Archie
  • Member for 6 years, 2 months
  • Last seen more than a month ago
  • Ghent, België
When should I use Gini Impurity as opposed to Information Gain (Entropy)?
36 votes

Generally, your performance will not change whether you use Gini impurity or Entropy. Laura Elena Raileanu and Kilian Stoffel compared both in "Theoretical comparison between the gini index and ...

View answer
AUC and classification report in Logistic regression in python
Accepted answer
6 votes

In order to calculate the AUC, you need to have probabilities. Therefore you should use the following function: roc=roc_auc_score(y_test, model.predict_proba(X_test)[:,1]) This will give you the ...

View answer
Binary Neural Network Classification or Multiclass Neural Network Classification?
Accepted answer
4 votes

I think you are making things more confusing then they are. Binary In this case you have two possible outputs: Obama = 1. Not-Obama (who in this case can only be Romney) = 0. Multi-Class In ...

View answer
Modern Feature Selection Review/Resources
Accepted answer
3 votes

I looked into it quite recently and found these papers: Saeys et al. (2007) (also already a bit dated, but a good overview, and I think the 'key' paper in this area). Dougherty et al. (2009) (...

View answer
How relevant is Self Organizing Maps in today's science?
2 votes

To give a practical example, still quite relevant. In the field of flow cytometry, a recent (2015) clustering algorithm, FlowSom, makes use of self-organizing maps. Even more recently (2016, see ...

View answer
Feature importance with scikit-learn Random Forest shows very high Standard Deviation
2 votes

Your result is not that weird. As lanenok states, you should in a first step increase the number of trees in order to make sure that you get a 'statistical' result concerning the feature importances. ...

View answer
Gradient boosting algorithm example
2 votes

As it states, the following presentation is a 'gentle' introduction to Gradient Boosting, I found it quite helpful when figuring out Gradient Boosting; there is a fully explained example included. ...

View answer
Is it advisable to combine two dataset?
1 votes

To add to this discussion, a proper evaluation will tell you quite a bit, and can be used to present the work: Create a test set for dataset 1. Create a test set for dataset 2. Train a model using ...

View answer