Welcome to HyperLearn!¶
HyperLearn aims to make Machine Learning algorithms run in at least 50% of their original time. Algorithms from Linear Regression to Principal Component Analysis are optimized by using LAPACK, BLAS, and parallelized through Numba.
Some key current achievements of HyperLearn:
- 70% less time to fit Least Squares / Linear Regression than sklearn + 50% less memory usage
- 50% less time to fit Non Negative Matrix Factorization than sklearn due to new parallelized algo
- 40% faster full Euclidean / Cosine distance algorithms
- 50% less time LSMR iterative least squares
- New Reconstruction SVD - use SVD to impute missing data! Has .fit AND .transform. Approx 30% better than mean imputation
- 50% faster Sparse Matrix operations - parallelized
- RandomizedSVD is now 20 - 30% faster
Example code¶
Singular Value Decomposition
import hyperlearn as hl
U, S, VT = hl.linalg.svd(X)
Pseudoinverse of a matrix using Cholesky Decomposition
from hyperlearn.linalg import pinvc
inv = pinvc(X)
# check if pinv(X) * X = identity
check = inv.dot(X)
QR Decomposition wanting only Q matrix
from hyperlearn import linalg
Q = linalg.qr(X, Q_only = True)
# check if Q == Q from full QR
q, r = linalg.qr(X)
- hyperlearn
- hyperlearn package
- Submodules
- hyperlearn.base module
- hyperlearn.linalg module
- hyperlearn.utils module
- hyperlearn.random module
- hyperlearn.exceptions module
- hyperlearn.multiprocessing module
- hyperlearn.numba module
- hyperlearn.solvers module
- hyperlearn.stats module
- hyperlearn.big_data.base module
- hyperlearn.big_data.incremental module
- hyperlearn.big_data.lsmr module
- hyperlearn.big_data.randomized module
- hyperlearn.big_data.truncated module
- hyperlearn.decomposition.base module
- hyperlearn.decomposition.NMF module
- hyperlearn.decomposition.PCA module
- hyperlearn.decomposition.PCA module
- hyperlearn.discriminant_analysis.base module
- hyperlearn.discriminant_analysis.QDA module
- hyperlearn.impute.SVDImpute module
- hyperlearn.metrics.cosine module
- hyperlearn.metrics.euclidean module
- hyperlearn.metrics.pairwise module
- hyperlearn.sparse.base module
- hyperlearn.sparse.csr module
- hyperlearn.sparse.tcsr module
- Module contents
- hyperlearn package
- hyperlearn.base
- hyperlearn.linalg
- License
- Contact