- scikit-feature
- Numpy
- Matplotlib
http://stats.stackexchange.com/questions/973/free-data-set-for-very-high-dimensional-classification
For testing:
- MNIST: 64x1797 (Handwritten Digits)
- Colon 2000x62 (Gene expression) http://genomics-pubs.princeton.edu/oncology/affydata/index.html
- Gisette: 5000x13500 (Handwritten Digits) http://archive.ics.uci.edu/ml/datasets/Gisette
- Arcena 10000x900 (mass-spectrometric) http://archive.ics.uci.edu/ml/datasets/Arcene
Final data sets:
- Dexter: 20000x2600 (Bag of Word) http://archive.ics.uci.edu/ml/datasets/Dexter
- Dorothea: 100000x1950 (Gene expression) http://archive.ics.uci.edu/ml/datasets/Dorothea
- PEMS: 138672 x 440 http://archive.ics.uci.edu/ml/datasets/PEMS-SF
