2019-02-15 Faster Polynomial Features#
The current implementation of
in scikit-learn computes each new feature
independently and that increases the number of
data exchanged between numpy and Python.
The idea of the implementation in
is to reduce this number by brodcast multiplications.
The second optimization occurs by transposing the matrix:
dense matrix are organized by rows in memory so
it is faster to mulitply two rows than two columns.
See Faster Polynomial Features.