What is ExtraTrees Classifier?

preview_player
Показать описание
ExtraTrees Classifier is an ensemble method which is much faster than RandomForest yet equall accurate. Extra trees seem much faster (about three times) than the random forest method (at, least, in scikit-learn implementation). This is consistent with the theoretical construction of the two learners.

On toy datasets, the following conclusions could be reached :
- Extra trees seem to keep a higher performance in presence of noisy features,
- When all the variables are relevant, both methods seem to achieve the same performance.

If you do have any questions with what we covered in this video then feel free to ask in the comment section below & I'll do my best to answer those.

If you enjoy these tutorials & would like to support them then the easiest way is to simply like the video & give it a thumbs up & also it's a huge help to share these videos with anyone who you think would find them useful.

Please consider clicking the SUBSCRIBE button to be notified for future videos & thank you all for watching.

You can find me on:

#ExtraTreesClassifier #ExtraTreeClassifier #Ensemble #MachineLearning #ML #DataScience
Рекомендации по теме
Комментарии
Автор

Wiki (and the paper they reference) says that extra trees take the entire dataset for training, not a sample without replacement.Plus I don't understand what you mean by the point to split on is randomly selected. If that is the case what is the algorithm optimizing?


I haven't read up extensively, but from what I can make out, some of the splits are random (which is supposed to be a hyper parameter). If we use too many random splits we are essentially not training anything.

RaunakThomas
Автор

It is not essential to choose square root of the number of features in individual trees of a random forest. However, this can be used as the initial value for cross-validation.

radicalpotato
Автор

Does each tree in a random forest use sqrt(n_features) or each node? As per your video you mention it is the former but to my understanding it is the latter.

vinaybharath
Автор

Hi Bhavesh, The video is very insightful, I came across it while using ranger package along with the splitting rule of variance. Can you please help, where can I find good resources to know more about it apart from CRAN repository

ransinghray
Автор

Dope quality
...! Man just take 1 min to subscribe ....

Thank you please make more videos on beginners to how to start on kaggle

subhaniguddu