks(fontsize = 10)
plt.ylabel('features', fontsize = 20)

The problem is that instead of the names of the elements, we get f0, f1, f2, f3, etc. ...... How to return the names of objects?

thank

Answer 1

first we get a list of function names before preprocessing

dtrain = xgb.DMatrix( X, label=y)
dtrain.feature_names

Then

bst.get_fscore()
mapper = {'f{0}'.format(i): v for i, v in enumerate(dtrain.feature_names)}
mapped = {mapper[k]: v for k, v in bst.get_fscore().items()}
mapped
xgb.plot_importance(mapped, color='red')

what all

Answer 2

For xgboost 0.82, the answer is quite simple, just replace the element name attribute with a list of element name strings.

trained_xgbmodel.feature_names = feature_name_list
xgboost.plot_importance(trained_xgbmodel)