def main(readcsv=read_csv, method='defaultDense'):
nFeatures = 6
nClasses = 5
nIterations = 1000
stepLength = 1.0e-4
infile = "./data/batch/logreg_train.csv"
# Read the data
data = readcsv(infile, range(nFeatures))
dep_data = readcsv(infile, range(nFeatures, nFeatures + 1))
nVectors = data.shape[0]
# configure a function
func = d4p.optimization_solver_cross_entropy_loss(nClasses, nVectors, interceptFlag=True)
func.setup(data, dep_data, None)
# configure a algorithm
stepLengthSequence = np.array([[stepLength]], dtype=np.double)
alg = d4p.optimization_solver_lbfgs(func,
stepLengthSequence=stepLengthSequence,
nIterations=nIterations)
# do the computation
nParameters = nClasses * (nFeatures + 1)
initialPoint = np.full((nParameters, 1), 0.001, dtype=np.double)
res = alg.compute(initialPoint)
# result provides minimum and nIterations
assert res.minimum.shape == (nParameters, 1)
assert res.nIterations[0][0] <= nIterations
return res
def _daal4py_cross_entropy_loss_extra_args(nClasses,
beta,
X,
y,
l1=0.0,
l2=0.0,
fit_intercept=True,
value=True,
gradient=True,
hessian=False):
X = make2d(X)
nSamples, nFeatures = X.shape
y = make2d(y)
beta = make2d(beta)
n = X.shape[0]
results_to_compute = _resultsToCompute_string(value=value,
gradient=gradient,
hessian=hessian)
objective_function_algorithm_instance = daal4py.optimization_solver_cross_entropy_loss(
nClasses=nClasses,
numberOfTerms=n,
fptype=getFPType(X),
method='defaultDense',
interceptFlag=fit_intercept,
penaltyL1=l1 / n,
penaltyL2=l2 / n,
resultsToCompute=results_to_compute)
objective_function_algorithm_instance.setup(X, y, beta)
return (objective_function_algorithm_instance, X, y, n)
