I have a dataset with between 10,000 and 100,000 feature values. The number of datapoints is between 1,000 and 10,000. I want to perform a LASSO on this dataset but can't really find any good software to do so. Does anyone have any suggestions?
- Anybody can ask a question
- Anybody can answer
- The best answers are voted up and rise to the top
Check the article by Wu Chen Hastie Sobel Lange - Genome-wide association analysis by lasso penalized logistic regression - 2009. They mention a 'swindle' that is not hard to implement + then you can simply work with glmnet (there is a new version out recently which promises a performance improvement but I haven't had a chance to check it out).