scripts/builtin/lm.dml

#-------------------------------------------------------------
#
# Licensed to the Apache Software Foundation (ASF) under one
# or more contributor license agreements.  See the NOTICE file
# distributed with this work for additional information
# regarding copyright ownership.  The ASF licenses this file
# to you under the Apache License, Version 2.0 (the
# "License"); you may not use this file except in compliance
# with the License.  You may obtain a copy of the License at
#
#   http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing,
# software distributed under the License is distributed on an
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
# KIND, either express or implied.  See the License for the
# specific language governing permissions and limitations
# under the License.
#
#-------------------------------------------------------------

# The lm-function solves linear regression using either the direct solve
# method or the conjugate gradient algorithm depending on the input size
# of the matrices (See lmDS-function and lmCG-function respectively).
#
# .. code-block:: python
#
#   >>> import numpy as np
#   >>> from systemds.context import SystemDSContext
#   >>> from systemds.operator.algorithm import lm
#   >>> 
#   >>> np.random.seed(0)
#   >>> features = np.random.rand(10, 15)
#   >>> y = np.random.rand(10, 1)
#   >>> 
#   >>> with SystemDSContext() as sds:
#   ...     weights = lm(sds.from_numpy(features), sds.from_numpy(y)).compute()
#   ...     print(weights)
#   [[-0.11538199]
#    [-0.20386541]
#    [-0.39956034]
#    [ 1.04078623]
#    [ 0.43270839]
#    [ 0.18954599]
#    [ 0.49858969]
#    [-0.26812763]
#    [ 0.09961844]
#    [-0.57000751]
#    [-0.43386048]
#    [ 0.55358873]
#    [-0.54638565]
#    [ 0.2205885 ]
#    [ 0.37957689]]
#
#
# INPUT:
# --------------------------------------------------------------------
# X        Matrix of feature vectors.
# y        1-column matrix of response values.
# icpt     Intercept presence, shifting and rescaling the columns of X
# reg      Regularization constant (lambda) for L2-regularization. set to nonzero
#          for highly dependant/sparse/numerous features
# tol      Tolerance (epsilon); conjugate gradient procedure terminates early if L2
#          norm of the beta-residual is less than tolerance * its initial norm
# maxi     Maximum number of conjugate gradient iterations. 0 = no maximum
# verbose  If TRUE print messages are activated
# --------------------------------------------------------------------
#
# OUTPUT:
# ---------------------------------------------------------------
# B     The model fit beta that can be used as input in lmPredict
# ---------------------------------------------------------------

m_lm = function(Matrix[Double] X, Matrix[Double] y, Integer icpt = 0,
    Double reg = 1e-7, Double tol = 1e-7, Integer maxi = 0, Boolean verbose = TRUE)
    return (Matrix[Double] B) {
  if( ncol(X) <= 1024 )
    B = lmDS(X, y, icpt, reg, verbose)
  else
    B = lmCG(X, y, icpt, reg, tol, maxi, verbose)
}